What's new with clinical trial data transparency?

After being involved with data transparency for a few years, I continue to be pleasantly surprised by the continuous progress with respect to data transparency for clinical trials.  At the Fifth Installment of the SAS Clinical Trial Data Transparency Forum, I was amazed by the amount of new information that speakers added to my existing knowledge of data transparency for clinical trials data.

Interesting new information included the human resources challenge, the growth of disease-specific repositories and the availability of an assessment on the research potential for increased access to the clinical trial data.

Resources, resources, resources

Speakers from sponsor companies clearly outlined the human resource challenge inherent in the gathering and de-identification of the clinical trial data.   Some companies are changing processes for new trials to ease the future data transparency support challenge.

Allocating resources to support data transparency efforts was highlighted as a major issue in smaller firms. Possible approaches to solve the data transparency data preparation human resources challenge are:

  • Creating dedicated transparency data preparation teams.
  • Outsourcing the activity to a vendor.
  • Using the existing clinical study teams.

Disease-specific data repositories

Prior to the conference, I was aware of the success of Project Data Sphere – an initiative of the CEO Roundtable on Cancer’s Life Sciences Consortium. Project Data Sphere aims to accelerate cancer research by allowing access to the comparator arms of historical cancer trial data sets.

During the conference, I learned of the availability of schizophrenia clinical trials data through the Open Translational Science in Schizophrenia (OPTICS). OPTICS fosters translational science in schizophrenia research by making clinical trial data plus observational studies and trials available through the NIH (via dbGaP) accessible to qualified investigators.

This is welcome news that new disease-specific repositories are being developed. The potential for disease-specific data repositories to advance science and impact human health in the future is immense.

Assessing the research potential - Wellcome Trust report

And speaking of the potential impact of increased data transparency for clinical trials data, a thought-provoking presentation from a representative of the Wellcome Trust  discussed a report commissioned by their organization titled Assessing the research potential of access to clinical trial data.

The study is comprehensive and an excellent source of information for anyone interested to learn more about clinical trial data transparency and the potential benefits to medical research.

Want to learn more?

Increased access to clinical trial data for authorized researchers can be a valuable resource for a generation of new medical knowledge. The new insights will have the potential to improve public health over for decades to come.

No matter how closely you have followed data transparency issues, I suspect you will learn a great deal from the video recording of the Fifth Installment of the SAS Clinical Trial Data Transparency ForumAnd you can learn more about the SAS data transparency solution.

Clinical trial data transparency is a rapidly evolving topic where sources of new information are a valuable resource. The Fifth Installment of the SAS Clinical Trial Data Transparency Forum did an excellent job of providing me with new knowledge.

Post a Comment

Visualizing the customer journey through analytics

42-23789610 (1)SAS customers across all industries are solving amazingly complex business problems – in record time – with advanced analytics from SAS. And health care is no exception. In fact, the health care industry may soon be leading the way in rapid analytics innovation.

Read what Ravi Shanbhag from UnitedHealthCare has to say about using social media data and SAS® analytics to build lightning-fast insights around competitor behavior and customer risk, including this tidbit about the customer journey:

To find out which customers might be likely to default on their premiums, they decided to take a birds-eye view of all systems.  The team used grid computing to look at structured data, then loaded a broad set of possible attributes to SAS® Visual Analytics for a decision tree analysis. And that’s what helped them pinpoint where the problems might be. Armed with that knowledge, United can now help people into more affordable products or even change their payment plans.

Want to hear more stories like this? Don’t miss the SAS Health Analytics Virtual Forum (free registration) streaming live from SAS Headquarters on May 20, 2015.

Post a Comment

The NHS: Time to care about big data

Considered to be one of the UK’s most precious institutions, it's no surprise that the National Health Service (NHS) has been ranked as one of the most important issues in this year’s general election. Phrases like ‘building an NHS with the time to care,’ will no doubt be ringing in the ears of the electorate and public alike over the next month.

Electoral pledges have been focused on investing more funding and human resources, joined up services from home to hospital, and guaranteeing appointments. Whilst investment is imperative, I’m keen to point out how the NHS can be more efficient and how big data could dramatically cut our country’s care bill.

It goes without saying that the NHS is a relentless producer of data – be it patient data, performance data, clinical data or textual unstructured data. However, despite the breadth of a nationalised health care system, this data is immensely siloed. Hidden within this data are valuable insights that can identify trends, potential outbreaks in diseases or peaks in medical conditions. This data, if used correctly, could be the pill the NHS has been looking for.

PatientDataAllAnalytics

One example of data being put to good use is at Royal Brompton & Harefield NHS Foundation Trust, where they have in excess of 400 data systems and 20 clinical data sets. It uses data to make evidence-based decisions based on its research into heart and lung conditions. It has been able to bring numerous disparate data sources together into a single system. A single source of the truth makes it possible for a consultant to eventually have all the information about a patient immediately in front of them, giving a much clearer picture for earlier decision-making – e.g. whether to provide emergency treatment.

The Trust also uses advanced analytics to uncover unexpected or less obvious connections between data. This could be a previously unknown link between a medication and a certain condition, or links between lifestyle and recovery from operations. Crucially, the analytical capability means these insights can be rapidly identified. For example, in certain situations patients may no longer have to go into hospital and sit in a waiting room for hours. Through better understanding of the patient from their data, it may be possible to intervene early and deal with their situation in a different way. It should also lead to more rapid diagnosis and treatment. All these outcomes deliver obvious benefits in reduced costs and lower demands on services.

Using big data analytics techniques more widely could anticipate pandemics or peaks in demand on A&E (accident and emergency) services. This is where significant efficiency savings can be found by putting additional resources into A&E to manage expected peaks, and vice versa when demand subsides. The data can also be analysed to delve deeper into what causes peaks and troughs in demand, further improving predictions and resource allocation.

Our greatest medical discoveries are borne from repeated testing and repeated failure. Much effort is being spent across the health care industry to understand the correlating genome sequence for many patients covering different conditions and outcomes. This creates masses of data, but the good news is that the technology can now process all that data much quicker than before. Already medical researchers have begun tailoring treatments for different patients. For example, clinicians can prescribe drugs with a varying level of toxicity according to how susceptible the patient might be to treatment, which is based on the evidence from data.

Big data analytics provides a quicker route to efficiency savings and new breakthroughs, which can help revolutionise the NHS – unlike blindly throwing more money at it.

Find out how better use of data and analytics can prevent more NHS scandals.

Post a Comment

Research just got easier: Open clinical trial data holds tremendous promise for medical research

Our own Matt Becker and Christian Nimsch contributed to this post.

You might be surprised at the wealth of information you have access to!

The worldwide movement towards open data has swept through many industries in a highly publicized fashion. And for health care, there is a real promise of using data to achieve transformation.

The first step in using data is to foster an environment of data transparency that provides access to relevant data. Think of the Human Genome Project. One of the hallmarks of the project, and some would say the key to its success, is that sequence information was in the public domain and readily accessible to all.  Similarly, when we evaluate the efficacy, safety and effectiveness of pharmaceutical and biotech innovation, we often turn as a first resource to data generated via the clinical development process (clinical trials). Surprisingly to many, most major pharmaceutical companies have recently provided transparent access to their clinical trial data.

clinical trial data transparencyThe move towards open and transparent access to clinical trial data has been going on without much publicity. It’s now possible for researchers to access vast amounts of anonymized patient-level data from clinical trials at no cost. Rather than continue the practice of basing research on abstracted information and reports, researchers are free to use source data to enhance their projects and further validate their findings. In fact, many major organizations have created virtual workspaces for researchers to request, access and analyze data in a controlled environment from multiple sponsor companies within the same research project, all from the same place.

Almost all major pharmaceutical companies worldwide have a framework in place to make this patient-level clinical trial data available to researchers. Many biopharmaceutical sponsors have added information to their company websites regarding their data transparency initiatives and how to request access to clinical study data. Although there is currently no master list of organizations that participate in this movement, some industry groups are attempting to create such a record. Clinicalstudydatarequest.com is an excellent resource for medical researchers in that it posts transparency information for eleven sponsor organizations participating in clinical trial data transparency efforts. In addition, researchers can contact each pharmaceutical company directly and request access to the clinical trial data.

You’ll be surprised at the wealth of information you have access to!

Post a Comment

Virtual care technology: change home health care and empower patients

From guest blogger, Kay Eron, General Manager Health IT & Medical Devices at Intel

Today, many health care organizations are experimenting with and implementing the art of virtual care technology. Innovation in technology is finally able to address the need to go beyond brick and mortar, and drive “care anywhere” when it’s needed. While technology is enabling providers to drive virtual care initiatives to increase quality of care, provide patients with more access, and improve patient empowerment, there is the question: How secure is the ecosystem in which more and more personal health information is being exposed?

Current technology

First, let’s look at where we are currently. Health care is one of the most dynamic industries today, thanks to digital technology and industry and government coming together to address some major pain points that existed for many decades. We’re finally at a point where many of the “what if we could” ideas that clinicians and patients had earlier can be realized. For example, many providers are driving initiatives around virtual care, including telehealth and remote patient monitoring from within patients’ homes.

In the future, payers may be able to use HIT and device information to analyze big data and provide the optimal plans for patients in different demographics given the geographic region where they live, family history and lifestyle. Add to this, patients can be empowered with tools, devices and information to proactively manage their own health outside the hospital in a way that really makes sense.

Wearables and mobility

Simple forms of home monitoring have existed for years. However, today there is a market disruption with new form factors of clinical wearables and connectivity solutions that are easier to use and can better transfer and give access to patient data. Smartphones and tablets have become an integral part of people’s lives and can serve as a tool for telehealth, as well as a hub for clinical patient information. This makes the implementation of virtual care much easier. Patients now have options to cost-effective solutions to manage their health more proactively.

At the same time, this proliferation of devices and data also increases the risk of data attack. Any point where data is collected, used Data Securityor stored can be at risk and needs to be secured. For example, if the wearable devices collecting the data are outside the US and that data is being uploaded to the cloud inside the US, then the use of these wearables can represent trans-border data flow. This can be a significant concern, especially for countries or regions with strong data protection laws such as the EU. We all must be diligent on how the data can be captured, transmitted and protected. Intel offers a security solution that integrates with the user experience with fast encryption and cost reduction, and continues to work with customers to solve data privacy and security challenges.

The security challenge

Overall, it’s wonderful to see so many health care institutions driving virtual care. It’s definitely moving outside the traditional venues to more comfortable settings closer to what patients need. However, this also exposes more patient health information outside the hospital walls and outside patients’ homes.>

To address this vulnerability, at Intel, when we design a solution, we build security into our core hardware. This differentiates how the users experience security. To have a great experience, they shouldn’t be subjected to data breaches or other security incidents. Technology needs to be smarter about detecting user context, risks, and guiding the user to safer alternatives. It’s imperative that devices function reliably and be free of malware. We have a focus to drive consistent security performance across the computer continuum of care.

That brings us back to the original question: how secure is the ecosystem? Security is a critical role in providing data that providers, payers and patients can rely on. Reliable security will more readily foster adoption of virtual care. Depending on the types of patient information collected, used, retained or shared, and how it’s maintained, security can be designed to optimally protect privacy. It’s a complex area, but given the value of health data, I’m hopeful that organizations will start to design their virtual care solutions and ecosystem with security as one of the most important pillars.

Find out more information and read the latest blog posts on health IT at the Intel Health and Life Sciences Community.

Post a Comment

Moving to value-based health care with episodes of care

The move to value-based payments is well underway and accelerating. The shift is putting unprecedented pressure on health care providers to better manage the cost and quality of care they deliver. Who will have a much better shot of success? Organizations that understand how well they are performing, where they have opportunities to improve and, their capacity to redesign care delivery.

In fact, the acceleration to value-based payments is being fueled by encouraging results from the field. Many strategies, whether technology or labor-intensive, are helping providers deliver better value and are bending the cost-curve.

Unfortunately, it’s challenging, slow and expensive work without guarantee of success.  Strategies and interventions may not be efficient enough to scale beyond targeted populations or pilot programs. Given limited resources, providers must to be smarter about where they invest and how they execute those strategies.

This is where SAS can help. SAS applies advanced analytics to complex clinical and financial data so providers can be more efficient in selecting and acting on opportunities. For providers under financial risk for the cost and quality of care they deliver to their patients, SAS has SAS® Episode Analytics.

Episodes of careThis solution derives clinically relevant episodes of care from patient service and diagnosis information. Episodes such as a joint replacement, stroke or congestive heart failure are defined collections of services spanning the care continuum over a period of time. While services related to the patient’s condition are differentiated from those that aren’t, the solution also identifies which services are potentially avoidable (e.g. infection, readmission or adverse medication event.) This is invaluable to help providers bring the clinical team into the improvement process because it provides clinical evidence that can drive change.

Imagine a new lens through which  you can view the quality of care delivered across the entire care continuum. Providers haven’t had this in the past. When you apply this lens to a population of patients, providers understand which clinical conditions are driving health care spending and how much of the care delivered is related to complications.  Automatically construct episodes of care based on standardized (or your organization’s customized) episode definitions. The standard episode definitions cover:

  • Chronic conditions.
  • Procedures.
  • Acute medical events.
  • System related failures.
  • Cancer.
  • Obstetrics.

Depending on the population, these episodes capture as much as 85 percent of inpatient costs and 60-70 percent of overall medical costs.

You can gain more insights through other advanced capabilities, including:

  • Methods for attributing providers to episodes to promote accountability and comparison.
  • Risk and severity adjustments to explain variations in cost and provider performance.
  • Association of a patient’s episodes to each other to understand causality and unintended consequence.
  • Customization of episode definitions for differing population, contracting and provider needs.

When providers use episodes of care as a foundation for measuring their performance, they're better equipped to succeed with new value-based payment models. With SAS Episode Analytics, providers have the information they need to:

  • Identify and target poor quality, high-cost and unwarranted variation.
  • Engage clinicians and support staff in performance improvement around quality issues.
  • Design care pathways and programs to optimize outcomes.
  • Plan and budget with greater confidence.
  • Model contract scenarios and support negotiations with health plans.

Analyzing how services are delivered by episodes of care will be a key differentiator for health care providers as they transition to value-based payments. Episodes of care bring the focus on cost and quality to the true outputs of health care delivery.

Interested in learning more about how SAS can help you accelerate your successful transition to value-based payments? Join us at HIMSS Annual Conference 2015, April 12-16, 2015 in Chicago; Booth 4016 in the South Hall.

Post a Comment

A healthy case for cloud analytics

Patients at risk of avoidable hospital-acquired conditions, such as sepsis or venous thrombosis, can be identified earlier, which enables care teams to intervene more actively and reduce the likelihood of these life-threatening complications from occurring.

Care teams and patients can be notified about gaps in care or variation from evidence-based best practice, which can reduce unnecessary variation, either due to underuse or overuse.

By adopting techniques that are widely used in other consumer-friendly industries, patients can receive highly personalized care team-directed interventions through a variety of traditional and emerging delivery channels, including smartphones and health apps, thereby improving patient engagement. 

With a little ingenuity, the data we already have can be used to improve patient health while reducing organizational costs and risks. But it could be working so much harder.

health data analyticsPredictive analytics helps you see and plan for the future. Hindsight leads to insight and to foresight. Big data technologies let you apply analytics to vast data sources. Masses of genomic, electronic health record and claims data, as well as data from smart home sensors and wearable devices, can be brought together to reveal important insights at both the individual and population level to support better operational and medical decisions – and, ideally, bring analytic insights right to the point of care.

Imagine being able to have an intelligent safety net that provides 24x7x365 surveillance of a near-unlimited number of biological, behavioral and environmental factors that might influence a person’s health risk and experience. Or to evaluate alternative treatments by looking at factors that affect length of stay and incidence of readmission. Reveal which therapeutic regimens work best for what types of patients. Uncover disease patterns. Identify at-risk patients or assess the performance of individual physicians.

As our health care system transformation continues, analytic insights will be fundamental to economic survival. Well-informed care decisions and operational decisions become critical as we bring more of the previously uninsured onto the health care rolls and transform health care systems from a fee-for-service model to pay-for-value.

The case for cloud analytics

Much of the potential of big data analytics for health care remains untapped, and technology has been a perceived barrier. IT departments, already stretched thin, can be understandably reluctant to invest in the infrastructure. The data center will have to be engineered for peak processing loads, leaving much capacity idle (translate, inefficient) the rest of the time. It will require technical specialists to support the daily maintenance, inevitable upgrades and major surgeries – the forklift upgrades of data center hardware. It will consume months of analysts’ time to create and deploy the analytical software.

Not with cloud analytics. With cloud analytics, one or more key elements of data analysis – data sources, data models, application processing, computing power, analytic models, and sharing or storage of results – reside on shared infrastructure managed by a cloud service provider. IT departments can focus on core business initiatives instead of managing on-site technologies. Computing resources are virtualized, allocated as needed for great efficiency, and available on-demand on any device. Users get fast access to the answers they need from anywhere. All for a subscription or pay-per-use fee instead of a huge capital investment.

Hadoop is a natural for the cloud. Hadoop is an open source software framework for running applications on large clusters of commodity hardware. As such, Hadoop is a remarkably low-cost and scalable alternative to big data center servers. Need more power? Just add more off-the-shelf servers.

Hadoop brings a high-tech twist to the adage “many hands make light work.” It delivers enormous processing power with its ability to handle virtually limitless concurrent tasks and jobs across the cluster. Computationally intensive algorithms that would take hours or days to process using traditional analytical software can now run in minutes in memory.

Cloud analytics in action

SAS® for Health AnalyticsDignity Health, one of the largest health systems in the US, is working to develop a cloud-based, big data platform powered by a library of clinical, social and behavioral analytics. Over time, the platform will connect and share data across the system’s 39 hospitals and more than 9,000 affiliated providers. The goal is to help doctors, nurses and other providers better understand patients and tailor their care for better outcomes and lower costs.

For example, Dignity Health sees the following opportunities to use cloud analytics for data-driven insights to:

  • Plan care for individuals and populations, including predictive disease management.
  • Define and apply best practices to reduce readmission rates.
  • Determine best practices for addressing congestive heart failure and sepsis.
  • Predict the risk of sepsis or kidney failure, and intervene early to reduce negative outcomes.
  • Better manage pharmacy costs and outcomes.
  • Use performance data to drive best practices based on outcomes and value.
  • Strengthen reimbursement models, with a focus on paying for outcomes.
  • Create tools to improve each patient’s experience.

The analytics platform is being developed using our deep experience in medical research, health care, health insurance and pharmaceutical industries. So it starts smart, but it gets smarter over time. Algorithms in analytical models can learn interactively from the data. With every iteration, the models deliver more accurate results – faster.

Big data technologies have redefined the possibilities for using data – terabytes and petabytes of it – to dramatically improve health care costs, the care experience and patient outcomes. Cloud analytics puts it within easy reach.

Post a Comment

A strategy for population health analytics: Assess and report performance across the continuum (Part 3 of 10)

Any improvement program begins with honestly assessing current performance and identifying causal factors that drive the desired effects. Without such an assessment, the improvement effort is reliant upon blind luck and likely doomed to suffer a myriad of unintended consequences.

Any strategy to improve the health of populations, therefore, must start with establishing a baseline for the causal factors. Herein, analytics plays a key role in identifying correlation but requires smart people to establish causality. Smart people, equipped with the right tools and armed with trustworthy information, can perform root-cause analysis and identify opportunities quickly. Data visualization and exploration will certainly speed the process, but the real benefit comes from democratization of data through enterprise-wide interactive reports to gain a single version of truth across the organization. Thus, reporting becomes a foundational measurement capability by which you can monitor and validate all improvement initiatives.

Performance reporting needs to be personal, visual, mobile and interactive. Static reports only succeed in creating more questions than answers and, ultimately, frustrate users into cynical disregard and skepticism about the value of the reported information. For decision makers to want to use reported information in their decision-making process, they must first trust the accuracy and validity of the information and, secondly, they must be able to interpret and understand the results. Lastly, the information must be “actionable” – meaning specific and granular enough that the decision maker can affect a change by making different/better decisions. That’s a tall order, but we shouldn’t stop there.

The reported information should also be sufficiently granular, highly portable, securely shareable, and social – meaning that report users can collaborate with other care team members across the system to interpret, brainstorm and take action to improve the situation. Due to privacy concerns and our fragmented EMR (electronic medical record) infrastructure, this is one of the most challenging aspects of reporting health care performance in meaningful ways. However, success in population health management depends on our ability to unlock the data buried in the EMR, and surface insights to care team members who can affect change. This will transform reporting into an ongoing performance assessment cycle that enables evergreen prioritization of intervention programs and resource investments.

Population Health Wheel

The SAS Center for Health Analytics and Insights: Population Health Wheel

Until recently, it was extremely difficult to assess health care delivery performance at the episode level. Up until now we’ve relied on groupings of ICD/APG/DRG codes, but the business and clinical logic required to link discrete encounters together into clinically meaningful episodes wasn’t systematic. New, and increasingly sophisticated techniques for episode analysis are becoming available and are based on more clinically relevant episode definitions, such as those made available by HCI3's Prometheus Payment. These new episode structures are designed from the ground up to support value-based payment models that span the care continuum. Your population health analytics (PHA) strategy should include cost-effective methods to analyze episodes, identify variation in cost and quality, eliminate waste, and reduce the incidence of potentially avoidable complications. This is, I believe, a key factor in proving the value of care coordination and justifying the investment in a more connected system of care.

After establishing baseline performance measures and identifying and understanding root causes, we can move into phase three of the strategy and define clinically relevant population cohorts and identify gaps in care. In the next installment (4) of this series, we’ll discuss techniques to quantify risk and the value of decision trees.

Post a Comment

A strategy for population health analytics: Integrate and prepare data (Part 2 of 10)

In the eight-step approach to population health analytics (PHA) that we at the SAS Center for Health Analytics and Insights (CHAI) recommend, the first step is to “Integrate and Prepare Data.” But before we jump directly into a discussion about this first step, let’s take a moment to consider the following question: How much time did you spend in a doctor’s office or hospital (as a patient) last year? And now, compare that number to the amount of time you spent at work, at home, at an airport, in a car, on a bus, on the phone, out with friends, online, shopping, dancing, cooking, exercising, and whatever else you do while awake. I sincerely hope your ratio of minutes spent in a health care setting was similar to mine: approximately 92:350,308. Keep that ratio in your mind as you consider how much data was generated by you – or about you – in a health care setting. Got a number in mind? Now, how does that number compare to the amount of data generated by you – or about you – in all those other settings combined?

Population Health Wheel

The SAS Center for Health Analytics and Insights: Population Health Wheel

This thought experiment helps us recognize the need to include non-traditional ‘big data’ such as social, consumer, survey, and environmental along with our more traditional clinical, pharmaceutical, biometric, and lab data. Additionally, we need to plan for new data types and sources such as streaming data from wearable fitness devices, self-reported data from smartphone apps, blogs and forums, genomic data, and the digital output (audio and video) from telemedicine encounters. Successful integration of this data will require the use of fuzzy-logic to match, merge and de-duplicate with a high degree of accuracy. Perhaps most important, is the ability to mine unstructured (text) data to apply machine learning and natural language processing to extract value from clinician notes and patient verbatims.

Matching and attributing data from disparate sources to the correct person – be they patient or provider – is no mean feat. It’s not uncommon to find 30 percent or more duplication in patient’s EMR records. The problem is a bit like trying to bail water out of a boat before plugging the holes in the hull. Thus, an ounce of prevention in the form of data quality at the point of entry, is worth a pound of cure. However, most health care settings don’t yet enforce rigorous data entry protocols, so it becomes necessary to profile the data and set up repeatable processes to remediate data quality issues. Whatever technology you choose, be sure it routes data quality decisions to the appropriate data steward for quick and secure resolution.

Once you have a cleanly integrated dataset, you can begin the process to prepare that data for analysis. It’s been noted that 80 percent of the work required to find an analytically driven solution is directly related to data preparation. To best prepare data for meaningful use requires a combination of subject-matter knowledge (to identify what a signal might look like) and data science (to know how to tease that signal out of the noise.) Volumes have been written on the subject of data preparation. For population health analytics, the first and most formidable problem you’ll likely face is missing data. As such, it will be necessary to impute data and use advanced statistical methods for gauging reliability.

While this first step seems monumental, it’s important to anticipate and plan for the subsequent phases of the strategy. In Part 3 of this series, we’ll explore what it takes to assess performance across the continuum and report it in impactful ways.

Post a Comment

A strategy for population health analytics (Part 1 of 10)

The promise of Big Data and analytics in managing population health is one of the most hyped, yet least understood opportunities in health care today. The Center for Health Analytics and Insights at SAS hopes to change that by offering you practical advice to help you create a winning strategy for your organization. In this ten-part blog series, we’ll describe the technological capabilities you’ll need, anticipate some of the challenges you’ll overcome, and outline the many benefits you’ll receive from adopting population health analytics (PHA).

The motivation

The combination of government reform and consumerism is driving the health care industry shift from fee-for-service (FFS) to fee-for-value (FFV) – sometimes characterized as a move toward more “accountable care.” Proponents believe that economic opportunities – in the form of shared savings or value-based payments – will encourage health care providers to accept risk for delivering improved outcomes at lower-than-expected cost. This opportunity is already motivating a significant number of entrepreneurial health care providers to begin transforming their traditional care delivery process from responsive episodic care into cross-continuum coordinated care, for defined groups of patients. This emerging delivery model is often referred to as “population health management”.

The challenge

We know that managing population health requires providers to blur the boundaries between public health and the medical treatment of individuals. As health care providers accept financial responsibility for the health care costs of certain groups of people, the need for – and value proposition of – investment in longitudinal cross-continuum care becomes evident. Scarce clinical resources, thin margins and competing priorities require efficient deployment and judicious management of those resources, at scale. Thus, providers on this journey will need health information technologies (HIT) that enable automation, ensure accuracy and integrate seamlessly into clinical workflows.

The strategy in a nut shell

Population Health Wheel

The Wheel of Population Health Analytics (PHA) from the Center for Health Analytics and Insights at SAS

The Center for Health Analytics and Insights at SAS collated best practices and advice from experts across the US into a strategy we call population health analytics, or PHA. As shown at the top of the graphic of the PHA wheel, the strategy begins with integrating data from diverse sources and preparing it for analysis. This leads directly into assessing performance across the continuum of care. System-level performance reporting inevitably surfaces opportunities for improvement that will require providers to “peel back successive layers of the onion” and define increasingly granular cohorts of patients, ultimately ending with a “population of one.” Then, by understanding the needs and risks of each unique individual, providers can design interventions and tailor programs to engage each patient in a personalized care plan. Automation and workflow integration support the delivery of interventions that were strategically designed to improve care coordination and performance. Lastly, by measuring the impact (success or failure) of each intervention, experimenting with new methods, and testing incremental quality improvements along the way, providers can learn and adapt to optimize the entire process.

There are some important considerations for each of the eight analytical competencies, which we will cover in parts 2 through 9 of this series. In subsequent entries, we’ll elaborate on the business rationale, the desired output and the enabling technology that powers each capability. Check back for part 2 of the PHA Strategy series. In the meantime, please tell me your thoughts and ask us your questions in the comments section below.

Post a Comment
  • About this blog

    Welcome to the SAS Health and Life Sciences blog. We explore how the health care ecosystem – providers, payers, pharmaceutical firms, regulators and consumers – can collaboratively use information and analytics to transform health quality, cost and outcomes.

  • Health Analytics Executive Virtual Forum
    www.sas.com/virtual15
    #healthanalytics
  • Subscribe to this blog

    Enter your email address:

    Other subscription options

  • Archives