{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,30]],"date-time":"2026-10-30T09:37:23Z","timestamp":1793353043633,"version":"4.5.0"},"reference-count":30,"publisher":"American Medical Association (AMA)","issue":"7","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JAMA Netw Open"],"abstract":"Importance<\/jats:title>Machine learning has potential to transform cancer care by helping clinicians prioritize patients for serious illness conversations. However, models need to be evaluated for unequal performance across racial groups (ie, racial bias) so that existing racial disparities are not exacerbated.<\/jats:p><\/jats:sec>Objective<\/jats:title>To evaluate whether racial bias exists in a predictive machine learning model that identifies 180-day cancer mortality risk among patients with solid malignant tumors.<\/jats:p><\/jats:sec>Design, Setting, and Participants<\/jats:title>In this cohort study, a machine learning model to predict cancer mortality for patients aged 21 years or older diagnosed with cancer between January 2016 and December 2021 was developed with a random forest algorithm using retrospective data from the Mount Sinai Health System cancer registry, Social Security Death Index, and electronic health records up to the date when databases were accessed for cohort extraction (February 2022).<\/jats:p><\/jats:sec>Exposure<\/jats:title>Race category.<\/jats:p><\/jats:sec>Main Outcomes and Measures<\/jats:title>The primary outcomes were model discriminatory performance (area under the receiver operating characteristic curve [AUROC], F1 score) among each race category (Asian, Black, Native American, White, and other or unknown) and fairness metrics (equal opportunity, equalized odds, and disparate impact) among each pairwise comparison of race categories. True-positive rate ratios represented equal opportunity; both true-positive and false-positive rate ratios, equalized odds; and the percentage of predictive positive rate ratios, disparate impact. All metrics were estimated as a proportion or ratio, with variability captured through 95% CIs. The prespecified criterion for the model\u2019s clinical use was a threshold of at least 80% for fairness metrics across different racial groups to ensure the model\u2019s prediction would not be biased against any specific race.<\/jats:p><\/jats:sec>Results<\/jats:title>The test validation dataset included 43\u202f274 patients with balanced demographics. Mean (SD) age was 64.09 (14.26) years, with 49.6% older than 65 years. A total of 53.3% were female; 9.5%, Asian; 18.9%, Black; 0.1%, Native American; 52.2%, White; and 19.2%, other or unknown race; 0.1% had missing race data. A total of 88.9% of patients were alive, and 11.1% were dead. The AUROCs, F1 scores, and fairness metrics maintained reasonable concordance among the racial subgroups: the AUROCs ranged from 0.75 (95% CI, 0.72-0.78) for Asian patients and 0.75 (95% CI, 0.73-0.77) for Black patients to 0.77 (95% CI, 0.75-0.79) for patients with other or unknown race; F1 scores, from 0.32 (95% CI, 0.32-0.33) for White patients to 0.40 (95% CI, 0.39-0.42) for Black patients; equal opportunity ratios, from 0.96 (95% CI, 0.95-0.98) for Black patients compared with White patients to 1.02 (95% CI, 1.00-1.04) for Black patients compared with patients with other or unknown race; equalized odds ratios, from 0.87 (95% CI, 0.85-0.92) for Black patients compared with White patients to 1.16 (1.10-1.21) for Black patients compared with patients with other or unknown race; and disparate impact ratios, from 0.86 (95% CI, 0.82-0.89) for Black patients compared with White patients to 1.17 (95% CI, 1.12-1.22) for Black patients compared with patients with other or unknown race.<\/jats:p><\/jats:sec>Conclusions and Relevance<\/jats:title>In this cohort study, the lack of significant variation in performance or fairness metrics indicated an absence of racial bias, suggesting that the model fairly identified cancer mortality risk across racial groups. It remains essential to consistently review the model\u2019s application in clinical settings to ensure equitable patient care.<\/jats:p><\/jats:sec>","DOI":"10.1001\/jamanetworkopen.2024.21290","type":"journal-article","created":{"date-parts":[[2024,7,10]],"date-time":"2024-07-10T15:04:24Z","timestamp":1720623864000},"page":"e2421290","source":"Crossref","is-referenced-by-count":15,"title":["Fairness in Predicting Cancer Mortality Across Racial Subgroups"],"prefix":"10.1001","volume":"7","author":[{"given":"Teja","family":"Ganta","sequence":"first","affiliation":[{"name":"Division of Hematology and Medical Oncology, Icahn School of Medicine at Mount Sinai, New York, New York"},{"name":"Tisch Cancer Institute, Icahn School of Medicine at Mount Sinai, New York, New York"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Arash","family":"Kia","sequence":"additional","affiliation":[{"name":"Department of Anesthesiology, Perioperative and Pain Medicine, Icahn School of Medicine at Mount Sinai, New York, New York"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Prathamesh","family":"Parchure","sequence":"additional","affiliation":[{"name":"Institute for Healthcare Delivery Science, Icahn School of Medicine at Mount Sinai, New York, New York"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Min-heng","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute for Healthcare Delivery Science, Icahn School of Medicine at Mount Sinai, New York, New York"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Melanie","family":"Besculides","sequence":"additional","affiliation":[{"name":"Institute for Healthcare Delivery Science, Icahn School of Medicine at Mount Sinai, New York, New York"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Madhu","family":"Mazumdar","sequence":"additional","affiliation":[{"name":"Institute for Healthcare Delivery Science, Icahn School of Medicine at Mount Sinai, New York, New York"},{"name":"Tisch Cancer Institute, Icahn School of Medicine at Mount Sinai, New York, New York"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cardinale B.","family":"Smith","sequence":"additional","affiliation":[{"name":"Division of Hematology and Medical Oncology, Icahn School of Medicine at Mount Sinai, New York, New York"},{"name":"Tisch Cancer Institute, Icahn School of Medicine at Mount Sinai, New York, New York"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"10","published-online":{"date-parts":[[2024,7,10]]},"reference":[{"issue":"2","key":"zoi240677r1","doi-asserted-by":"publisher","first-page":"369","DOI":"10.3390\/diagnostics11020369","article-title":"A multi-center, multi-vendor study to evaluate the generalizability of a radiomics model for classifying prostate cancer: high grade vs low grade.","volume":"11","author":"Castillo T","year":"2021","journal-title":"Diagnostics (Basel)"},{"issue":"4","key":"zoi240677r2","doi-asserted-by":"publisher","first-page":"e556","DOI":"10.1200\/OP.20.00663","article-title":"Creating and validating a predictive model for suitability of hospital at home for patients with solid-tumor malignancies.","volume":"17","author":"Chen","year":"2021","journal-title":"JCO Oncol Pract"},{"issue":"12","key":"zoi240677r3","doi-asserted-by":"publisher","DOI":"10.1001\/jamaoncol.2020.4759","article-title":"Effect of integrating machine learning mortality estimates with behavioral nudges to clinicians on serious illness conversations among patients with cancer: a stepped-wedge cluster randomized clinical trial.","volume":"6","author":"Manz","year":"2020","journal-title":"JAMA Oncol"},{"issue":"11","key":"zoi240677r4","doi-asserted-by":"publisher","first-page":"1544","DOI":"10.1001\/jamainternmed.2018.3763","article-title":"Potential biases in machine learning algorithms using electronic health record data.","volume":"178","author":"Gianfrancesco","year":"2018","journal-title":"JAMA Intern Med"},{"issue":"12","key":"zoi240677r5","doi-asserted-by":"publisher","first-page":"866","DOI":"10.7326\/M18-1990","article-title":"ensuring fairness in machine learning to advance health equity.","volume":"169","author":"Rajkomar","year":"2018","journal-title":"Ann Intern Med"},{"issue":"12","key":"zoi240677r6","doi-asserted-by":"publisher","first-page":"4138","DOI":"10.1002\/cam4.v10.12","article-title":"Artificial intelligence in oncology: path to implementation.","volume":"10","author":"Chua","year":"2021","journal-title":"Cancer Med"},{"issue":"11","key":"zoi240677r7","doi-asserted-by":"publisher","first-page":"981","DOI":"10.1056\/NEJMp1714229","article-title":"Implementing machine learning in health care\u2014addressing ethical challenges.","volume":"378","author":"Char","year":"2018","journal-title":"N Engl J Med"},{"issue":"5","key":"zoi240677r8","doi-asserted-by":"publisher","DOI":"10.2196\/36388","article-title":"Evaluation and mitigation of racial bias in clinical machine learning models: scoping review.","volume":"10","author":"Huang","year":"2022","journal-title":"JMIR Med Inform"},{"key":"zoi240677r9","doi-asserted-by":"publisher","DOI":"10.1016\/j.ebiom.2022.104250","article-title":"Algorithmic fairness in computational medicine.","volume":"84","author":"Xu","year":"2022","journal-title":"EBioMedicine"},{"issue":"6464","key":"zoi240677r10","doi-asserted-by":"publisher","first-page":"447","DOI":"10.1126\/science.aax2342","article-title":"Dissecting racial bias in an algorithm used to manage the health of populations.","volume":"366","author":"Obermeyer","year":"2019","journal-title":"Science"},{"issue":"1","key":"zoi240677r11","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1001\/jama.2023.25051","article-title":"President Biden\u2019s executive order on artificial intelligence\u2014implications for health care organizations.","volume":"331","author":"Mello","year":"2024","journal-title":"JAMA"},{"issue":"6","key":"zoi240677r12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3457607","article-title":"A survey on bias and fairness in machine learning.","volume":"54","author":"Mehrabi","year":"2021","journal-title":"ACM Comput Surv"},{"issue":"5","key":"zoi240677r13","doi-asserted-by":"publisher","first-page":"1559","DOI":"10.1007\/s11606-019-05446-0","article-title":"Use and meaning of \u201cgoals of care\u201d in the healthcare literature: a systematic review and qualitative discourse analysis.","volume":"35","author":"Secunda","year":"2020","journal-title":"J Gen Intern Med"},{"issue":"7","key":"zoi240677r14","doi-asserted-by":"publisher","first-page":"1203","DOI":"10.1200\/JCO.2009.25.4672","article-title":"End-of-life discussions, goal attainment, and distress at the end of life: predictors and outcomes of receipt of care consistent with preferences.","volume":"28","author":"Mack","year":"2010","journal-title":"J Clin Oncol"},{"issue":"17","key":"zoi240677r15","doi-asserted-by":"publisher","first-page":"1533","DOI":"10.1001\/archinternmed.2010.322","article-title":"Racial disparities in the outcomes of communication on medical care received near death.","volume":"170","author":"Mack","year":"2010","journal-title":"Arch Intern Med"},{"issue":"1","key":"zoi240677r16","doi-asserted-by":"publisher","first-page":"130","DOI":"10.1186\/s12885-019-5333-x","article-title":"Breaking silence: a survey of barriers to goals of care discussions from the perspective of oncology practitioners.","volume":"19","author":"Piggott","year":"2019","journal-title":"BMC Cancer"},{"issue":"1","key":"zoi240677r17","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1007\/s11864-019-0698-2","article-title":"Prognosticating for adult patients with advanced incurable cancer: a needed oncologist skill.","volume":"21","author":"Chu","year":"2020","journal-title":"Curr Treat Options Oncol"},{"issue":"3","key":"zoi240677r18","doi-asserted-by":"publisher","first-page":"355","DOI":"10.1016\/j.pec.2006.06.011","article-title":"Cancer communication patterns and the influence of patient characteristics: disparities in information-giving and affective behaviors.","volume":"62","author":"Siminoff","year":"2006","journal-title":"Patient Educ Couns"},{"issue":"1","key":"zoi240677r19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12916-014-0241-z","article-title":"Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis (TRIPOD): the TRIPOD statement.","volume":"13","author":"Collins","year":"2015","journal-title":"BMC Med"},{"issue":"1","key":"zoi240677r21","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests.","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach Learn"},{"issue":"13","key":"zoi240677r23","doi-asserted-by":"publisher","first-page":"811","DOI":"10.3109\/08958378.2014.955932","article-title":"Screening tests: a review with examples.","volume":"26","author":"Maxim","year":"2014","journal-title":"Inhal Toxicol"},{"issue":"3","key":"zoi240677r24","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0092209","article-title":"Area under precision-recall curves for weighted and unweighted data.","volume":"9","author":"Keilwagen","year":"2014","journal-title":"PLoS One"},{"issue":"12","key":"zoi240677r28","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2023.45050","article-title":"Guiding principles to address the impact of algorithm bias on racial and ethnic disparities in health and health care.","volume":"6","author":"Chin","year":"2023","journal-title":"JAMA Netw Open"},{"issue":"5","key":"zoi240677r29","first-page":"518","article-title":"The Social Security Death Index (SSDI) most accurately reflects true survival for older oncology patients.","volume":"3","author":"Huntington","year":"2013","journal-title":"Am J Cancer Res"},{"issue":"1","key":"zoi240677r30","first-page":"30","article-title":"Comparing cancer registry abstracted and self-reported data on race and ethnicity.","volume":"44","author":"Atekruse","year":"2017","journal-title":"J Registry Manag"},{"key":"zoi240677r20","unstructured":"NAACCR Data Standards & Data Dictionary Database (formerly volume II). North American Association of Central Cancer Registries. Accessed May 3, 2024. https:\/\/www.naaccr.org\/data-standards-data-dictionary\/"},{"key":"zoi240677r22","unstructured":"Apache Spark 2.3.0. Machine Learning Library (MLlib) Guide. Accessed May 3, 2024. https:\/\/spark.apache.org\/docs\/2.3.0\/ml-guide.html"},{"key":"zoi240677r25","unstructured":"National Institutes of Health. Ending structural racism. Accessed May 3, 2024. https:\/\/www.nih.gov\/ending-structural-racism"},{"key":"zoi240677r26","unstructured":"AMA adopts guidelines that confront systemic racism in medicine. Press release. American Medical Association. June 15, 2021. Accessed May 3, 2024. https:\/\/www.ama-assn.org\/press-center\/press-releases\/ama-adopts-guidelines-confront-systemic-racism-medicine"},{"key":"zoi240677r27","unstructured":"Agency for Healthcare Research and Quality. National healthcare quality and disparities reports. Accessed May 3, 2024. https:\/\/www.ahrq.gov\/research\/findings\/nhqrdr\/index.html"}],"container-title":["JAMA Network Open"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/jamanetwork.com\/journals\/jamanetworkopen\/articlepdf\/2820964\/ganta_2024_oi_240677_1719929569.45305.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,10]],"date-time":"2024-07-10T15:04:31Z","timestamp":1720623871000},"score":1,"resource":{"primary":{"URL":"https:\/\/jamanetwork.com\/journals\/jamanetworkopen\/fullarticle\/2820964"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,10]]},"references-count":30,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2024,7,1]]}},"URL":"https:\/\/doi.org\/10.1001\/jamanetworkopen.2024.21290","relation":{},"ISSN":["2574-3805"],"issn-type":[{"value":"2574-3805","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7,10]]}}}