TY - RPRT A1 - Ribers, Michael Allan A1 - Ullrich, Hannes T1 - Machine learning and physician prescribing: a path to reduced antibiotic use T2 - Berlin School of Economics Discussion Papers N2 - Inefficient human decisions are driven by biases and limited information. Health care is one leading example where machine learning is hoped to deliver efficiency gains. Antibiotic resistance constitutes a major challenge to health care systems due to human antibiotic overuse. We investigate how a policy leveraging the strengths of a machine learning algorithm and physicians can provide new opportunities to reduce antibiotic use. We focus on urinary tract infections in primary care, a leading cause for antibiotic use, where physicians often prescribe prior to attaining diagnostic certainty. Symptom assessment and rapid testing provide diagnostic information with limited accuracy, while laboratory testing can diagnose bacterial infections with considerable delay. Linking Danish administrative and laboratory data, we optimize policy rules which base initial prescription decisions on machine learning predictions and delegate decisions to physicians where these benefit most from private information at the point-of-care. The policy shows a potential to reduce antibiotic prescribing by 8.1 percent and overprescribing by 20.3 percent without assigning fewer prescriptions to patients with bacterial infections. We find human-algorithm complementarity is essential to achieve efficiency gains. T3 - Berlin School of Economics Discussion Papers - 19 Y1 - 2023 UR - https://nbn-resolving.org/urn:nbn:de:kobv:b1570-opus4-49769 UR - https://berlinschoolofeconomics.de/insights/bse-discussion-papers U6 - https://doi.org/10.48462/opus4-4976 ET - No. 19 ER - TY - RPRT A1 - Ullrich, Hannes A1 - Ribers, Michael Allan T1 - Machine predictions and human decisions with variation in payoffs and skill: the case of antibiotic prescribing T2 - Berlin School of Economics Discussion Papers N2 - We analyze how machine learning predictions may improve antibiotic prescribing in the context of the global health policy challenge of increasing antibiotic resistance. Estimating a binary antibiotic treatment choice model, we find variation in the skill to diagnose bacterial urinary tract infections and in how general practitioners trade off the expected cost of resistance against antibiotic curative benefits. In counterfactual analyses we find that providing machine learning predictions of bacterial infections to physicians increases prescribing efficiency. However, to achieve the policy objective of reducing antibiotic prescribing, physicians must also be incentivized. Our results highlight the potential misalignment of social and heterogeneous individual objectives in utilizing machine learning for prediction policy problems. T3 - Berlin School of Economics Discussion Papers - 27 KW - Economics Y1 - 2023 UR - https://nbn-resolving.org/urn:nbn:de:kobv:b1570-opus4-51112 UR - https://berlinschoolofeconomics.de/insights/bse-discussion-papers U6 - https://doi.org/10.48462/opus4-5111 ET - No. 27 ER -