Artificial intelligence stands to transform precision medicine: AiCure

By Jenni Spinner

- Last updated on GMT

(Colin Anderson Productions pty ltd/iStock via Getty Images Plus)
(Colin Anderson Productions pty ltd/iStock via Getty Images Plus)
An expert from the AI-focused technology company shares insights as to how it can be harnessed to better interpret, and even predict, patient behavior.

Artificial intelligence is increasingly being harnessed in various aspects of drug development, from discovering compounds with life-saving potential, to identifying potential patients, and more. Outsourcing-Pharma recently spoke with Rich Christie, chief medical officer of AI-focused solutions provider AiCure, about how AI can be used to analyze and predict patient behavior, develop precision medicine solutions, and improve both care and quality of life.

OSP: Could you please share the ‘elevator presentation’ description of AiCure—who you are, what you do, and what sets you apart from other companies operating in the same space?

RC: AiCure is a patient-focused technology company that empowers life science and healthcare organizations with actionable insights to accelerate drug development and improve patient care. With more than a decade of experience managing complex protected health information (PHI) in regulated settings, AiCure helps organizations to optimize care at each step of the clinical continuum by delivering objective, predictive behavioral, and interventional insights, uniquely built on unbiased patient-level audio and visual data capture. This ultimately informs proactive decision-making in clinical research, high-quality drug development for effective commercialization, and expanded reach of personalized patient care.

Through our smartphone-based mobile application, Patient Connect, we leverage computer vision and AI to gather audio and visual data about a patient. This helps sponsors gain an objective, deep understanding of both a patient’s adherence to their care plan as well as their overall response to treatment. Not only is our offering unique in its focus on the patient’s lived experience with disease, but also in the manner in which our algorithms are built.

Since our beginnings, we worked diligently to ensure our facial recognition algorithm was built using diverse data to ensure our tools work with all patients regardless of skin tone, environment, dress, and more. This has helped us ensure our customers can conduct inclusive research representative of real-world populations.

OSP: Please talk a bit about how the field of precision medicine has advanced in recent years.

OSP_PM2022_Aicure_RC
Rich Christie, chief medical officer, AiCure

RC: The challenge of precision medicine lies in matching the right patient with the right drug at the right point in their disease. The life science industry is increasingly realizing that this starts with understanding the nuances of an individual patient’s condition and response to treatment. Sporadic in-person visits only offer a brief glimpse into a patient’s condition at the time of the visit, but the stretches of time between these visits hold critical information about the state of their disease, a treatment’s efficacy, and its impact on their quality of life.

More and more, we see pharma sponsors turn to AI-powered and predictive tools to augment these traditional check-ins. Technology that helps objectively and proactively capture a patient’s daily experience can give sponsors and sites vital insights to inform targeted, personalized patient care, both in terms of what interventions and support might work best, as well as any timely adjustments needed to their treatment plan.

OSP: Specifically, how has artificial intelligence been used to further precision medicine in the clinical research space?

RC: Just as genomics transformed oncology care over the last several decades and offered the ability to treat with precision, the behavioral measurements we are now able to capture with AI tools will help catalyze precision medicine in drug development and tailor interventions with unprecedented specificity.

For example, novel patient assessments such as video- and audio-based digital biomarkers can identify the subtleties of a patient’s wellbeing and response to treatment in ways that in-person assessments alone cannot. Particularly for conditions with symptoms that need to be or can be assessed with audio and visual cues by tracking metrics such as a patient’s facial expressions, eye twitches, speech, or movement, digital biomarkers help detect specific behaviors associated with certain diseases and treatments with more precision than ever before.

By assessing these objective insights over time, physicians can understand how medications are impacting a person’s quality of life, such as their ability to tie their shoe or write their name and make informed decisions about the future of their care plan. 

OSP: Please talk about the use of AI to track patients and predict their behavior.

OSP_PM2022_AiCure_pic
(Colin Anderson Productions pty ltd/iStock via Getty Images Plus)

RC: In addition to digital biomarkers, AI-powered predictive analytics can also help drive precision medicine by predicting patient behavior before trials even begin. Using a placebo lead-in period, AI can help predict if a patient will likely adhere to their treatment plan, or if they tend to have trouble staying on track.

Knowing this in advance can help sites effectively focus on patients who may need more support once they are enrolled in the trial, tailoring their interventions and personalizing resources accordingly to keep them engaged. Predicting a patient’s future behavior based on past behavior allows sites to be more proactive and personal in their engagement tactics.

OSP: How can this information then be used to tailor treatment and interventions?

RC: Digital biomarkers allow sponsors to capture objective insights about a patient’s experience to help guide treatment and intervention decisions. For example, knowing a person with depression is experiencing increased fatigue or slower speech than usual may mean the clinician needs to revisit the patient’s treatment plan to try and improve their response by changing their dosage.

For conditions like multiple sclerosis whose symptoms wax and wane over time, tracking micro-expressions with such sensitivity means clinicians can track trends over time to understand what intervention is going to provide the most value for that patient, and when it will be best to intervene. Especially when combined with more traditional assessments for patients to report how they are feeling, sponsors can achieve a more holistic, personalized picture of how a patient is doing through these tools.

OSP: What do you think might be next for precision medicine advancement?

RC: AI-powered tools such as digital biomarkers are a unique, relatively new approach to precision medicine. But these solutions are often developed behind closed doors, with their proprietary algorithms under lock and key.

A critical way to realize AI’s full potential is by breaking down these barriers and turning to open-source communities so algorithms can be adequately tested and vetted. Trust for the potential of these tools needs to be built in the public domain, with the research and academic community weighing in on their performance, opportunities for their use, and areas for improvement.

Another factor of precision medicine is the ever-increasing amounts and sources of patient data. Trying to extract meaningful insights from these growing data sources to drive precision medicine can be a challenge. AI platforms can help aggregate data and derive actionable insights around a patient’s experience and disease progression, providing a more holistic view to adequately personalize care.

OSP: Do you have anything to add?

RC: AI can be a catalyst for precision medicine, helping sponsors better understand how medications work, and their impact on specific patients, and ultimately bridge clinical findings into real-world applications. The increased use of these AI-powered tools, however, comes with a responsibility for developers to ensure they are built with their intended patient population in mind.

If developers don’t embrace diverse, representative data sets, AI has the propensity to perpetuate unseen biases. As we look ahead, we need to be vigilant in mitigating the potential impact of biases on the applications of AI tools, or else risk the trust of the life science and healthcare communities in their value.

Related news

Show more

Related products

show more

Saama accelerates data review processes

Saama accelerates data review processes

Content provided by Saama | 25-Mar-2024 | Infographic

In this new infographic, learn how Saama accelerates data review processes. Only Saama has AI/ML models trained for life sciences on over 300 million data...

More Data, More Insights, More Progress

More Data, More Insights, More Progress

Content provided by Saama | 04-Mar-2024 | Case Study

The sponsor’s clinical development team needed a flexible solution to quickly visualize patient and site data in a single location

Using Define-XML to build more efficient studies

Using Define-XML to build more efficient studies

Content provided by Formedix | 14-Nov-2023 | White Paper

It is commonly thought that Define-XML is simply a dataset descriptor: a way to document what datasets look like, including the names and labels of datasets...

Related suppliers

Follow us

Products

View more

Webinars