Zachary Tran , Julianne Byun , Ha Yeon Lee , Hans Boggs , Emma Y. Tomihama , Sharon C. Kiang
{"title":"血管外科人工智能中的偏见","authors":"Zachary Tran , Julianne Byun , Ha Yeon Lee , Hans Boggs , Emma Y. Tomihama , Sharon C. Kiang","doi":"10.1053/j.semvascsurg.2023.07.003","DOIUrl":null,"url":null,"abstract":"<div><p><span>Application of artificial intelligence (AI) has revolutionized the utilization of big data, especially in patient care. The potential of deep learning models to learn without </span><em>a priori</em><span> assumption, or without prior learning, to connect seemingly unrelated information mixes excitement alongside hesitation to fully understand AI's limitations. Bias, ranging from data collection and input to algorithm development to finally human review of algorithm output affects AI's application to clinical patient presents unique challenges that differ significantly from biases in traditional analyses. Algorithm fairness, a new field of research within AI, aims to mitigate bias by evaluating the data at the preprocessing stage, optimizing during algorithm development, and evaluating algorithm output at the postprocessing stage. As the field continues to develop, being cognizant of the inherent biases and limitations related to black box decision making, biased data sets agnostic to patient-level disparities, wide variation of present methodologies, and lack of common reporting standards will require ongoing research to provide transparency to AI and its applications.</span></p></div>","PeriodicalId":51153,"journal":{"name":"Seminars in Vascular Surgery","volume":"36 3","pages":"Pages 430-434"},"PeriodicalIF":3.3000,"publicationDate":"2023-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Bias in artificial intelligence in vascular surgery\",\"authors\":\"Zachary Tran , Julianne Byun , Ha Yeon Lee , Hans Boggs , Emma Y. Tomihama , Sharon C. Kiang\",\"doi\":\"10.1053/j.semvascsurg.2023.07.003\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p><span>Application of artificial intelligence (AI) has revolutionized the utilization of big data, especially in patient care. The potential of deep learning models to learn without </span><em>a priori</em><span> assumption, or without prior learning, to connect seemingly unrelated information mixes excitement alongside hesitation to fully understand AI's limitations. Bias, ranging from data collection and input to algorithm development to finally human review of algorithm output affects AI's application to clinical patient presents unique challenges that differ significantly from biases in traditional analyses. Algorithm fairness, a new field of research within AI, aims to mitigate bias by evaluating the data at the preprocessing stage, optimizing during algorithm development, and evaluating algorithm output at the postprocessing stage. As the field continues to develop, being cognizant of the inherent biases and limitations related to black box decision making, biased data sets agnostic to patient-level disparities, wide variation of present methodologies, and lack of common reporting standards will require ongoing research to provide transparency to AI and its applications.</span></p></div>\",\"PeriodicalId\":51153,\"journal\":{\"name\":\"Seminars in Vascular Surgery\",\"volume\":\"36 3\",\"pages\":\"Pages 430-434\"},\"PeriodicalIF\":3.3000,\"publicationDate\":\"2023-09-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Seminars in Vascular Surgery\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0895796723000558\",\"RegionNum\":3,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"PERIPHERAL VASCULAR DISEASE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Seminars in Vascular Surgery","FirstCategoryId":"3","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0895796723000558","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"PERIPHERAL VASCULAR DISEASE","Score":null,"Total":0}
Bias in artificial intelligence in vascular surgery
Application of artificial intelligence (AI) has revolutionized the utilization of big data, especially in patient care. The potential of deep learning models to learn without a priori assumption, or without prior learning, to connect seemingly unrelated information mixes excitement alongside hesitation to fully understand AI's limitations. Bias, ranging from data collection and input to algorithm development to finally human review of algorithm output affects AI's application to clinical patient presents unique challenges that differ significantly from biases in traditional analyses. Algorithm fairness, a new field of research within AI, aims to mitigate bias by evaluating the data at the preprocessing stage, optimizing during algorithm development, and evaluating algorithm output at the postprocessing stage. As the field continues to develop, being cognizant of the inherent biases and limitations related to black box decision making, biased data sets agnostic to patient-level disparities, wide variation of present methodologies, and lack of common reporting standards will require ongoing research to provide transparency to AI and its applications.
期刊介绍:
Each issue of Seminars in Vascular Surgery examines the latest thinking on a particular clinical problem and features new diagnostic and operative techniques. The journal allows practitioners to expand their capabilities and to keep pace with the most rapidly evolving areas of surgery.