OASIS: a personal health informatics mobile APP designed to provide personalized insights to promote cognitive and behavioral responses, symptom self-management, and reduce symptom burden

The National Institute of Environmental Health Sciences awarded The University of Iowa $349,875 on August 6, 2026, under the Medical Library Assistance program (CFDA 93.879) to develop and evaluate OASIS, a multimodal mobile app designed to help cancer patients undergoing treatment manage symptom burden through patient education, self-monitoring, social support, and personalized risk predictions derived from electronic health record data.

The project will refine OASIS using human-centered design and predictive modeling to optimize patient engagement and deliver actionable insights. Specific aims include understanding patient perceptions and usability of symptom risk predictions, refining predictive models using EHR and patient-reported data, and evaluating app features through factorial A/B testing. Findings will inform scalable, generalizable strategies to personalize and sustain engagement in mHealth interventions.

Work is performed in Iowa City, Iowa. The period of performance runs through July 31, 2030.

Abstract

Cancer symptom burden remains a persistent challenge for patients undergoing treatment, often leading to diminished quality of life, treatment delays, and increased healthcare utilization. OASIS (oncology associated symptoms & individualized strategies) is a multimodal mobile APP intervention designed to support symptom management through patient education, self-monitoring, social support, and personalized risk predictions derived from electronic health record (EHR) data. Preliminary studies demonstrate feasibility, usability, and promising reductions in symptom burden. This R01 project aims to refine and evaluate OASIS using a human- centered design approach and predictive modeling to optimize engagement and deliver actionable insights. Specific aims include: (1) understanding patient perceptions and usability of symptom risk predictions, (2) refining predictive models using EHR and patient-reported data, and (3) evaluating APP features through factorial a/b testing. Findings will inform scalable, generalizable strategies to personalize and sustain engagement in mhealth interventions.