AUTHOR=Lu Jonathan , Sattler Amelia , Wang Samantha , Khaki Ali Raza , Callahan Alison , Fleming Scott , Fong Rebecca , Ehlert Benjamin , Li Ron C. , Shieh Lisa , Ramchandran Kavitha , Gensheimer Michael F. , Chobot Sarah , Pfohl Stephen , Li Siyun , Shum Kenny , Parikh Nitin , Desai Priya , Seevaratnam Briththa , Hanson Melanie , Smith Margaret , Xu Yizhe , Gokhale Arjun , Lin Steven , Pfeffer Michael A. , Teuteberg Winifred , Shah Nigam H. TITLE=Considerations in the reliability and fairness audits of predictive models for advance care planning JOURNAL=Frontiers in Digital Health VOLUME=4 YEAR=2022 URL=https://www.frontiersin.org/journals/digital-health/articles/10.3389/fdgth.2022.943768 DOI=10.3389/fdgth.2022.943768 ISSN=2673-253X ABSTRACT=

Multiple reporting guidelines for artificial intelligence (AI) models in healthcare recommend that models be audited for reliability and fairness. However, there is a gap of operational guidance for performing reliability and fairness audits in practice. Following guideline recommendations, we conducted a reliability audit of two models based on model performance and calibration as well as a fairness audit based on summary statistics, subgroup performance and subgroup calibration. We assessed the Epic End-of-Life (EOL) Index model and an internally developed Stanford Hospital Medicine (HM) Advance Care Planning (ACP) model in 3 practice settings: Primary Care, Inpatient Oncology and Hospital Medicine, using clinicians' answers to the surprise question (“Would you be surprised if [patient X] passed away in [Y years]?”) as a surrogate outcome. For performance, the models had positive predictive value (PPV) at or above 0.76 in all settings. In Hospital Medicine and Inpatient Oncology, the Stanford HM ACP model had higher sensitivity (0.69, 0.89 respectively) than the EOL model (0.20, 0.27), and better calibration (O/E 1.5, 1.7) than the EOL model (O/E 2.5, 3.0). The Epic EOL model flagged fewer patients (11%, 21% respectively) than the Stanford HM ACP model (38%, 75%). There were no differences in performance and calibration by sex. Both models had lower sensitivity in Hispanic/Latino male patients with Race listed as “Other.” 10 clinicians were surveyed after a presentation summarizing the audit. 10/10 reported that summary statistics, overall performance, and subgroup performance would affect their decision to use the model to guide care; 9/10 said the same for overall and subgroup calibration. The most commonly identified barriers for routinely conducting such reliability and fairness audits were poor demographic data quality and lack of data access. This audit required 115 person-hours across 8–10 months. Our recommendations for performing reliability and fairness audits include verifying data validity, analyzing model performance on intersectional subgroups, and collecting clinician-patient linkages as necessary for label generation by clinicians. Those responsible for AI models should require such audits before model deployment and mediate between model auditors and impacted stakeholders.