Interdisciplinary Expertise to Advance Equitable Explainable AI
The field of artificial intelligence (AI) is rapidly influencing health and healthcare, but bias and poor performance persists for populations who face widespread structural oppression. Previous work has clearly outlined the need for more rigorous attention to data representativeness and model perfo...
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , |
|---|---|
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | |
|---|---|
| container_issue | |
| container_start_page | |
| container_title | |
| container_volume | |
| creator | Bennett, Chloe R Cole-Lewis, Heather Farquhar, Stephanie Haamel, Naama Babenko, Boris Lang, Oran Fleck, Mat Traynis, Ilana Lau, Charles Horn, Ivor Lyles, Courtney |
| description | The field of artificial intelligence (AI) is rapidly influencing health and
healthcare, but bias and poor performance persists for populations who face
widespread structural oppression. Previous work has clearly outlined the need
for more rigorous attention to data representativeness and model performance to
advance equity and reduce bias. However, there is an opportunity to also
improve the explainability of AI by leveraging best practices of social
epidemiology and health equity to help us develop hypotheses for associations
found. In this paper, we focus on explainable AI (XAI) and describe a framework
for interdisciplinary expert panel review to discuss and critically assess AI
model explanations from multiple perspectives and identify areas of bias and
directions for future research. We emphasize the importance of the
interdisciplinary expert panel to produce more accurate, equitable
interpretations which are historically and contextually informed.
Interdisciplinary panel discussions can help reduce bias, identify potential
confounders, and identify opportunities for additional research where there are
gaps in the literature. In turn, these insights can suggest opportunities for
AI model improvement. |
| doi_str_mv | 10.48550/arxiv.2406.18563 |
| format | Article |
| fullrecord | <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2406_18563</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2406_18563</sourcerecordid><originalsourceid>FETCH-LOGICAL-a673-da1d9568d211307c22ad85f0aeedcc82be09980c91518cd45e23eb253bee26283</originalsourceid><addsrcrecordid>eNotj0GLwjAUhHPZw-LuD9iT_QPtJi9NTE9SSlcLghfv5TV5QqDWmnaL_nutepqBGYb5GPsRPEmNUvwXw9VPCaRcJ8IoLT_ZuupGCs4P1vet7zDcovLaUxj9QNF4jnI3YWcpKi__fsSmpTlu8dGcfV59sY8jtgN9v3XBDn_lodjGu_2mKvJdjHolY4fCZUobB0JIvrIA6Iw6ciRy1hpoiGeZ4TYTShjrUkUgqQElGyLQYOSCLV-zT4K6D_70uFrPJPWTRN4B8zhDmg</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Interdisciplinary Expertise to Advance Equitable Explainable AI</title><source>arXiv.org</source><creator>Bennett, Chloe R ; Cole-Lewis, Heather ; Farquhar, Stephanie ; Haamel, Naama ; Babenko, Boris ; Lang, Oran ; Fleck, Mat ; Traynis, Ilana ; Lau, Charles ; Horn, Ivor ; Lyles, Courtney</creator><creatorcontrib>Bennett, Chloe R ; Cole-Lewis, Heather ; Farquhar, Stephanie ; Haamel, Naama ; Babenko, Boris ; Lang, Oran ; Fleck, Mat ; Traynis, Ilana ; Lau, Charles ; Horn, Ivor ; Lyles, Courtney</creatorcontrib><description>The field of artificial intelligence (AI) is rapidly influencing health and
healthcare, but bias and poor performance persists for populations who face
widespread structural oppression. Previous work has clearly outlined the need
for more rigorous attention to data representativeness and model performance to
advance equity and reduce bias. However, there is an opportunity to also
improve the explainability of AI by leveraging best practices of social
epidemiology and health equity to help us develop hypotheses for associations
found. In this paper, we focus on explainable AI (XAI) and describe a framework
for interdisciplinary expert panel review to discuss and critically assess AI
model explanations from multiple perspectives and identify areas of bias and
directions for future research. We emphasize the importance of the
interdisciplinary expert panel to produce more accurate, equitable
interpretations which are historically and contextually informed.
Interdisciplinary panel discussions can help reduce bias, identify potential
confounders, and identify opportunities for additional research where there are
gaps in the literature. In turn, these insights can suggest opportunities for
AI model improvement.</description><identifier>DOI: 10.48550/arxiv.2406.18563</identifier><language>eng</language><subject>Computer Science - Artificial Intelligence ; Computer Science - Computer Vision and Pattern Recognition ; Computer Science - Computers and Society ; Computer Science - Learning</subject><creationdate>2024-05</creationdate><rights>http://creativecommons.org/licenses/by/4.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,776,881</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2406.18563$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2406.18563$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Bennett, Chloe R</creatorcontrib><creatorcontrib>Cole-Lewis, Heather</creatorcontrib><creatorcontrib>Farquhar, Stephanie</creatorcontrib><creatorcontrib>Haamel, Naama</creatorcontrib><creatorcontrib>Babenko, Boris</creatorcontrib><creatorcontrib>Lang, Oran</creatorcontrib><creatorcontrib>Fleck, Mat</creatorcontrib><creatorcontrib>Traynis, Ilana</creatorcontrib><creatorcontrib>Lau, Charles</creatorcontrib><creatorcontrib>Horn, Ivor</creatorcontrib><creatorcontrib>Lyles, Courtney</creatorcontrib><title>Interdisciplinary Expertise to Advance Equitable Explainable AI</title><description>The field of artificial intelligence (AI) is rapidly influencing health and
healthcare, but bias and poor performance persists for populations who face
widespread structural oppression. Previous work has clearly outlined the need
for more rigorous attention to data representativeness and model performance to
advance equity and reduce bias. However, there is an opportunity to also
improve the explainability of AI by leveraging best practices of social
epidemiology and health equity to help us develop hypotheses for associations
found. In this paper, we focus on explainable AI (XAI) and describe a framework
for interdisciplinary expert panel review to discuss and critically assess AI
model explanations from multiple perspectives and identify areas of bias and
directions for future research. We emphasize the importance of the
interdisciplinary expert panel to produce more accurate, equitable
interpretations which are historically and contextually informed.
Interdisciplinary panel discussions can help reduce bias, identify potential
confounders, and identify opportunities for additional research where there are
gaps in the literature. In turn, these insights can suggest opportunities for
AI model improvement.</description><subject>Computer Science - Artificial Intelligence</subject><subject>Computer Science - Computer Vision and Pattern Recognition</subject><subject>Computer Science - Computers and Society</subject><subject>Computer Science - Learning</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj0GLwjAUhHPZw-LuD9iT_QPtJi9NTE9SSlcLghfv5TV5QqDWmnaL_nutepqBGYb5GPsRPEmNUvwXw9VPCaRcJ8IoLT_ZuupGCs4P1vet7zDcovLaUxj9QNF4jnI3YWcpKi__fsSmpTlu8dGcfV59sY8jtgN9v3XBDn_lodjGu_2mKvJdjHolY4fCZUobB0JIvrIA6Iw6ciRy1hpoiGeZ4TYTShjrUkUgqQElGyLQYOSCLV-zT4K6D_70uFrPJPWTRN4B8zhDmg</recordid><startdate>20240529</startdate><enddate>20240529</enddate><creator>Bennett, Chloe R</creator><creator>Cole-Lewis, Heather</creator><creator>Farquhar, Stephanie</creator><creator>Haamel, Naama</creator><creator>Babenko, Boris</creator><creator>Lang, Oran</creator><creator>Fleck, Mat</creator><creator>Traynis, Ilana</creator><creator>Lau, Charles</creator><creator>Horn, Ivor</creator><creator>Lyles, Courtney</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20240529</creationdate><title>Interdisciplinary Expertise to Advance Equitable Explainable AI</title><author>Bennett, Chloe R ; Cole-Lewis, Heather ; Farquhar, Stephanie ; Haamel, Naama ; Babenko, Boris ; Lang, Oran ; Fleck, Mat ; Traynis, Ilana ; Lau, Charles ; Horn, Ivor ; Lyles, Courtney</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a673-da1d9568d211307c22ad85f0aeedcc82be09980c91518cd45e23eb253bee26283</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Computer Science - Artificial Intelligence</topic><topic>Computer Science - Computer Vision and Pattern Recognition</topic><topic>Computer Science - Computers and Society</topic><topic>Computer Science - Learning</topic><toplevel>online_resources</toplevel><creatorcontrib>Bennett, Chloe R</creatorcontrib><creatorcontrib>Cole-Lewis, Heather</creatorcontrib><creatorcontrib>Farquhar, Stephanie</creatorcontrib><creatorcontrib>Haamel, Naama</creatorcontrib><creatorcontrib>Babenko, Boris</creatorcontrib><creatorcontrib>Lang, Oran</creatorcontrib><creatorcontrib>Fleck, Mat</creatorcontrib><creatorcontrib>Traynis, Ilana</creatorcontrib><creatorcontrib>Lau, Charles</creatorcontrib><creatorcontrib>Horn, Ivor</creatorcontrib><creatorcontrib>Lyles, Courtney</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Bennett, Chloe R</au><au>Cole-Lewis, Heather</au><au>Farquhar, Stephanie</au><au>Haamel, Naama</au><au>Babenko, Boris</au><au>Lang, Oran</au><au>Fleck, Mat</au><au>Traynis, Ilana</au><au>Lau, Charles</au><au>Horn, Ivor</au><au>Lyles, Courtney</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Interdisciplinary Expertise to Advance Equitable Explainable AI</atitle><date>2024-05-29</date><risdate>2024</risdate><abstract>The field of artificial intelligence (AI) is rapidly influencing health and
healthcare, but bias and poor performance persists for populations who face
widespread structural oppression. Previous work has clearly outlined the need
for more rigorous attention to data representativeness and model performance to
advance equity and reduce bias. However, there is an opportunity to also
improve the explainability of AI by leveraging best practices of social
epidemiology and health equity to help us develop hypotheses for associations
found. In this paper, we focus on explainable AI (XAI) and describe a framework
for interdisciplinary expert panel review to discuss and critically assess AI
model explanations from multiple perspectives and identify areas of bias and
directions for future research. We emphasize the importance of the
interdisciplinary expert panel to produce more accurate, equitable
interpretations which are historically and contextually informed.
Interdisciplinary panel discussions can help reduce bias, identify potential
confounders, and identify opportunities for additional research where there are
gaps in the literature. In turn, these insights can suggest opportunities for
AI model improvement.</abstract><doi>10.48550/arxiv.2406.18563</doi><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | DOI: 10.48550/arxiv.2406.18563 |
| ispartof | |
| issn | |
| language | eng |
| recordid | cdi_arxiv_primary_2406_18563 |
| source | arXiv.org |
| subjects | Computer Science - Artificial Intelligence Computer Science - Computer Vision and Pattern Recognition Computer Science - Computers and Society Computer Science - Learning |
| title | Interdisciplinary Expertise to Advance Equitable Explainable AI |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-02T10%3A45%3A06IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Interdisciplinary%20Expertise%20to%20Advance%20Equitable%20Explainable%20AI&rft.au=Bennett,%20Chloe%20R&rft.date=2024-05-29&rft_id=info:doi/10.48550/arxiv.2406.18563&rft_dat=%3Carxiv_GOX%3E2406_18563%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |