Cargando…
Considerations in the reliability and fairness audits of predictive models for advance care planning
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 condu...
Autores principales: | , , , , , , , , , , , , , , , , , , , , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9634737/ https://www.ncbi.nlm.nih.gov/pubmed/36339512 http://dx.doi.org/10.3389/fdgth.2022.943768 |
_version_ | 1784824561051631616 |
---|---|
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. |
author_facet | 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. |
author_sort | Lu, Jonathan |
collection | PubMed |
description | 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. |
format | Online Article Text |
id | pubmed-9634737 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | Frontiers Media S.A. |
record_format | MEDLINE/PubMed |
spelling | pubmed-96347372022-11-05 Considerations in the reliability and fairness audits of predictive models for advance care planning 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. Front Digit Health Digital Health 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. Frontiers Media S.A. 2022-09-12 /pmc/articles/PMC9634737/ /pubmed/36339512 http://dx.doi.org/10.3389/fdgth.2022.943768 Text en © 2022 Lu, Sattler, Wang, Khaki, Callahan, Fleming, Fong, Ehlert, Li, Shieh, Ramchandran, Gensheimer, Chobot, Pfohl, Li, Shum, Parikh, Desai, Seevaratnam, Hanson, Smith, Xu, Gokhale, Lin, Pfeffer, Teuteberg and Shah. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY) (https://creativecommons.org/licenses/by/4.0/) . The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. |
spellingShingle | Digital Health 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. Considerations in the reliability and fairness audits of predictive models for advance care planning |
title | Considerations in the reliability and fairness audits of predictive models for advance care planning |
title_full | Considerations in the reliability and fairness audits of predictive models for advance care planning |
title_fullStr | Considerations in the reliability and fairness audits of predictive models for advance care planning |
title_full_unstemmed | Considerations in the reliability and fairness audits of predictive models for advance care planning |
title_short | Considerations in the reliability and fairness audits of predictive models for advance care planning |
title_sort | considerations in the reliability and fairness audits of predictive models for advance care planning |
topic | Digital Health |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9634737/ https://www.ncbi.nlm.nih.gov/pubmed/36339512 http://dx.doi.org/10.3389/fdgth.2022.943768 |
work_keys_str_mv | AT lujonathan considerationsinthereliabilityandfairnessauditsofpredictivemodelsforadvancecareplanning AT sattleramelia considerationsinthereliabilityandfairnessauditsofpredictivemodelsforadvancecareplanning AT wangsamantha considerationsinthereliabilityandfairnessauditsofpredictivemodelsforadvancecareplanning AT khakialiraza considerationsinthereliabilityandfairnessauditsofpredictivemodelsforadvancecareplanning AT callahanalison considerationsinthereliabilityandfairnessauditsofpredictivemodelsforadvancecareplanning AT flemingscott considerationsinthereliabilityandfairnessauditsofpredictivemodelsforadvancecareplanning AT fongrebecca considerationsinthereliabilityandfairnessauditsofpredictivemodelsforadvancecareplanning AT ehlertbenjamin considerationsinthereliabilityandfairnessauditsofpredictivemodelsforadvancecareplanning AT lironc considerationsinthereliabilityandfairnessauditsofpredictivemodelsforadvancecareplanning AT shiehlisa considerationsinthereliabilityandfairnessauditsofpredictivemodelsforadvancecareplanning AT ramchandrankavitha considerationsinthereliabilityandfairnessauditsofpredictivemodelsforadvancecareplanning AT gensheimermichaelf considerationsinthereliabilityandfairnessauditsofpredictivemodelsforadvancecareplanning AT chobotsarah considerationsinthereliabilityandfairnessauditsofpredictivemodelsforadvancecareplanning AT pfohlstephen considerationsinthereliabilityandfairnessauditsofpredictivemodelsforadvancecareplanning AT lisiyun considerationsinthereliabilityandfairnessauditsofpredictivemodelsforadvancecareplanning AT shumkenny considerationsinthereliabilityandfairnessauditsofpredictivemodelsforadvancecareplanning AT parikhnitin considerationsinthereliabilityandfairnessauditsofpredictivemodelsforadvancecareplanning AT desaipriya considerationsinthereliabilityandfairnessauditsofpredictivemodelsforadvancecareplanning AT seevaratnambriththa considerationsinthereliabilityandfairnessauditsofpredictivemodelsforadvancecareplanning AT hansonmelanie considerationsinthereliabilityandfairnessauditsofpredictivemodelsforadvancecareplanning AT smithmargaret considerationsinthereliabilityandfairnessauditsofpredictivemodelsforadvancecareplanning AT xuyizhe considerationsinthereliabilityandfairnessauditsofpredictivemodelsforadvancecareplanning AT gokhalearjun considerationsinthereliabilityandfairnessauditsofpredictivemodelsforadvancecareplanning AT linsteven considerationsinthereliabilityandfairnessauditsofpredictivemodelsforadvancecareplanning AT pfeffermichaela considerationsinthereliabilityandfairnessauditsofpredictivemodelsforadvancecareplanning AT teutebergwinifred considerationsinthereliabilityandfairnessauditsofpredictivemodelsforadvancecareplanning AT shahnigamh considerationsinthereliabilityandfairnessauditsofpredictivemodelsforadvancecareplanning |