Ian Pan1, Laura B Nolan1, Rashida R Brown1, Romana Khan1, Paul van der Boor1, Daniel G Harris1, Rayid Ghani1. 1. Ian Pan is with the Department of Biostatistics, School of Public Health, Brown University, Providence, RI. Laura B. Nolan is with the Population Research Center, School of Social Work, Columbia University, New York, NY. Rashida R. Brown is with the Division of Epidemiology, School of Public Health, University of California, Berkeley. Romana Khan is with the Kellogg School of Management, Northwestern University, Evanston, IL. Paul van der Boor and Rayid Ghani are with the Center for Data Science and Public Policy, University of Chicago, Chicago, IL. Daniel G. Harris is with the Department of Human Services, Illinois State Government, Chicago.
Abstract
OBJECTIVES: To evaluate the positive predictive value of machine learning algorithms for early assessment of adverse birth risk among pregnant women as a means of improving the allocation of social services. METHODS: We used administrative data for 6457 women collected by the Illinois Department of Human Services from July 2014 to May 2015 to develop a machine learning model for adverse birth prediction and improve upon the existing paper-based risk assessment. We compared different models and determined the strongest predictors of adverse birth outcomes using positive predictive value as the metric for selection. RESULTS: Machine learning algorithms performed similarly, outperforming the current paper-based risk assessment by up to 36%; a refined paper-based assessment outperformed the current assessment by up to 22%. We estimate that these improvements will allow 100 to 170 additional high-risk pregnant women screened for program eligibility each year to receive services that would have otherwise been unobtainable. CONCLUSIONS: Our analysis exhibits the potential for machine learning to move government agencies toward a more data-informed approach to evaluating risk and providing social services. Overall, such efforts will improve the efficiency of allocating resource-intensive interventions.
OBJECTIVES: To evaluate the positive predictive value of machine learning algorithms for early assessment of adverse birth risk among pregnant women as a means of improving the allocation of social services. METHODS: We used administrative data for 6457 women collected by the Illinois Department of Human Services from July 2014 to May 2015 to develop a machine learning model for adverse birth prediction and improve upon the existing paper-based risk assessment. We compared different models and determined the strongest predictors of adverse birth outcomes using positive predictive value as the metric for selection. RESULTS: Machine learning algorithms performed similarly, outperforming the current paper-based risk assessment by up to 36%; a refined paper-based assessment outperformed the current assessment by up to 22%. We estimate that these improvements will allow 100 to 170 additional high-risk pregnant women screened for program eligibility each year to receive services that would have otherwise been unobtainable. CONCLUSIONS: Our analysis exhibits the potential for machine learning to move government agencies toward a more data-informed approach to evaluating risk and providing social services. Overall, such efforts will improve the efficiency of allocating resource-intensive interventions.
Authors: Kelly J Thomas Craig; Nicole Fusco; Thrudur Gunnarsdottir; Luc Chamberland; Jane L Snowdon; William J Kassler Journal: Online J Public Health Inform Date: 2021-12-24
Authors: Jennifer Villani; Sheri D Schully; Payam Meyer; Ranell L Myles; Jocelyn A Lee; David M Murray; Ashley J Vargas Journal: Am J Prev Med Date: 2018-10-25 Impact factor: 5.043