HEALTHCARE
HEALTHCARE
Managing Clinical Trials With a Health Equity Criteria
By Dominique Demolle , PhD , CEO Cognivia
Driven by ethics and real-world evaluation , implementing health equity in clinical development faces several challenges . These include recruiting patients from diverse communities ; addressing Social Determinants of Health ( SDOH ) such as socioeconomic status , education , physical environment , and access to healthcare ; managing data variability from greater diversity ; and ensuring treatment adherence and patient retention . An integrated approach is required from the very beginning , at the stage of the clinical development plan .
Clinical trial implementation and interpretation can no longer follow historical methods . Embracing new approaches and technologies , such as integrating machine learning ( ML ), artificial intelligence ( AI ), and digital health into clinical trials , presents a transformative opportunity to advance equity , enhance diversity , and improve the predictability of trial outcomes , all while accelerating drug development and better aligning with real-world conditions .
Patient Retention and Adherence To Study Procedures and Treatment
Patients from challenging socioeconomic backgrounds may face specific barriers such as transportation issues , unstable housing , or limited access to healthcare , all of which can affect their ability to adhere to trial protocols . Identifying participants disproportionately affected by SDOH allows us to tailor and personalize engagement strategies . Educating them about clinical research , offering transportation assistance , or providing mobile monitoring , digital health tools options can help ensure more equitable participation .
Drug adherence in clinical trials is also one of the most pressing challenges and may lead to inconclusive or misleading efficacy data . Adherence rates in clinical trials vary widely , often influenced by the complexity of drug regimens , side effects , health literacy and psychosocial factors affecting participants .
Incorporating predictive models that analyze behavioral patterns and identify participants at risk of non-adherence is essential . Use of machine learning to forecast adherence probabilities based on a combination of demographic , psychological , and health-related factors , enable proactive engagement of participants and facilitate personalized support strategies . This can help ensure consistent adherence and improve data reliability .
Economic Implications of Improving Adherence
Improving adherence has clear economic benefits . Trials with higher adherence rates are more likely to produce clear , actionable data , reducing the need for costly follow-up studies or extended trial durations . Furthermore , enhanced adherence reduces the risk of patient conditions worsening in particular in chronic diseases or compound resistance , especially in the context of chronic conditions like HIV , where inconsistent treatment can drive drug-resistant strains . This is dramatic for the patients and results in higher healthcare costs .
Using innovative , AI-driven tools to support adherence ensures the integrity of clinical trial data while making the drug development process more cost-effective and efficient . These forward-thinking approaches help overcome one of the most pervasive barriers in clinical research , underscoring the importance of health equity and patient-centered trial design which can be extended to real world conditions .
Addressing Data Variability in Clinical Trials
While broader participant populations in clinical research are the best venue to investigate safety and efficacy in the real world , they also introduce greater heterogeneity of data .
Clinical trial outcomes can be significantly influenced by data variability . Variability in subjective and objective endpoints can skew efficacy data , impacting the speed and success of bringing new drugs to market . The emphasis on health equity necessitates a comprehensive approach to designing trials that account for patient diversity while employing predictive models to minimize this variability .
Physiologically-based pharmacokinetics ( PBPK ), population-based pharmacokinetics ( PopPK ), biomarkers , and awareness of metabolic factors related to ethnicity can help limit data variability and make necessary adjustments . However , specific sources of variability resulting from patients ' personalities , traits , emotional status , and the influence of SDOH also need to be addressed .
Using tools , as the ones offered by Cognivia ( https :// cognivia . com ), that leverage behavioral science and predictive modeling to address these challenges will become essential . They could optimize trial data interpretation by capturing the influence of these factors , helping to mitigate placebo response , for example . Placebo response is largely influenced by expectations , which can vary depending on SDOH .
Dominique Demolle , PhD , CEO , Cognivia
Additionally , capturing overall participant-specific characteristics will be required .
By understanding how psychological factors influence outcomes , we can better interpret trial data , reduce biases , and ensure more representative and equitable participation across diverse populations .
ML and AI : Catalysts for Equitable and Efficient Trial Design
Machine learning and AI technologies are driving a paradigm shift in clinical research . These tools can predict patient outcomes with greater precision by analyzing vast datasets and identifying patterns related to demographics , health conditions , and genetic predispositions . Such innovations are instrumental in designing trials that are not only more inclusive but also more efficient . Critical pieces of information , new information , about a trial participant like their traits of personality , their motivations for participating in trials , and more , provide different insights of critical importance .
Dr . Dominique Demolle is the CEO at Cognivia and holds a PhD in biochemistry from the University of Brussels . She has held various leadership positions at Eli Lilly and Company and has extensive knowledge in global early phase drug development . Dr . Demolle consulted with pharmas and biotechs before founding Cognivia and contributed to the clinical development of dozens of drugs and several launches . Most recently , she has been recognized as one of the 2022 ’ s Most Inspiring People in the life sciences for the annual PharmaVoice 100 awards .
February 2025 COMMERCE 9