"What is Your Envisioned Future?": Toward Human-AI Enrichment in Data Work of Asthma Care

Patient-generated health data (PGHD) is crucial for healthcare providers' decision making, as it complements clinical data by providing a more holistic view of patients' daily conditions. We interviewed 20 healthcare providers in asthma care to envision future technologies to support their PGHD use. We found that healthcare providers want future artificial intelligence (AI) systems to enhance their ability to treat patients by analyzing PGHD for profiling risk and predicting deterioration. Despite the potential benefits of AI, providers perceived various challenges of AI use with PGHD, including AI-driven data inequity, added burden, lack of trust toward AI, and fear of being replaced by AI. Clinicians wished for a future of co-dependent human-AI collaboration, where AI will help them to improve their clinical practice. In turn, healthcare providers can improve AI systems by making AI outputs more trustworthy and humane. Through the lens of data feminism, we discuss the importance of considering context and aligning the complex human infrastructure before designing or deploying PGHD-based AI systems in clinical settings. We highlight the opportunity to design for human-AI enrichment, where humans and AI not only partner with each other for improved performance, but also enrich each other to enhance each other's work overtime.