{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T10:20:23Z","timestamp":1778754023460,"version":"3.51.4"},"reference-count":45,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T00:00:00Z","timestamp":1652140800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T00:00:00Z","timestamp":1652140800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Digit. Med."],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Racial and ethnic minorities have borne a particularly acute burden of the COVID-19 pandemic in the United States. There is a growing awareness from both researchers and public health leaders of the critical need to ensure fairness in forecast results. Without careful and deliberate bias mitigation, inequities embedded in data can be transferred to model predictions, perpetuating disparities, and exacerbating the disproportionate harms of the COVID-19 pandemic. These biases in data and forecasts can be viewed through both statistical and sociological lenses, and the challenges of both building hierarchical models with limited data availability and drawing on data that reflects structural inequities must be confronted. We present an outline of key modeling domains in which unfairness may be introduced and draw on our experience building and testing the Google-Harvard COVID-19 Public Forecasting model to illustrate these challenges and offer strategies to address them. While targeted toward pandemic forecasting, these domains of potentially biased modeling and concurrent approaches to pursuing fairness present important considerations for equitable machine-learning innovation.<\/jats:p>","DOI":"10.1038\/s41746-022-00602-z","type":"journal-article","created":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T10:03:22Z","timestamp":1652177002000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["Algorithmic fairness in pandemic forecasting: lessons from COVID-19"],"prefix":"10.1038","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9183-016X","authenticated-orcid":false,"given":"Thomas C.","family":"Tsai","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6333-1729","authenticated-orcid":false,"given":"Sercan","family":"Arik","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5550-3559","authenticated-orcid":false,"given":"Benjamin H.","family":"Jacobson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinsung","family":"Yoon","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4153-4722","authenticated-orcid":false,"given":"Nate","family":"Yoder","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dario","family":"Sava","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Margaret","family":"Mitchell","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Garth","family":"Graham","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tomas","family":"Pfister","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,5,10]]},"reference":[{"key":"602_CR1","doi-asserted-by":"publisher","unstructured":"Cramer, E. Y. et al. Evaluation of individual and ensemble probabilistic forecasts of COVID-19 mortality in the US. medRxiv, 2021.2002.2003.21250974, https:\/\/doi.org\/10.1101\/2021.02.03.21250974 (2021).","DOI":"10.1101\/2021.02.03.21250974"},{"key":"602_CR2","unstructured":"American Hospital Association & AHA Center for Health Innovation. COVID-19 Models: Forecasting the Pandemic\u2019s Spread and Planning for Recovery. (September, 2020)."},{"key":"602_CR3","unstructured":"Centers for Disease Control and Prevention. COVID-19 Pandemic Planning Scenarios. (September 10, 2020)."},{"key":"602_CR4","doi-asserted-by":"publisher","first-page":"190","DOI":"10.1093\/jamia\/ocaa210","volume":"28","author":"E R\u00f6\u00f6sli","year":"2021","unstructured":"R\u00f6\u00f6sli, E., Rice, B. & Hernandez-Boussard, T. Bias at warp speed: how AI may contribute to the disparities gap in the time of COVID-19. J. Am. Med. Inform. Assoc. 28, 190\u2013192 (2021).","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"602_CR5","doi-asserted-by":"publisher","unstructured":"Adler, N. et al. Addressing social determinants of health and health disparities: a vital direction for health and health care. NAM Perspectives, https:\/\/doi.org\/10.31478\/201609t (2016).","DOI":"10.31478\/201609t"},{"key":"602_CR6","doi-asserted-by":"publisher","first-page":"S186","DOI":"10.2105\/AJPH.2009.166082","volume":"100","author":"PA Braveman","year":"2010","unstructured":"Braveman, P. A., Cubbin, C., Egerter, S., Williams, D. R. & Pamuk, E. Socioeconomic disparities in health in the United States: what the patterns tell us. Am. J. Public Health 100, S186\u2013S196 (2010).","journal-title":"Am. J. Public Health"},{"key":"602_CR7","doi-asserted-by":"publisher","first-page":"1750","DOI":"10.1001\/jama.2016.4226","volume":"315","author":"R Chetty","year":"2016","unstructured":"Chetty, R. et al. The association between income and life expectancy in the united states, 2001-2014. JAMA 315, 1750\u20131766 (2016).","journal-title":"JAMA"},{"key":"602_CR8","doi-asserted-by":"publisher","first-page":"571364","DOI":"10.3389\/fpubh.2020.571364","volume":"8","author":"DJ Lundon","year":"2020","unstructured":"Lundon, D. J. et al. Social determinants predict outcomes in data from a multi-ethnic cohort of 20,899 patients investigated for COVID-19. Front Public Health 8, 571364\u2013571364 (2020).","journal-title":"Front Public Health"},{"key":"602_CR9","doi-asserted-by":"publisher","first-page":"1099","DOI":"10.1016\/S0140-6736(05)71146-6","volume":"365","author":"M Marmot","year":"2005","unstructured":"Marmot, M. Social determinants of health inequalities. Lancet 365, 1099\u20131104 (2005).","journal-title":"Lancet"},{"key":"602_CR10","doi-asserted-by":"publisher","first-page":"768","DOI":"10.1056\/NEJMms2025396","volume":"384","author":"ZD Bailey","year":"2020","unstructured":"Bailey, Z. D., Feldman, J. M. & Bassett, M. T. How structural racism works \u2014 racist policies as a root cause of u.s. racial health inequities. N. Engl. J. Med. 384, 768\u2013773 (2020).","journal-title":"N. Engl. J. Med."},{"key":"602_CR11","doi-asserted-by":"publisher","first-page":"994","DOI":"10.1097\/SLA.0000000000003911","volume":"271","author":"AP Loehrer","year":"2020","unstructured":"Loehrer, A. P. & Tsai, T. C. Perpetuation of inequity: disproportionate penalties to minority-serving and safety-net hospitals under another medicare value-based payment model. Ann. Surg. 271, 994\u2013995 (2020).","journal-title":"Ann. Surg."},{"key":"602_CR12","doi-asserted-by":"publisher","first-page":"444","DOI":"10.15585\/mmwr.mm6617e1","volume":"66","author":"TJ Cunningham","year":"2017","unstructured":"Cunningham, T. J. et al. Vital signs: racial disparities in age-specific mortality among Blacks or African Americans \u2014 United States, 1999\u20132015. Mmwr. Morbidity Mortal. Wkly. Rep. 66, 444\u2013456 (2017).","journal-title":"Mmwr. Morbidity Mortal. Wkly. Rep."},{"key":"602_CR13","doi-asserted-by":"publisher","first-page":"1003","DOI":"10.1001\/jamainternmed.2017.0918","volume":"177","author":"L Dwyer-Lindgren","year":"2017","unstructured":"Dwyer-Lindgren, L. et al. Inequalities in life expectancy among US counties, 1980 to 2014: temporal trends and key drivers. JAMA Intern. Med. 177, 1003\u20131011 (2017).","journal-title":"JAMA Intern. Med."},{"key":"602_CR14","unstructured":"Kochanek, K. D., Anderson, R. N. & Arias, E. Leading causes of death contributing to decrease in life expectancy gap between black and white populations: United States, 1999\u20132013. NCHS Data Brief, 1\u20138 (2015)."},{"key":"602_CR15","doi-asserted-by":"publisher","first-page":"757","DOI":"10.1007\/s11524-017-0210-x","volume":"94","author":"EL Tung","year":"2017","unstructured":"Tung, E. L., Cagney, K. A., Peek, M. E. & Chin, M. H. Spatial context and health inequity: reconfiguring race, place, and poverty. J. Urban Health 94, 757\u2013763 (2017).","journal-title":"J. Urban Health"},{"key":"602_CR16","unstructured":"Agency for Healthcare Research and Quality. National Healthcare Quality and Disparities Report. (Rockville, MD, 2019)."},{"key":"602_CR17","unstructured":"Institute of Medicine Committee on Understanding and Eliminating Racial and Ethnic Disparities in Health Care. In Unequal Treatment: Confronting Racial and Ethnic Disparities in Health Care (eds. Smedley, B. D., Stith, A. Y. & Nelson, A. R.) (National Academies Press (US) 2003)."},{"key":"602_CR18","doi-asserted-by":"publisher","first-page":"e2014746118","DOI":"10.1073\/pnas.2014746118","volume":"118","author":"T Andrasfay","year":"2021","unstructured":"Andrasfay, T. & Goldman, N. Reductions in 2020 US life expectancy due to COVID-19 and the disproportionate impact on the Black and Latino populations. Proc. Natl Acad. Sci. 118, e2014746118 (2021).","journal-title":"Proc. Natl Acad. Sci."},{"key":"602_CR19","unstructured":"Kaiser Family Foundation. COVID-19 hospitalization and death rates among active epic patients by race\/ethnicity. (September 21, 2020)."},{"key":"602_CR20","doi-asserted-by":"publisher","first-page":"447","DOI":"10.1126\/science.aax2342","volume":"366","author":"Z Obermeyer","year":"2019","unstructured":"Obermeyer, Z., Powers, B., Vogeli, C. & Mullainathan, S. Dissecting racial bias in an algorithm used to manage the health of populations. Science 366, 447\u2013453 (2019).","journal-title":"Science"},{"key":"602_CR21","doi-asserted-by":"publisher","first-page":"2477","DOI":"10.1056\/NEJMc2029240","volume":"383","author":"MW Sjoding","year":"2020","unstructured":"Sjoding, M. W., Dickson, R. P., Iwashyna, T. J., Gay, S. E. & Valley, T. S. Racial bias in pulse oximetry measurement. N. Engl. J. Med. 383, 2477\u20132478 (2020).","journal-title":"N. Engl. J. Med."},{"key":"602_CR22","doi-asserted-by":"publisher","first-page":"874","DOI":"10.1056\/NEJMms2004740","volume":"383","author":"DA Vyas","year":"2020","unstructured":"Vyas, D. A., Eisenstein, L. G. & Jones, D. S. Hidden in plain sight \u2014 reconsidering the use of race correction in clinical algorithms. N. Engl. J. Med. 383, 874\u2013882 (2020).","journal-title":"N. Engl. J. Med."},{"key":"602_CR23","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1016\/j.jclinepi.2020.06.004","volume":"128","author":"RE Glover","year":"2020","unstructured":"Glover, R. E. et al. A framework for identifying and mitigating the equity harms of COVID-19 policy interventions. J. Clin. Epidemiol. 128, 35\u201348 (2020).","journal-title":"J. Clin. Epidemiol."},{"key":"602_CR24","doi-asserted-by":"publisher","first-page":"288","DOI":"10.1136\/jech-2013-203118","volume":"68","author":"T Lorenc","year":"2014","unstructured":"Lorenc, T. & Oliver, K. Adverse effects of public health interventions: a conceptual framework. J. Epidemiol. Commun. Health 68, 288 (2014).","journal-title":"J. Epidemiol. Commun. Health"},{"key":"602_CR25","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1016\/j.jclinepi.2013.08.005","volume":"67","author":"J O\u2019Neill","year":"2014","unstructured":"O\u2019Neill, J. et al. Applying an equity lens to interventions: using PROGRESS ensures consideration of socially stratifying factors to illuminate inequities in health. J. Clin. Epidemiol. 67, 56\u201364 (2014).","journal-title":"J. Clin. Epidemiol."},{"key":"602_CR26","doi-asserted-by":"publisher","first-page":"460","DOI":"10.1038\/s42256-021-00362-7","volume":"3","author":"S Kapur","year":"2021","unstructured":"Kapur, S. Reducing racial bias in AI models for clinical use requires a top-down intervention. Nat. Mach. Intell. 3, 460\u2013460 (2021).","journal-title":"Nat. Mach. Intell."},{"key":"602_CR27","unstructured":"Kendi, I. X. How to be an antiracist. (Random House, 2019)."},{"key":"602_CR28","doi-asserted-by":"publisher","first-page":"1327","DOI":"10.1038\/s41591-020-1020-3","volume":"26","author":"K Owens","year":"2020","unstructured":"Owens, K. & Walker, A. Those designing healthcare algorithms must become actively anti-racist. Nat. Med. 26, 1327\u20131328 (2020).","journal-title":"Nat. Med."},{"key":"602_CR29","doi-asserted-by":"publisher","first-page":"866","DOI":"10.7326\/M18-1990","volume":"169","author":"A Rajkomar","year":"2018","unstructured":"Rajkomar, A., Hardt, M., Howell, M. D., Corrado, G. & Chin, M. H. Ensuring fairness in machine learning to advance health equity. Ann. Intern. Med. 169, 866\u2013872 (2018).","journal-title":"Ann. Intern. Med."},{"key":"602_CR30","doi-asserted-by":"publisher","unstructured":"Rozier, M. D., Patel, K. K. & Cross, D. A. Electronic health records as biased tools or tools against bias: a conceptual model. Milbank Q., https:\/\/doi.org\/10.1111\/1468-0009.12545 (2021).","DOI":"10.1111\/1468-0009.12545"},{"key":"602_CR31","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-021-00511-7","volume":"4","author":"S\u00d6 Arik","year":"2021","unstructured":"Arik, S. \u00d6. et al. A prospective evaluation of AI-augmented epidemiology to forecast COVID-19 in the USA and Japan. npj Digital Med. 4, 146 (2021).","journal-title":"npj Digital Med."},{"key":"602_CR32","doi-asserted-by":"publisher","unstructured":"Rader, B. et al. Geographic access to United States SARS-CoV-2 testing sites highlights healthcare disparities and may bias transmission estimates. J. Travel Med. 27, https:\/\/doi.org\/10.1093\/jtm\/taaa076 (2020).","DOI":"10.1093\/jtm\/taaa076"},{"key":"602_CR33","doi-asserted-by":"publisher","first-page":"1362","DOI":"10.1377\/hlthaff.2020.00581","volume":"39","author":"GP Kanter","year":"2020","unstructured":"Kanter, G. P., Segal, A. G. & Groeneveld, P. W. Income disparities in access to critical care services. Health Aff. 39, 1362\u20131367 (2020).","journal-title":"Health Aff."},{"key":"602_CR34","doi-asserted-by":"publisher","first-page":"395","DOI":"10.1377\/hlthaff.2019.01394","volume":"39","author":"TC Buchmueller","year":"2020","unstructured":"Buchmueller, T. C. & Levy, H. G. The ACA\u2019s impact on racial and ethnic disparities in health insurance coverage and access to care. Health Aff. 39, 395\u2013402 (2020).","journal-title":"Health Aff."},{"key":"602_CR35","doi-asserted-by":"publisher","first-page":"1984","DOI":"10.1377\/hlthaff.2020.01040","volume":"39","author":"JF Figueroa","year":"2020","unstructured":"Figueroa, J. F., Wadhera, R. K., Lee, D., Yeh, R. W. & Sommers, B. D. Community-level factors associated with racial and ethnic disparities in COVID-19 rates In Massachusetts. Health Aff. 39, 1984\u20131992 (2020).","journal-title":"Health Aff."},{"key":"602_CR36","doi-asserted-by":"publisher","first-page":"e2019933","DOI":"10.1001\/jamanetworkopen.2020.19933","volume":"3","author":"R Khazanchi","year":"2020","unstructured":"Khazanchi, R., Evans, C. T. & Marcelin, J. R. Racism, not race, drives inequity across the COVID-19 continuum. JAMA Netw. Open 3, e2019933\u2013e2019933 (2020).","journal-title":"JAMA Netw. Open"},{"key":"602_CR37","doi-asserted-by":"publisher","first-page":"1046","DOI":"10.1377\/hlthaff.2011.1365","volume":"32","author":"J Dimick","year":"2013","unstructured":"Dimick, J., Ruhter, J., Sarrazin, M. V. & Birkmeyer, J. D. Black patients more likely than whites to undergo surgery at low-quality hospitals in segregated regions. Health Aff. 32, 1046\u20131053 (2013).","journal-title":"Health Aff."},{"key":"602_CR38","doi-asserted-by":"publisher","first-page":"893","DOI":"10.1093\/oxfordjournals.aje.a114892","volume":"127","author":"S Piantadosi","year":"1988","unstructured":"Piantadosi, S., Byar, D. P. & Green, S. B. The ecological fallacy. Am. J. Epidemiol. 127, 893\u2013904 (1988).","journal-title":"Am. J. Epidemiol."},{"key":"602_CR39","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1038\/sj.jes.7500533","volume":"17","author":"BA Portnov","year":"2007","unstructured":"Portnov, B. A., Dubnov, J. & Barchana, M. On ecological fallacy, assessment errors stemming from misguided variable selection, and the effect of aggregation on the outcome of epidemiological study. J. Expo. Sci. Environ. Epidemiol. 17, 106\u2013121 (2007).","journal-title":"J. Expo. Sci. Environ. Epidemiol."},{"key":"602_CR40","doi-asserted-by":"publisher","first-page":"438","DOI":"10.1093\/biostatistics\/kxj017","volume":"7","author":"J Wakefield","year":"2006","unstructured":"Wakefield, J. & Shaddick, G. Health-exposure modeling and the ecological fallacy. Biostatistics 7, 438\u2013455 (2006).","journal-title":"Biostatistics"},{"key":"602_CR41","doi-asserted-by":"publisher","first-page":"461","DOI":"10.1177\/004912417500300406","volume":"3","author":"DF Hawkins","year":"1975","unstructured":"Hawkins, D. F. Estimation of nonresponse bias. Sociol. Methods Res. 3, 461\u2013488 (1975).","journal-title":"Sociol. Methods Res."},{"key":"602_CR42","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1056\/NEJMp2016822","volume":"383","author":"I Holmdahl","year":"2020","unstructured":"Holmdahl, I. & Buckee, C. Wrong but useful \u2014 what covid-19 epidemiologic models can and cannot tell us. N. Engl. J. Med. 383, 303\u2013305 (2020).","journal-title":"N. Engl. J. Med."},{"key":"602_CR43","unstructured":"Chuang, C.-Y. & Mroueh, Y. In International Conference on Learning Representations (2021)."},{"key":"602_CR44","unstructured":"Zemel, R., Wu, Y., Swersky, K., Pitassi, T. & Dwork, C. In Proceedings of the 30th International Conference on Machine Learning Vol. 28 (eds. Sanjoy, D. & David, M.) 325\u2013333 (PMLR, Proceedings of Machine Learning Research, 2013)."},{"key":"602_CR45","doi-asserted-by":"crossref","unstructured":"Zhang, B. H., Lemoine, B. & Mitchell, M. Mitigating Unwanted Biases with Adversarial Learning. AIES \u201818: Proceedings of the 2018 AAAI\/ACM Conference on AI, Ethics, and Society, 335\u2013340.","DOI":"10.1145\/3278721.3278779"}],"container-title":["npj Digital Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41746-022-00602-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-022-00602-z","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-022-00602-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,25]],"date-time":"2022-11-25T07:57:59Z","timestamp":1669363079000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41746-022-00602-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,10]]},"references-count":45,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2022,12]]}},"alternative-id":["602"],"URL":"https:\/\/doi.org\/10.1038\/s41746-022-00602-z","relation":{},"ISSN":["2398-6352"],"issn-type":[{"value":"2398-6352","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,5,10]]},"assertion":[{"value":"19 April 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 April 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 May 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"59"}}