Smiling Female Patient in Wheelchair Leaving Hospital

Length of Stay (LOS) Deep Dive

Managing patient length of stay isn’t about pushing patients out the door as quickly as possible. It’s about providing the best, most appropriate and effective care in the optimum time, without unnecessary disruption or delay.
When caregivers are empowered to make the right clinical decisions with swift confidence, hospitals optimize length of stay to improve and sustain care quality, patient satisfaction, and capacity management.
leaving hospital
Every unnecessary minute of a patient’s stay increases risks and impacts outcomes and experience:
  • Increased risk of falls, infections, and other hospital acquired conditions
  • Reimbursement penalties for poor throughput performance
  • Frustration and diminished satisfaction for patients with delayed treatments and discharge

Baselines and Data Related to Hospital Length of Stay (LOS):
  • Average hospital LOS nationwide in 2017 was 5.7 days
  • Common diagnoses for inpatient stays include birth complications, acute myocardial infarction, complications of device, cardiac dysrhythmias, mood disorders, pneumonia, congestive heart failure, and osteoarthritis
  • Average LOS varies considerably by state, based on demographics and population distribution, with lows of 4.4 in Utah to 7.5 in Alaska and 8.8 in Wyoming

LOS Impacts Care Quality, Patient Satisfaction, and Readmissions

Managing length of stay improves performance in all metrics that matter for hospitals, including care quality, patient satisfaction, and readmissions:
  • Patients are more satisfied and HCAHPS scores improve when they are not overwhelmed with excessive physician consultations during their inpatient stay, something that AI-enabled prescriptive analytics helps diminish. Research says “fewer inpatient consultations was the strongest predictor of patient satisfaction.”
  • Research shows that reduced length of stay reduces readmissions, largely due to reduced risk of infection and hospital acquired conditions. As average LOS for VA patients dropped 27 percent from 5.44 days in 1997 to 3.98 days, 30-day readmission rates also fell from 16.5 percent to 13.8 percent.
  • A five-year Emory University Hospital initiative saw an average LOS reduction of 5 days to 4.5 days correspond with in-hospital mortality drop from 2.3 to 1.1 deaths per 100 encounters.


    LOS and Financial Health

    Length of stay significantly affects financial impact and opportunity:

    Regulatory Implications of LOS

    • Patient throughput efficiency measures now make up 25 percent of CMS reimbursement scores. CMS penalizes hospitals that do not fall within national ranges for length of stay and cost of care for Medicare patients.
    • The LOS measure has been added to existing quality and safety measures in the Leapfrog hospital survey.
    • To improve access to beds, The Joint Commission (TJC) has stipulated that hospitals have processes that:
      • Support patient flow throughout the hospital
      • Measure available supply of beds and efficiency of patient care areas
      • Report measurements to leadership
      • Use data to drive improvements in patient flow processes

    Promise for Improvement: The Jvion Machine Reduces Length of Stay While Improving Outcomes

    Hospitals that have adopted the Jvion Machine have demonstrated significant improvement in patient throughput:
    • At least 50 percent reduction in work effort—intelligent clinical guidance reduces workload as well as patient care review events and actions
    • Estimated 10 to 30 percent reduction in excess patient days
    • Jvion outlier LOS outlier vector focuses review and specific clinical attention on patients who most need it
    • Individualized approach specific to each patient and care approach for optimum care and LOS—stay long enough for the right care, and not too long for care activities that might not advance positive outcomes

    Overall Healthcare Impact

    The average cost per inpatient day in all areas is $2,271. The Jvion outlier vector projects a reduction in inpatient days of 10 percent to 30 percent.
    By preventing even two percent of potential excess patient days* cost savings across the nation would result in savings of $8.8 billion.
    * (Total US Admissions 2016 – 35,061,292 x average U.S. length of stay of 5.5 days in 2016 = 192,837,106 total patient days * 0.2) = 3,856,742 days x $2,271 per day cost = $8.88 billion.

    All Cause Readmissions

    More than any other single measure, readmissions has come to define success in value-based care.
    • Many care factors influence patient readmissions, including diagnostic accuracy, workflow and care coordination, effective discharge planning, clinical decisions and interventions, medication management, and more. With all of those components of care quality in play, patient readmissions performance has become a bellwether for success in value-based care in hospitals.
    • vaccination
    From the inception of the ACA, the Centers for Medicare and Medicaid Services (CMS) identified preventable 30-day readmissions as a critical care quality measure—with significant reimbursement rewards and penalties for performance.
    Ten years in, new discussion and debate still emerges as to whether hospitals have or have not truly decreased readmissions. The target also keeps moving, as hospitals prepare for new rules to grade readmissions performance against peer benchmarks.
    The imperative for hospitals and systems remains to continue addressing readmissions performance as a top quality and financial priority. Let’s look at the data that spell out the challenges—and how the Jvion Machine is delivering reliable success in reducing hospital readmissions rates.

    The readmissions directives cover these six clinical conditions:
      • Heart attack
      • Heart failure
      • Pneumonia
      • Chronic obstructive pulmonary disease (COPD)
      • Elective hip or knee replacement
      • Coronary artery bypass graft (CABG)

    Many clinical and demographic factors influence readmissions—too many for even the best clinicians to observe and consider without prescriptive analytic capability:
      • Use of high-risk medications
      • Multiple medications for the same condition
      • More than six chronic conditions
      • Unplanned hospitalizations within the last six to 12 months
      • Low health literacy
      • Limited social interaction
      • Lower socioeconomic status
      • Discharge against medical advice

    The industry data reflects the challenges in reducing and managing readmissions:
    • Nearly 20 percent of Medicare patients discharged from a hospital are readmitted within 30 days, which costs Medicare $15 billion to $18 billion per year
    • Overall, 36.1 percent of all 30-day readmissions occurred within seven days
    • Often inadequate discharge planning contributes to readmissions, with poor coordination among hospital and community clinicians and lack of community-based care
    • Medicare patients contributed to $20.1 billion in total hospital costs for potentially preventable hospitalizations
    • In 2017 2,573 hospitals were penalized for too many 30-day readmissions
    • Readmissions stays are about 50 percent longer than overall average length of acute care stay at 6.4 days (estimated mean LOS)

    Patient and Healthcare Impact

    • Jvion has a demonstrated track record across multiple hospitals of reducing readmissions by at least 10 percent.
    • Consider a hospital with a readmission rate of 13 percent (1,300 readmissions per 10,000 discharges). The Jvion Machine would help avoid 130 readmissions—an estimated cost savings of $1.43 million.


    Akintoye, E., Briasoulis, A., Egbe, A., Dunlay, S. M., Kushwaha, S., Levine, D., . . . Weinberger, J. (2017). National Trends in Admission and In‐Hospital Mortality of Patients With Heart Failure in the United States (2001–2014). Journal of American Heart Association, 1-14. doi:

    Boccuti, C., & Casillas, G. (2017, March). Aiming for fewer hospital u-turn: The Medicare hospital readmission reduction progrma. Retrieved from Kaiser Family Foundation:

    Centers for Medicare & Medicaid Service. (2018, March 26). Hospital Readmissions Reduction Program (HRRP). Retrieved from

    Davis, J. D., Olsen, M. A., Bommarito, K., LaRue, S., Saeed, M., Rich , M. W., & Vader, J. M. (2017). All-Payer Analysis of Heart Failure Hospitalization 30-Day Readmission: Comorbidities Matter. The American Journal of Medicine, 130(1), 93.e9-93.e28. Retrieved from

    Fitch, K., Engel, T., & Lau, J. (2017). The Cost of Worsening Heart Failure in the Medicare Fee For Service Population: An Actuarial Analysis. Milliman, 1-29. Retrieved from

    Gheorghiade, M., Vaduganathan, M., Fonarow, G. C., & Bonow, R. O. (2013). Rehospitalization for Heart Failure. Journal of American College of Cardiology, 61(4), 391-403. Retrieved from

    Heidenreich , P. A., Albert , N. A., Allen, L. A., Bluemke, D. A., Butler, J., Fonarow , G. C., . . . Trogdon, J. G. (2013). Forecasting the Impact of Heart Failure in the United States. Circulation: Heart Failure, 1-14. doi:DOI: 10.1161/HHF.0b013e318291329a

    Lagoeiro, A. J., Mesquita, E. T., Rabelo, L. M., & Souza Jr., C. V. (2017). Understanding Hospitalization in Patients with Heart Failure. International Journal of Cardiovascular Sciences, 30(1), 81-90. Retrieved from

    Masoud Shafazand, H. P. (2012). Patients with worsening chronic heart failure who present to a hospital emergency department require hospital care. BMC Research Notes, 5, 132. Retrieved from

    Masuri, A., Althouse, A., McKibben, J., Thoma, F., Mathier, M., Ramani, R., . . . Mulukutla, S. (2018). Outcomes of Heart Failure Admissions Under Observation Versus. Journal of the American Heart Association, 1-7. doi:DOI: 10.1161/JAHA.117.007944

    Ogah, O. A. (2017). Heart Failure: Definition classification, and pathophysiology - a mini-review. Nigerian Journal of Cardiology, 14(1), 9. Retrieved from;year=2017;volume=14;issue=1;spage=9;epage=14;aulast=Adebayo;aid=NigJCardiol_2017_14_1_9_201913

    Quaglietti, S. E., Atwood, J. E., Ackerman, L., & Froelicher, V. (2000). Management of the patient with congestive heart failure using outpatient, home, and palliative care. Progress in Cardiovascular Diseases, 43(3), 259-274. Retrieved from

    Ziaeian, B., & Gregg, F. C. (2016). The Prevention of Hospital Readmissions in Heart Failure. Progress in Cardiovascular Disease, 58(4), 379-385. Retrieved from

    Behavioral Health AI Funnel

    The Jvion Machine's Behavioral Health Vectors

    Mental health readmission

    With Jvion’s Mental Health Readmission Vector, providers can identify those patients who upon admission to the hospital are at risk for a mental health-related readmission to a psych unit or psychiatric facility within the next 30 days following discharge. This vector provides clinicians with the individualized recommended interventions tailored to each patient’s clinical and socioeconomic risk factors. These may include actions such as: the receipt of appropriate inpatient interventions; an increase in access to community resources prior to discharge; education that is delivered and received as it relates to managing their condition upon discharge and to prevent future admissions; and increased patient and family engagement.

    Opioid Abuse

    Jvion’s Opioid Abuse Vector helps tackle the growing problem of opioid abuse by determining the likelihood that a patient will develop an opioid addiction within the next six months regardless of their current or previous opioid use. Clinicians are able to view patient-level risk outputs, which include the contributing clinical and socioeconomic risk factors that are driving the addiction risk. The machine also takes into account all patients across a population because more than 30% of opioid abuse starts with heroin, not prescription pain killers. This approach reduces the likelihood of missing a patient who has is at risk of opioid abuse but who has not had an opioid prescription in the past. The vector also generates individualized recommended interventions to help personalize clinical actions so that they are most effective at driving down risk while also promoting patient engagement.


    Jvion’s Suicide Risk Vector predicts which patients are at risk for having an emergency department or inpatient visit due to self-harm, suicidal ideation, suicide attempt or suicide within the next six months. The machine is able to focus on self-harm and suicide risk and can identify risks that might otherwise go undetected. This vector empowers clinicians with the individualized recommended interventions that include more focused screening and matching patients with the most effective mental health resources.


    Oncology AI Funnel

    The Jvion Machine's Oncology Vectors

    30-day mortality risk

    Anticipating end-of-life care decisions about the appropriate or preferred treatment can be challenging for healthcare providers and burdensome for patients and their families. The final month of life is demanding clinically and financially with approximately 75% of the total cost of cancer treatment occurring in the final 30 days of life. Understanding the difficulty of end-of-life care, providers are looking to AI-enabled prescriptive analytic capabilities to ensure that high-quality care is being delivered that is consistent with a patient’s needs, values, and preferences.
    The Jvion Oncology 30 Day Mortality Vector supports clinical decision-making by predicting the final stages of a patient’s terminal illness with a primary endpoint of early hospice/palliative care. The Jvion Machine accounts for more than 4,500 clinical, social, and behavioral factors to determine which intervention and care path will improve a patient’s quality of life over the final 30 days. Whether it is symptom management, preparing the family and/or caregivers, or promoting a social support system, these individualized recommendations redirect the plan of care toward the actions that will meet the needs of a patient and his/her family. In addition, these recommendations minimize unnecessary clinical workload, avoid aggressive and unwanted measures of care, and optimize palliative care and/or hospice enrollment based on the patient’s preferences.

    30-day readmission risk

    Current reported readmission rates for cancer patients discharged from medical services are as high as 27%. Oncology patients may have multiple and complex comorbidities as a result of not only the etiology of their malignancy but also the expected, and thus not completely preventable, complications of treatment. The majority of cancer patient readmissions are due to the acute onset of symptoms, complications of therapy, and progression of disease. Many of these are oftentimes manageable in the ambulatory care setting if the most effective actions that will reduce the risk of a readmission are identified and actioned.
    The Jvion Oncology 30-day Readmission Vector identifies patients that show a high propensity for multiple inpatient readmissions within the next 30 days. The machine empowers clinicians with the patient specific clinical and socioeconomic risk factors driving this risk, which are accounted for in the machine’s recommended interventions. The goal of the vector is to promote targeted interventions in the ambulatory setting the enhance disease outcomes, quality of life, and cost-effective delivery of care while preventing unnecessary readmissions.

    6-month deterioration risk

    Patients with cancer can deteriorate under various circumstances. Understanding the patient’s functional status can help in determining the best treatment for an individual patient’s quality of life. The current clinical state for measuring how cancer impacts daily living abilities takes into account a five-point scale derived from the Eastern Cooperative Oncology Group’s (ECOG) Scale of Performance Status. But this is a limited approach to identifying a patient’s level of functioning. There are many factors that can predict whether someone is likely to do well or poorly with their disease and not all of those factors may be identified in the clinical setting.
    The Jvion Oncology 6 Month Deterioration Vector takes into account the clinical, social, and behavioral risk factors to predict the likelihood of a functional decline. The Jvion Machine determines a patient’s risk propensity while in the ambulatory setting and prior to the onset of clinical symptoms and/or an acute impact on the patient’s daily activities (e.g. ability to care for themselves, daily activity, physical ability). The individualized recommended interventions direct caregiver attention to not only focus on symptom management but also to address the existing gaps in the patient’s social environment and cognitive function.

    Avoidable admission

    Hospitalizations in patients with cancer are particularly common due to the acute condition and acute symptom onset. Approximately 19% of hospitalizations in patients with gastrointestinal cancer are potentially avoidable and clinicians directly involved in caring for patients with cancer agree that nearly 1 in 4 hospitalizations (23%) are potentially avoidable. Reducing acute hospitalizations is an important strategy for improving the quality, value, and patient-centeredness of cancer care. And optimal outpatient support in the ambulatory setting will better serve these patients in avoiding and inpatient admission.
    The Jvion Oncology Avoidable Admissions Vector predicts which patients are at risk to be admitted to a hospital within the next 30 days while the patient is still in the ambulatory setting. With this information, care coordinators are able to address individual patient needs and risk factors driving the admission risk by actioning on the individualized recommended interventions delivered by the Jvion Machine.

    Patient experience and pain management

    Pain is among one of the most disturbing and restricting consequences of cancer treatment or care. The incidence of pain amongst cancer patients ranges from 53-64% from an advanced disease stage to all stages of the disease. In addition, two-thirds of cancer patients report that pain interferes with their activities of daily living, and half believe that their healthcare providers do not prioritize the quality of life in their overall plan of care.
    The Jvion Oncology Pain Management Vector predicts those patients who are at risk for poorly controlled pain as it relates to their condition. Taking into account the comprehensive risk factors associated with pain management – including physical, clinical, social, and behavioral—the care team is able to take specific actions to address a patient’s needs. The Jvion Machine empowers clinicians with individualized recommended interventions aimed at increasing education on pain assessment and management, facilitating referrals to pain specialists as needed, improving patient adherence to plan of care, minimizing costs associated with ongoing pain management, and reducing unnecessary emergency room visits through the care continuum. Moreover, the care team is able to overcome existing barriers with cancer pain management through the increased communication and collaboration across the multidisciplinary care team and the patient and family members.

    Depression risk

    Depression is a common co-morbidity of cancer that has a detrimental effect on quality of life, compliance to the plan of care, and additional complications. It has a considerable impact on healthcare utilization and cost, and is associated with substantial suffering. In addition, it often goes undiagnosed or untreated, which can have considerable impacts on the patient. Prompt recognition of a patient’s risk for depression and effective treatment are critical to address the cancer patient's quality of life.
    The Jvion Oncology Depression Risk Vector predicts those patients who are at risk for depression within the next six months while the person is still in the ambulatory setting. The oncology depression risk vector takes into account those patients with a previous or current diagnosis with depression as well as those with a propensity toward depression. This enables care coordinators to better understand which patients are most likely to be depressed and which patients are or are not receiving adequate treatment and/or resources to better manage their depression. Based upon the individualized risk factors (clinical and socioeconomic) identified for each patient, actionable recommended interventions are provided to the care team. These individualized recommended interventions enable care coordinators to effectively address individual patient needs, whether clinical or socioeconomic based, to best manage the patient’s plan of care, ensure adherence to medical treatments, and enhance quality of life.

    No-show risk

    For cancer patients, missing an appointment can have a huge impact on current treatment and the possibility that the cancer will return. In one study published by the International Journal of Radiation Oncology Biology Physics, cancer patients who missed radiation therapy appointments were at a greater than 2x risk of a recurrence. The reasons behind a missed appointment are varied. The financial burden of cancer treatment alone can push people to skip a scheduled doctor visit or not fill a prescription. There are also socioeconomic factors including access to transportation that compound the problem.
    The Jvion No-show Vector identifies patients who are at a high risk for missing their appointment and provides advance notification along with the actions that will most likely reduce noncompliance. In addition to identifying those who are at a high risk for a no-show appointment, the machine analyzes each patient at the appointment/encounter level and the visit level (i.e. time and day of appointment) to determine the appropriate recommended intervention. These additional interventions identify patients that could benefit from alternative settings or community engagement including telehealth kits, transportation assistance, after-hours appointments, and in home visits. Additionally, the Jvion Machine provides post discharge lists to identify those patients that are likely to no show 48 hours post discharge and again for those at risk to no-show within the next 7-14 days.


    Young Child Oncology Patient

    Understanding the Oncology Care Model

    • Cancer is one of the most prevalent and devastating diseases in the United States. While the disease impacts individuals of all ages, the largest proportion of cancer patients are over 65 and Medicare beneficiaries.1 As part of the Centers for Medicare & Medicaid Services (CMS) Innovation Center, the Oncology Care Model (OCM) was created to test new payment models and services delivered to cancer patients. The five-year model is designed to test strategies that drive quality outcomes while reducing costs for care provided for six months following a patient’s first chemotherapy treatment.1
    • oncology patient
    The model includes a two-part payment approach:
    • Monthly Enhanced Oncology Services (MEOS) Payments: which pay for enhanced services delivered to beneficiaries
    • Performance-Based Payment (PBP): which encourages member practices to improve quality and reduce costs across the six-month episode of care
    In addition to incentive payments, the model also requires that participating practices implement a practice redesign initiative aimed at improving cancer patient outcomes and quality of life. These requirements include:
    • Enhanced patient services including patient navigation, a comprehensive care plan, 24x7 patient access, and treatments and therapies that adhere to national clinical guidelines
    • The use of data to drive continuous quality improvement
    • The use of certified electronic health record technology3
    Performance is tracked through a set of quality measures that span claims-based and practice-reported measures that cover:
    • Communication and care coordination
    • Person and caregiver experience and outcome
    • Clinical quality of care2
    Taken together, the OCM program aims to help transform cancer care in a way that empowers clinicians with the information and tools they need to drive quality outcomes. Through the OCM, participating practices are working to improve care coordination, symptom management, palliative care, and end-of-life care. And with the growing demand for high-quality cancer treatment, this program along with other innovation projects will push healthcare forward toward our shared goal of improved patient outcomes and the experience of care.

    [1] Centers for Medicare & Medicaid Services, "Oncology Care Model,", 09 06 2016. [Online]. Available: [Accessed 21 05 2018].

    [2] Centers for Medicare & Medicaid Services Innovation Center (CMMI), Oncology Care Model Overview, Washington, DC: CMMI, 2018.

    [3] Center for Medicare & Medicaid Services, "ONCOLOGY CARE MODEL OTHER PAYER (OCM-OP) CORE MEASURE SET," 07 05 2018. [Online]. Available: [Accessed 17 05 2018].


    Elderly Male Patient in Wheelchair with Grandkids

    Prevent Heart Failure Readmissions and Improve Quality

    Heart failure admissions occur with 22 percent of all patients discharged—the highest rate of any readmissions event.
    • Many characteristics of heart failure events complicate treatment and increase readmissions risks. Most people entering the hospital with heart failure get admitted immediately, often with no intervening assessment or treatment. Many patients don’t comply with drug or dietary care guidance after their discharge, representing two-thirds of heart failure readmissions. And the readmissions for heart failure happen fast, with an average time of 12 days.
    • fun-with-grandkids

    Heart failure is prevalent and pervasive:
    • 5.7 million American adults live with heart failure (Ziaeian & Gregg, 2016)
    • One million hospitalizations for heart failure occur annually (Gheorghiade, Vaduganathan, Fonarow, & Bonow, 2013)
    • 70% of heart failure readmissions are for non-heart failure diagnoses, most commonly other cardiovascular conditions, pulmonary disease, and infections (Davis, et al., 2017)
    • There are 500,000 new cases of heart failure each year in the United States (Ogah, 2017)

    Heart failure will increase 46% from 2012 to 2030, with greater than 8 million adults living with the chronic condition.

    (Ziaeian & Gregg, 2016)

    Reimbursement Penalties in Full Force

    Hospitals addressing readmissions performance must act quickly. CMS uses three full years of data to determine penalties, so hospitals need to document and report positive performance data as quickly as possible to cycle it into the three-year rolling sample.

    The full 3 percent penalties for reimbursement are now in place. The reduced payments apply to all Medicare admissions—not just those that resulted in readmissions.


    Patient and Healthcare Impact

    • Heart failure readmissions cost $7,580 per episode (Davis, et al., 2017)—costing a mid-sized to large hospital with 1,000 discharges and 220 readmissions about $1.7 million.
    • The Jvion Heart Failure Vector has reduced readmissions for the condition by as much as 60 percent. That would eliminate 132 of the 220 annual readmissions—a savings of $1,000,000.
    • Extrapolated across the 1,000,000 heart failure admissions annually, the Jvion Machine has a potential to improve outcomes for 130,000 patients and save more than $1 trillion in healthcare costs.

    Davis, J. D., Olsen, M. A., Bommarito, K., LaRue, S., Saeed, M., Rich , M. W., & Vader, J. M. (2017). All-Payer Analysis of Heart Failure Hospitalization 30-Day Readmission: Comorbidities Matter. The American Journal of Medicine, 130(1), 93.e9-93.e28. Retrieved from

    Fitch, K., Engel, T., & Lau, J. (2017). The Cost of Worsening Heart Failure in the Medicare Fee For Service Population: An Actuarial Analysis. Milliman, 1-29. Retrieved from

    Gheorghiade, M., Vaduganathan, M., Fonarow, G. C., & Bonow, R. O. (2013). Rehospitalization for Heart Failure. Journal of American College of Cardiology, 61(4), 391-403. Retrieved from

    Ogah, O. A. (2017). Heart Failure: Definition classification, and pathophysiology - a mini-review. Nigerian Journal of Cardiology, 14(1), 9. Retrieved from;year=2017;volume=14;issue=1;spage=9;epage=14;aulast=Adebayo;aid=NigJCardiol_2017_14_1_9_201913

    Ziaeian, B., & Gregg, F. C. (2016). The Prevention of Hospital Readmissions in Heart Failure. Progress in Cardiovascular Disease, 58(4), 379-385. Retrieved from

    Empty Hospital Bed

    Where Other Solutions Fall Short: The Jvion Machine Better Prevents Inpatient Falls

    • Inpatient falls are a problem that extends beyond just the elderly to any patient who has experienced some kind of physiological change as a result of his or her medical condition, medications, procedures, and/or testing.1 Oftentimes, preventing a fall is difficult and the challenge is complicated by variations in fall prevalence across different types of nursing units.2 What is consistent is the devastating impact that a fall can have on a patient, his or her family, and the overall healthcare system.
    • inpatient falls
    For patients, falls are the leading cause of a move to a skilled-nursing facility, result in severe injury in 20-30% of all cases, and can result in a 10-15% reduction in life expectancy. For families, falls not only increase caregiving burdens, they also have a significant financial impact.3 And for the healthcare system as a whole, falls contribute to an average increase of 6.3 days in the hospital, add up to an additional $14,000 on average per episode, and cost Americans more than $100 billion per year.3,1
    Current methods for predicting falls use scaled scores (i.e. Morse Falls Scales, Hector Davis Scale). The problem with these tools is that they tend to overestimate fall risk. They typically deliver high rates of false positives, which undermines efforts to allocate resources efficiently and more effectively prevent fall occurrences.
    The Jvion Machine empowers clinicians with the insights that better identify at-risk patients and deliver the individualized actions that will mitigate the risk of a fall. And it does this at admission.
    What we know is that best practices include the integration of an effective tool to predict falls and the development of a tailored, patient-specific care plan that addresses the unique drivers contributing to a patient’s risk.1 With Jvion’s falls vector, clinicians have access to a machine that accounts for the more than 4,500 clinical and non-clinical factors that could contribute to the likelihood that an individual will fall. At admission, providers can identify if someone is at risk of a fall within the next 12 hours and the actions that will reduce the risk. These insights can be incorporated directly in the care plan and updated every 12 hours with new data from the machine. And the Jvion solution can do this using the clinical documentation on hand—even in the absence of validated fall events.
    Jvion’s falls vector helps hospitals more strategically allocate resources (i.e. patient sitters) and minimize clinician workload by implementing the right interventions on the right patients. This means that providers are able to better utilize virtual monitoring systems versus inpatient sitters; they can implement individualized interventions upon admission; and they can minimize the waste associated with overused resources. Taken together, providers can reduce their resources by ~75% using the risk and intervention outputs delivered by Jvion’s solution—the number one prescriptive analytics for preventable harm solution designed specifically for healthcare.

    [1] The Joint Commission, "Preventing falls and fall-related injuries in health care facilities," Sentinel Event, no. 55, pp. 1-5, 28 September 2015.

    [2] M. Erin D. Bouldin, P. Elena M. Andresen, P. Nancy E. Dunton, P. M. Michael Simon, P. Teresa M. Waters, M. Minzhao Liu, P. Michael J. Daniels, R. P. F. Lorraine C. Mion and M. Ronald I. Shorr, "Falls among Adult Patients Hospitalized in the United States: Prevalence and Trends," Journal of Patient Safety, vol. 9, no. 1, pp. 13-17, 2013.

    [3] Indiana University, "Falls: How Big Is the Problem," The Trustees of Indiana University, Bloomington, 2004.


    A Prescriptive Analytic Solution to the Problem of No-Shows

    • The problem of patient no-shows is a vexing one that spans the care spectrum. These events include instances where patients fail to attend an appointment, arrive too late for an appointment, or cancel an appointment on too short of a notice.1 Estimates are that anywhere from 14-50% of primary care appointments are no-shows.1
    • no-shows
    The impacts of missed appointments are substantial. For providers, no-shows have a direct hit to revenues with total dollar impacts ranging by specialty. They also contribute to decreased provider satisfaction and wasted time.2 For patients, the consequences can be dire. Missed appointments can lead to poor chronic condition management, a lack of preventative care, and the increased possibility of an avoidable hospital visit.1
    A disproportionate segment of the patient population tends to drive the largest percentage of no-shows. In one study conducted at the Cleveland Clinic, 1.5% of patients accounted for 20% of all missed appointments.3 Following the 80/20 rule that seems to hold true for so much of healthcare, the outlier patients that make up 20% of the population tend to drive most of the no-shows and, consequently, have the biggest cost impact to provider operations.
    There are some shared characteristics associated with a higher risk of a no-show appointment. These span clinical and non-clinical attributes including a history of no-shows, age, ethnicity, socioeconomic status, behavioral health conditions, and co-morbidities.1 Patient perception also plays a significant role in attendance. Emotions, perceived disrespect, and a lack of education around the scheduling system have all been linked to the likelihood of a no-show instance.4
    The Jvion Machine is being used by providers to help not only identify potential no-shows, but to determine the best possible action that will have the biggest potential impact on driving patient attendance. The machine, which uses an Eigen-based backbone, delivers:
    • The patients at-risk of missing an appointment, showing up late, or cancelling within a specified timeframe
    • The factors influencing that risk of cancelation including the clinical and non-clinical drivers such as lack of access to transportation, depression, and language barriers
    • Insight into which patients can be impacted and the specific actions that will reduce the risk of a no-show appointment
    With the Jvion Machine, providers know when overbooking appointments is the best strategy to mitigate potential operational losses and when actions including reminders, patient transportation, and education will drive a patient to attend his or her appointment. Jvion’s solution is helping providers better manage patient appointment scheduling to reduce losses and optimize practice resource utilization. But the most important outcome of this vector is the impact that it has on patient care. The machine is helping ensure the best possible outcome for patients. By knowing how to engage a person so that they make it to an appointment can reduce the risk of complications and the deterioration that leads to preventable stays in the hospital and avoidable pain and suffering.3

    [1] T. Gebhart, "No-Show Management in Primary Care: A Quality Improvement Project," Sholar Archive, p. 28, 13 April 2017.

    [2] P. Bjorn Berg, B. Michael Murr, M. David Chermak, M. Jonathan Woodall, M. M. Michael Pignone, M. M. Robert S. Sandler and P. Brian Denton, "Estimating the Cost of No-shows and Evaluating the Effectos of Mitigation Strategies," Medical Decision Making, vol. 33, no. 8, pp. 976-985, 2013.

    [3] M. Fred DeGrandis, L. Hultine and M. Craig Nielsen, Reducing No-Shows to Enhance Patient Access and Provider Satisfaction, ACHE Managment Innovations Poster Session, 2016.

    [4] P. Naomi L. Lacy, M. M. Audrey Paulman, B. Matthew D. Reuter and M. A. F. Bruce Lovejoy, "Why We Don't Come: Patient Perceptions on No-Shows," The Annals of Family Medicine, vol. 2, no. 6, pp. 541-545, 2004.


    Man in Wheelchair Overlooking Ocean

    Relieving the Pressure: Taking on Pressure Injuries with the Jvion Machine

    • Most people recall the tragic horse riding accident that paralyzed Superman actor Christopher Reeve. Even after his injury, he went on to bravely lead awareness of spinal injury and paralysis and act and direct for film and television. What many don’t recall is the Reeve died not from his spinal injuries, but from sepsis—a blood infection—caused by a pressure injury.
    • wheelchair-bound
    In the past, pressure ulcers were often considered an unavoidable byproduct of clinical bed stays of all lengths, acute or extended. Some clinicians concluded that as long as the patients’ primary conditions improved, a pressure ulcer was a secondary concern.
    We in healthcare know better now. Pressure injuries cause pain for everyone, in many ways. The patient suffers from extensive pain and discomfort that lasts and requires treatment long after discharge. Pressure ulcers can trigger more serious infections or sepsis, two serious and imminently avoidable negative outcomes. Medicare long ago stopped reimbursing for treatment of many type of pressure injuries deemed preventable with appropriate care.
    Yet for such a common condition—2.5 million reported pressure injuries annually costing as much as $11.6 billion—we have historically still worked in the dark when it comes to prevention. Prevention studies have been limited in scope and remedy.
    And pressure ulcers contribute to many negative outcomes we work hard to avoid:
    • 30-day readmissions
    • Extended length of stay in both acute and post-acute settings
    • Reduced patient, doctor, and nurse satisfaction
    • Mortality (60,000 deaths per year, a 2.8 times greater risk)1
    • Litigation (17,000 lawsuits per year: ARHQ 2014)
    Strong evidence suggests that a huge number of pressure injuries go unreported—perhaps by 10 times or more. This data is consistent with observations and claims among Jvion clients as well.
    Clearly, patient care without clear guidance on pressure injury risk, prevention, intervention, and treatment costs our patient communities and providers dearly. The Jvion Machine, applying comprehensive intelligence to patient clinical and exogenous data, delivers remarkable results in reducing pressure ulcers and improving outcomes:
    • An average reduction of hospital acquired pressure injuries of 45 percent
    • Five times the precision and effectiveness impact when compared with performance of the Braden Scale, the current standard and underlying assessment tool in most EHRs
    Such performance changes the game for reducing pressure injuries. It also highlights how the Jvion Machine is becoming the critical artificial intelligence asset for healthcare, providing the core “brain” that can see all patient community clinical and demographic data, assess risk at every stage, and recommend the most successful and timely interventions.
    As healthcare providers expand the vectors with the Jvion Machine that determine risk and response for more and more conditions, they truly gain power to better treat entire patient populations. Consider the comprehensive knowledge, intelligence, and positive outcomes the machine enables across critical performance measures in healthcare (many of the same ones that overlap with pressure injuries):
    Delivering the best, most effective, compassionate and reliable quality care for patient populations depends on much more than just one rigid model addressing a single or limited clinical issue or condition. Today’s reality demands the comprehensive visibility into all data about patient communities, with complete understanding of risk at every stage. It requires swift recommendations for effective treatment and intervention. The Jvion Machine is not the future of healthcare—it’s the present.
    1N.C.C. Karen Bauer, M. Kathryn Rock, M. F. F. R. R. F. Munier Nazzal, O. Jones and M. P. and Weikai Qu, "Pressure Ulcers in the United States’ Inpatient Population From 2008 to 2012: Results of a Retrospective Nationwide Study," Ostomy Wound Management, vol. 62, no. 11, p. 30–38, 2016.


    Male Silhouette Behavioral Health

    A Prescriptive Analytic Approach to Suicide Prevention

    • The same shame and stigma associated with depression apply to those at risk for suicide. Often people contemplating suicide mistakenly feel that they are a burden to those around them, making them even less likely to confide their dark thoughts to anyone. By the time someone writes a suicide note, it’s likely too late to intervene.
    • suicide prevention
    This tragedy touches far too many lives. Suicide leads all causes of death in all age groups. For people aged 15 to 34, only unintended non-lethal injury occurs more frequently. Between 1999 and 2014, the per capita rate of suicide increased 24 percent. Suicide took the lives of more than 44,000 people in 2015. Within the general population, the suicide attempt rate is about 0.5%.
    The Jvion Machine applies artificial intelligence to understand comprehensive clinical, socioeconomic and other data to identify suicide risk within a community or patient population. The Jvion Suicide/Self-harm Vector helps tackle this growing problem by identifying those most at risk of having an emergency department or inpatient visit due to self-harm, suicidal ideation, suicide attempt, or suicide in the next six months.
    Here’s one example of how AI-enabled prescriptive analytic technology, tuned rapidly to focus on self-harm and suicide risk, can identify risks that might otherwise go undetected. The Association for Suicide Prevention lists increased alcohol use among many factors that indicate suicide risk. A patient undergoing routine bloodwork might return an elevated liver enzyme panel—a possible marker for excessive alcohol intake. As an isolated data point, it may not raise alarm for depression or suicidal thoughts, especially if the patient isn’t forthcoming about his or her drinking habits. The doctor might schedule follow up such as a hepatitis panel, or simply tell the patient they will continue to monitor the enzyme counts in future visits.
    The Jvion Machine, however, understands that clinical data as part of a comprehensive patient picture. Paired with other clinical and exogenous data, the machine can see risk that might go unseen (or unspoken) otherwise. It can identify the 5 percent of people who are at more than 10X risk of a suicide attempt. For 10,000 patients, the machine can narrow the scope of clinical action to the 500 who are at risk of whom 50 will attempt suicide. Recommendations for intervention focus on screening and matching individual patients with the most effective resources.
    Suicide is the ultimate tragedy for victims and their loved ones. New frontiers in AI-enable prescriptive technology are providing hope and opportunities for prevention and intervention we couldn’t have imagined even a few years ago. It’s truly a miracle of healing potential.


    Prescription Pills Opioid Epidemic

    Prescriptive Analytic Technology Gives Hope in the Fight Against Opioid Addiction

    The staggering, tragic toll of opioid-related deaths and overdoses seems to grow daily.
    The number of deaths from opioid overdose in 2016 (the most recent full year reported) was almost 46,000. Deaths from synthetic opioids—primarily Fentanyl—multiplied more than six times from 2013 to 2016 alone. (Opioids in this chart include synthetic opioids, heroin, natural and semi-synthetic opioids, and methadone.)
    Source: CDC WONDER
    This explosion in opioid deaths has even contributed to a decrease in U.S. life expectancy.
    "This is really a fast-moving epidemic that's getting worse," said Dr. Anne Schuchat, acting director of the CDC.
    The overdose cases and deaths only tell part of the story. This risk among the population speaks to our challenges in turning these bleak trends around. According to the American Society of Addiction Medicine, almost 2.6 million Americans have a substance abuse disorder involving prescription pain killers or heroin. More than 75 percent involve misuse of prescription pain killers.
    This epidemic raises special challenges and complications for physicians. They have a duty to treat patients compassionately and manage their pain, but also must mitigate the risk of opioid addiction. It creates complex conflicts, as evidenced by the recent opposition by doctors to proposed Medicare rules that would allow insurers to restrict or deny filling legitimate prescriptions for certain pain medications. How do doctors appropriately heal patients while recognizing and treating abuse risks?
    Technology, in the form of Jvion's AI-enabled prescriptive analytics, stands to provide breakthrough understanding, visibility and direction to help physicians target and treat patients at risk of opioid abuse. It’s built with remarkable intelligence that can absorb clinical and socioeconomic data for entire patient communities and provide crisp, clear, comprehensive profiles of risk and recommended treatments. Symptoms that in isolation might not raise a risk flag for doctors become part of a comprehensive patient “biography.” Using this clinical intelligence asset as a foundation, Jvion collaborates with healthcare organizations to apply specific “vectors” that comprehend risk profiles for an endless number of illnesses and conditions—including opioid abuse and other behavioral health conditions.

    Jvion’s Opioid Abuse Vector effectively and efficiently identifies individuals at increased likelihood of abusing opioids within the next year—regardless of their current prescribed opioid use. The machine accounts for all patients within a population to recognize risk regardless of whether a patient’s addiction started with heroin or prescription pain killers. Clinicians see patient-level risk outputs that include contributing clinical and socioeconomic factors. The machine also recommends personalized clinical actions most effective at reducing risk.

    The technology may seem complex—the machine makes more than a quadrillion clinical and non-clinical considerations for each patient. But the Jvion Machine works elegantly and quickly, providing clinicians with clear risk profiles and guidance within weeks of setup. Once it’s running it provides details and treatment guidance for patients in real time, using technology called Eigen spheres to continuously learn, interpret and communicate risk and treatment at all stages.

    Most importantly, technology is not the end unto itself—it’s about how it can help us prevent harm and heal. AI-enabled prescriptive analytics represents a promising, hopeful frontier in addressing the vexing human tragedy of the growing opioid epidemic.


    Getting Beyond the Stigma — The Prescriptive Analytic Breakthrough for Depression

    The face of depression can deceive us.
    • John Moe, comedian and former host of the NPR show “Wits,” explores this contradiction in his popular podcast “The Hilarious World of Depression.”

      The episodes feature interviews with well-known comedians, including Dick Cavett and Andy Richter, sharing their stories of struggles with depression and how sometimes the person laughing hardest is hiding the most pain.

    • depression
    Now in its second year, the show brings levity to a serious subject, making the topic more accessible and somehow less frightening and stigmatized.
    That stigma is a recurring theme on the podcast and reflects the challenges the medical community faces in identifying patients at risk of depression. When people fear opening up to doctors or loved ones, depression can hide in plain sight.
    And that’s a big problem. An estimated 6.7 percent of the U.S. population suffers from at least one major depressive episode each year. Unfortunately, only 35 percent of patients with severe symptoms see a mental health provider. Only about 20 percent receive care consistent with current guidelines.
    Here’s where the Jvion Machine makes a major, unique difference. The AI-enabled prescriptive analytic solution works beyond the stigma, assessing and understanding comprehensive clinical and exogenous data to identify depression risk. Unbiased, unemotional data can speak when patients themselves are reluctant to.
    The Jvion Major Depression Vector improves the diagnosis rate for major depression and identifies the most appropriate treatment from the best resources. The vector identifies the risk of a patient experiencing a major depressive episode within the next six months. It considers both the medical and socioeconomic factors driving the individual’s risk and makes intelligent recommendations for screening, referrals, and overcoming individual barriers to treatment.


    The results of the Jvion Machine for identifying depression risk have been remarkable.
    • Statistically outperforms published prediction models using patient questionnaires
    • High risk group has 10 times the risk of developing an episode of major depression
    • Almost 7 percent of episodes could be prevented by acting on the 3 percent of patients at highest risk

    That specific understanding of risk targets at various stages (not just the highest risk patients) and ability to identify depression risk well in advance set the Jvion Machine apart. As noted, the depression vector outperformed prediction models that rely on patient questionnaires—a particularly challenging approach when dealing with depression and its associated stigma.
    With the vector approach, an organization can get this tremendous insight into depression risk among a patient population in just a couple of weeks. The Jvion Machine serves as an artificial intelligence asset for your healthcare organization, providing the ability to turn on vectors for additional conditions with ease—be it depression, sepsis, readmissions, chronic conditions, and anything else you can imagine. The opportunities for recognizing risk in patient communities are literally without bounds.
    And the Jvion Machine enables intervention. It finds the people within the community on a trajectory toward a potentially avoidable depression event and directs clinicians to take the best next steps for patient outcomes. The machine offers the most comprehensive advance in healthcare to address the unique challenges in diagnosing depression and deliver consistently better outcomes.
    People like John Moe are helping shine a spotlight on depression and ease the stigma attached.
    “’Well, if I own up to having a mental illness, am I going to be committed? Are people going to see me as unstable?’” Moe said in an interview with Mother Jones magazine about the podcast. “What that stigma fails to own up to is that people with mental illness are your friends and neighbors and co-workers, living regular lives.”
    At the same time, the Jvion Machine and the Major Depression Vector are shining an unprecedented light on entire patient populations, identifying depression risk and intervention for those who previously might have quietly slipped through the cracks.
    Patient with Leg Injury

    Sepsis Readmission

    • The Jvion Machine identifies those individuals who had sepsis on the index admission who are at risk of a readmission and it delivers the recommended actions that will reduce that risk.

      This vector enables the right clinical action and engagement with community resources to ensure the best possible patient outcome.

    • injury-management
    Because the machine goes beyond simple risk stratification to identify the individualized factors driving the risk, the recommended interventinos that it delivers are tailored to the demographic, socioeconomic, and clinical conditions that drive so much of the risk that a patient will return to the hospital.
    Treatment for Sepsis

    Avoiding Sepsis in the Hospital Using the Jvion Machine

    • Centers for Disease Control and Prevention (CDC) defines sepsis as the body’s extreme response to infection. It occurs when an infection that a patient already has triggers a life-threatening chain reaction. More than 1.5 million people get sepsis and at least 250,000 Americans die from sepsis each year. While anyone can get an infection that can lead to sepsis, there are groups of people who are at higher risk including adults over 65, people with chronic conditions, people with a compromised immune system, and children younger than one.
    • vaccination
    Historically, it has been very hard to identify patients at risk of sepsis before onset of the infection. Existing methods have not met performance thresholds and tend to lead to extensive and expensive laboratory testing. With the application of the Jvion Machine, however, we are identifying:
    • Individuals at risk of sepsis before they enter the hospital
    • Patients who are at risk of sepsis when they are in the acute care setting
    • Patients who had sepsis on the index admission who are at risk of readmission
    • The individualized interventions that will lower risk and lead to an improved outcome for a specific patient
    This capability is driven by the transformative Eigen approach that underpins the Jvion Machine. By combining the established Eigen Sphere infrastructure—which enables the analysis of  socioeconomic, behavioral, and clinical factors—with extensive clinical intelligence, the machine is able to more precisely and effectively identify patients on a trajectory toward sepsis. The resulting outputs enable faster and more effective clinical action that ultimately leads to improved outcomes for patients and the hospital.



    • [1] Centers for Disease Control and Infection, "Sepsis - Basic Information," U.S. Department of Health & Human Services, 16 September 2016. [Online]. Available: [Accessed 6 September 2917 ].
    • [2] Centers for Disease Control and Prevention, "Protect Your Patients from Sepsis Infographic," Department of Health and Human Services, 1 January 2016. [Online]. Available: [Accessed 6 September 2017].
    • [3] P. Thomas Desautels, B. Jacob Calvert, P. c. a. Jana Hoffman, B. Melissa Jay, M. Yaniv Kerem, M. P. Lisa Shieh, M. David Shimabukuro, M. M. Uli Chettipally, M. M. Mitchell D Feldman, M. Chris Barton, S. David J Wales and M. Ritankar Das, "Prediction of Sepsis in the Intensive Care Unit With Minimal Electronic Health Record Data: A Machine Learning Approach," JMIR Med Inform, vol. 4, no. 3, p. 28, July - Sept 2016.

    Targeted, Primary Prevention of Sepsis with the Jvion Machine

    • Sepsis, a body’s overactive, toxic response to an infection, is one of the most expensive and deadly syndromes. But detecting sepsis is difficult in large part because many of its signs and symptoms can be mistaken for other conditions. This challenge is compounded by the need to detect and treat sepsis as early as possible to avoid escalation and possible death.

      Using the Jvion Machine, we are changing the way we identify and prevent sepsis to shift it from one of secondary care to primary prevention. Here is how.

    • vaccination
    According to the Centers for Disease Control and Prevention (CDC), more than 90% of adults and 70% of children who developed sepsis had a health condition that put them at risk. More than 40% of these cases were developed within the community setting. And within that group, certain types of diseases and infections led to sepsis more often including infections of the lungs, urinary tract, skin, and gut.
    In a recent study published in the Morbidity and Mortality Weekly Report, more than 70% of patients who had a sepsis admission had a health event within the past 30 days stemming from a chronic condition that likely required frequent medical attention. While most sepsis initiatives focus on early detection and education, these occurrences could have been prevented through targeted strategies including vaccinations and disease management. But effective prevention requires the ability to determine who is at risk of developing sepsis within the ambulatory setting and before any signs are present. This is exactly where the Jvion Machine is helping providers to do.
    By determining who within the community is at risk of sepsis and the clinical actions that will reduce that risk, providers are using the Jvion Machine to align programs such as pneumonia vaccinations to sepsis reduction initiatives. This capability is enabled by the machine’s Eigenspace platform that more effectively identifies the individuals who are on track to sepsis and the best actions that will result in a better health outcome for a patient. This is the only solution and approach able to provide a path to primary sepsis prevention for community-based sepsis events. And it is the only machine with the breadth and flexibility to help patients across settings and populations.



    • [1] Sepsis Alliance, "Definition of Sepsis," Sepsis Alliance, 1 1 2017. [Online]. Available: [Accessed 18 09 2017].
    • [2] Centers for Disease Control and Prevention, "Making Health Care Safer Think sepsis. Time matters.," Centers for Disease Control and Infection: National Center for Emerging and Zoonotic Infectious Diseases, Atlanta, 2016.
    • [3] M. Shannon A. Novosad, P. Mathew R.P. Sapiano, D. Cheri Grigg, M. Jason Lake, D. Misha Robyn, M. Ghinwa Dumyati, M. Christina Felsen, M. Debra Blog, M. Elizabeth Dufort, P. Shelley Zansky, M. Kathryn Wiedeman, M. Lacey Avery, M. Raymund B. Dantes, M. John A. Jernigan, M. Shelley S. Magill, M. Anthony Fiore and M. Lauren Epstein, "Vital Signs: Epidemiology of Sepsis: Prevalence of Health Care Factors and Opportunities for Prevention," Morbidity and Mortality Weekly Report, vol. 65, no. 33, pp. 864-869, 23 August 2016.

    Emergency Room High Utilizers

    ER high utilizers have been defined as "people of modest means and poor health who go in and out of emergency rooms day after day, their fundamental health issues rarely resolved, at a tremendous and ever-growing cost to hospitals, municipalities and taxpayers." These individuals are largely suffering from chronic conditions and live in areas with restricted access to outpatient care facilities.

    Emergency departments become the primary care provider for many who are unable to access and/or lack the resources needed to secure a regular primary care physician.

    The impact to the system is significant. ER high utilizers and the resulting avoidable ER visits translate into increased resource constraints, financial waste, and overcrowding. The Emergency department is an expensive place to deliver care -- especially when the care administered is for non-emergency occurrences. According to the New England Healthcare Institute (NEHI), approximately $32B is wasted each year on avoidable ER visits.

    The focus on these patients is primarily driven by the need to cut healthcare costs. While ER high utilizers are seen as a major contributor to waste, the equation isn't straight forward. Getting these patients to use primary care pathways is a start, but it doesn't address clinical and social complexity driving what are deemed avoidable ER visits. High utilizer interventions have to be tailored and account for the nuances within the population. For example, mental health and substance-abuse are contributing factors to avoidable ER visits and are correlated with high-levels of spend/resource allocation. The lack of mental health resources is a major underlying driver for these visits and one that has been well documented.

    As value-based models of care and reimbursement redefine accountability and performance both inside and outside of the hospital gain industry traction, more focus will be placed on preventing avoidable ER visits and implementing interventions within the community. Finding the right care environment that leads to better health outcomes will ultimately reduce waste across the system, not just within the ER. And while ER high utilizers are a complex patient cohort, the right levels of care coordination and community-based interventions can help reduce the burden that they place on the hospital while improving the overall health of individual patients.

    Cognitive Technology Empowers Swift, Effective Healthcare Workflows—Improving Patient Outcomes and Empowering Caregivers Let’s start with a quick study in what makes a technology fail. The CueCat was a much-hype... Blog | Read More

    COPD Foundation, GSK, Geisinger Health System, and Jvion Team Together to Help COPD Patients Jun 2017 | Announcements | More CarolinaEast Selects Jvion to Support Patient Quality Goals Sep 2017 | Announcements | More


    Jamieson D. The Treatment of Kenny Farnsworth. Washington Post Magazine 2009.

    Emergency Department Overuse: Providing the Wrong Care at the Wrong Time. Cambridge, MA: New England Healthcare Institute; 2008

    Frequent Users of the ER Fact Sheet; American College of Emergency Physicians.

    Chronic Condition Management
     with Prescriptive Analytics

    • According to the National Council on Aging...

      • 92% of older adults have one, and 77% have at least two chronic conditions
      • Heart disease, cancer, stroke, and diabetes cause almost 60% of all deaths each year
      • Diabetes impacts 23% of the older population
      • An additional 57 million Americans aged 20+ have pre-diabetes
      • 90% of Americans aged 55+ are at risk for high blood pressure
    • Chronic conditions comprise more than three-quarters of the healthcare spend in the United States.

      In addition to patient suffering, chronic diseases also contribute to higher rates of avoidable admissions and readmissions. The Center for Managing Chronic Disease has outlined the circles of influence that help manage chronic diseases and avoid complications.

    • These circles of influence include:

      • Self-management
      • Family
      • Clinical expertise
      • Work/school
      • Community awareness
      • Environment
      • Policy

    Chronic diseases are complex problems that lead to higher mortality, utilization of services, and a greater cost. A recent study released by the Centers for Disease Control and Prevention (CDC) concluded that nearly 66% of all adult discharges from community-based hospitals have Multiple Chronic Conditions (MCCs). MCCs are associated with higher numbers of avoidable admissions and hospitalizations, and increase the risk of readmissions. Moreover, rates of avoidable admissions, hospitalizations, and readmissions are compounded by payer type, race, sex, and age indicating the complex nature of MCCs and the interplay with racial and socioeconomic factors.
    As our population ages and chronic conditions are compounded, managing individuals with one or multiple illnesses will take an even more central role. Finding ways to predict possible readmission risks and complications to drive interventions and self-management will help improve overall health while reducing the risk of hospitalization.
    The good news is that evidence strongly suggests that tailored interventions are not only feasible, they are highly effective at reducing admissions, length of stay, and avoidable readmissions for these individuals.


    Nearly 66% of all adult discharges from community-based hospitals have multiple chronic conditions.


    Nurse and Patient Bedside Visit

    Readmissions Reduction Program

    Reducing avoidable readmissions is a key goal for the Centers for Medicare & Medicaid (CMS).

    There are good reasons why...

    One in every five elderly patients discharged from the hospital is rehospitalized within 30 days

    Medicare patients contributed to $20.1 billion on total hospital costs for potentially preventable hospitalizations

    The estimated cost of unplanned hospital admissions made up $17.4 billion of the $102.6 billion total hospital payments made by Medicare

    Patients under active readmission prevention programs are more likely to have an improved functional status and quality of life

    The Hospital Readmission Program, part of the Affordable Care Act (ACA), requires CMS to reduce payments to hospitals that have demonstrated “excess readmissions.” This program applies to discharges that occur after October 1, 2012 and that are included in subpart I of 42 CFR part 412.

    Hospital risk standardized readmission measures are included for:

    Acute myocardial infarction (AMI)

    Heart failure (HF)

    Pneumonia (PN)

    These initial conditions have been updated to include:

    Chronic obstructive pulmonary disease (COPD)

    Total hip arthroplasty (THA) and total knee arthroplasty (TKA)

    Coronary artery bypass graft (CABG) surgery

    This year, hospitals can lose up to three percent of their Medicare payments under the penalty. Based on a hospital's 30-day readmissions performance on the conditions covered under the program, a penalty is determined. For each penalized hospital, CMS will reduce payments for inpatient stays between October 2014 and September 2015. This penalty applies to any condition. For example, Kaiser Health News provided the following scenario: “(I)f Medicare would normally pay a hospital $15,000 for a kidney failure patient, with a 1.5 percent penalty Medicare would deduct $225 and pay $14,775.” ** Currently, 2,597 hospitals (more than half of all hospitals in the United States) face fines. For more information on the Readmissions Reduction Program, visit the


    Medicare's Readmission Penalties Hit New High. Kaiser Health News; Rau. August 2. 201

    MN Community Measurement Hospital Readmission and Potentially Avoidable Admissions Impact and Recommendation Document; Update May 2011

    Impact of a Comprehensive Heart Failure Management Program on Hospital Readmission and Functional Status of Patients With Advanced Heart Failure

    A Guide To Medicare's Readmissions Penalties And Data

    Patient-Centered Prescriptive AnalyticsGrady Health’s Adoption of the Jvion Machine Delivers 500% Return and Decreases Readmissions by 10% Grady Health’s Adoption of the Jvion Machine Delivers 500% Return and Decreases Readmissions by 1... Testimonials | Read More Man in Wheelchair Leaving HospitalMercy Medical Center Lowers Rates of All-Cause Readmissions by 20+% and Avoids $4M+ in Costs Mercy Medical Center Lowers Rates of All-Cause Readmissions by 20+% and Avoids $4M+ in Costs ... Testimonials | Read More

    Grady Health System Is Working to Lower Readmissions with Jvion’s Clinical Predictions Sep 2016 | Latest Press | More Washington State Hospital Association Selects Jvion to Support Statewide Quality Initiative Sep 2018 | Announcements | More

    Clostridium Difficile Bacteria

    Clostridium Difficile Infection

    • Clostridium Difficile (C. Difficile) is a bacterial cause of diarrhea in hospitalized patients and in those who have been treated with prolonged antibiotics. It is characterized by watery diarrhea with dehydration and overwhelming abdominal sepsis and shock. The infection is hard to detect as it overlaps with many other causes of diarrhea and requires a high “index of suspicion” on the part of caregivers. Moreover, the bacteria that causes C. Difficile is resistant and hard to eradicate.
    • Clostridium Difficile Bacteria
    A Clostridium Difficile Infection (CDI) causes significant risk of morbidity and increased costs for providers and the patients suffering from the infection. In a recent study conducted by the National Heart, Lung, and Blood Institute (NHLBI), the average hospital cost for CDI per case ranges from $9,000 to $11,500 and one in 11 patients over the age of 65 will die within a month of a CDI diagnosis. The total cost of U.S. healthcare for CDIs approaches $500 Million per year. And the average increase in length of stay directly attributed the infection varies widely between 3 and 21 days.
    The Jvion Machine is equipped to identify patients at risk of developing a CDI during a hospital stay and deliver the personalized interventions that will prevent the infection. The machine incorporates the latest CDI research and clinical intelligence to pin point individuals on a risk trajectory toward a CDI while accounting for those asymptomatic patients who are nearly impossible to detect. The machine renders granular, patient-level propensity information that is customizable to a provider’s operational needs. The clinical actions enabled by the Jvion Machine empower care givers with the information they need to work collaboratively across functions to lower CDI rates and losses while improving health outcomes.

    Conquering C. Difficile Associated Diarrhea with Probiotics

    According to a recent study published by the Cochrane Library, the administration of probiotics to those at high-risk of developing C.difficile-associated diarrhea (CDAD) reduced a patient’s risk by 70%. This finding provides a low-cost, non-invasive option for reducing incidences of CDAD and the associated patient suffering. But the effectiveness of the treatment requires the early identification of at-risk patients who could benefit from probiotics. This is where the Jvion Machine is bridging the gap between new treatments and at-risk populations.

    The patient population at high-risk of developing CDAD comprises 15% of the total patient population. These individuals are at more than 10% risk of developing the infection with an overall incidence rate of 1.7%.

    The Jvion Machine is able to correctly identify 95% of all CDAD cases in the 15% of the population where the risk is greater than 10%. For a medium-size hospital with a patient population of 20,000, 3,000 patients would be at high-risk, and of those 323 would develop CDAD. If probiotics are administered to the high-risk population, it stands to reason that 226 or (70%) of these incidences could be prevented.

    Probiotics cost $24 per patient. Using the Jvion Machine, we can target the administration of these probiotics to the 15% of the population at high-risk of an infection. The total spend of the intervention across all 3,000 patients comes to $72,000. The cost estimate per CDAD episode cited within the Cochrane study is $7,286. By preventing the anticipated 226 cases of CDAD, we would avoid $1,646,636 in costs. The total cost savings after accounting for the cost of treatment is $1,574,636. And this is all enabled by the ability to identify who is on a trajectory toward CDAD risk, providing the right information on the contributors to that risk, and enabling the clinical action that will lead to the best possible outcomes—in this case probiotics.



    Provider-based Impact Deep Dive: Bundled Payments

    As part of a drive toward innovation, the Centers for Medicare & Medicaid Services (CMS) continues to roll out episode-based payment initiatives focused on improving cardiac and orthopedic care.

    These programs include the current Comprehensive Care for Joint Replacement (CJR) model and proposed:

    Acute Myocardial Infarction (AMI) Model;

    Coronary Artery Bypass Graft (CABG) Model;

    Surgical Hip and Femur Fracture Treatment (SHFFT) Model; and

    Cardiac Rehabilitation (CR) Incentive Payment Model

    This intelligence along with a patient’s clinical history are mapped within the machine’s Eigen-based architecture to pin point the interventions that will drive the highest levels of engagement for each individual patient. With this propensity information, clinicians can better align clinical actions and resources to the patients who are most likely to benefit and engage with specific care activities and interventions.

    These models all share common goals aimed at enabling collaboration, communication, and prevention; and improving the quality and efficiency of care for Medicare patients. The distinct feature of episode-based payments is the incentive to deliver better care at a lower cost from the time a patient is admitted through 90 days post-discharge.

    The carrots and sticks that are core to the program have helped to deliver significant savings across participating providers. In a recent study published in JAMA Internal Medicine, covered episodes under the current CJR saw a decrease of $5,577 or 20.8%. New bundles, which are scheduled to go live in July 2017, will extend the current program to include patients admitted for heart attacks, bypass surgery, and/or cardiac rehabilitation following a heart attack or heart surgery. The CJR program will be replaced by the SHFFT model, which extends the covered treatments to include patients who receive surgery after a hip fracture.

    Mastering your CJR patient population means that your patients are healthier, you better allocate your resources, and that you avoid potential repayments to Medicare at the end of the model performance year.

    Jvion's Cognitive Clinical Success Machine is specifically designed to help providers manage at-risk, episode-based bundled payment models by empowering providers with a high-definition view into patient predispositions, risk manifestations, that the actions and interventions that will:

    Identify - at the time of admission - patients who are likely to have a nosocomial event

    Optimize the inpatient length of stay

    Stop 30/60/90 day readmissions

    Align patients that the post-acute care environment that will drive the best quality outcomes

    Reduce risk across care transition points

    Enable the best care action paths to improve outcomes while reducing costs

    Jvion's Cognitive Clinical Success Machine accounts for the massive and complex body of patient data including the exogenous factors that account for 60% of a person's health outcomes. The machine does this using a quadrillion cognitive machine dimensions and up to 10,000 factors to enable a high definition view of the patient 30, 60, 90 and up to 365 days into the future. This view accounts for the full patient portrait of risk across all care settings and enable the best action paths that will prevent avoidable complications and improve outcomes. When applied to a specific bundle, providers are enabled with the tool and recommendations they need to drive individualized interventions at every point across the episode of care.

    • 1
    • 2