In this study, most-selective ensemble models are developed for the prediction of the success rate of clinical pregnancy. These models are compared from different aspects of three different types of treatments, IVF/ICSI and IUI.
- Comparison of Accuracy and AUC of Models:
In the first step, the results were achieved by each approach and their criteria in three treatments were compared in terms of accuracy, and AUC as in Figure 1 is shown. Among these models, Bagging and Random Forest accomplished the best mean values of accuracy and AUC for IVF/ICSI procedure, Bagging accuracy (0.74) and AUC (0.79) and Random Forest accuracy (0.72) and AUC (0.80). However, for IUI procedure, Bagging and Random Forest's mean of accuracy is equally 0.85 and Random Forest's mean of AUC is higher than Bagging, it almost gained better results. Overall, it is observed that Random Forest is a suitable model for three treatments.
- Comparison SHAP VALUE of Models:
In the second step, the value of sperm parameters in predicting the success rate of the clinical pregnancy is illustrated based on the best model (Random Forest) from the previous step. In Figure 2, the impact of each feature in predicting the model and their relationship, are shown for each treatment procedure. Notable, in the IUI procedure, sperm parameters (morphology, motility, and count) had significant negative impacts on clinical pregnancy according to the Random Forest model. However, the coefficient of influence of sperm motility on predicting clinical pregnancy has been reported to be positive for some patients having IVF/ICSI procedures, while the morphology and count factors had negative impacts.
- Evaluation of the association between sperm parameters and pregnancy:
In addition, the statistical results related to the association between sperm parameters and pregnancy are illustrated in Figure 3. In this figure, the difference between the values of sperm parameters in successful and unsuccessful pregnancy groups was assessed using a student t-test. The findings revealed that in clinical pregnancies after the IVF/ICSI procedure, there was a significant difference in values of parameters (morphology and count) in the successful and unsuccessful groups. Notable, the morphological parameter was significantly different in both pregnancy outcomes in IUI procedure. In contrast, the count parameter was not considerably different between the successful and unsuccessful groups.
- Comparison of sperm parameters in treatments based on cycles:
Determining a cut-off value for the feature can provide valuable information for gynecologists. In this study, for each of these sperm parameters, a cut-off was computed to derive an evidence-based decision rule. In terms of clinical pregnancy, the optimal count parameter cut-offs were 54 million (p-value:0.02, 95%-CIs:1.05- 2.13) and 35 (p-value: 0.03, 95%-CIs:1.06-2.86) in IVF/ICSI and IUI procedures, respectively. The cut-off point for the morphological parameter in each of the procedures approach was also found to be 30 with a p-value of 0.001. However, no significant cut-off for the motility factor was obtained for the methods.
In Additional, statistical information about sperm parameters in different courses for three methods is provided based on the WHO recommendation 15. From the results obtained in Tables 1 and 2, it can be seen that most of the patients in the three procedures were in the first course of the procedure. Also, the results showed the fact that in the IVF/ICSI groups for most patients in the first and second course of the procedure, sperm parameters are lower than the average set by WHO. However, in the IUI group, sperm parameters report a higher-than-average level (Table 2). Moreover, for patients whose sperm parameters are below average, IVF procedures achieved better results. Especially for the second course of procedure, they gained higher success rates in clinical pregnancies. Furthermore, for patients with sperm parameters above the mean value reported by WHO, the IUI method reached better results and two courses of procedure were more successful.
Table 1: Comparison of sperm parameters in IVF/ICSI procedure based on courses.
Patients (N=599 (
|
IVF/ICSI 1) N=433 (
|
IVF/ICSI 2) N=124(
|
IVF/ICSI 3) N=42 (
|
Spermiogram below Avg (N=29.04%) (CPR=(38/5%),FHR=(30/4%))
|
128
(CPR =37/5%;
FHR =20/3%
|
36
(CPR =100%;
FHR =97/2%
|
10
(CPR =20%;
FHR =20%
|
Spermiogram Avg (N=5)
(CPR =0.0%, FHR =0.0%))
|
3
(CPR =0.0%,
FHR =0.0%)
|
1
(CPR =0.0%,
FHR =0.0%))
|
1
(CPR =0.0%,
FHR =0.0%))
|
Spermiogram above Avg (N=140)
(CPR =22/1%, FHR =18/5%)
|
103
(CPR =22/3%,
FHR =15/53%)
|
26
(CPR =23/7%,
FHR =23.7%)
|
11
(CPR =36.3%,
FHR =36/3%
|
*Spermiogram Average for Sperm Count (10*6) WHO Standard Count is 33-46; Sperm Motility is 38-42; and Sperm Morphology is 30-40. ** CPR as clinical pregnancy rate and FHR as fetal heart rate.
Table 2: Comparison of sperm parameters in IUI procedure based on courses.
Patients (N=954)
|
IUI 1 (N=775)
|
IUI 2 (N=150)
|
IUI 3 (N=29)
|
Spermiogram below Avg(N=0.9%)
(CPR =0.0%, FHR =0.0%))
|
8
(CPR =0.0%,
FHR =0.0%))
|
1
(CPR =0.0%,
FHR =0.0%))
|
0
(CPR =0.0%,
FHR =0.0%))
|
Spermiogram Avg (N=0.3%)
(CPR =1(33/3), FHR =1(33/3))
|
2
(CPR =33/3%,
FHR =33/3%)
|
1
(CPR =33/3%,
FHR=33/3%)
|
0
(CPR =33/3%,
FHR =33/3%)
|
Spermiogram above Avg (N=52.3%)
(CPR =69 (13/82); FHR =61 (12/2))
|
409
(CPR =13/93%;
FHR =12/22%
|
76
(CPR =15/78%;
FHR =14/47%)
|
14
(CPR =0.0%,
FHR =0.0%))
|
*Spermiogram Average for Sperm Count (10*6) WHO Standard Count is 33-46; Sperm Motility is 38-42; and Sperm Morphology is 30-40.
** CPR as clinical pregnancy rate and FHR as fetal heart rate.
Analysis of sperm parameters based on infertility diagnosis for IVF/ICSI and IUI procedures:
Since infertility is strongly related to sperm parameters, we performed this analysis for IVF/ICSI and IUI groups by examining the successful and unsuccessful pregnancy groups. The results obtained from Figure 4 shows that in the IVF/ICSI procedure, only the values of morphology parameter in terms of clinical pregnancy had a significant difference between the successful and unsuccessful groups. However, in the two groups of unexplained infertility and female infertility, this difference was also significant in terms of clinical pregnancy. Furthermore, in the IUI procedure, only for patients with female infertility, the morphology factor in both types of pregnancy is significantly different between successful and unsuccessful groups.