The integration of Artificial Intelligence (AI), automation, and data analytics into the revenue cycle management (RCM) of healthcare facilities marks a transformative leap toward operational excellence. In an era where financial sustainability is as crucial as clinical outcomes, these technologies are pivotal in optimizing processes from patient intake to final billing, ensuring that healthcare providers not only survive but thrive in a competitive market.

At our infectious disease lab, the implementation of AI and data analytics has revolutionized how we manage our revenue cycle. By automating routine tasks, we have freed up valuable time for our staff to focus on more complex, value-added activities. Automation of data entry and claims processing reduces the likelihood of errors and speeds up the turnaround time, directly impacting our cash flow and reducing the days in accounts receivable.

One of the most significant advantages of using AI is its ability to analyze vast amounts of data to identify trends and patterns that would be impossible for a human to discern. This capability allows us to anticipate issues before they become problematic, such as identifying which claims are likely to be denied based on historical data. With predictive analytics, we are proactive rather than reactive, which not only increases our revenue but also reduces the stress on our staff and improves our relationships with patients and insurers.

AI transforms data into actionable insights, enhancing efficiency and profitability in healthcare.

Moreover, machine learning (ML) models within our AI systems continuously learn from new data. As they become more sophisticated, they offer increasingly accurate forecasts and deeper insights into our lab’s financial operations. This ongoing learning process is crucial for adapting to the ever-changing landscape of healthcare regulations and insurance policies.

Our organization has also capitalized on data analytics to fine-tune our pricing strategies and to ensure compliance with billing regulations. By analyzing the outcomes of thousands of past transactions, we can set competitive prices that maximize our revenue without compromising patient care. Furthermore, compliance monitoring through AI-driven systems ensures we adhere to all billing regulations, reducing the risk of costly penalties and legal issues.

The integration of these technologies extends beyond internal operations to enhance patient interactions. Our patient portal, powered by AI, offers personalized experiences where patients can easily access their billing information, understand their payment options, and communicate with billing representatives seamlessly. This not only improves patient satisfaction but also expedites payments, positively affecting our cash flow.

In addition to these operational improvements, AI and data analytics significantly enhance our strategic decision-making capabilities. With access to real-time data and advanced analytical tools, our management team can make informed decisions quickly, addressing potential financial discrepancies and optimizing overall financial health.

Furthermore, the ability of AI to integrate with other technological advancements, such as electronic health records (EHRs), further streamlines our operations. This integration ensures that all patient data is synchronized across platforms, minimizing the risk of data silos, and ensuring that every department has access to the same accurate and updated information. This seamless integration helps in maintaining consistency in billing practices and patient care services.

Our commitment to leveraging AI extends to training our staff to effectively utilize these tools. By holding regular training sessions and workshops, we ensure that our team is not only comfortable but also proficient in using the latest technologies. This empowerment enables them to contribute actively to our ongoing efforts to refine and improve our revenue cycle processes.

Additionally, AI tools help us manage the complexities of insurance verification and eligibility checks with greater accuracy. By automating these processes, we reduce the instances of claim rejections due to coverage errors. This not only speeds up the billing process but also decreases the burden on our patients, who can be confident that their coverage is correctly verified at the outset of their healthcare journey.

Moreover, AI-driven analytics assist us in identifying inefficiencies in our billing and service delivery models, allowing us to make necessary adjustments. These adjustments are often predictive rather than reactive, positioning us to address potential issues before impacting our operations. This foresight saves time and resources and supports our strategic goals of maintaining financial health and patient satisfaction.

The adoption and continual advancement of these technologies in our revenue cycle processes illustrate a commitment to innovation and excellence in healthcare management. As these tools evolve, so too does our ability to meet the needs of the patients we serve and the staff we support, ensuring a future where healthcare and technology work hand in hand for the betterment of all involved. As we continue to harness these powerful technologies, we not only foresee a more robust financial footing for our lab but also a greater capacity to provide exceptional care to our patients.

Through ongoing investments in AI and data analytics, we not only optimize our current operations but also pave the way for future innovations. These technologies allow us to stay at the forefront of the healthcare industry, continually improving our services and outcomes. By embracing AI and automation, we not only enhance our operational efficiencies but also ensure a higher standard of care, which is the cornerstone of our mission in healthcare.

The post Leveraging AI in Revenue Cycle Management for Healthcare appeared first on HealthTech Magazines.

No one in healthcare will forget March 2020, staring down the worst pandemic in living memory. Society shut down. People started dying at unheard-of rates in Italy, and shortly later NY City. MultiCare Health Systems, an 11-hospital healthcare system in the Pacific Northwest, near where the first US cases were reported, needed to know what to expect.

The data science team at MultiCare addressed the problem by modeling case increases in the communities we serve, first with exponential growth models, but within two weeks, we realized logistic (S-shaped) growth models fit the data better. We were not hit hard in that first wave, and we have continued to model Covid cases across our system through subsequent waves, giving advance notice of a surge and providing our leaders with data-driven insights.

The future of healthcare is big data. But big data by itself just sits in an enterprise data warehouse and runs up storage fees. Healthcare data scientists are essential in moving beyond reports and static dashboards. Data needs to be turned into actionable intelligence for a healthcare system to benefit.

Healthcare data scientists can help an organization get the greatest return on their data infrastructure investment.

Endless Opportunity. The problems that can be addressed with data science are essentially endless. Will a patient be readmitted after discharge? Which patients will have a prolonged hospital course? Can we identify those patients who will develop sepsis earlier and start lifesaving treatment sooner? These problems are readily amenable to predictive modeling and are already commonly deployed in hospitals across the country.

This is just the leading edge of what predictive modeling can do. Many systems are large enough to provide comprehensive datasets on a wide range of patients and conditions. Each disease can be approached using predictive modeling. For many common ailments, a patient’s journey can be mapped along a pathway, with each node in the pathway representing a decision point. It is not hard to imagine a future where dozens, even hundreds of pathways guide a patient’s care, with each downstream step in the journey modeled, and the optimal course of action presented for each individual.

Healthcare is undergoing a generational change as we move away from fee-for-service and towards shared savings and population-based care. Therefore, the need for accurate predictions will increase: who is most likely to be admitted to the hospital? Who will benefit from an intervention to keep them out of the emergency room? Should that intervention be an additional visit with their primary care doctor, transportation assistance to a specialist or another intervention, like a home health visit?

And, as great as the opportunities are in clinical care, as data becomes more and more available, improving a healthcare system’s operational processes may have just as much potential.

Business Analyst or Data Scientist? Do we really need data scientists? A healthcare system’s core competency will always be healthcare delivery, isn’t an analyst enough?

There are a number of steps involved in turning data into a true understanding of the problem. Querying data is often surprisingly challenging: the databases of some electronic medical records (EMR) are composed of more than 20,000 unique tables. Data needs to be aggregated, its quality assessed, and presented in a way that it can be understood by end users. Advanced analytics include machine learning (ML), forecasting, cluster analysis and the ability to hypothesis test. These skills usually require an advanced degree, although not necessarily these days given the availability of online training. But with these abilities, a data scientist can provide insight beyond what you can gather from a dashboard.

The Role of the Vendor. Can’t advanced analytics just be purchased from specialized companies? Certainly, the level of sophistication needed to develop deep learning algorithms is not something many healthcare systems will be able to support. Natural Language Processing (NLP) in particular has made a lot of progress in the last few years and will soon be pulling knowledge out of free text. Third party vendors will be helpful here, but fully realizing their potential will require people who understand both the algorithm and the use cases. 

In a larger sense, data science can help an organization develop insight long before it gets to the level of an RFP. Many people in healthcare have deep knowledge about esoteric fields. They may want to explore a hunch with genuine financial and clinical implications. Having access to a data science team, people who leaders know personally and can connect with to talk through a problem, can make all the difference.

Additionally, healthcare organizations need to develop the sophistication to evaluate a third party’s claims. Does a purchased model accurately predict what end users think it does? Even models published in peer-reviewed, academic journals cannot be assumed to be accurate on a specific organization’s population. A model needs to perform for an entire population, but also needs to be evaluated for bias on the vulnerable groups a system cares for.

The Clinician Data Scientist? Two decades ago, it was hard to imagine that we would have doctors who specialize not just in patient care but in optimizing the use of the electronic medical record. Now, over two thousand doctors are board certificated in clinical informatics, with hundreds more becoming certified every year. The value proposition for clinician data scientists may be even greater.

Big Data and Data Science are Essential to the Future of Healthcare. Data science is not an add-on, but a process to integrate into healthcare decision-making. As organizations make bigger and bigger investments in enterprise data warehouses and data aggregation platforms, healthcare data scientists are the best way to assure return on that investment.

The post The Case for the Healthcare Data Scientist appeared first on HealthTech Magazines.

Healthcare’s primary problem is not the lack of data, but the lack of fidelity and usability of the available data. The challenge is collating, interpreting, and distilling data to a usable state and getting those data to the right person, at the right time. Additionally, healthcare data is unwieldy and fractured, continuing to fracture exponentially as more care channels and options emerge. New channels generate new data silos that make safe, effective care difficult. Compounding this issue, costs of health insurance, care delivery, and medications continue to rise, placing adequate healthcare out of reach for many. As a result, the quality of care across the US continues to lag significantly behind other countries.

Patients are the reason healthcare exists, and yet, they are rarely centered in their information or care.

Also, the US healthcare is experiencing an unprecedented period of change, brought on by industry pressures, which makes an already complex system more cumbersome and perilous.

These pressures include: 

• Dramatic shifts in consumer expectations: Younger consumers are not satisfied with traditional healthcare, and consumers of all age groups are more willing than ever to try non-traditional services. Millennials and gen Z, who make up 42% of the population and 21% of healthcare services, expect convenience, affordability, transparency, and quality and are redefining how they engage in every stage of their care.
  
  
• Fragmentation: The delivery of care through established service paths (e.g., doctors, clinics, and medical centers) must now compete with non-traditional service paths that represent emerging types of service delivery (e.g., walk-in or retail clinics, outpatient surgery hospitals, virtual health, on-demand services, in-home services, or digital therapeutics).
  
  
• Increased regulatory pressures: The burden of new and existing laws regulating healthcare—such as HITECH, HIPAA, ACA, FDASIA, and MACRA/MIPS—affects providers by increasing their administrative load and by adding or increasing penalties for services that do not meet a set of prescribed quality, interoperability, and performance criteria. These burdens slow the delivery of care and reduce patient interface time with doctors and their clinical staff, alongside a host of other factors that can negatively impact care delivery, patient outcomes, and provider reimbursement.
  
  
• Hyper-specialization as the knowledge about diseases accelerates: Medical research continues to reveal the complexity behind disease causes and treatments. As research unravels the genome, microbiome, and proteome, referred to as multiomics, to understand their role in health and wellness, physicians become more specialized to turn discoveries into better outcomes for patients.
  
  

Data is duplicated and conflicting due to issues with standards

Because most health record systems do not consolidate information, numerous patient and provider-reported health records result in duplication, retention of outdated information, and leave room for error. Also, payer data often inaccurately reflects patient care and services provided due to the complicated nature of billing practices. Often, to ease workflow, patient services are billed based on a short list of memorized codes or the first code to populate a search, resulting in loss of fidelity. Therefore, providers don’t uniformly have access to accurate reference records which creates an overwhelming burden on providers trying to find the information needed to make recommendations.

Projects to enable interoperability are costly and time-consuming

Traditional data transformation and sharing methods are complex and deduplicating of the data with any precision is time-consuming and risky. Important changes in a patient’s record can take weeks or even months to emerge, as the data integration does not happen in near real time. There are existing methods of sharing more cleanly within like EMRs, but even in that method, there are issues reconciling data due to the differences in system setup (x field in system A is blood pressure, whereas it’s y field in system B).

The patient is never in control of their data

Patients are the reason healthcare exists, and yet, they are rarely centered in their information or care. They have little control of their data and, in most cases, have no concept of how the data is used and where it’s shared. Also, all too often, patient-provided information fails to be integrated with the patient’s record thereby ignoring critical pieces of information. By ignoring the patient as a vital part of healthcare and its interoperability, data sharing and cleansing become complex and diminishes the capabilities of healthcare providers to make data-based diagnoses and treatment decisions.

What can and should be done?

We should strive for a single, golden record for every person on Earth that is updated in real-time as changes happen and allows for notification of significant events to be delivered to the right person at the right time. And that record should be owned by the individual, not the system.

There have been many barriers to this in the past, but the most significant challenge has been to uniquely identify each person and all of the entities and assets they interact with.

Luckily, technologies and tools emerging on the market now can systematically address these issues through AI and machine learning. Tasks considered nearly impossible, like merging 20 medical records and distilling the information down to a single record, can now be done at scale, with the patient owning the overall outcome.

One emerging company consolidates health and wellness data into a single, standardized record under secure control of the patient that facilitates seamless data exchange amongst healthcare and life science constituents. The technology leverages syntactic, structural, and semantic interoperability techniques in addition to patient-level interventions when AI cannot resolve the data cleansing automatically.

In addition to focusing on rich medical data, this company continuously fills gaps with real-time, real-world data from multiple sources (e.g., wearable and medical devices), in conjunction with social determinants of health (SDOH) and patient-reported information.

How do we get there?

While companies like this are working to solve this problem, there are cultural barriers in the US that need to be overcome. To truly achieve patient-owned interoperability, data hoarding and profiteering concepts need to be addressed. Healthcare needs to be democratized for a more equitable landscape. Platforms that democratize health information shift people from passive to active participants within their own health outcomes. After all, it is ultimately the patient that bears the burden of adverse health outcomes, not the providers.

The post Transitioning to Patient-owned Data appeared first on HealthTech Magazines.

It is 2025; you are on your way to a 10 am appointment with your PCP (primary care provider). You receive a text with a link to their wayfinding app which provides directions to your on-site parking space. Once you park, you receive a 2^nd text that provides access to a wayfinding application that gives you turn-by-turn directions to your provider’s office. As you walk into the building, facial recognition checks you into your appointment and a 3^rd text connects you with the ‘virtual clipboard’ where you can confirm/update your demographic, insurance and clinical information, the reason for your visit, take a photo of your insurance card and generally complete any pre-visit information while you wait. Once you have completed the pre-visit paperwork, you are directed to exam room 3, where the turn-by-turn directions get you to the exam room, where you are greeted by your doctor.

The doctor has your chart up and is reviewing your recent imaging study from the local reference imaging site, as well as the lab work done last month during your pre-employment physical. They talk with you about your blood sugar, heart rates, ECG and activity levels that were sent from your apple watch. They also remind you to refill your blood pressure medication as the information received from the pharmacy/insurance company shows that you have not refilled your medication in the last 90 days (which provides only 30-day increments).

Some would consider this an ideal encounter with their provider organization and for the future patient, interoperability and health information exchange (HIE) that delivers the right data, at the right time, for the right person, to the right person, across multiple states, systems and organizations are required for that reality. All of that exchange would be done directly, between participating organizations and their IT systems, magically behind the scenes, with no manual intervention by the patient nor the provider would be the expectation, but it’s far from today’s reality.

People suggest that healthcare interoperability falls short of other industries, for example, banking, but there is no data exchange between banks until you present your ‘card’. Banking also has the credit reporting agencies – Experian, TransUnion, and Equifax – which aggregate your financial information – which is reported directly to them by the banks – there is no such corollary in healthcare.

In today’s world – information is knowledge, power, currency, and the key to ensuring you and your loved ones get the right care, at the right time, in the right setting (without additional costs).

Health Information Exchange (the verb) has been fraught with patient identity issues. Specificity the usability, timeliness, manner of transmission, workflow integration and so on – the list of barriers exceeds the list of accomplishments on many fronts, but the foundational layer of digitized health data was brought forward by the EHR incentive program rolled out in the 2010s. This program encouraged EHR adoption amongst the provider communities, supported by technical and training resources from Regional Extension Centers and sped forward with the more recent expansion of health data exchange requirements via 21st Century Cures and TEFCA. These regulatory instruments have provided additional guardrails that are moving healthcare interoperability and standards adoption forward to reduce, remove, and eliminate a number of those barriers.

The future-forward interoperability framework will need the authority and ability to identify actors, create and deliver consent, and allow for health information to be participants in every exchange.

Still to be resolved are issues around patient, provider, and organizational identities. These are foundational components necessary to facilitate health information exchange and puts data in the right place to enable the best possible care encounter for each patient (think personalized medicine). The future-forward interoperability framework will need the authority and ability to identify actors, create and deliver consent and allow for health information to be participants in every exchange.

Organization Directory services for FHIR APIs and the like still need a home as well as a vetting authority to provide a trust framework for the consortia to be comfortable with making any exchange – patient identity with a consent mechanism that enables seamless and informed exchange also needs a home. Not to mention the need for an architecture that enables a ‘single patient identifier’ that can be shared by the patient with each of the care providers/organizations at the beginning of each encounter.

This global identifier could then be connected to the overall exchange framework and enable patient notification (and consent) of any exchanges between organizations, directly by the patient. Ideally, the industry creates that capability to enable a patient with a technology that easily supports record tracking and aggregation (think longitudinal health record) where encounters with each organization and provider are ‘logged’ with the identity of the patient and connection methodology for the organization. That ‘log’ could then be accessed by the network to connect and collect appropriate data via the supported methodology for each organization.

The future of just-in-time interoperability, where the right, correct and appropriate data arrives at the right time, in the correct system workflow for each ‘data consumer’ and it will require the implementation of trusted identity services to be in place for all participants/actors who are part of the health information exchange data fabric.

The penultimate goal is to enable a health data fabric where each ‘data consumer’ participating in the exchange gets the information needed to facilitate all clinical and administrative aspects of each encounter. That exchange should not be associated with significant costs, should happen in real-time, and enhance the quality of each individual encounter. This ultimately leads to the improved overall health of the patient and reduced costs, which so far has been the ‘Moby Dick’ of health data interoperability.

The post From the Crow’s Nest: The Search for Perfect Health Data Exchange appeared first on HealthTech Magazines.

Every day there is a new need for technology. New use cases and opportunities continue to challenge the status quo, if the status quo as we know still exists. The iPhone, now celebrating its 15^th anniversary, revolutionized the world. But the newest and youngest generation does not know life without these devices and expectations of delivery of information are rapid and instant. Healthcare needs to also deliver overall in this space.

In a business sector that has traditionally been behind on the transformation maturity scale, how do you pivot to the quicker and more effective delivery of technology? Among many things that came from the pandemic, one important finding is that healthcare professionals’ understanding and awareness of technology has increased substantially. This drastic maturity forward in how technology is delivered now brings a crossroads. The maturity model now must include more clinical involvement. What do nurses need? What do doctors need? What do patients need? How can clinicians deliver patient care most effectively? What is the true lexicon they work in now? Internally, we developed a council that brought stakeholders from different areas in the organization to discuss foundational technology and roadmap. The most important deliverable is to focus on those business needs and collaborate on technologies and transformations that bring the most value. This feedback loop is essential to understand how rapidly the demands have grown for these areas, which challenges the need to deliver quicker.

Traditional Infrastructure and Operations has to give way to stronger business partnerships and understanding of needs, especially as technology has aligned so closely to patient care. With a technology focus on business, it is important to grow the depth of technology, beyond the traditional data center, endpoint, and mobile. So the new challenge is how traditional I&O teams engineer and administer these newer technologies in the same ecosphere as traditional technology. Today’s transformational journeys of healthcare organizations are full steam ahead. This is the maturity of transformation. But what is the lift needed to not just grow from the legacy systems, but to accelerate that journey quickly? A careful balance. What brings this together is a fully realized roadmap that must be matured to adopt new architectures and platforms that focus on the new deliverables and innovation needed. 

Foundational technology is a building block for the delivery of services, whether it is through the traditional data center or cloud partners and connectivity and technology.

Now, an expanded focus on delivery foundational architecture leads to outcomes for today and tomorrow for delivering better patient care. But what does an organization do to provide focus on sunsetting the current and technology platforms? Years ago, it was the ability to virtualize servers; then it was the ability to build in the cloud; then it was building containers to deliver quickly. But what if an organization is still using a large number of physical servers? This is an essential challenge for I&O leaders. Here is where the partnerships between IT and healthcare stakeholders must provide focus on what is needed to move forward. Steering committees and councils are habitually the avenues to discuss this. My organization focuses on this balance and need. We have developed roadmaps with achievable timelines so delivery of new architectures can be completed in congruence with twilighting the right legacy systems.

As this journey of digital transformation endures, infrastructure and technology teams can accentuate the opportunities to deliver quickly to support patient care. The technology roadmap to move maturity must prevail to be successful. Skillsets and capabilities must also mature. 

With the expansion of patient care virtually through the pandemic, one area that continues to accelerate care is the ability for home health. The different technologies for home health, such as wearables and other monitoring solutions, bring a new focus. My organization is working collectively to connect all these different devices seamlessly and securely, beyond the traditional means. Self Service and automation accelerate these capabilities, delivering critical success factors for patient care. This does not go without a challenge. How do we balance the safety and security of technology with enablement? The internal collaboration and partnerships allow for the most appropriate architecture to be created, especially with Cyber Security. New partnerships need to be formed to deliver self-service models and conjoin the interoperability opportunities up and down the stack. In the end, it is important to continue to be patient-focused.

This portfolio of technology expansion increases the need of interoperability. As my organization continues to grow and expand, the demand for additional smart devices, such as patient beds and RTLS, brings more avenues for data needs. The effort is finding the right strategic partners for foundational technology to support these additional data, considering the needs to transport this data effectively. It is imperative to solidify wired and wireless network architectures for the increased density of data, but also magnify other technologies like Bluetooth and IR. What types of devices do patients interact with during their in-person care and how to deliver these interoperability mechanisms are the new focus.

Foundational technology is a building block for the delivery of services, whether it is through the traditional data center or cloud partners and connectivity and technology. It is important to continuously evaluate the technology maturity roadmap. The rapid pace of delivery and maturity can certainly bring a loss of focus on the important milestones needed on the journey. How does traditional technology I&O balance the need for 5×9’s or better, while also supporting a growing digital transformation practice where trial and error is key to find the right solution? This is addressed with the right collaboration and expectations set.

There is an excitement about the possibilities of digital prospects. The importance of organizational vision and support drives how technology decisions bring new value. The foundational technology must support the needs of clinicians, researchers and especially patients in this digital age.

The post Delivering Technology in a Rapidly Changing Ecosystem appeared first on HealthTech Magazines.

Population health is a key part of the American Heart Association’s mission of being a relentless force for a world of longer and healthier lives. COVID-19 has accelerated the adoption of technology outside of the healthcare setting not only to reduce exposure to the virus, but also to improve access to care. As a result, health technology has advanced to the level that key biometrics, such as blood pressure, glucose, physical activity, and even heart rhythm, can be captured through wearables and connected devices outside of the healthcare setting and accessed by the care team.

An SMBP platform can bridge between the BP device and the EHR and solve the problem of manual data entry and selective reporting.

An effective population health approach using health technology is one that is high volume, high impact, cost-effective, and promotes health equity. A successful population health/data integration strategy is defined by a positive health metric and an economic value. The strategy must be both scalable and sustainable, so if it does not meet both criteria, it will not be seen as a success. Key elements for successful digital health outcomes include using a trusted source and a scientific approach, connecting to a healthcare delivery system, providing a secure technology and digital solutions platform that allows delivery to very large groups, providing an intuitive, consumer/patient-facing interface, and having the ability to continuously monitor data to evaluate usage and outcomes. In addition, there are numerous gaps throughout the system that make this challenging, including the digital divide, lack of trust and science/validation gaps.

A classic example of population health utilizing a data integration strategy is self-measured blood pressure (SMBP), which is the person taking blood pressure (BP) readings at home, connected to a secure cloud, and integrated into the electronic health record (EHR). Nearly half of the 116 million adults in the US with hypertension do not have their BP under control. Rates of BP control are disproportionately lower among racial, ethnic, and socio-economic groups. High BP is associated with an increased risk of heart disease and stroke and is a vital indicator of overall health. Achievement of BP control is associated with better health outcomes and is cost-effective.

The American Heart Association’s Center for Health Technology and Innovation has been at the forefront of digital solutions for BP control, including community and home-based strategies such as Check.Change.Control and National Hypertension Control Initiative and the Self-Measured Blood Pressure Digital Health Platform Provider Landscape, which provides best practices for BP control, especially in under-resourced communities.

The management of high BP has been based on measurements taken in the healthcare setting. Regular out-of-office BP measurements provide a better picture of the individual’s blood pressure trends and has the added benefit of allowing the patient to be more active participant in their care. An SMBP platform can bridge between the BP device and the EHR and solve the problem of manual data entry and selective reporting. The process begins with the patient being identified for SMBP by a healthcare professional. The patient has access to a secure portal and a validated BP device. The patient takes BP readings at home and returns to the clinic for follow-up. The BP device must be accessible and compatible with the portal. In addition to uploading the data to the EHR, the patient must also be given access to the readings for feedback. The professional must be able to access the readings in a manner that does not break their clinical workflow. The professional must be able to monitor the individual’s progress and evaluate the success of the overall program. To be sustainable, the data must also integrate with the EHR, billing and reporting systems.

The mere existence of home BP monitoring does not lead to blood pressure control. Relaying the readings to a healthcare professional remains a critical step to inform clinical decision-making and action, to diagnose, and optimize pharmacologic and non-pharmacologic treatment plans. Methods of data transfer range from low and non-tech approaches that are paper-based, to intermediate and hybrid approaches of connecting the blood pressure device to an app or cloud-based data portal, to a fully integrated solution from the BP device to the EHR.

The Food and Drug Administration’s approval to market a BP device does not imply that it has been validated to deliver clinically accurate and useful blood pressure readings and the Centers for Medicare and Medicaid require the use of a validated device for reimbursement. The accuracy and utility of SMBP depend on the use of a device that has been validated for accuracy, such as those on the US Blood Pressure Validated Device Listing. Data capture can be from the device, a patient portal, or a mobile application. The data can be shared with the healthcare professional by showing the data during an office visit, via email or external dashboard, or within the EHR. Once the healthcare professional has access, the data must be validated and presented to meet minimum acceptable standards for clinical decisions.

A key challenge is presenting the information to the user in a way that they understand and can use to make good, well-informed decisions, and to the healthcare professionals in a manner, they can trust. For the end-user, this is done by presenting the information in a clear and concise manner with actionable steps. For the healthcare professional, this is done by taking a science and evidence-based approach and providing context. For end-users and health professionals, data security and storage, as well as access and privacy are always important, while interoperability and integration into the EHR is also an important factor. The desired outcome is improved BP control, resulting in improved quality of life for patients and healthcare professionals, and a more accessible, cost-effective, and equitable healthcare system.

The post Health Technology Support for Population Health and Data Integration appeared first on HealthTech Magazines.

As health systems navigate their way through an unparalleled age of technological advancement, CIOs can tap into an overwhelming number of state-of-the-art solutions capable of driving their digital transformation strategies forward. From wearables to mobile health devices, augmented reality to machine learning, the choices are seemingly endless.

And while all this technology is captivating, it also can be blinding. It’s too easy for health systems to let technology run the business of health care. Instead, it’s the business of health care that must drive the technology, because digital transformation will only make a real impact on a health system if it ultimately helps to improve care delivery and patient outcomes.

We’re fortunate at Atlantic Health System to have innovative, diverse leadership and a team of health care professionals covering a span of generations—baby boomers, Gen Z’ers, millennials and Gen X’ers—that embody this philosophy. Working together, we tackle digital transformation with a single question: What is the problem we’re trying to solve? Many times, the answers come from the clinical side rather than the technical side.

This methodical, collaborative approach gives us a system of checks and balances that ensures the technologies we invest in will help us achieve a specific ROI. It also allows us to make technological enhancements that augment—and not replace—the care our health care professionals deliver. We always include the human element in our workflows to strengthen the patient-clinician bond.

Over the past 12 – 18 months, we’ve seen encouraging results from two particular technologies: AI and Big Data. In both cases, the primary measurement is how well these solutions can help health care professionals treat disease sooner, creating better health throughout the communities we serve.

How AI enhances Medical Imaging

As Atlantic Health System grows and cares for more people, delivering highly sophisticated medical imaging takes high priority. As we searched for optimal imaging solutions, we prioritized technology that could help our radiologists and health care professionals get more efficient, find abnormalities faster and contact patients sooner for follow-up tests and appointments that can save lives.

To achieve these goals, we implemented three highly integrated solutions. The first, a modern picture archive and communication system (PACS), streamlines the entire radiology workflow.

By integrating our PACS solution with our Epic EHR, our radiologists can now access patient information and images from a single cloud-based system with enterprise-grade security that offers enhanced protection from ransomware and other malicious attacks. Our clinicians report high satisfaction with the quality of images on our new PACS system.

The second tool in our radiology arsenal is a FDA-approved decision support software solution. It uses AI to scan large volumes of images (such as CT scans), flag images that contain abnormalities and move them to the top of a radiologist’s or health care professional’s to-do list.

While the technology flags suspected acute pathologies, the human element is the key factor in this workflow. That’s because it’s the clinician who reviews the flagged images, identifies potential life-threatening anomalies—intracranial hemorrhage, acute spinal fractures, pulmonary emboli—and expedites patient care so patients with the most acute needs get seen right away.

Rounding out our medical imaging technology cycle is a radiology report management solution. It uses AI and NLP to comb through clinical notes and imaging scans. It then notifies the care team if and when patients need to follow up. This helps our health care professionals close the loop with patients faster and find potential diseases earlier.

We used EDAP data to identify potential COVID-19 hot spots and quickly ramp up supplies, staffing and resources in facilities that served those communities.

Viewing Big Data from an enterprise-level

Most businesses today are ingesting more data than ever before, and health care is no exception. However, most health care organizations have data spread across multiple legacy systems or locked in department-specific silos, which reduces the ability to act on that data. We faced the same challenge of bringing data together so we could make optimal business decisions.

Our answer: building an Enterprise Data and Analytics Platform (EDAP). The EDAP solution gathers data from 63 different sources, including our Epic EHR, claims data, health quality data, financial data and more. EDAP allows us to ingest, curate, create and model data, giving us a robust data pipeline capable of creating predictive and prescriptive models.

In addition to investing in EDAP, we’ve recruited highly skilled data scientists and aligned them with each vertical inside our health system. The expertise of our data analysts, combined with EDAP technology, allows us to identify operational, financial and clinical efficiencies and ultimately improve patient care.

One real-world example of how EDAP benefits patient care came during the COVID-19 pandemic. We used EDAP data to identify potential COVID-19 hot spots and quickly ramp up supplies, staffing and resources in facilities that served those communities.

Fueling adoption of innovative technologies

Implementing emerging AI-powered technologies and other modern solutions is just one part of the battle. The second is fully adopting them. At Atlantic Health System, we incorporate both e-learning and in-person instruction to make sure all health care professionals and users know how to use the technology, understand the workflow and interpret the data they’re reviewing, fueling widespread adoption and competency.

And while AI and Big Data are showing the best results for us right now, we’re also introducing many other emerging platforms—from customer experience technology to machine-learning-driven solutions and even augmented reality. Each is at a different maturity level. By looking at these solutions through the lens of problem-solving, then taking a pragmatic approach to implementation and training, we’ll keep developing innovations that help us expand the number of people we can help in our communities and enhance the care we provide them.

The post Using AI and Big Data to Improve Medical Imaging and Care Outcomes appeared first on HealthTech Magazines.

With a heavy concentration on translational and clinical research at Memorial Sloan Kettering Cancer Center (MSK), there is an ever-growing need to leverage data across the clinical, research and education missions. While as a cancer center, our organization has a singular focus of disease, our data and technology needs are consistent with the needs of the larger healthcare industry. And our overall outlook reflects the demands of larger society. Atti Riazi says, “We must go through a radical revolution in terms of how we view IT— no longer seeing it as things and products, but instead focusing on the experience, intelligence, and insights from all the technology we deploy.”

The advances in differentiating types of data storage and federation, as well as the ability to create an access and delivery layer across disparate data sources, has fostered the emergence of a different way to think about data—the data fabric. There are a few transformative core components of our data fabric, all housed in a strong metadata layer including a concept-driven catalog, data lineage, master and reference data management, and data de-identification. These contribute to the advancement of healthcare by providing clarity and transparency while also protecting sensitive data classes like PHI (Protected Health Information) and PII (Personal Identifiable Information).

Our catalog and use of standard ontologies in biomedical research and patient care allow our fabric to provide transparency to the meaning of our data—clarity previously obscured by the myriad of independent transactional systems used in healthcare. Since clinical and administrative data is often spread across multiple systems, it is challenging for users to understand what data means and how it connects to each other across systems. A billing system might provide data about a patient’s diagnosis and comorbidities using standard billing codes, while the impact of drug interactions is housed in the EHR, and outcomes are buried in provider notes. The context of this integrated information is critical in both the clinical and research realms. By extracting the meaning of each of these domains of data and representing them in an integrated catalog, users can find new pathways of care and create new insights for research. 

While the focus of healthcare must always remain in the provider-patient relationship, the administrative functions of healthcare enable better care. Operations must look at data in the aggregate, which lays bare the inconsistencies and quality issues across a medical center. A data fabric allows for data to be selected and managed through the metadata, providing the ability to track data through its lifecycle and pinpoint the opportunities for its quality improvements. With a robust data stewardship program, an organization can use master and reference data management to create a unified picture of data, allowing operations to manage interactions organization-wide. The regulatory and ethical considerations around the privacy of an individual’s data are continuously advancing, and technology is emerging to automatically de-identify data as it moves through systems. Our data fabric transforms our ability to use near real-time data while protecting data privacy. There is no longer the requirement to send unique datasets through manual de-identification code, delaying the use of data at the moment. 

Adoption across the organization is varied, with some areas showing reluctance to adopt the change, while others are racing to embrace the new technology.

Present day, the value of data in understanding and controlling infectious disease is on the forefront of many people’s minds. Atti Riazi says, “What is the benefit of knowing about COVID-19 or Ebola a month earlier, or understanding that a few less inches of rain will create drought, food shortages, unrest, and instability in a region the following year? Data has great value in providing insight into so many social, health, and environmental issues; by sharing information freely, we can better predict such disasters and take much more effective action. Tech companies can help governments, NGOs, and civil society with big data projects through funding and providing expertise, tools, and data itself.”

The technology behind our integrated data fabric layer contributes to the transformation of our industry by enhancing the meaning of data and enabling more flexible use, with the data constantly in motion through its lifecycle—although, as with any transformative program, it is not without its challenges. The technology is still being conceived, and a stable, integrated technology has yet to emerge in the industry. Today, organizations that have a fully realized fabric have invested millions of dollars and years to achieve those ends, and a fabric platform approach to data management is outside the reach of many medical centers.

With any new technology, the early adopters will suffer the wounds of the ‘bleeding-edge’ to enable true transformation of the industry; it requires the foresight and will of those institutions to lead healthcare, and clinical and translational research, into the next era. In addition to the burden of commitment, any transformation bears the delicate challenges of change management. Our approach uses two main components—education through data literacy initiatives, and tool training as users bring specific use cases—to transform how we think about an organizational data platform.

Adoption across the organization is varied, with some areas showing reluctance to adopt the change, while others are racing to embrace the new technology. The former group poses the challenge of requiring tactical and significant resource commitment to help our users adopt the new approach to thinking about data. The latter group poses the challenge of demanding changes faster than the technology can be built. To remain on a successful trajectory, our program has adopted a concentrated approach to change management, a change we feel is a departure from a traditional ‘build it and they will come’ mentality. Through these efforts, and mindful of the overall benefit of data globally, we are trying a wide variety of outreach, training, and communication strategies, and measuring the success of each so we can continuously optimize not only the technology we are building, but also the enterprise-wide adoption. 

The post Managing the Evolving Data Landscape in Cancer Care and Research appeared first on HealthTech Magazines.

By Valmeek (Vick) Kudesia, VP Clinical Informatics and Advanced Analytics, Commonwealth Care Alliance^®

“I’m a doctor and an engineer. I build things to take care of people.”

The first overnight of my medical internship was spent working in the medical intensive care unit (ICU). One of my patients, “John,” suffered an esophageal perforation—a serious side effect of cancer treatment. Soon after John’s arrival to the ICU, I called my attending physician to discuss the results of the many laboratory tests and procedures. He listened quietly as I interpreted the long list of data and then asked, “Vick, when do you think he will die? Would he want his family by his side? Would they want to be by his side?” At that moment, I had a sobering realization. My attending physician helped me understand that all the data pointed to a complete story about John—he would die on my watch, unable to advocate for himself, and my job was to keep him alive so that he could pass away (humanely) with his family by his side.

In healthcare, data could be the vehicle for decision-making and learning. Unfortunately, some of the increased use of data and electronic documentation in healthcare has also led to undesirable (or de-humanizing) outcomes (such as risk stratification algorithms that reinforce systemic racism by underestimating the medical needs of African Americans). To minimize these undesirable outcomes, data should proactively show clinicians the “whole story” associated with a person’s needs, particularly if that person is unable to ask for help or doesn’t know all the ways that help is needed.

In my current role at Commonwealth Care Alliance^® (CCA) leading Clinical Informatics and Advanced Analytics, I have seen firsthand the power of data when these invisible factors are delivered directly to clinicians daily.

The COVID-19 pandemic brought greater emphasis to the “invisible factors” that impact health. These can include systemic racism, housing and food insecurities, loneliness, fear, inability to visit pharmacies or grocery stores, inability to visit clinics, closures of food pantries, closures of community services, changes in services or common areas in senior housing, and other relevant social determinants of health (SDOH). These factors are very important to a person’s whole story, but they are often invisible to both clinicians and patients. Broader use of data to capture and reveal the effects of these invisible factors is needed to humanize—instead of de-humanizing—data-informed processes in healthcare. This is specifically important in value-based care or other risk-bearing contracts where the whole story is critical to achieve high-quality care.

The recent rise of reverse extract transform load (ETL) data technologies will allow data and the latest analytical insights to more easily travel from an analytic environment to “everyday work software” and inform employees when that insight carries the most value (such as when speaking with a customer via phone or chat). Data and insights will play a broader and proactive role in employees’ daily experience—like an “ally” that delivers specific insights even if the employee doesn’t know what to ask.

Imagine what might happen if healthcare

1) broadened its use of data and analytics by describing interactions between SDoH factors and clinical outcomes and

2) proactively informed clinicians (at the point of care) of SDoH factors and outcome interactions specific to their patient.

Data would be a proactive therapeutic ally that unveiled a complete story of how to help a patient, even if neither clinician nor patient knew to ask. For example, a patient might have a higher risk of decompensated congestive heart failure than suggested by their level of heart function because they do not have reliable transportation to a grocery store to obtain healthier foods. This is an essential information to display to a clinician in an EHR at the point of care. Value-based or risk-bearing care arrangements are also likely to gain greater financial advantages from this complete and proactive information.

In my current role at Commonwealth Care Alliance^® (CCA) leading Clinical Informatics and Advanced Analytics, I have seen firsthand the power of data when these invisible factors are delivered directly to clinicians daily. At CCA, every day during the COVID-19 pandemic resulted in a deeper appreciation for a patient’s whole story and how these invisible factors can impact health and quality of life. During COVID-19, CCA accelerated its use of technology to meet the new understanding of patients’ needs. For instance, to better meet the medical, behavioral, and social needs of our members—many of whom didn’t know how to ask for help—we launched medical and behavioral health virtual care visits, deployed smart-speakers in homes to help monitor patients remotely, and utilized proactive paramedic home visits with remote patient monitoring and predictive analytics to reduce the need for unplanned acute care. We also faced and overcame many obstacles related to data and system integration/interoperability, wireless/cellular broadband availability, and rapidly changing logistics (e.g., timed expiration of COVID-19 vaccine vials once opened).

Clinicians often work to “pull the right data” or “put in the right data” so that they can “do the right work.” In contrast, imagine a world in which, every day, the right clinicians, without asking, received the right data needed to fully care for every patient. Healthcare has an opportunity to use the same emerging technologies that maximize commerce but direct those technologies to maximize our understanding of every patient. Through this humanizing use of data, we create a therapeutic ally that unveils patients’ needs and differences in an actionable, humane way and reinforces person-centered care.

The post Humanizing Uses of Data appeared first on HealthTech Magazines.

Mountain Area Health Education Center (MAHEC) is part of the North Carolina AHEC system. Over the last 4+ years, it has tripled in size, making it the largest non-profit in Western North Carolina. Growth comes in the services provided in family medicine, internal medicine, obstetrics and gynecology, psychiatry, behavioral health, and dental services and also in the education sector, where students and residents come to advance their education. The employee population grew from about 300 to over 900 today. The challenges and opportunities of this growth, plus ensuring technology, process and needed support can scale, are exciting opportunities we face every day, and they are not always easy.

MAHEC’s mission is to train and retain healthcare professionals while ensuring patients in our 16 county region of Western North Carolina have access to quality care. These are very rural regions where access is limited and connecting, whether in person or via telehealth, requires creative solutions. In order to meet patient needs, we have hired new faculty and staff, opened new offices and clinics, implemented telehealth options, and developed new ideas for the best patient experience. Keeping new and existing staff current on how to best use new technology requires leadership and staff adoption. As a learning institution, some team members are just getting started in their healthcare career and much of what we do is very new to them.

We are piloting several initiatives right now in which we will use data to evaluate the effectiveness of change. I am very optimistic that we will move forward with some of the changes, or we won’t.

I’m not a physician. I have been in technology my entire career. I am stretched more than expected to consider the point of view of the physician and staff providing care, but even more important is the impact of technology and change on our patients. 

These challenges are not unique to MAHEC or many other healthcare organizations. Leading through change is both exhilarating and exhausting. Technology is part of the solution but not the entire answer.  I spend a great deal of time thinking about the human side of technology – the change management side. With new providers on staff that have worked with different electronic health records, existing staff who remember when things used to be simpler – a time they long to return to – and a technology team that continually needs to upgrade and learn new skills, we are asked to do more, differently every day. Yet, our success is dependent on people.

Our technology needs include everything from continuous security management to improving the patient telehealth solution when many of the patients in our region have limited access to reasonable bandwidth. Our organization is also moving from an environment where individual clinics have autonomy in workflow and processes to a more holistic view of how we provide the best patient experiences consistently across the region. Consistency across the organization is as much about using technology as it is about realizing we need to change. Complexity to succeed involves engaging everyone from our CEO to our administrative staff.   

Communication is the focal point for success when dealing with large transformational projects. The ability to listen to needs, acknowledge concerns, share positives, and find the balance for as much of the staff as possible means spending a lot of time with people. I’ve been in technology for over 20 years and have led a couple of very large transformational projects. I’ve learned the hard way, through a couple of failures, that how we lead the people through change makes or breaks a successful technology project, whether it is updating computers, changing an EHR (huge), adopting new financial or human resource systems, rolling out an organization chat software or any project large or small. 

Finding the balance to bring as many people along as possible in any transition is key. Thinking about the standard bell curve, approximately 10% will follow change because they are excited by it. 10% may never accept the change, no matter how hard you try. The best strategy that I learned from some former colleagues was to focus on the 80% that could go either way. With the right inclusion and strategy, they will come with you. Many people work too hard to convince the negative 10% because we want them to engage, it leaves others feeling left out.   

With so many stakeholders, how do we look at all these opportunities, make the best decisions, and always strive to improve patient care? Data really helps! That is not new, but depending on the culture, it may not be the norm. In our rapid growth environment, moving fast also means using our previous experiences, our track record of success, and our desire to be innovative to inform our decisions. As we have grown, larger the impact and scale of our decisions is greater and finding some balance that includes data is more important than ever. Whether assessing the call volume and answer rates for our scheduling team for the best service outcomes, looking at standards of care across our patient population with an equity lens, monitoring performance measures in all clinics, or building solutions that can make the work easier and care better, we engage data as a component to drive change. 

Data supports the strategy and decisions. It also balances some of the emotions or feelings in the process because institutional learning and knowledge are highly valued. We are piloting several initiatives right now in which we will use data to evaluate the effectiveness of change. I am very optimistic that we will move forward with some of the changes, or we won’t. Based on what we learn, how we quantify the value, and by listening to our pilot group, we will know what worked and what didn’t. I’m excited about this work, it is based on technology, but the people will determine the success.. 

The post Technology Change Management – It’s the People appeared first on HealthTech Magazines.