A machine learning algorithm can optimize the day of trigger to improve in vitro fertilization outcomes.

OBJECTIVE: To determine whether a machine learning causal inference model can optimize trigger injection timing to maximize the yield of fertilized oocytes (2PNs) and total usable blastocysts for a given cohort of stimulated follicles. DESIGN: Descriptive and comparative study of new technology. SETTING: Tertiary academic medical center. PATIENT(S): Patients undergoing IVF with intracytoplasmic sperm injection from 2008 to 2019 (n = 7,866). INTERVENTION(S): Causal inference was performed with the use of a T-learner. Bagged decision trees were used to perform inference. The decision was framed as either triggering on that day or waiting another day. All patient characteristics and stimulation parameters on a given day were used to determine the recommendation. MAIN OUTCOME MEASURE(S): Average outcome improvement in total 2PNs and usable blastocysts compared with the physician's decision. RESULT(S): For evaluation of average outcome improvement on 2PNs, the benefit of following the model's recommendation was 3.015 (95% CI 2.626, 3.371) more 2PNs. For total usable blastocysts, the benefit was 1.515 (95% CI 1.134, 1.871) more usable blastocysts. Given that the physicians-model agreement was 52.57% and 61.89%, respectively, algorithm-assisted trigger decisions yield, on average, 1.430 more 2PNs and 0.577 more total usable blastocysts per stimulation. The most important features weighted in the model's decision were the number of follicles 16-20 mm in diameter, the number of follicles 11-15 mm in diameter, and estradiol level, in that order. CONCLUSION(S): The use of this machine learning algorithm to optimize trigger injection timing may lead to a significant increase in the number of 2PNs and total usable blastocysts obtained from an IVF stimulation cycle when compared with physician decisions. Future research is required to confirm these findings prospectively.

Changing stimulation protocol on repeat conventional ovarian stimulation cycles does not lead to improved laboratory outcomes.

OBJECTIVE: To evaluate whether physicians' choice of ovarian stimulation protocol is associated with laboratory outcomes. DESIGN: Retrospective cohort study. SETTING: Single academic center. PATIENT(S): The subjects were 4,458 patients who completed more than one in vitro fertilization ovarian stimulation cycle within 1 year. On second stimulation, 49% repeated the same protocol and 51% underwent a different one. INTERVENTION(S): Estradiol priming antagonist, antagonist +/- oral contraceptive pill priming, long luteal protocol, Lupron (Lupron [AbbVie Inc, North Chicago, IL]) stop protocol, and flare were compared. Logistic or linear regression with cluster robust standard errors to account for covariates and paired data was used. MAIN OUTCOME MEASURE(S): Oocytes collected (OC), fertilization rate, blastocyst progression (BP), usable embryos (UE), and euploid rate (ER). RESULT(S): First stimulation outcomes were comparable across all protocols for FR, BP, UE, and ER but were different for OC, after adjustment for covariates. For OC, the effect of switching protocols differed according to the type of the second stimulation. There was improvement in OC if the same stimulation was repeated, except for flare. In addition, there were slight, significant improvements in fertilization rate (difference in values or coefficient of 0.02; 95% confidence interval [CI], 0.004, 0.4) and UE (coefficient 1.25; 95% CI, 0.79, 1.72) when the same stimulation was repeated. There were no changes in BP (coefficient 0.03; 95% CI, -0.01, 0.08) or ER (coefficient 0.01; 95% CI, -0.04, 0.06) when protocols were changed. In a low-BP subgroup, greater improvement was seen when the same protocol was repeated (coefficient 0.03; 95% CI 0.01, 0.04). CONCLUSION(S): There was a slight but significant improvement in laboratory outcomes when the same stimulation protocol was repeated, so careful consideration should be made before switching stimulation protocols for the purpose of improving laboratory outcomes.