Development of a dynamic machine learning algorithm to predict clinical pregnancy and live birth rate with embryo morphokinetics
Liubin Yang, Mary Peavey, K. Kaskar, Neil Chappell, Lynn Zhu, Darius J. Devlin, Cecilia T. Valdés, Amy K. Schutt, Terri L. Woodard, P.W. Zarutskie, R. Cochran, William E. Gibbons
Abstract
Objective: To evaluate the feasibility of generating a center-specific embryo morphokinetic algorithm by time-lapse microscopy to predict clinical pregnancy rates. Design: A retrospective cohort analysis. Setting: Academic fertility clinic in a tertiary hospital setting. Patients: Patients who underwent in vitro fertilization with embryos that underwent EmbryoScope time-lapse microscopy and subsequent transfer between 2014 and 2018. Interventions: None. Main Outcome Measures: Clinical pregnancy. Results: =.356). Other clusters had pregnancy rates of 51%-60%. Conclusions: This study shows the feasibility of a clinic-specific, noninvasive embryo morphokinetic simple machine learning model to predict clinical pregnancy rates.