In 2020, the Department of Justice estimated that fraudulent, wasteful, and abusive (FWA) billing practices account for more than $100 billion of the nation’s healthcare expenditures.¹ Today, the National Healthcare Anti-Fraud Association (NHCAA) conservatively estimates that healthcare FWA costs the nation about $68 billion annually, representing 3% of the nation’s $2.26 trillion in healthcare spending.²  FWA estimates from commercial health plans range as high as $230 billion annually, or 10% of total healthcare spending.³ 

This lost money is far from a concept or abstraction. Every dollar lost to fraudulent, wasteful or abusive billing hurts patients, honest providers, payors and governments. Third-party benefits providers often receive outsized blame for these costs, when in reality, fraud, waste, and abuse is extremely difficult to detect using conventional methods because providers submitting excessive or fraudulent billing claims are constantly changing their methods to avoid detection. 

Fortunately, new advances in artificial intelligence (AI) technology provide our industry a clear path forward to lowering healthcare costs by reducing excessive or overbilling in a way that rewards good providers and returns more dollars to patient care. By helping healthcare payors detect and prevent fraudulent, wasteful and abusive billing practices in greater quantities and before payments are made, it is estimated that up to $1 trillion in fraudulent, wasteful, and abusive costs can be eliminated from U.S. healthcare by 2030. It’s time to stop blaming benefits providers for spiraling costs and start addressing the technology that powers their day-to-day healthcare claims editing, audit and review systems. Here are the key concepts to consider. 

Static Claims Editing Systems Are Exploitable

Most healthcare benefit systems are based on a static, rules-based or use case-based technology that audit a very narrow set of criteria in determining whether a healthcare claim should be paid to the provider. While these systems do a good job of processing and paying billions of claims each year, their antiquated technology allows hundreds of billions of dollars in excessive bills or fraudulent bills to be paid. It’s not because the claims management companies don’t want to stop fraudulent and excessive billing, it’s because their technology can’t see the exploitation that’s occurring. 

Technology Has To See Provider Behaviors, Relationships and Outliers 

When cases are reviewed and adjudicated using traditional rules-based, use case-based and conventional AI methods, dynamic provider behaviors, relationships and outliers are hard to detect. You have to see a provider’s behavior around a claim and all claims and that provider’s relationships with other providers in order to detect fraudulent, wasteful and abusive billing at a significant level before claims are paid out. This means that this sophisticated, interdependent relationship between providers, a current claim form, historical claim forms, and all other providers in a network has to be able to be identified, analyzed and reported on in less than one second when a claim is submitted for payment. 

The Promise of Artificial Intelligence 

AI scares a lot of people, because it is hard to wrap your arms around what it is. Simply stated, one definition of artificial intelligence (AI) is technology that thinks and does what a human can do, but much faster. Even this simple description leaves out the benefit of unsupervised AI being able to identify an infinite number of ‘math problems’ that a human might not even know to look for in a data set. 

Early AI, and much of the conventional AI used in healthcare FWA detection and payment integrity work today, is not much more than a really advanced Excel spreadsheet. Much of the conventional AI operates using structured machine learning. This means that a machine is trained to perform an algorithm or series of algorithms that take an “if-then” approach to analyzing data. 

These structured machine-learning approaches are very helpful, but miss a lot of the dynamic trends, patterns and outliers that can be detected by advanced, unsupervised machine learning. To ‘see’ all of the FWA activity, you have to deploy unsupervised machine learning that identifies trends, patterns and outliers without being “told” specifically to go perform the task. This enables payors to see new fraud trends and patterns forming in near real-time that are indicators of behaviors and relationships that may be signs of excessive payments, over-payments, or even fraud. In short, you can see things and stop things from happening that you did not even know to tell your technology or staff to pursue. 

The Reality Of Integr8 AI^™ Technology In Stopping FWA 

Integr8 AI technology is a new generation of artificial intelligence that is patented for the detection of operational threats. The first application of the technology is to enable healthcare payors – commercial health plans, TPAs, CMS programs, etc. – to take a dynamic, provider-centric approach to processing, auditing and paying healthcare claims. This technology has proven to increase FWA detection by 2X to 10X in initial commercial use, all because it can “see” FWA activity that conventional technology can’t see. And Integr8 AI can see it in a way that does not slow down the claims editing, review and payment process. 

As one payment integrity executive said, “We need to be able to see the FWA activity that we all know is there. Current technology just doesn’t let us see the volume of FWA that next-generation Integr8 AI technology enables. The best part is that this type of technology operates on top of our current claims editing system. We don’t have to make new capital investments to make a big difference fast.”  

The Bottom Line for Benefits Providers

The battle against spiraling healthcare costs has important implications for every stakeholder in the healthcare value chain, but third-party benefits providers stand to benefit the most when fraudulent, wasteful and abusive costs are controlled. Today, almost a third of all insured Americans receive their health coverage through a third-party provider. Removing fraudulent, wasteful, and abusive costs helps benefits providers lower the cost of benefits for customers and their employees, automate and streamline operations, and increase bottom-line profitability. Technology, like Integr8 AI, enables the benefits to be quantified quickly and recognized almost immediately – regardless of what claims editing and adjudication system is being used. 

Now is the time for benefits providers to embrace sophisticated AI solutions for claims management, moving from a relatively static, claims-based model to a dynamic, provider-centric model. It’s time to take control in the fight against adaptable, malicious actors. That fight starts and ends with thinking about the technologies we have in place. 

About Theja Birur 
Theja Birur is the founder of 4L Data Intelligence and inventor of the patented Integr8 AI intelligence platform. She has 20 years of experience in analytics and artificial intelligence with most of that focused on solving payment and quality challenges for healthcare payers and public health agencies. Her career includes work in the government sector with the Ontario Ministry of Health in Canada, with IBM as a management consultant, and in the IBM Innovation Lab focused on analytics. Prior to founding 4L Data Intelligence, Theja worked as a consultant for the California State Compensation Insurance Fund where she was an Associate Director over Big Data and Data Warehouse functions.

What You Should Know:

• Amino Health, the leading digital healthcare guidance company, today announced $80 million in both equity and debt financing led by Transformation Capital and Oxford Finance LLC, respectively.
• In the face of declining digital health investment, this funding underscores the success of Amino Health’s proven model and enables the company to scale its technology and continue its strong growth trajectory. 

Funding to Lead to Broadening of Amino Health’s Horizons in Attempt to Improve Healthcare Guidance

Amino Health has dedicated the last decade to developing a digital navigation experience that intuitively guides members to high-quality, cost-effective care through their unique health plans and benefits. As the health technology market exploded with the launch of new solutions, Amino Health steadily grew to support 1.6 million members, with a 97% customer retention rate and a net promoter score of 80+. Today, the company connects members to high-value providers and facilities at three times the rate of the baseline population, influencing cost savings, increased member satisfaction, and improved health outcomes.

Though its founding roots are in providing a direct-to-consumer product, Amino Health now is delivered through an enterprise subscription model, bringing its configurable, industry-leading consumer solution to the members of participating health plans, third-party administrators, benefits administrators and concierge care vendors. 

“While healthcare has evolved significantly over the last 10 years, Amino Health has remained steadfast in our commitment to the needs of patients by empowering them with the information necessary to make informed healthcare decisions,” said David Vivero, CEO and co-founder of Amino Health. “This investment and financing validate our core belief that putting people first has value in healthcare, and the need for pioneering technology solutions that support this endeavor is not only important – it’s imperative. In a crowded, highly regulated market, this funding will fuel Amino’s continued growth, product innovation and ability to facilitate deep integrations with enterprise partners to support more patients at scale.”

Amino Health’s easy-to-use technology platform views healthcare’s complexity as an inevitable result of the innovation taking place across the industry. Market expansion, new regulatory requirements, and an increase in available data – like the published negotiated rates required by the federal Transparency in Coverage (TIC) Rule – make navigation technology a critical tool for plan members and the companies that provide health benefits to them. In response to recent regulations, Amino Health enhanced its platform to surpass TIC Rule requirements by integrating new pricing data into their intuitive navigation experience that guides members to the highest quality, most cost-effective corners of their networks. 

What You Should Know:

• Lucem Health, a Mayo Clinic Platform portfolio company, has closed a Series A venture capital funding round of $7.7M led by Mayo Clinic, Granger Management and Mercy (St Louis).
• Lucem Health helps clinical AI innovators transform data science into innovative, trusted solutions that can detect diseases earlier and optimize care delivery, positively impacting patient lives, improving the physician and provider experience, and ultimately producing improved outcomes.

How Lucem AI Platform Works

The Lucem Health Platform takes data from any source, normalizes and connects it to any AI model or algorithm, and delivers the resulting predictive insights seamlessly into existing clinical workflows. By embedding seamlessly into PACS, EHRs, and other data-driven workflows, the Lucem Health Platform makes it easier for hospitals, clinics, and physician practices to build, train, and scale AI models using their own data.

Expansion Plans

The funding will be used to advance development of Lucem Health’s platform for clinical AI solution deployment, grow the company’s solution portfolio and expand its sales and marketing capacity. The company recently launched Lucem Health Reveal, a family of solutions which uses AI and existing data to identify patients at higher risk of serious or chronic disease.

Related: Mayo’s Lucem Health Launches AI-Driven Early Disease Detection Platform

“AI has tremendous potential to transform and augment how physicians and providers practice medicine, make decisions and serve their patients. Yet, so far, we have barely scratched the surface of AI’s potential in healthcare,” said Sean Cassidy, founding CEO of Lucem Health. “We started Lucem Health to accelerate integration of powerful AI-generated insights into care delivery workflows in a thoughtful, responsible way. In a challenging market for raising capital, we appreciate our investors’ confidence and support.”

What You Should Know:

• Emory Healthcare (EHC) today announced a partnership with NeuroFlow to support and improve the delivery of psychiatric services for both patients and providers at their Brain Health Center and several sites across Georgia.
• NeuroFlow, which offers a cloud-based registry and enterprise platform to help facilitate collaborative care, will support EHC clinical services’ data-driven approach to patient care, with a sharpened focus on improving communication between care teams, including primary care providers, behavioral health specialists and care coordinators.
• The implementation of NeuroFlow in Emory Healthcare’s primary care clinics will begin in May 2023, with plans to expand to additional clinics throughout the year.

Increasing Access to Behavioral Health Services

The strategic partnership will seek to complement and scale Emory’s new collaborative care model (CoCM) within its primary care clinics. The CoCM is part of Emory’s Integrated Behavioral Health (IBH) Program, which was formed by the Department of Psychiatry and Behavioral Sciences to help meet significant access demands for behavioral health services in the EHC network. CoCM is embedding licensed specialists called behavioral health care managers (BHCMs) to work in EHC primary care clinics alongside primary care clinicians to provide psychotherapy onsite and serve as liaisons with psychiatric consultants.

Through NeuroFlow, Emory patients are given 24/7 access to self-directed content that reinforces psychotherapy guided by the program’s BHCMs and provides care teams with frequent measures of patient progress. This engagement between office or telehealth visits supports traditional care and can lead to faster recovery, better overall outcomes and fewer readmissions.

“This collaboration introduces the type of technology needed to assist our healthcare providers and patients in bridging the gap between mental and physical health,” says William McDonald, PhD, chair of Emory’s Department of Psychiatry and Behavioral Sciences. “While our teams already practice collaborative, integrated care, this partnership serves as a driving force to expand and enhance these endeavors throughout the Emory ecosystem, ultimately resulting in improved outcomes and reduced costs.”

What You Should Know:

• AmerisourceBergen (AB), a global healthcare company, has announced a strategic partnership with SteadyMD, a B2B telehealth infrastructure provider for the co-creation of a telehealth solution focused on Test to Treat opportunities. The solution is being offered as a pilot to independent community pharmacies across the US.
• In addition to the commercial partnership, AmerisourceBergen has also made a minority investment in SteadyMD through its venture fund AB Health Ventures.

Test to Treat Pilot

AmerisourceBergen’s telehealth solution is being developed to expand the number of Test to Treat services that independent pharmacies can offer to patients. The Test to Treat initiative was launched in 2022 to help provide quick and equitable access to COVID-19 testing and treatment in the early days of infection. The model is intended to provide a seamless patient experience and designed to reach high-risk, underserved populations.

With its telehealth solution, AmerisourceBergen is evaluating the long-term viability of the Test to Treat model for use cases, beyond COVID-19, to improve access to treatment. The pilot program has been launched across a group of 130 independent retail pharmacies, including members of the Good Neighbor Pharmacy network. Over a span of 12 weeks, pilot participants will utilize the SteadyMD platform to provide patients with a quick and accessible Test to Treat option within their pharmacy, at an affordable price. Patients can test for an illness or condition and then, if deemed necessary by a SteadyMD physician, consult with them on demand through the telehealth platform and receive a prescription for treatment.

Pharmacies participating in the telehealth pilot program can use the solution to help patients obtain COVID-19 oral antiviral therapies, as appropriate. AmerisourceBergen and SteadyMD will continuously evaluate opportunities to expand use cases during and after the program.

“The Test to Treat initiative is an important acknowledgement of the role of pharmacists and pharmacies as accessible healthcare providers and destinations,” said Jenni Zilka, Senior Vice President, Good Neighbor Pharmacy Field Programs & Services at AmerisourceBergen. “In order for pharmacies to continue making a sustainable impact on the communities they serve, we need to continue providing them the tools, resources, and authority to provide necessary clinical services, where appropriate. AmerisourceBergen’s exploration of a telehealth solution with SteadyMD to enhance the scope of the Test to Treat model is just one way we’re continuing to support the important role of the pharmacist in the healthcare ecosystem.”

What You Should Know:

Morgan Health, the JPMorgan Chase & Co. business unit announced a $25M investment in Kindbody, a fertility clinic network and global family-building benefits provider for employers offering the full-spectrum of reproductive care from preconception to postpartum through menopause.

Kindbody is a technology-driven fertility clinic network and family-building benefits provider for employers offering virtual and in-person care supporting 112 leading employers, covering more than 2.4 million lives. The company’s clients span virtually every industry and include Walmart, Medtronic, Lyft and GEICO. Kindbody serves patients at 32 signature clinics and hundreds of partner clinics in the U.S.

A New Generation of Fertility Care

Kindbody’s clinically-managed program covers the full-spectrum of reproductive health, including both female and male fertility, which encompasses fertility assessments and education, fertility preservation, genetic testing, in vitro fertilization (IVF), donor and surrogacy services, and adoption, as well as a full continuum of reproductive care including physical, mental and emotional support.

Kindbody’s model is unique in that it is the only family-building benefits provider for employers that owns and operates fertility clinics. The company saves employers 25%-30% by contracting directly to provide comprehensive virtual and in-person care to their employees. As the direct provider of care, Kindbody is uniquely positioned to decrease cost, improve the patient experience and deliver better health outcomes.

What You Should Know:

• Solera Health, the premier technology platform for connecting people seamlessly and easily to health solutions that work, announces a multi-year strategic partnership with Horizon Healthcare Services, New Jersey’s largest health insurer with more than 3.6 million members.
• Through this strategic partnership, Solera will provide its technology platform to connect Horizon members to a personalized experience of innovative and effective curated networks of digital point solution programs to manage their health. 

Enabling Seamless Access to Digital and Community-Based Health Solutions

Horizon will leverage Solera’s industry-leading expertise in driving member engagement to enroll members in their best-fit health management solutions via the company’s proprietary clinical AI. Solera’s matching algorithm has been tuned based on millions of engaged members to navigate individuals to the health management solutions that best meet their clinical acuity level and behavioral characteristics. 

Solera’s condition management platform reduces the operational burden and complexity of managing point solutions for health plans. Through a single point of integration, Solera provides Horizon with a ‘digital front door’ to evidence-based non-clinical and clinical solutions. This unified consumer benefits experience enables rapid deployment and cost savings by simplifying challenging administrative tasks, like claims processing, ASO group configuration, point solution oversight, and point solution performance reporting at the group and individual level to maximize impact and enable decision support for future point solution investments. 

“Horizon members are demanding more from their healthcare, and we are committed to providing them with access to health solutions that will empower them to achieve their best health,” said Norville Barrington, Director, EXPAND Development, Horizon. “With Solera’s approach of offering curated condition networks utilizing a value-based care model, Horizon’s intent is to provide a more individualized solution for each member in an efficient and cost-effective way, while continuing to strive to deliver optimal health outcomes.”

Horizon’s mission and vision is to empower its members to achieve their best health through delivering innovations that improve healthcare quality, affordability, and member experience. This partnership with Solera helps Horizon realize that ambition by ensuring each member receives the customized, whole-person care needed to deliver superior outcomes at lower cost.

Though we seldom see their use in our modern world and, even then, only in fiction, there was a time when it was common for people to actually use things like crystal balls and divining rods to try to uncover unknown yet valuable information. As unbelievable as it may seem, soothsayers peered into crystal balls aiming to help seekers look into the future for guidance, while prospectors would rely earnestly on divining rods as they attempted to locate underground riches of water or oil.

While we may still entertain such images in some of the literature, TV, and movie fantasies we enjoy, in our modern professional world, we tend to entrust industry predictions to those with real, practical knowledge of the business landscape, because they trek, mine, and drill there regularly.

The world of medtech is no different, and for me and my team, connected care is the ground we travel, excavate, and explore on a daily basis. As we venture further into 2023, here’s our perspective on some of the connected care trends we expect to see on the road ahead, from digital therapeutics to remote patient monitoring and clinical trial management.

Precision engagement is an emerging development within digital therapeutics

One of the fast-growing categories within medicine today is digital therapeutics (DTx), which is the delivery of evidence-based treatment through digital solutions that help prevent, manage, or treat a disorder or disease. One recent report valued the global DTx market at $4.2 billion in 2021 and predicted it would expand at a compound annual growth rate of 26.1% between 2022 and 2030, with other estimates projecting even faster growth.

Within DTx, the emergence of precision engagement is a development that holds great promise, especially for chronic conditions where day-to-day choices and behaviors have a significant impact on health outcomes—conditions like diabetes, obesity, and hypertension.

While remote patient monitoring is clearly important for giving care teams visibility into the management of a patient’s condition in order to facilitate vital provider interventions, those living with chronic conditions requiring day-to-day management must also make dozens of additional decisions every day. But initiating provider interventions for all of these would simply not be possible nor even desirable. With diabetes, for example, these can range from food and exercise choices to the need to take medications or interact with a medical device, like a glucose monitor or an insulin pen or pump.

Enter precision engagement. Just as precision medicine can utilize a patient’s genetics or metabolic profile to uniquely fine-tune the dosing of a drug to an individual, precision engagement—with the help of AI and machine learning—can be used by digital health developers and physicians to program connected care platforms to issue electronic interventions or “nudges” that are uniquely tailored and helpful to the individual patient.

These digital nudges prompt a patient to take necessary actions throughout the day that are not only personalized to their needs but delivered in a way that is consistent with their lifestyle and preferences, leading to a better likelihood of engaging the patient and, ultimately, guiding them to better health outcomes. These digital interventions are known in behavioral medicine as just-in-time adaptive interventions or JITAI, and they are helping healthcare professionals use software to precisely engage the right patients with the right interventions at the right time.

With precision engagement, these solutions programmed into connected care platforms are able to digitally “learn” about an individual patient’s preferences from their responses to questions and from the daily decisions they make in their self-management as they engage with the platform’s corresponding app. This learning enables the software to personalize future digital nudges for the patient.

Precision engagement software might be used, then, to help identify the right moment of the day to generate a nudge, like suggesting the patient eat an apple or take a walk at a specific time of day because that’s when the individual is most receptive to such a suggestion.

Or, a digital nudge might involve time- or activity-triggered reminders, such as the need to take medication or to sync the patient’s medical device to the connected-care platform. It might even send the patient an encouraging message prompted by their reaching of a daily target, such as meeting a specific exercise goal.

Precision engagement can even tailor the type of communication used for nudges, from the use of a pop-up message or the suggestion of a video or article to the kind of voice used—maybe through empathy or even humor—to deliver the nudge. 

Precision engagement is one of the most exciting new developments within digital therapeutics, using digital health tools to deliver highly personalized, time-adaptive interventions in ways that lead to positive behavior change, extraordinary patient experiences, and improved health outcomes.

The need for greater RPM awareness is resulting in a measured pace of adoption

While necessity may have forced the issue for care teams during the pandemic regarding the adoption of telemedicine appointments, it turns out that remote patient monitoring (RPM) is still “one component of telehealth that has lagged,” according to the Medical Group Management Association (MGMA). In a Stat poll of 586 healthcare leaders taken by MGMA last year, the association found that 75% of medical practices had yet to offer RPM services.

Despite patients’ positive perspectives of RPM, demonstrated outcomes, payor recognition of RPM’s value, and the establishment of reimbursement mechanisms, the actual pace of RPM adoption has turned out to be more deliberate than these factors had originally led many to predict. In fact, in our work, we’ve found that a large part of preparing providers to make the actual leap to RPM adoption has really been a challenge of growing awareness.

For one thing, we’ve found that in the busy world of providing clinical care, some providers simply haven’t gotten a complete understanding of what RPM reimbursement looks like. So, we continue to chip away at the task of making sure our provider partners have the latest information.

And while some may have caught wind of RPM reimbursement, we’re coming across other providers who have the misconception that only Medicare reimburses for RPM. In reality, there are dozens of private payors covering RPM, with some reimbursing at even higher levels than Medicare. 

Another misconception we encounter among some providers is the mistaken belief that, to get reimbursement for RPM, they must implement every piece of it all at once, from getting patients set up and syncing their data to analyzing the data and providing patient consults. Not only is that not true, but the idea of such a weighty burden is partly why CMS has assigned unique CPT codes for discrete RPM activities. For many providers, implementing RPM is such a significant change management challenge that it actually makes the most sense for them to start small, which they can do by getting patients set up and focusing them on simply sharing their data remotely on a monthly basis. With that, providers can begin submitting for reimbursement, then build from there.

One of the most useful steps for providers unsure of where to begin is to find a reliable partner who specializes in RPM planning and implementation. Resources like AMA’s recently published 12-step RPM Playbook can help, as it covers every stage of establishing a fully operational RPM program.

Pandemic-induced use of decentralized clinical trials provided an up-close view of their efficiencies and is leading to increased adoption

Decentralized clinical trials (DCTs) are trials in which some or all study assessments are conducted at locations other than the investigator site via either tele-visits, mobile or local healthcare providers, local labs and imaging centers, home-delivered investigational products and/or mobile technologies. During the pandemic, when thousands of non-COVID trials—some 80%—were interrupted, virtual trial companies experienced an explosion in demand.

And if market projections are any indicator, demand for DCTs will continue to increase, with an analysis issued earlier this year projecting the global DCT market will grow from $6.1 billion in 2020 to nearly $16.3 billion in 2027.

While the need for social distancing that precipitated the sharp uptick in DCT demand may have subsided from its peak during the pandemic, it’s clear that continued demand for DCTs will be driven primarily by the efficiencies of the model that researchers witnessed first-hand during the pandemic.

One of the biggest advantages of DCTs is how they boost trial enrollment, as they often allow for patients to sign up and participate from home via remote monitoring. Remote participation opens trials and the benefits they provide to those living outside urban centers, which means the trend toward DCTs is also broadening the number and diversity of eligible enrollees.

DCTs can also reduce patient dropout rates and speed up study timelines, two of biggest challenges in life sciences R&D. And they help researchers realize significant cost savings from decreases in the number of physical trial sites and reductions in research staff and travel.

Driven by this wide range of efficiencies benefiting subjects, researchers, and study sponsors, it’s expected the demand for DCTs will continue to ramp this year and in the future.

Overall, we expect 2023 to be a year where our prospecting and development efforts in the connected care landscape will continue producing exciting advancements that will enable us to better support patients living with chronic conditions as well as the physicians and teams who care for them.

About Russ Johannesson

Russ Johannesson is Chief Executive Officer at Glooko, a leading provider of connected care, patient engagement, digital therapeutics, and clinical trial optimization. Deployed in over 30 countries and 8,000 clinical locations, Glooko’s mission is to improve the lives of people with chronic conditions by connecting them with their caregivers and equipping both with digital health technology for improved outcomes.

According to Grand View Research, the global artificial intelligence (AI) in the healthcare market size was valued at USD 15.4 billion in 2022 and is expected to grow at a compound annual growth rate (CAGR) of 37.5% from 2023 to 2030, to reach an estimated USD 208.2 billion. That’s an impressive growth rate, indicating the expected value delivery to a mostly early-phase adoption of AI in the healthcare marketplace. With such aggressive predicted growth, many health industry professionals may ask themselves why they are not investigating AI yet.

AI deploys applications that mimic human-level intelligence, while machine learning (ML) is the subset of those applications that are not explicitly programmed or learned. Together, these rapidly evolving technologies are driving efficiency and productivity across a wide range of industrial manufacturing. 

For pharmaceutical and healthcare manufacturers, AI offers deep predictive and data analytics capabilities, and those implementing AI in their manufacturing processes stand to benefit from improved productivity, higher efficiency, and faster production of life-saving drugs or medical devices. The use of AI technology enables, for example, manufacturers to analyze patterns in data sets to understand the implications, benefits, and success rates of new drugs before launching them into the market. Applications such as process modeling enable manufacturers to develop new insights and deliver predictive quality values before measurement information is available, predictive maintenance to eliminate unplanned downtime, and intelligent machine monitoring to eliminate equipment-driven production deviations. Customers can run manufacturing design scenarios and extrapolate from small experimental design cases to optimally determine the next predicted step for more successful test cases. AI, when properly designed, is expected to merge human and machine intelligence to accelerate innovation.

Applications of AI Technology

Imagine equipment essential to producing an in-specification insulin pump (something a large population, and I, rely on). Such equipment is monitored during the production of each pump with classical regulatory measurements and control systems. Today, with modern intelligent AI monitoring, known deviations or anomalies can be detected for any measurements outside normal ranges. Medical device companies know that using and evaluating leading-edge technologies can identify failures earlier within a significantly less costly time frame. This change in technology can dramatically impact manufacturers and end customers.

Modeling predictive control uses mathematical models to drive performance to maximize yields, productivity, and energy efficiency in drying, fermentation, distillation, crystallization, filtration, and other processes familiar to healthcare manufacturing. One relevant focus for healthcare and validation is AI ‘explainability,’ or the ability to understand what drives action and how adaptive/ intelligent applications respond to different conditions. Inexplicable applications seem much less favored in healthcare and life science, as understanding assists AI evaluation and validation. ‘Black box’ closed solutions are less likely to meet the requirements of this set of needs. To be clear, validation is defined as assuring a specific system will consistently meet the requirements and intended use, these are significantly easier to specify and verify compliance with explainable and not black box AI.

Implementation Considerations

Before applications scale to hundreds of use cases in each facility, industrial customers will want to understand the cloud strategy and start to adopt a cloud management infrastructure. While local access has excellent benefits, having shared-cloud management and application control access from the cloud can be essential to provide quick and specialized data science oversite or support whenever needed. A single cloud infrastructure that can monitor and oversee hundreds or thousands of applications simplifies tracking what is working, and what is being used, and identifying any applications that are turned off, failed, or need attention. The cloud can mean a local private cloud or a secure public cloud. Still, the fundamental value proposition is a browser, distributed access to information, and connection of the stakeholder to data to support decision-making. Cloud-based strategies create efficient and distributed environments that can push technology or security updates automatically to many systems. In the IT to OT world that is developing IT system management practices, this will be desired before too long.

This use case inherently takes data, learns to develop a digital twin of the system of interest, and leverages an adaptive digital twin running in parallel to manufacturing to evaluate and support intelligent decision-making. 

So, what are some of the use cases that this can lead to in the future? 

Many come to mind. Users will be more connected to product maintenance and design teams. The connected world means users who are better informed about their product experiences and motivated to get something more valuable and straightforward in the future, will want to provide medical device manufacturers with feedback on product issues. A direct connection and cloud data store of standard input from many customers can drive early and/or ongoing device updates. This means improved device ownership and more compliant usage, alongside updates that improve user alerts and experiences. This will become important in the early days of, for example, closed-loop blood sugar to insulin pump control, but I do not anticipate that decreasing in the later stages of adoption. Imagine a future where continuous blood glucose monitoring is becoming more and more integrated with insulin pump control.  Users currently familiar with adapting their own dosage to carbohydrate intake and activity levels will have “hands-free” adjustments but also discover their own expectations of necessary information levels to be comfortable and be able to accept these new automatic adjustments.  As more devices become more connected to the manufacturer, this can promote extended utilization and more active device checkups/check-ins, if needed, from device alerts.

Predictive Maintenance

In both manufacturing and medical facilities, the investment required in equipment is significant. The cost of a high-end MRI machine, for example, can be north of $3M, no small change. On a larger scale, the time and capital investment required to build a pharma manufacturing facility is considerable. Construction can take between 5 and 10 years and cost up to $2B. 

The common theme here is that to recoup investment as quickly as possible, optimizing equipment use is key to operational efficiency. More patients can be treated. More devices or therapeutics are produced. That said, equipment failure is a fact of life. Disruptions cost money. Patients must rebook appointments. Manufacturing is delayed. 

Remote maintenance has been the accepted model of support for almost three decades. Performance parameters are set and monitored, and deviations are flagged so that technicians can assess necessary maintenance, order replacement parts and so forth. This all takes time, and it’s reactive. As the saying goes, “prevention is better than cure,” and it’s here that AI and Machine Learning (ML) are starting to play an increasingly important role as equipment connectivity to direct monitoring networks moves into the mainstream. 

Capital equipment manufacturers are now able to partner with customers, to minimize potential downtime through predictive maintenance. ML learns from past system data and experiences to identify normal and deviated operational patterns which support intelligent predictions with minimal need for human intervention. By collecting enough deep device data AI algorithms can define and model failure modes and predict when a potential failure event becomes more likely. A lot of the investments are being made in collecting data from equipment out in the field and being able to draw insights from that, whether in terms of predictive maintenance, better performance, and efficiencies. The data can be so detailed that equipment manufacturers know where and what components are prone to failure, depending on the usage pattern, and the frequency of use, so they can proactively schedule service calls or advise customers of potential issues, based on that data collection, to ensure action is taken to maximize uptime.  

Future Opportunities

Given customer approval, treatment success metrics can be aligned with broader populations, and dosing can be improved via connection to health devices that are becoming more sophisticated. This data can be monitored with duplicate anomaly detection and alert mechanisms used in IT systems to provide early hack detection. In the case of medical impacts, it is personally critical and valuable, however, in the manufacturing plant, sets of AI applications will integrate to provide both local and holistic oversight. The health of the line or plant can be monitored to provide information on decisions such as sanitation or contamination risks, or safety issues when things like systemic anomalies are detected. In addition, production planning and scheduling switchovers can be coordinated and optimized to efficiently manage the site or line activity, maximizing production runs with quality.

It’s still being determined whether these opportunities will happen sooner or later. However, the value achieved and expected from digitizing operations with learning engines and human staff augmentation is exciting. Decision support from helpful, intelligent agents will maximize the value of feedstock, equipment, people, and products.

About Michael Tay

 Michael Tay is the Platform Lead at Rockwell Automation, a global leader in digital transformation and industrial automation. Michael’s been working in the area of modeling and AI for more than thirty years with seven patents in the areas of Model Predictive Control and Real-Time Optimization across a variety of industries. His current focus is on democratizing and simplifying successful ML in helping to drive manufacturing performance.

What You Should Know:  

• Kaiser Foundation Hospitals and Geisinger Health are teaming up to launch Risant Health and a definitive agreement to make Geisinger the first health system to join Risant Health to expand access to value-based care in more communities across the country. Upon regulatory approval, Geisinger becomes part of the new organization through acquisition.
• Risant Health is a new nonprofit organization, created by Kaiser Foundation Hospitals, to expand and accelerate the adoption of value-based care in diverse, multi-payer, multi-provider, community-based health system environments.
• Jaewon Ryu, MD, JD, has been selected to serve as CEO of Risant Health. Dr. Ryu will transition from his current role as president and CEO at Geisinger Health as the transaction between Risant Health and Geisinger closes.

Risant Health’s Vision

Risant Health is a nonprofit affiliate of Kaiser Foundation Hospitals, which will be headquartered in the Washington, DC, metro area. Risant Health’s vision is to improve the health of millions of people by increasing access to value-based care and coverage and raising the bar for value-based approaches that prioritize patient quality outcomes. In addition to Geisinger, Risant Health will grow its impact by acquiring and connecting a portfolio of likeminded, nonprofit, value-oriented community-based health systems anchored in their respective communities.

Health systems acquired by Risant Health will   continue to operate as regional or community-based health systems serving and meeting the needs of their communities, providers and health plans while gaining expertise, resources, and support through Risant Health’s value-based platform. Risant Health will operate separately and distinctly from Kaiser Permanente’s core integrated care and coverage model while building upon Kaiser Permanente’s 80 years of expertise in value-based care.

Geisinger Acquisition Impact

Geisinger will maintain its name and mission, and will continue to work with other health plans, employed physicians, and independent providers. At the same time, Geisinger will build on its foundation by benefitting from Risant Health’s value-based platform that offers the best in value-based care practices and capabilities in areas such as care model design, pharmacy, consumer digital engagement, health plan product development, and purchasing. As the first health system to become part of Risant Health, Geisinger will participate in developing the organization’s strategy and operational model.

Electronic medical records (EMRs) – software systems where physicians, nurses, and other healthcare workers store, retrieve, and act on clinical data – are fundamentally broken. This sentiment is so widely shared among healthcare workers that it has become almost trite to point it out. Patients feel it too – we’ve lost count of the number of times we’ve heard “isn’t it in my chart?” when we ask a question during a clinical visit.

Unfortunately, the vast majority of EMRs do not facilitate storing, retrieving, or acting on information in an efficient or intuitive way. The most broken element of most charts is the free-text segments – where clinicians store narrative text data about the patient’s medical concerns, their own diagnostic impressions, and their treatment plans.

Free-text segments are critical both to pass information forward into the future and to collaboratively manage information across a team of generalists and specialists in different roles. It’s not possible to store all of that information in your head anymore, even if it was feasible 50 years ago (which is also doubtful). It’s a disservice to patients to imagine that we could. So we need a good electronic system to help. There are many ways a clever system designer could build software to organize free-text data for a single patient – data about multiple medical topics, collaboratively stored, retrieved, and used by numerous healthcare professionals, evolving over the course of years. An ideal system would, at a bare minimum, make it easy to store and organize information intuitively, such that it would be quick to retrieve relevant data later.

The specific way that most clinicians and EMR companies (in America, at least – we can’t speak to anywhere else) have chosen to organize this data is empirically terrible. It’s terrible because clinicians hate using it. It’s terrible because you can’t find relevant information quickly because charts are riddled with useless, out-of-date, and erroneous information, scattered across hundreds of different documents. The information which is both relevant and correct requires herculean effort to find. Clearly, the EMR is failing at its most basic job. Beasley et al elucidated a great framework for this ‘information chaos’ over 10 years ago, and it’s still accurate.

In our study, we used the information chaos framework: particularly, the two hazards described in the Beasley paper as “information overload” and “information scatter”. We examined a corpus of >100 million free-text notes written by thousands of different healthcare workers at our hospitals and clinics to quantify information overload and scatter. Information overload is pretty easy to quantify. We just counted the total free-text data in the corpus; this was ~32 billion words, eight times the size of the English Wikipedia at the time we checked. It was astonishing to us that a single academic healthcare system in one city in one country over 6 years produced eight times more free-text data than the global resource dedicated to capturing all of the human knowledge worth knowing. Not all of that information is relevant to a particular doctor visit or hospital admission, to be sure, but a clinician is still responsible for knowing the subset of the information that is relevant. To do that, you need a system that facilitates finding the relevant information among the irrelevant noise. The more noise there is, the more infeasible this gets and the more acutely healthcare workers feel the pain of a badly designed system.

Speaking of noise, we next looked at a subset of information overload well-known to clinicians – duplicate information. This is information that is already in a patient chart, but for whatever reason a clinician sees fit to repeat it again in a separate text document in the same chart (in clinical parlance, each individual document is called a “note”). We found that just over 50% of words were duplicated, that this fraction has been increasing over the past 6 years, and that this phenomenon is ubiquitous across all patients, clinicians, and healthcare worker types. That means 16 billion words have been duplicated over the past 6 years in just one health system. Many clinicians who reached out to us were surprised that the fraction was so low – predicting that 70% or more would be duplicated. This staggering statistic illustrates the degree to which the current free-text information management paradigm is broken. It should be a call to action – to deeply revamp documentation to save patients from medical error and clinicians from information management burnout.

“Now, wait a second!” some clinicians might be saying. “Sometimes information stays the same, so it makes sense to re-document it!” For instance, if a patient has a cough on July 3rd when they see you in the clinic, and they still have the same cough on July 12th, maybe you re-write (or more likely, copy and paste) the phrase “patient has a productive cough” in the July 12th note. Of note, information gets duplicated both across time (from past notes into future notes) and across teams (from one doctor or nurse’s note to another). Doesn’t it make sense that if information stays the same over time, you should re-document it?

Well, it would make sense if you take for granted everything about the underlying documentation paradigm, which you certainly shouldn’t. The obvious responses by anyone familiar with modern word processing software outside of a healthcare context are “(1) Why do you have to make a new text document every time you see the patient? Can’t you just edit the old document and track changes?” and “(2) Why does every healthcare worker have to maintain their own separate set of text documents? This sure sounds like a lot of wasted effort finding and collating information from other people’s notes. Can’t they just collaborate on a single shared document?” It’s hard to argue with these points. Sure, we all know colleagues who still send around multiple versions of word documents with convoluted names like “prospectus_020122_jsedits_v2_finaledits_060220” when collaborating, but we can likely all agree that collaborative documentation systems like Wikipedia or Google Docs provide much better software paradigms for collaborative editing of a text document which evolves over time. There’s absolutely no principled reason we can’t have a similar model in clinical documentation systems.

We believe that what we call the “note paradigm”is a key cause of massive amounts of duplication. The “note paradigm” is simply the two assumptions contested in the above paragraph: (1) that every new patient encounter requires a new document, and (2) that every healthcare worker must create their own documents. When a phenomenon is as ubiquitous and predictable as duplication, we can’t blame it on individual clinicians being “lazy” or even individual EMR vendors designing slow software or overwhelming user interfaces. The problem is deeper than the EMR level. It’s at the paradigm level, which underlies the assumptions about how documentation is done, how documentation systems should be built, and how medical care is regulated by the government and billed by insurance companies. It’s taught in medical schools that you have to write a “progress note” every time you see a patient, and that different specialists have to write their own “progress notes”. At this point, the note paradigm is the water we swim in; it becomes hard for many to even recognize that it is a specific design choice, or that it could be otherwise.

It’s easy to see how the note paradigm leads to information overload if you think about documentation incentives. Imagine a primary care clinician responsible for a patient with 5 different medical problems, all of which require adjustment of medications and 3-month check-ins. In this situation (assuming no eidetic memory), every 3 months, the clinician will need to remind themselves of all the relevant information about those problems, gather new information, incorporate it into decision-making, and document the new current state of the patient’s medical problems after the visit. Under the current paradigm, their choices are either (1) to use each of their notes as a complete and comprehensive state-of-the-patient, adding new information each time but keeping all of the old information around, or (2) just document the changes from the last visit to this visit in each note. Choice (1) leads to high information duplication as old information is persisted in every new note, but low scatter because all the relevant information is in the most recent document. High duplication increases textual errors as out-of-date information is perpetuated without change. On the other hand, choice (2) leads to shorter notes, low duplication, and high scatter because the information is now only contained in the entire set of notes, not just the most recent. High scatter necessarily increases the time needed to collate and synthesize the relevant text as all notes would need to be reviewed at every encounter to get the full story.

So without implementing a collaborative documentation system, there will remain an extremely strong trade-off between duplication and scatter and this will play out differently depending on the author’s role in a patient’s care. In particular, we’d expect that healthcare workers who treat patients’ medical problems over time (primary care doctors, psychiatrists, or specialists) would prefer to minimize scatter at the cost of high duplication. Extra work is done upfront to collate information so it can be copied forward and persistently available with minimal work. On the other hand, healthcare workers who treat patients’ problems temporarily (urgent care doctors, surgeons, nurses answering triage phone lines) would have no incentive to collate information and so would write brief notes that capture the problem at hand at the cost of high scatter. The real loser in these situations is the patient, who would be better treated if the long-term care team knew about the short-term problems, and the short-term care team had all the relevant context of the patient’s long-term care plan. 

This trade-off is exactly what we empirically see when we plot scatter vs. duplication for different note types in our study. Some note types have high duplication and low scatter, exemplified by physician progress notes which aim to summarize the entire current ‘state of the patient’. These notes are comprehensive (low scatter) but duplicate lots of past information. Other note types have high scatter and low duplication, exemplified by note types that document a single isolated event e.g. (“result” notes, which comment on the results of a particular lab test; or telephone encounter notes, which document a short phone call with a patient). Very few note types have both high duplication and high scatter, except for those that are almost entirely auto-generated boilerplate text. From this picture (and our own clinical experiences), we can infer that clinicians often duplicate text because the highly scattered alternative would be worse.

The electronic medical documentation system is broken and causing clinician burnout. It affects every patient and clinician, regardless of their medical problems or clinical role, and it should be taken seriously. If we want to fix the problem, we need to properly identify and label it. The software wrappers – the systems we use every day – are only a symptom of the real problem, the note paradigm and the underlying assumptions about documentation. Individual rules to “ban” or “limit” duplication provide a solution for a different problem, not for remedying the root cause of duplication. To address that, we have to understand the motivation, which is clearly to minimize scatter, and so any limitation on duplication has to be paired with a non-duplicative tool for decreasing scatter or increasing information density per screen. Acknowledging these problems is easy. Fixing them on the other hand, will require deep cultural changes in medical training and practice, as well as changes in the billing practices, governmental regulations, and legal requirements surrounding medical documentation. But what better way to answer the question, “Isn’t it in my chart?”, than “You’re right! It’s right here.”

About Subha Airan Javia, MD

Subha Airan Javia, MD, FAMIA, is the CEO of CareAlign, a clinical workflow management technology company. She is also a hospitalist at Penn Medicine.

About Jackson Steinkamp, MD

Jackson Steinkamp, MD, is an internal medicine resident at Penn Medicine with a degree from Chobanian & Avedisian School of Medicine at Boston University.

Hint & Eden Partner to Expand Virtual Direct Primary Care Offering Nationwide

What You Should Know:

• Hint Health, the company powering the Direct Primary Care (DPC) movement, and Eden Health, a leading national virtual and in-person primary care provider, today announced a partnership to expand the Hint Connect footprint with a virtual DPC offering across all 50 states.
• This partnership allows employers to offer a DPC network nationwide for patients who don’t have convenient access to a DPC practice in their communities.

Innovation in Healthcare Via In-Person and Virtual Direct Primary Care Plans

According to a poll, less than half of Americans are satisfied with the quality of U.S. healthcare. Long wait times to see a doctor, short appointments, and lack of coordination between care settings leave patients feeling like no one cares about them or their health. Furthermore, healthcare costs continue to rise despite a worsening patient experience. 

The benefits of Direct Primary Care include:  

1. Access: DPC physicians typically offer same-day or next-day appointments and use technology like telemedicine, e-mail, and text messaging to make themselves more accessible to their patients on demand.
2. Quality: DPC providers are able to spend more time with their patients. Standard primary care providers only have an average of 17 minutes to spend on each patient; with DPC, providers  spend up to an hour with patients to uncover the root cause of complex health issues and offer holistic care.
3. Cost: DPC is proven to sharply decrease costs and utilization in higher cost of care settings, including emergency department, hospital inpatient, and outpatient specialty costs. With DPC, patients pay one transparent, monthly fee and know exactly what is covered. They are able to visit the doctor when needed, instead of waiting until healthcare concerns get worse. 

Hint Connect is a nationally scaled network of Direct Primary Care practices that excels at building trusted clinical relationships locally. When employers or plans offer Hint Connect, members can choose between a fully virtual primary care model or an in-person/virtual hybrid based on their personal preference, geography, and health needs. When members select the in-person/virtual hybrid model, they and their families register with Hint Connect and choose a nearby DPC location. There is no copay or coinsurance for visits. 

When members choose the fully virtual primary care experience with Eden Health, they will be able to  connect with their provider within minutes and at the touch of a button, 24/7/365. Unlike many other telehealth  solutions, patients meet with the same clinician throughout their care journey, allowing them to develop a trusting, longitudinal relationship with their provider. All clinicians are fully-employed by Eden Health and are dedicated to serving their patient panel virtually. Patients receiving virtual care through Eden Health have access to primary care, urgent care, chronic disease management, wellness and care coordination services, all through a single app and free of cost. 

“Eden Health clinicians are more than just someone picking up extra hours after their full-time shift ends,” said Hint Health CEO, Zak Holdsworth. “Eden’s pioneering work to champion a true virtual Direct Primary Care model will allow us to further achieve our mission of making DPC the new standard in U.S. healthcare.”

This partnership means that employers and plans will no longer have to make the tough decision between local options and virtual-only options. Instead, employees will have the opportunity to choose the plan that’s right for them to receive the highest quality, full access, primary care for one flat membership fee built into their health plan. Hint Connect simplifies enrollment and eligibility management, billing, and invoicing for a seamless benefit management experience. 

Together, Hint and Eden offer a uniquely comprehensive solution for organizations looking to solve the national problem of healthcare access and quality.

What You Should Know:

• Market-leading Philips PACS is now available on AWS for industry-leading availability, reliability, security, and AI-supported workflow enhancements.
• Expansion of the collaboration with AWS will support the development and deployment of generative AI applications that further support efficient clinical workflows and enhance diagnostic capabilities. Market-leading Philips PACS is now available on AWS for industry-leading availability, reliability, security, and AI-supported workflow enhancements
• Philips will also use Amazon Bedrock as part of its efforts to develop generative AI applications to advance PACS image processing capabilities and simplify clinical workflows and voice recognition. Amazon Bedrock will enable Philips to develop Machine Learning-based applications quickly and reduce model development costs versus building Foundational Models (FMs) from scratch or running multiple task-specific model development efforts.

What You Should Know:

• Rimidi, a leading clinical management platform designed to optimize clinical workflows, enhance patient experiences and achieve quality objectives, today announced the company is now integrated with MEDITECH Greenfield.
• MEDITECH customers will  now able to utilize Rimidi’s cloud-based software platform within their existing workflow, further enhancing efforts to support efficient models of care for chronic disease management through Fast Healthcare Interoperability Resources (FHIR) application programming interface (APIs).
• The healthcare industry initially adopted FHIR as the protocol of choice for API-based data exchange to enable a seamless transfer of patient health information from multiple data sources. As the industry continues to strive toward a value-based care model, the overall healthcare API market is expected to increase to $309.86 million by 2032, allowing for more enhanced collaboration to enable better patient care. 

Rimidi/MEDITECH Greenfield Integration Benefits

Rimidi’s integration with MEDITECH allows clinicians to use Rimidi within their existing MEDITECH workflow. Specifically, the integration: 

What You Should Know:

• Imprivata launches Imprivata Digital Identity Maturity Model and Digital Identity Maturity Assessment, a custom-built to amplify the voice of clinicians and end-users in the decision-making process for a healthcare organization’s digital identity strategy.
• To help organizations assess and benchmark the maturity of their current strategy, Imprivata offers its Digital Identity Maturity Assessment.
• This self-service, interactive tool enables clinical leadership, IT, and security teams to quickly assess the effectiveness of their digital identity program based on current-state tools and processes. The output is a customized report that considers user outcomes, security, and compliance in alignment with the maturity model, with actionable insights to simultaneously drive improvements across all areas.