The ability to predict how a clinical trial participant will adhere to their treatment, and even respond to that treatment, has great promise to advance patient-centric clinical research. But, as we look to understand the impact a drug has on patients’ everyday health outside of a research environment, what happens to these unique, predictive findings around dosing and outcomes once a drug enters the real-world?
As real-world evidence and a deeper understanding of a patient’s lived experience with their treatment is increasingly important to a drug’s market success, it is critical to bridge the scientific understandings developed in a trial period to the real-world value created. Having consistent, accessible tools across both research and real-world deployment means we can tie back to all the predictive learnings from the research phase and apply them to personalize and predict a patient’s health journey. As these algorithms continue to mature with more high-quality data, a predictive model that combines both adherence and outcomes, and paints a picture for what it means to take a medication and to benefit from it, opens the door to treating with unprecedented precision across the lifecycle of a drug.
The power of combining dosing and outcomes
We know from our own predictive adherence algorithm that we can utilize rich information beyond if a dose was taken, including how long it takes a patient to dose, variations in the time of day they dose, how long after their alarm time they dose, and more. Achieving this level of insight in a clinical trial can inform future prescribing and when exactly patients should take their medication based on their anticipated response. For example, Parkinson’s patients take multiple pills throughout the day, timing dosing with when and what they eat, their activity level, and more, to keep them in the window where their symptoms are well managed. Predictive models can help clinicians and patients know the ideal dosing times for that individual patient to optimize their response.
Developing a toolkit of predictive knowledge in the formal setting of a clinical trial can give clinicians a baseline understanding of whether a drug is the right fit for their patient. This is particularly important for complex conditions with a wide array of symptom expressions. For example, PTSD has a very heterogeneous population with no one-size-fits-all treatment. Predictive models in clinical research can help us segment the population based on which medications they may respond well to, and which dosing patterns help optimize their response. As those same patients go into the real world and use the same smart phone-based tools, we can continue to connect back to those learnings and develop inferences about their wellbeing, flagging when it may be time for a clinician to check in.
Tapping into the patient experience
The impact a medication has on a person can be so much more than just its efficacy. As a drug enters the real-world, sponsors need to demonstrate how a treatment impacts a patient’s quality of life: How many work days were missed? How was their energy level? How many days did they go without a specific, subtle symptom? Providers need to have confidence that a new drug tested in the controlled clinical environment will apply to their patients’ specific needs.
Understanding and even predicting a patient’s lived experience requires monitoring them in their lived environment and capturing rich auditory and visual data. For example, for patients with a tremor, we can determine how a medication is impacting their ability to button their shirt. Using a cell phone to perform a TETRAS assessment, we could develop a predictive model that bridges between the magnitude of the tremor, the potential effect of their treatment, and the impact it will have on that patient and their ability to perform activities of daily living. Capturing measures of a patient’s quality of life means we can make the final connection on the effect of a drug and what people really care about – the value it’s creating in the real-world.
Making precision medicine a reality
Widely dispersed, smart phone-based tools help us make use of the quantitative, reliable assessments aggregated during clinical research, and allows sponsors to continue to understand the impact their medication is having on the people who take it. The future of medicine is treating the individual person, not a population. By taking in all the information you can about their particular circumstances, particular experience with the disease, and their individual response to medication during the research phase, we can optimize treatment plans to map to their unique needs, inform future care plan design, and provide new levels of proactive care.
