Embedding patient-reported outcomes at the heart of artificial intelligence health-care technologies
Samantha Cruz Rivera, Xiaoxuan Liu, Sarah Hughes, Helen Dunster, Elaine Manna, Alastair K. Denniston, Melanie Calvert
Abstract
Integration of patient-reported outcome measures (PROMs) in artificial intelligence (AI) studies is a critical part of the humanisation of AI for health. It allows AI technologies to incorporate patients' own views of their symptoms and predict outcomes, reflecting a more holistic picture of health and wellbeing and ultimately helping patients and clinicians to make the best health-care decisions together. By positioning patient-reported outcomes (PROs) as a model input or output we propose a framework to embed PROMs within the function and evaluation of AI health care. However, the integration of PROs in AI systems presents several challenges. These challenges include (1) fragmentation of PRO data collection; (2) validation of AI systems trained and validated against clinician performance, rather than outcome data; (3) scarcity of large-scale PRO datasets; (4) inadequate selection of PROMs for the target population and inadequate infrastructure for collecting PROs; and (5) clinicians might not recognise the value of PROs and therefore not prioritise their adoption; and (6) studies involving PRO or AI frequently present suboptimal design. Notwithstanding these challenges, we propose considerations for the inclusion of PROs in AI health-care technologies to avoid promoting survival at the expense of wellbeing.