Individualized embryo selection strategy developed by stacking machine learning model for better in vitro fertilization outcomes: an application study

Table 1 Baseline characteristics of the variables included in the training and validation data sets

Features	Training set (n = 5828)	Validation set (n = 3383)
Patient composition
SET	5264	3082
DET	564	301
Age*, y	30.46 ± 4.20	30.70 ± 3.94
Attempt times of IVF*	0.95 ± 0.43	0.78 ± 0.54
Antral follicle count*	13.64 ± 6.13	13.37 ± 6.36
Follicle stimulating hormone*, IU/L	7.59 ± 2.35	7.68 ± 2.79
Luteinizing hormone*, IU/L	4.71 ± 3.26	4.95 ± 6.08
E2 per mature oocyte, pmol/L	309.60 ± 141.26	265.68 ± 133.16
E2 on HCG day*, pmol/L	2810.88 ± 1424.43	2174.64 ± 1046.56
Endometrial Thickness*, mm	11.79 ± 2.40	11.98 ± 2.55
MetaphaseII(M II)*	9.86 ± 4.14	9.25 ± 4.02
2pronucleus(PN)*	6.79 ± 3.35	6.31 ± 3.22
Oocyte Number^a*	11.03 ± 4.45	10.64 ± 4.49
2PN/MII*	0.70 ± 0.19	0.69 ± 0.20
Frozen Sperm	6.0%	6.3%
Male Factor^b
Oligospermia	9.2%	10.3%
Asthenospermia	12.8%	20.0%
Azoospermia	7.1%	9.1%
Female Factor^b
Endometriosis	3.0%	4.4%
Ovulation Disorder	5.9%	7.8%
Unknown	5.2%	12.3%
Sperm Retrieval
Ejaculation	95.2%	95.2%
MESA	0.3%	0.7%
TESA	1.0%	1.3%
PESA	3.5%	2.8%
Stimulation Protocol^b
Agonist Protocol*	71.4%	70.8%
Antagonist Protocol	22.8%	28.5%
Endometrial Type^b
A*	83.3%	85.0%
B	2.0%	0.4%
C*	21.4%	19.7%
Infertility^c
Primary	64.9%	70.4%
Secondary*	35.1%	29.6%
Fertilization Method^b
IVF	72.5%	57.9%
ICSI*	24.5%	34.8%
Embryo Features
Number of Blastomere*	7.93 ± 0.89	8.06 ± 0.93
Fragment^d*	0.37 ± 0.50	0.32 ± 0.48
Equality^e*	0.91 ± 0.95	0.87 ± 0.91

*The selected features after performing feature selection are marked by asterisks
SET single-embryo transfer, DET double-embryo transfer, IVF in vitro fertilization, ICSI intracytoplasmic sperm injection, E2 estradiol, hCG human chorionic gonadotropin, MESA microscopic epididymal sperm aspiration, TESA testicular sperm aspiration, PESA percutaneous epididymal sperm aspiration
^aNumber of oocytes retrieved; ^b for multi-category features, the sum of the proportion for each category may not equal 100% because the missing value exists or another small proportion of category features is not included; ^c infertility is encoded by 0 or 1 if the patient is primary or secondary, respectively; ^d the fragment is encoded by three values: 1 to 3 representing no fragment, 5–15% fragment, and > 15% fragment, respectively; ^e the equality is encoded by five values, 0 to 4, and represent equal, sort of equal, unequal, sort very unequal, and very unequal, respectively.

ISSN: 1477-7827