Contributed Commentary by Jennifer Bradford

September 19, 2019 | Artificial intelligence (AI) has been made possible by the increase in accessible, large-scale computing power which, in turn, has brought machine learning (ML) to realization in clinical trials and research.

Applications of ML have proven successful in clinical research and clinical trials.  Years of structured trial data combined with real-world data and other sources provides new support for trial design, execution and analysis. Combining computational skills and drug development experience, data science teams can support the pharma and biotech industry to generate value through the application of machine learning.

Successful ML algorithms require large, quality datasets for their application. An ML algorithm utilizes a training and test set of data. The training dataset is used to fit the ML model and the test set is previously unseen data used to evaluate the performance of the model.

ML must be factually sound, meaningful, and facilitate decisions in the real world. Poor quality data may bias results leading to incorrect decisions that affect people’s health and safety. A Contract Research Organization has experience working with clinicians and scientists to formulate questions, identify appropriate datasets to address the questions and has expertise in processing, integrating, and analyzing diverse datasets to maximize its value.

ML Drives Efficiencies

Savings in time and dollars can be gained through efficiency improvements.  For example, an ML platform could support an initiative to run pre-clinical trials allowing for earlier identification of demographics most likely to respond to a drug and the identification of biomarkers that show the most promise for patient response, which refines the compound and the trial design.

ML-based predictive analytics are a tool for recruitment, retention activities, and patient engagement.  For example, identifying the right candidates at a faster rate can accelerate R&D timelines.  While a successful trial hinges on patient engagement, it’s becoming even more important as healthcare providers expand the use of apps and wearables to manage patient health.

The 2016 21^st Century Cures Act, sponsored by the FDA, is meant to accelerate medical product development and innovate and modernize clinical trial designs and outcome assessments to speed the development and review of medical products.  It’s encouraging studies utilizing real-world evidence and is developing methodologies for their use, which would allow ML analysis of larger datasets, i.e. the interpretation of wearables, data, or electronic health records.

Real-world data may also be used alongside multi-omic mapping of patients receiving an investigational product to create a “digital twin”: a representation of an individual reflecting their physiological and molecular status as well as their lifestyle over time. Digital twins could be used to understand what would have happened to an individual if they had received placebo or standard of care. This approach has shown utility in healthcare where a “digital twin” of a patient’s heart is created using medical data and models the unique characteristics of an individual’s heart. This model can be used by clinicians to test different treatment options by comparing possible outcomes without any real risk to the patient. 

A Treasure Trove of Data

Pharma companies may have an extensive R&D database containing years of data from clinical trials, lab experiments, and more. This data contains potential insights, at the patient level, waiting to be discovered by approaches such as natural language processing, which can sift through previous research documents for findings that are relevant to current research or by ML approaches across data pooled from many clinical studies.

An experienced team can pool together studies and integrate other data types, harmonizing different versions of data dictionaries and standards. In addition, they should be proficient in the application of ML across clinical and real-world data, identifying patterns to inform future trials, research, and generating business value.

ML in Clinical Research

The healthcare IT industry has embraced Google, Apple, Facebook, and Amazon, which have brought investment and innovation across all aspects of healthcare. Google is applying AI capabilities in the areas of disease detection, data interoperability, and health insurance.  Its DeepMind Health differentiates between healthy and cancerous tissue to improve radiation treatment. 

Scott Gottlieb, former FDA head, noted in a speech earlier this year that new streams of real-world data gathered directly from electronic health records and other data sources, paired with advances in ML, will be crucial for creating the next generation of clinical trials.  He stressed the importance of modernizing the clinical trial process to take advantage of IoT devices, claims, lab tests, and wearable devices.

While these new streams of real-world data can radically alter the efficacy of clinical trials, data science teams supporting clinical trials must be uniquely skilled at delivering high quality advice and results, not only for standard clinical trials, observational data and studies, but also to help businesses understand what is possible in this new frontier.