2025 DIA Annual Meeting: How AI and Machine Learning Can Improve Patient Reported Outcomes in Clinical Trials

In an interview with Applied Clinical Trials, Brian Ongioni, chief product officer, uMotif, discussed how the company actively incorporates patient and site feedback throughout the digital health product lifecycle to ensure its tools are both accessible and intuitive. By involving end users early in the development process, uMotif aims to reduce burden on patients and clinical sites alike, while also ensuring that digital endpoints are usable, meaningful, and capable of standing up to regulatory scrutiny. Ongioni shared insights into the company's co-design strategies, real-world examples from clinical trials, and his perspective on the evolving role of artificial intelligence in enhancing patient-reported outcomes.

ACT: Looking ahead, how do you envision AI and machine learning playing a role in refining patient-reported outcomes to reflect what truly matters to patients?

Ongioni: It’s definitely a hot topic, and I think there are several areas where AI can help. From an electronic adaptation standpoint, AI can be a major benefit in terms of speed and scalability—like translating materials from paper to electronic formats. More importantly, as it relates to capturing participants’ views, AI has the potential to elevate their voices and enable more meaningful feedback throughout the entire lifecycle of a trial. We're still in the early stages of applying AI in this space, and while there's healthy skepticism and criticism, I think it will be interesting to see how we continue to iterate and incorporate these technologies moving forward.

Full Interview Summary: uMotif integrates patient and site feedback throughout the product development lifecycle to ensure its digital health tools are accessible, intuitive, and truly reflective of end-user needs. This is achieved through dedicated patient and site committees that collaborate with product teams early in the software design process. Whether it involves evaluating new features or reviewing early-stage prototypes, these stakeholders provide input that is incorporated before study-specific implementations, ensuring accessibility is embedded from the outset rather than added later.

A notable example of this co-design approach occurred during a Parkinson’s disease trial. Patients were given access to the platform before the study launched, allowing uMotif to make critical adjustments to accommodate their specific motor challenges. This included redesigning screen navigation and repositioning measurement tools to reduce burden and ensure data could be reliably collected for the intended endpoints.

Balancing patient usability with site workflows is also a core focus. uMotif developed a “hub model” to streamline the experience for clinical sites, consolidating disparate systems into a unified platform. By observing and incorporating site input—such as understanding their daily routines and workflow priorities—the company optimized functionality to reduce administrative burden. This site-and-patient-first mindset extends to the validation of digital endpoints, where uMotif organizes separate workshops for patient and site committees to provide feedback on new instruments, ensuring their relevance, usability, and potential regulatory acceptability.

Looking ahead, uMotif sees artificial intelligence and machine learning playing an increasingly important role in refining patient-reported outcomes. These technologies could support the transition from paper to electronic formats and enhance scalability. While there’s ongoing skepticism, AI has the potential to help surface what matters most to patients by amplifying their voices throughout the development lifecycle, provided it is implemented thoughtfully and iteratively.