Predicting a live birth by artificial intelligence incorporating both the blastocyst image and conventional embryo evaluation parameters

Table 2 Discrimination ability of the best classifier of the original neural network architecture comparing the combination method[13]

Patient age (yr)	Accuracy	Sensitivity	Specificity	PPV	NPV	AUC	95%CI of the AUC	Cut-point
AI in this study
All ages	0.743	0.638	0.789	0.573	0.831	0.740	0.681-0.801	0.207
The combination method[13]
All ages	0.721	0.779	0.704	0.400	0.885	0.773	0.655-0.888	0.213
< 35	0.616	0.652	0.592	0.515	0.719	0.655	0.600-0.707	0.388
35-37	0.671	0.786	0.612	0.508	0.849	0.723	0.653-0.793	0.281
38-39	0.732	0.758	0.725	0.455	0.908	0.791	0.693-0.889	0.219
40-41	0.801	0.700	0.816	0.350	0.950	0.806	0.687-0.925	0.142
≥ 42	0.784	1.000	0.773	0.171	1.000	0.888	0.713-1.063	0.037

The number of the training data was 42792 consisted of both a blastocyst image and ten factors of conventional embryo evaluation (CEE). The value of the combination method was a function of multivariate logistic regression with CEE and artificial intelligence for predicting probability for live birth from an image of the blastocyst in patients categorized by age. The optimal cut-point of live birth was the value corresponding to the point with the lowest distance to the upper-left corner of the receiver operator characteristic curve[46]. The accuracies, sensitivities, and specificities were obtained by using cut-points. PPV: Positive predictive value; NPV: Negative predictive value; AUC: Area under the time concentration curve.