Archive for category Big Data

Artificial Intelligence for Real-World Evidence

Costas Boussios, VP of Data Science, OM1
Richard Gliklich, CEO, OM1

As artificial intelligence (AI) and Big Data are lauded for their potential uses in life sciences and healthcare, it is becoming difficult to differentiate between the myriad of terms and technologies and their real value in advancing real-world evidence (RWE).   In this article, we explore key AI and Big Data terms, their real-world application, and how they are building upon each other to transform our understanding of patient journeys and outcomes.

Big Data

Although Big Data is not required for artificial intelligence, much of the utility of AI comes from its application to large sets of information in the development of real world evidence.  The term Big Data reportedly was first used by NASA engineers in the 1980’s who were trying to work with datasets that exceeded their ability to store and analyze them with traditional computing software. Since then, the emergence of the world wide web and the development of advanced computing machinery and software applications has resulted in an explosion of data-generating applications. Today, Big Data is bigger and more ubiquitous than ever before.

The need to store, secure, query, process, analyze and manage Big Data has led to the development of numerous technological innovations over the last 20 years. Earlier proprietary solutions, such as the Google Distributed Filesystem, have been succeeded by widely available open-source technologies, such as Apache Hadoop.

Furthermore, Cloud Computing solutions such as Amazon Web Services, Microsoft Azure and Google Cloud provide flexible, on-demand computing capabilities with the potential of minimizing IT capital and maintenance expenses for organizations of any size. The availability of free or flexible cost capabilities, thanks to the open-source community and to Cloud computing platforms as described above, have resulted in enhanced democratization of Big Data capabilities across industry sectors and budgets.

From a real-world evidence perspective, one of the main advantages of Big Data infrastructure is the ability to maintain very large, heterogeneous and linked data sets that are highly available, where they can be queried and statistically processed rapidly and can be used in visualizations on a near real-time basis.  For example, not only can data be updated and added to existing visualizations such as for tracking the opioid epidemic on a real-time basis across the entire U.S., but even extremely large custom cohort studies, such as answering questions on lipid lowering therapy or type 2 diabetes, representing millions of people and billions of data points, can be accomplished in hours or days rather than months or years (if data needs to be collected).  In addition, important AI implementations have been made easier thanks to increased integration of AI algorithms with Big Data software.

Natural Language Processing (NLP)

Natural language processing (NLP) is an AI tool that can be described as the ability of a computer program to understand the human language and automatically extract contextual meaning. NLP can be particularly useful in processing and evaluating large amounts of unstructured data. In healthcare, a common application is to evaluate physician notes in patient medical records, and find relevant information. By applying NLP, a system can more easily and rapidly extract and analyze data that would otherwise be too burdensome for researchers. NLP replaces the highly cumbersome act of medical chart extraction using teams of researchers.

NLP Techniques range from simple word-based models for text classification to rich, structured models for syntactic parsing, collocation finding, word sense disambiguation, and machine translation.

The NLP demand for real-world evidence is highly driven by the tremendous increase in textual unstructured clinical data. The practice patterns used by physicians for the documentation of clinical notes as well as patient discharge summaries have generated an enormous amount of unstructured data. Such voluminous data needs to be structured and analyzed effectively for enhanced reporting and analytics.  NLP, combined with machine learning and deep learning as described below, is rapidly becoming accurate enough to automate or replace abstraction.  This drives significant efficiencies in generating information from text for real world evidence purposes.

For example, NLP can be applied to find information on treatment outcomes, adverse events, symptom presentation and referral patterns. Consider the following physician notes examples:

“He states the symptoms are controlled. Less than 1% BSA currently affected.

Stopped [Drug X] d/c ‘increased depression.’ On Paxil but “feels not helping.” No psoriasis flares.”

“She has psoriasis on the back of her legs, torso, scalp.  She uses a dermatologist.  She was off [Drug X] for a URI and flared up.

The underlined information are just examples of what is not captured in either billing or structured EMR data.  The ‘old way’ would be to use nurse abstractors to chart review a small sample of patients.  With advanced NLP, data on such things as reasons for discontinuation of a medication can now be captured at scale across tens of thousands of patients for less than the cost of a traditional chart review.

Machine Learning, Deep Learning and Cognitive Computing

Machine Learning (ML) is a library of algorithms that scour over large volumes of data to accurately and efficiently learn relationships found in recorded examples. Over the last 15-20 years, ML has gradually been replacing traditional statistical inference as the tool of choice for learning complex relationships in data. The key advantage of ML is the capability to operate on large numbers of engineered predictive features in datasets including outliers, noise and collinearities, without the stability and reliability concerns of traditional statistical modeling. One of our key applications of this capability has been in identifying patients with undiagnosed or underdiagnosed conditions.  For example, the current approach is to use coded billing information or prescriptions to identify patients.  Using ML, we are able to see much more complex patterns and interactions that are similar between patients with and without a particular diagnosis and able to confirm that the diagnosis is present but either unlabeled (such as in dementia) or unrecognized (such as in early presentation of rare diseases like muscular dystrophy).  This technology has the promise of improving diagnosis in the clinic as well as in research studies.

Deep learning is a newer generation of learning algorithms rooted in an older concept called neural networks.  Neural networks use an array of nodes to perform computations or decisions rapidly.  Deep learning can be thought of as stacking many neural networks. Deep learning has introduced the capability to effectively automate the generation of predictive features in various types of inference problems and thereby achieve breakthrough performance in applications such as image processing, speech recognition and language translation.  In healthcare, some of the key applications of deep learning that are being pursued are for reading radiology exams or pathology slides.

Predictive vs Prescriptive Analytics

One of the most intriguing and potentially game changing examples of machine learning is in the area of predictive and prescriptive analytics.  With traditional research approaches, evidence development focuses on evaluating and tracking what has already happened. But, how do we move from understanding what happened to being able to predict what will happen 6 months, a year, 5 years out?

Using different mathematical techniques and modeling, predictive analytics use existing data to find trends and patterns and tell us what might happen. They help to identify who is most at risk and what outcomes can be expected.

Traditionally, risk analytics have been performed using standard statistical techniques such as stepwise logistic regression. In these approaches, characteristics or risks are identified and added into models to determine their impact on the model performance.  While predictive analytics can be generated using traditional statistical approaches, ML enables models to be generated to include thousands of variables and millions of data points.  The result is usually more highly performant models as well as the ability to uncover more data relationships of importance that might not have been considered to be so prior to the analysis.

For example, we recently presented a machine learning based model for predicting heart failure readmissions that outperformed existing models (LACE Risk Score) by 10 points[1] and relied on another machine learning based variable that measures the aggregate disease burden of a patient (OM1 Medical Burden Index (OMBI™)[2] and which is the strongest single predictor of many outcomes (heart failure admission and readmission, resource utilization).

Prescriptive analytics are an advanced form of predictive analytics. The goal of prescriptive analytics is to make the information presented actionable to a decision maker. Prescriptive analytics tell us what to do about the information that the predictive models generated and help us to know which ones matter most and what actions to take. For example, a clinician might use predictive analytics to understand who is most at risk for a cardiac event, whereas prescriptive analytics might tell the provider which patients have alterable factors, such as weight loss or smoking status, and which ones will have the greatest impact on outcomes.

As one can imagine, the healthcare and real-world evidence applications of these AI driven capabilities are potentially enormous.  Clinicians are already using these capabilities to identify which patients are most likely to have poor clinical or financial outcomes and to proactively take actions to minimize that risk.   For example, avoiding a cardiac readmission can save a health care payer or at-risk provider $14,000-$18,000 on average per event.  The implications are similarly large for manufacturers.  Predictive analytics are now being applied to identify patients most likely to benefit from certain treatments, those likely to be adherent to therapy, or even those likely to suffer an adverse event.

Conclusion

Artificial intelligence and big data are transforming real-world evidence from a largely retrospective viewpoint to a more concurrent and forward-looking set of capabilities.  This paradigm shift also will drive RWE to the forefront of strategy for both healthcare and life sciences organizations.   While there are many different components of AI that offer new approaches and methods to evaluating and generating real-world evidence, one common thread throughout is the importance of big data and the interdependency on having access to enormous amounts of data.

By embracing the innovation in AI (and the availability of big data), researchers can generate real-world evidence that is more dynamic, timely, representative, comprehensive and cost-effective.  This next generation of real-world evidence will also have the ability to be used to measure, predict and personalize care in a way previously not possible. In the end, all healthcare stakeholders benefit when medical products and services are focused on and delivered to those who will benefit the most.


[1] Su Z , Brecht T , O’Donovan F , Boussios C , Menon V , Gliklich R , Fonarow GC. Machine Learning Enhanced Predictions of Hospital Readmission or Death in Heart Failure. AHA Scientific Sessions. November 11-15, 2017. Anaheim, CA.

[2] O’Donovan F, Brecht T, Kekeh C, Su Z, Boussios C, Menon V, Gliklich R, Fonarow G, Geffen D. Machine Learning Generated Risk Model to Predict Unplanned Hospital Admission in Heart Failure. AHA Scientific Sessions. November 11-15, 2017. Anaheim, CA.

 

, , , , , , , , , , ,

No Comments

Big Ideas for Big Data Analytics in Real-World Evidence: Insights from Dr. Rich Gliklich, CEO of OM1

profiles-c-suite

 

Rich Gliklich, MD, CEO of OM1Dr. Patti Peeples, CEO of HealthEconomics.Com, sat down with Dr. Rich Gliklich, CEO of OM1, to discuss how big data analytics are changing the face of real world evidence (RWE). The mission of this Cambridge, Massachusetts digital health company is forward-thinking, like its leader: to solve the problem of determining and understanding the true results of healthcare and offer a more complete view of patient outcomes. By bringing together multiple data sources at the individual patient level to construct patient journeys, OM1 rapidly measures and forecasts patient outcomes, combining expertise in clinical research and informatics with big data technology and advanced data science to reinvent how real world evidence is generated and used.

HealthEcoOM1logonomics.Com asked Dr. Gliklich to shares his views on major transformational changes in evidence development and how these will drive a more personalized delivery of healthcare in the future.

[HE.Com] With the influx of big data, how do you think the pharmaceutical industry’s approach to real-world evidence should evolve? Are patient registries still relevant?

[RG]  Healthcare data is growing at an astounding rate. This creates both challenges and opportunities.  Pharma is being asked to demonstrate value to more and more stakeholders. We define Value as:  Value = Outcomes/Cost, and thus, Pharma will increasingly seek deeper clinical information and true outcomes to help demonstrate value and justify their prices.

To get to this critical evidence, they will need to turn to highly specialized capabilities and data for particular conditions, and they will need these data regularly updated, because the dynamics in the market change. For most organizations, it will be more cost-effective and timely to subscribe to sources that track and analyze these changes, than to build out the infrastructrure and acquire the data independently, such as from clinical trials and prospective patient registries.

The goals of patient registries are still relevant—from understanding the natural history of a disease to meeting a post market safety commitment.  But, big data plus advanced technologies creates alternative opportunities to meet those goals across many therapeutic categories and conditions, and to do so with very large patient numbers (orders of magnitude more patients vs registries), and at a fraction of the cost.

he.com-big data technology graphic

Click this image to see a larger version.

[HE.Com] Are there disease or therapeutic areas where using big data, as you’ve described, may be more effective? What types/level of disease and patient level data could we get to that is different than what we have access to today with traditional registries and trials?   

[RG] Conditions where comprehensive patient journeys can be readily captured through linking different data sources will be most amenable to using big data.  There are a number of conditions where this is the case, from airway to cardiovascular and immunologic diseases to name a few. And, the number of such conditions with comprehensive patient journeys using disparate data linking is growing every day. Beyond traditional clinical and laboratory data available through registries and trials, we are now able to collect more and more patient-generated data, cost information, socioeconomic data, mortality, and so on. In addition to a more thorough understanding of the patient experience, these approaches also have the advantage of collecting information on all patients. This removes some of the enrollment biases we see in both registries and trials. The graphic below demonstrates the large sample size that can be attained through linked data compared with the sample size from a typical prospective registry.

Linked Big Data in Healthcare

Click this image to see a larger version.

 

[HE.Com] Recently STAT News reported that Actemra® (tocilizumab) was responsible for hundreds of deaths and that the risks for life threatening complications were as high or higher than competing products. Could you comment on this finding, and is there a better way to look at this situation, using a big data perspective?

The STAT report was based on the FDA Adverse Event Reporting System.  The problem with those systems is that they are based on voluntary reporting and there is no denominator to actually determine the incidence of the events. This creates potential bias in reporting, since clinicians who are aware of a potential problem with a drug are then more likely to report events associated with it. Using big data, we can have a true denominator where the number of exposed patients and the number of events are both known, and these are derived from a combination of data sources.

In response to the STAT report, OM1 rapidly analyzed 120,000 patients on DMARDS (disease-modifying antirheumatic drugs) over the past 12 months to assess these findings in a more systematic and controlled analysis using big data. We did not find the same difference in event rates when patients carefully adjusted for comorbidities. Since the results are not yet published, I cannot go into details, but it demonstrates the power of using big data to respond rapidly to safety and other signals that may come up from time to time.

[HE.Com] How will payer needs for RWE evolve over the next 5 years, and what are the opportunities for service providers (pharma, researchers, data analytics companies) to address these future needs? 

As payers move towards value-based care, they need a deeper understanding of clinical outcomes beyond what is available in their own claims data sets. While the goal is to understand the clinical outcome, meaning the patient and provider-relevant impact of the treatment on the patient, the actual results today are tabulated from what transactions were billed for by the doctor or hospital.  As a result, these outcomes have generally focused on easily measured billing items such as hospitalizations, adverse event rates or complications of procedures.

But data derived from these sources lacks clinical depth and nuance. Critical questions are unanswered when using billing data for outcomes assessment. How serious was the hospitalization?  Did the patient return to normal functioning and well-being?  Did the underlying disease process improve or worsen as result of the treatment?  None of this is actually measurable in claims data. These shortcomings are leading payers and pharma to seek more clinically-focused RWE, and each will do it for their own purposes.  Payers will also increasingly partner with pharma to support value-based assessments and outcomes based contracts.

[HE.Com] How will patients’ use of big data evolve? Are there case studies of patient use that will become the norm for other disease states in the future?

Both patients, and providers on behalf of patients, will use big data to personalize healthcare.  Big data analytics that are focused on outcomes will support better decision-making for patients. As a result, patients will have the opportunity to better understand their own specific risks and benefits with respect to different therapies, as well as their likelihood to achieve both positive and negative outcomes. Let me give you a generalized example. In the future, a patient with rheumatoid arthritis will be able to know that for patients like them, 80% improved with drug A vs. 40% with drug B and these results were derived from broad big data rather than limited clinical trials. In this scenario, a typical patient will have much more information to make informed choices about their own or their loved one’s healthcare.

[HE.Com] What regulatory hurdles or opportunities do you see as they relate to big data, RWE, or related evidence dissemination?

Regulatory interest in big data and RWE is at an all time high as recent regulations such as the 21st Century Cures Act are driving regulators to consider RWE as a potential replacement for other forms of evidence generation around and post-approval.  In Section 505F of the Cures Act, it states, “The Secretary shall establish a program to evaluate the potential use of real world evidence (1) to help support approval of a new indication under section 505(e); and, (2) to help support or satisfy post-approval study requirements.” The program is to be implemented “within 2 years” and ‘real world evidence’ is defined as data “from sources other than clinical trials”. At the same time, some of these new paths to use RWE for these purposes are untested and there will certainly be some growing pains. Examples of such hurdles are seen in the work we do with outcomes-based contracting where issues regarding measurement outside of the label and Medicaid best price continue to create barriers.

As researchers, we are doing our part to facilitate better informed decisions for individual impact, using our intelligent data cloud to transform population data into precision health. And we’re trying to get deeper into clinical and patient data, more quickly. But there is much work to be done.

[HE.Com] Thank you, Rich. For more information on the work of Dr. Gliklich and colleagues in the area of RWE, view the recent on-demand webinars by clicking on the links below. 

OUTCOMES-AS-KEY

Click the image to request access to the webinar.

BIG-DATA

Click the image to request access to the webinar.

Rich Gliklich, MD, CEO of OM1About Rich Gliklich, MD

Rich is the CEO of OM1, a healthcare technology company focused on understanding the patient journey and the true results of healthcare. Since 2014, Rich has been an XIR at General Catalyst, where he supports businesses in the healthcare industry. Prior to joining General Catalyst, Rich was President of the Outcome division of Quintiles, the largest provider of biopharmaceutical development and commercial outsourcing services, and he also served on its Executive Committee through its 2013 IPO.   Prior to Quintiles, Rich was Founder, CEO and Chairman of Outcome, a health information and services company that served more than 2,500 healthcare organizations and a majority of the global top 30 life sciences companies.  Rich led Outcome from its start as a spin-off from his Harvard affiliated research laboratory in 1998 through its acquisition by Quintiles in October 2011.  In addition to his experience as an entrepreneur and executive, Dr. Gliklich is well known in the areas of registries, outcomes and analytics.  He is senior editor of the landmark publication by the U.S. Agency for Healthcare Research and Quality (AHRQ) handbook “Registries for Evaluating Patient Outcomes: A User’s Guide” and the PI for the Outcomes Measures Framework, which focuses on standardization of outcomes measurement.  Rich has led several key national and international efforts focused on evaluating the safety, effectiveness, value and quality of healthcare.  Rich also holds several patents for both health outcomes systems and medical devices. Rich is a graduate of Yale University and Harvard Medical School and a former Charles A. Dana Scholar at the University of Pennsylvania. Rich is also a surgeon and the Leffenfeld Professor at Harvard Medical School.

 

If you or someone you know would like to be featured in the HealthEconomics.Com CEO Profiles Series, contact Dr. Patti Peeples, CEO of HealthEconomics.Com. 

, , , ,

No Comments