no-shows.jpg

A Cognitive 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

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

Jvion’s Cognitive 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 Cognitive Machine 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 solution 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.

Individualized, Patient-specific Cognitive Machine Application This large safety-net hospital, headquartered in Cleveland, OH, is using Jvion’s Cognitive Machin... Testimonials | Read More 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

Jvion's Machine Identifies Patients at Risk of Experiencing a Major Depressive Episode Feb 2018 | Announcements | MoreJvion Launches Latest Clinical Vector Aimed at Preventing Opioid Abuse Mar 2018 | Latest Press | More

wheelchair-bound.jpg

Relieving the Pressure: Taking on Pressure Injuries with the Cognitive Engine

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.

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 Cognitive 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 cognitive 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 cognitive 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 cognitive machine enables across critical performance measures in healthcare (many of the same ones that overlap with pressure injuries):

Reducing readmissions

Improving workflows and reducing length of stay

Improving customer satisfaction and HCAHPS scores

Bedside patient rescue

Reducing hospital acquired infections and conditions

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 cognitive 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.

Making AI Work in a Small Hospital This 160-bed hospital serving coastal Carolina has taken bold steps in cognitive machine applicat... Testimonials | Read More 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

Jvion's Machine Identifies Patients at Risk of Experiencing a Major Depressive Episode Feb 2018 | Announcements | MoreJvion Launches Latest Clinical Vector Aimed at Preventing Opioid Abuse Mar 2018 | Latest Press | More

suicide-prevention.jpg

A Cognitive 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.

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%.

Jvion’s Cognitive Clinical Success 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 cognitive 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 cognitive machine, however, understands that clinical data as part of a comprehensive patient picture. Paired with other clinical and exogenous data, the cognitive machine can see risk that might go unseen (or unspoken) otherwise. The cognitive machine 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 cognitive 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.

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

Individualized, Patient-specific Cognitive Machine Application This large safety-net hospital, headquartered in Cleveland, OH, is using Jvion’s Cognitive Machin... Testimonials | Read More

Jvion's Machine Identifies Patients at Risk of Experiencing a Major Depressive Episode Feb 2018 | Announcements | MoreJvion's Solution Out-predicts Stress Tests and CT Coronary Angiograms in Predicting 12-month Acute Myocardial Infarction Events Feb 2016 | Announcements | More

opioid-abuse.jpg

Cognitive Technology Gives Hope in the Fight Against Opioid Addiction

The staggering, tragic toll of opioid-related deaths and overdoses seems to grow daily.

The CDC reported that emergency room visits for overdoses increased 30 percent from July 2016 through September 2017. Overdoses increased among men and women in every age group and every region of the country. Illinois alone saw a 66 percent increase in opioid overdose trips to the ER.

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 the Cognitive Clinical Success Machine, 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 cognitive 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. Cognitive clinical intelligence represents a promising, hopeful frontier in addressing the vexing human tragedy of the growing opioid epidemic.

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

Individualized, Patient-specific Cognitive Machine Application This large safety-net hospital, headquartered in Cleveland, OH, is using Jvion’s Cognitive Machin... Testimonials | Read More

Jvion's Machine Identifies Patients at Risk of Experiencing a Major Depressive Episode Feb 2018 | Announcements | MoreCOPD Foundation, GSK, Geisinger Health System, and Jvion Team Together to Help COPD Patients Jun 2017 | Announcements | More

depression.jpg

Getting Beyond the Stigma — The Cognitive 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.

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 Jvion’s cognitive technology makes a major, unique difference. The cognitive machine 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.

Making AI Work in a Small Hospital This 160-bed hospital serving coastal Carolina has taken bold steps in cognitive machine applicat... Testimonials | Read More
Individualized, Patient-specific Cognitive Machine Application This large safety-net hospital, headquartered in Cleveland, OH, is using Jvion’s Cognitive Machin... Testimonials | Read More

CarolinaEast Medical Center Selects Jvion to Support Patient Quality Goals Sep 2017 | Announcements | MoreJvion Launches Vector Focused on Suicide and Self-harm Jan 2018 | Announcements | More

The results of the Cognitive Clinical Success 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 cognitive 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 cognitive 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 cognitive 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 cognitive 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 cognitive machine and the Jvion 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.

injury-management.jpg

Sepsis Readmission

The Cognitive Clinical Success 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.

Because the machine accounts for the full etiology of the readmission, the recommended actions 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.

sepsis.jpg

Avoiding Sepsis in the Hospital Using the Cognitive Clinical Success 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.

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. However, with the application of the Cognitive Clinical Success Machine’s Eigen-based engine, 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

This capability is driven by the transformative Eigen approach that underpins Jvion’s machine. By combining the established Eigen Sphere infrastructure—which enable the analysis of more than a quadrillion 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.

Reducing CAUTI Costs and Improving Overall Patient Care "They looked to Jvion for a predictive solution to help target and reduce Catheter Associated Uri... Testimonials | Read More

Jvion’s C. Difficile Vector Lowers Infection Rates and Improves Health Jul 2017 | Latest Press | MoreUMC Health System Selects Jvion’s Cognitive Machine to Drive Improvements in Care Quality Mar 2018 | Announcements | More

References

[1] Centers for Disease Control and Infection, "Sepsis - Basic Information," U.S. Department of Health & Human Services, 16 September 2016. [Online]. Available: https://www.cdc.gov/sepsis/basic/index.html. [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: https://www.cdc.gov/sepsis/pdfs/HCP_infographic_protect-your-patients-from-sepsis_508.pdf. [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.

vaccination.jpg

Targeted, Primary Prevention of Sepsis with the Cognitive Clinical Success 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 Cognitive Clinical Success 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.

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 Cognitive Clinical Success 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 Cognitive Clinical Success 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.

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

Making AI Work in a Small Hospital This 160-bed hospital serving coastal Carolina has taken bold steps in cognitive machine applicat... Testimonials | Read More

COPD Foundation, GSK, Geisinger Health System, and Jvion Team Together to Help COPD Patients Jun 2017 | Announcements | MoreSisters of Charity to Apply Jvion's Cognitive Machine to Prevent Opioid Abuse and More Effectively Address Depression and Suicide Feb 2018 | Announcements | More

References

[1] Sepsis Alliance, "Definition of Sepsis," Sepsis Alliance, 1 1 2017. [Online]. Available: https://www.sepsis.org/sepsis/definition/. [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.jpg

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.

Making AI Work in a Small Hospital This 160-bed hospital serving coastal Carolina has taken bold steps in cognitive machine applicat... Testimonials | Read More
Individualized, Patient-specific Cognitive Machine Application This large safety-net hospital, headquartered in Cleveland, OH, is using Jvion’s Cognitive Machin... Testimonials | Read More

CarolinaEast Medical Center Selects Jvion to Support Patient Quality Goals Sep 2017 | Announcements | MoreJvion's Machine Identifies Patients at Risk of Experiencing a Major Depressive Episode Feb 2018 | Announcements | More

References

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.

diabetes-glucose-check.jpg

Chronic Condition Management Through Cognitive Machines

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.

What Makes Technology Truly Transform Healthcare? Consider the MRI and the Cognitive Machine Most technology advances in iterations. New healthcare devices and technologies often improve on... Blog | Read More The Box of Medical Magic: The Cognitive Clinical Success Machine Every healthcare practice and hospital has endured a tough technology adoption. A new system intr... Blog | Read More

Jvion Launches Vector Focused on Suicide and Self-harm Jan 2018 | Announcements | MoreCOPD Foundation, GSK, Geisinger Health System, and Jvion Team Together to Help COPD Patients Jun 2017 | Announcements | More

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

References

National Council on Aging: Chronic Disease Fact Sheet

The Center for Managing Chronic Disease: What is Chronic Disease

Steiner CA, Friedman B. Hospital Utilization, Costs, and Mortality for Adults With Multiple Chronic Conditions, Nationwide Inpatient Sample, 2009.

bedside-visit.jpg

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 CMS.gov.

References

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

clostridium-difficile.jpg

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.

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.

Jvion’s Cognitive Clinical Success Machine is equipped to identify patients at risk of developing a CDI during a hospital stay. 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 Cognitive Clinical Success 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 Jvion’s Cognitive 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%.

Jvion’s Cognitive 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 Jvion’s Cognitive 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.

Reducing CAUTI Costs and Improving Overall Patient Care "They looked to Jvion for a predictive solution to help target and reduce Catheter Associated Uri... Testimonials | Read More

Jvion’s C. Difficile Vector Lowers Infection Rates and Improves Health Jul 2017 | Latest Press | MoreCarolinaEast Medical Center Selects Jvion to Support Patient Quality Goals Sep 2017 | Announcements | More

References

Clin Microbiol Infect. 2012 Mar;18(3):282-9. doi: 10.1111/j.1469-0691.2011.03571.x. Epub 2011 Jun 10.

J Hosp Infect. 2014 Sep;88(1):12-21. doi: 10.1016/j.jhin.2014.04.011. Epub 2014 May 17

The use of probiotics to prevent Clostridium difficile diarrhea associated with antibiotic use. 19 December 2017; Goldenberg JZ, Yap C, Lytvyn L, Lo C, Beardsley J, Mertz D, Johnston BC. http://www.cochrane.org/CD006095/IBD_use-probiotics-prevent-clostridium-difficile-diarrhea-associated-antibiotic-use.

stethoscope-exam.jpg

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.

customer-satisfaction.jpg

Improving the Patient Experience with Cognitive Science

CMS, along with the Agency for Healthcare Research and Quality (AHRQ) developed the HCAPS survey to assess a patient’s experience and perspectives on hospital care. At a high level, the key levers included within the survey are communication, responsiveness, pain management, care transition and planning, hospital environment, and overall rating. But the challenge with the survey is that it is retrospective. By the time the hospital finds out about gaps in a patient’s experience, he or she has already been discharged.

To help providers proactively identify potential gaps in the patient experience, the Cognitive Clinical Success Machine is identifying patients at admission who have a high propensity of experiencing a gap in care. For example, the machine uses the complex Eigen Sphere topology within its Eigenspace platform to identify specific factors such as illiteracy that influence a patient’s care experience. It leverages all of the data and intelligence it has to flag these gaps in care and alert care givers to the possibility that a specific patient will have a poor experience across key levers such as communication. Providers are able to apply this intelligence to adjust the methods and resources used to support a patient such as medication labels that include pictures instead of written instructions. The ultimate goal and outcomes is to drive up patient engagement and adherence by addressing gaps in the patient experience, which translate into improved health and care quality.

 

Learn how hospitals across the country are using Jvion's Cognitive Clinical Success Machine to stop patient illness, improve intervention effectiveness, and drive toward value-based models of care and reimbursement.

eigen-spheres2.jpg

Engaged Patients and The Cognitive Clinical Success Machine

To determine a patient’s likelihood to engage with a specific clinical action or intervention, the Cognitive Clinical Success Machine makes sense of the thousands of socioeconomic and behavioral factors that influence the propensity to engage.

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.

UnityPoint Health is Bringing the Power of AI to Patients Feb 2018 | Announcements | MoreJvion’s Cognitive Clinical Success Machine Helps Improve a Patient’s Care Experience Sep 2017 | Latest Press | More

 

Learn how hospitals across the country are using Jvion's Cognitive Clinical Success Machine to stop patient illness, improve intervention effectiveness, and drive toward value-based models of care and reimbursement.

check-pulse.jpg

Bedside Patient Rescue in the Workflow

BPR is built as a “push system” that drives assessment, follow up, and automated escalation. It is focused on enabling time-limited escalation of expertise to the bedside to stop deterioration and reduce mortality.

BPR Workflow Example...

An alert is sent to the RN. The Bedside Nurse signs and factor scores; Charge Nurse checks with bedside nurse as needed

An alert is sent to the Service Provider. Service provider evaluates and resolves; Bedside nurse SBAR and assist as needed. Enter vital signs and Factor score after interventions; Charge nurse checks with bedside nurse as needed.

An alert is sent to re-check patient. Service provider re-asses, broaden differential, check intervention intensity; Bedside nurse SBAR and assist as needed. Enter vital signs and Factor score; Charge nurse checks with bedside nurse as needed

Consult broaden differential, consult team, validate goals and plan of care; Service provider communicate interventions, results and plan; Bedside nurse SBAR and assist as needed. Enter vital signs and Factor score; Charge nurse checks with bedside nurse as needed

The addition of the BPR vector to Jvion’s Cognitive Clinical Success Machine will extend our ability to stop patient deterioration and save more lives. Working in collaboration with the Mayo Clinic team, we have developed something that is positioned to help countless patients and the clinicians who care for them.

image-600x400-04.png

Based on an analysis performed as part of the Bedside Patient Rescue (BPR) project, failure to recognize acute patient deterioration is the most common contributor to mortality*. But current early warning scores that combine expert opinion and classical statistical models are not very effective in lowering mortality rates.

catheters.jpg

Hospital Acquired Conditions Overview

Hospital Acquired Conditions (HACs) are conditions that are defined by section 5001(c) of the Deficit Reduction Act of 2005 that...

  • Are high cost, high volume or both,
  • Result in the assignment of a case to a DRG that has a higher payment when present as a secondary diagnosis, and
  • Could reasonably have been prevented through the application of evidence‑based guidelines.

catheters

These common medical errors add up to more than $4.5 billion in additional spending each year.

HAC Scores

HAC scores are based on six quality measures that fall into two domains.

Domain 1: Agency for Healthcare Research and Quality (AHRQ) Patient Safety Indicator (PSI) measure 90 Composite

Domain 2: Centers for Disease Control and Prevention (CDC) National Healthcare Safety Network (NHSN) Healthcare-Associated Infection (HAI) measures including:

Central Line-Associated Bloodstream Infection (CLABSI)

Catheter-Associated Urinary Tract Infection (CAUTI)

Surgical Site Infection (SSI) (colon and hysterectomy)

Methicillin-resistant Staphylococcus aureus (MRSA) bacteremia

Clostridium difficile Infection (CDI)

References

More Info

For more information on the HAC Reduction Program, please visit CMS at CMS.gov

Measures

Hospital-Acquired Condition (HAC) Reduction Program

Methodology

How Hospital-Acquired Conditions Are Calculated

CMS

A brief overview of CMS’ Medicare payment policy for selected HACs, PDF document

surgical-equipment.jpg

Healthcare Associated Infections Overview

Healthcare-Associated Infections (HAIs) are cited by the World Health Organization (WHO) as a critical public health problem because of the impact that HAIs have on morbidity and mortality around the world. The most common global HAIs include infections of surgical wounds, the blood stream, the urinary tract, and the lower respiratory tract.

surgical-equipment

In addition to the most common infections, diseases including severe acute respiratory syndrome (SARS), viral hemorrhagic fevers such as Ebola, avian influenza, and pandemic influenza have placed special focus on the ability of providers to stop the spread of outbreaks within the facility and out into the community. Adding to the complexity is the emergence of antibiotic resistance that has created "super-bugs," which are difficult to treat and manage. This is critically important for hospitals that may act as "permanent reservoirs" of resistant bacteria.

Within the United States, HAIs are estimated to impact close to 1M people per year according to a 2011 Centers for Disease Control and Prevention (CDC) report.

The infections break down to:

  • Pneumonia: 157,500
  • Gastrointestinal Illness: 123,100
  • Urinary Tract Infections: 93,300
  • Primary Blood Stream Infections: 71,900
  • Surgical Site Infections: 157,500
  • Other Types of Infections: 118,500

A recent CDC study found that on any given day, approximately 1 in 25 hospital patients has an HAI. Moreover, about 75,000 patients with an HAI died while in the hospital.

In 2008, the Federal Steering Committee for the Prevention of Health Care-Associated Infections was established.

This group includes individuals from the Department of Health and Human Services, U.S. Department of Defense, U.S. Department of Labor, and U.S. Department of Veterans Affairs. This group developed The National Action Plan to Prevent Health Care-Associated Infections: Road Map to Elimination in 2009. This plan provides a framework and direction on how to eliminate HAIs within acute care settings, outpatient settings, and long-term care facilities. Additionally, the Partnership for Patients program was established under the Centers for Medicare & Medicaid Services (CMS). This program is aimed at driving public-private partnerships to reduce HAIs and readmissions. Twenty-six organizations are working with more than 3,700 hospitals to meet target reduction levels over the next three years.

References

Core components for infection prevention and control programmes Infection Prevention and Control in Health Care Informal Network Report of the Second Meeting, 26 - 27 June 2008, Geneva, Switzerland

Centers for Disease Control and Prevention: Healthcare-associates Infections (HAIs)

Multistate Point-Prevalence Survey of Health Care–Associated Infections; The New England Journal of Medicine

Office of Disease Prevention and Health Promotion; National Action Plan to Prevent Health Care-Associated Infections Road Map to Elimination

Stone, P, et al. "State of infection prevention in US hospitals enrolled in the National Health and Safety Network." American Journal of Infection Control 42, no. 2 (2014): 94-99.