Machine learning algorithms in constructing prediction models for assisted reproductive technology (ART) related live birth outcomes
Abstract Currently applicable models for predicting live birth outcomes in patients who received assisted reproductive technology (ART) have methodological or study design limitations that greatly obstruct their dissemination and application. Models suitable for Chinese couples have not yet been ide...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-12-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-024-83781-x |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841559414499180544 |
|---|---|
| author | Junwei Peng Xiaoyujie Geng Yiyue Zhao Zhijin Hou Xin Tian Xinyi Liu Yuanyuan Xiao Yang Liu |
| author_facet | Junwei Peng Xiaoyujie Geng Yiyue Zhao Zhijin Hou Xin Tian Xinyi Liu Yuanyuan Xiao Yang Liu |
| author_sort | Junwei Peng |
| collection | DOAJ |
| description | Abstract Currently applicable models for predicting live birth outcomes in patients who received assisted reproductive technology (ART) have methodological or study design limitations that greatly obstruct their dissemination and application. Models suitable for Chinese couples have not yet been identified. We conducted a retrospective study by using a database includes a total of 11,938 couples who underwent in vitro fertilization (IVF) treatment between January 2015 and December 2022 in a medical institution of southwest China Yunnan province. Multiple candidate predictors were screened out by using the importance scores. Four machine learning (ML) algorithms including random forest, extreme gradient boosting, light gradient boosting machine and binary logistic regression were used to construct prediction models. An initial assessment of the predictive performance was conducted and validated by using cross-validation and bootstrap methods. A total of seven predictors were identified, namely maternal age, duration of infertility, basal follicle-stimulating hormone (FSH), progressive sperm motility, progesterone (P) on HCG day, estradiol (E2) on HCG day, and luteinizing hormone (LH) on HCG day. Of the four predictive models, the random forest model and the logistic regression model were considered to have the optimal performance, with the areas under the receiver operating characteristic curve (AUROC) curves of 0.671 (95% CI 0.630–0.713) and 0.674 (95% CI 0.627–0.720). The Brier scores were 0.183 (95% CI 0.170–0.196) and 0.183 (95% CI 0.170–0.196), respectively. Considering the simplicity of model fitting, we recommend the logistic regression model as the best predictive model for live birth. Furthermore, maternal age, P on HCG day and E2 on HCG day were deemed to have the highest contribution to model prediction. |
| format | Article |
| id | doaj-art-1e8f30a7e52b4cd8831c2d34c71121f3 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-1e8f30a7e52b4cd8831c2d34c71121f32025-01-05T12:30:45ZengNature PortfolioScientific Reports2045-23222024-12-0114111010.1038/s41598-024-83781-xMachine learning algorithms in constructing prediction models for assisted reproductive technology (ART) related live birth outcomesJunwei Peng0Xiaoyujie Geng1Yiyue Zhao2Zhijin Hou3Xin Tian4Xinyi Liu5Yuanyuan Xiao6Yang Liu7Reproductive Medicine Department, Second Affiliated Hospital of Kunming Medical UniversityReproductive Medicine Department, Second Affiliated Hospital of Kunming Medical UniversityReproductive Medicine Department, Second Affiliated Hospital of Kunming Medical UniversityReproductive Medicine Department, Second Affiliated Hospital of Kunming Medical UniversityDivision of Epidemiology and Health Statistics, School of Public Health, Kunming Medical UniversityDivision of Epidemiology and Health Statistics, School of Public Health, Kunming Medical UniversityDivision of Epidemiology and Health Statistics, School of Public Health, Kunming Medical UniversityReproductive Medicine Department, Second Affiliated Hospital of Kunming Medical UniversityAbstract Currently applicable models for predicting live birth outcomes in patients who received assisted reproductive technology (ART) have methodological or study design limitations that greatly obstruct their dissemination and application. Models suitable for Chinese couples have not yet been identified. We conducted a retrospective study by using a database includes a total of 11,938 couples who underwent in vitro fertilization (IVF) treatment between January 2015 and December 2022 in a medical institution of southwest China Yunnan province. Multiple candidate predictors were screened out by using the importance scores. Four machine learning (ML) algorithms including random forest, extreme gradient boosting, light gradient boosting machine and binary logistic regression were used to construct prediction models. An initial assessment of the predictive performance was conducted and validated by using cross-validation and bootstrap methods. A total of seven predictors were identified, namely maternal age, duration of infertility, basal follicle-stimulating hormone (FSH), progressive sperm motility, progesterone (P) on HCG day, estradiol (E2) on HCG day, and luteinizing hormone (LH) on HCG day. Of the four predictive models, the random forest model and the logistic regression model were considered to have the optimal performance, with the areas under the receiver operating characteristic curve (AUROC) curves of 0.671 (95% CI 0.630–0.713) and 0.674 (95% CI 0.627–0.720). The Brier scores were 0.183 (95% CI 0.170–0.196) and 0.183 (95% CI 0.170–0.196), respectively. Considering the simplicity of model fitting, we recommend the logistic regression model as the best predictive model for live birth. Furthermore, maternal age, P on HCG day and E2 on HCG day were deemed to have the highest contribution to model prediction.https://doi.org/10.1038/s41598-024-83781-xInfertilityIn vitro fertilizationClinical prediction modelMachine learningLive birth |
| spellingShingle | Junwei Peng Xiaoyujie Geng Yiyue Zhao Zhijin Hou Xin Tian Xinyi Liu Yuanyuan Xiao Yang Liu Machine learning algorithms in constructing prediction models for assisted reproductive technology (ART) related live birth outcomes Scientific Reports Infertility In vitro fertilization Clinical prediction model Machine learning Live birth |
| title | Machine learning algorithms in constructing prediction models for assisted reproductive technology (ART) related live birth outcomes |
| title_full | Machine learning algorithms in constructing prediction models for assisted reproductive technology (ART) related live birth outcomes |
| title_fullStr | Machine learning algorithms in constructing prediction models for assisted reproductive technology (ART) related live birth outcomes |
| title_full_unstemmed | Machine learning algorithms in constructing prediction models for assisted reproductive technology (ART) related live birth outcomes |
| title_short | Machine learning algorithms in constructing prediction models for assisted reproductive technology (ART) related live birth outcomes |
| title_sort | machine learning algorithms in constructing prediction models for assisted reproductive technology art related live birth outcomes |
| topic | Infertility In vitro fertilization Clinical prediction model Machine learning Live birth |
| url | https://doi.org/10.1038/s41598-024-83781-x |
| work_keys_str_mv | AT junweipeng machinelearningalgorithmsinconstructingpredictionmodelsforassistedreproductivetechnologyartrelatedlivebirthoutcomes AT xiaoyujiegeng machinelearningalgorithmsinconstructingpredictionmodelsforassistedreproductivetechnologyartrelatedlivebirthoutcomes AT yiyuezhao machinelearningalgorithmsinconstructingpredictionmodelsforassistedreproductivetechnologyartrelatedlivebirthoutcomes AT zhijinhou machinelearningalgorithmsinconstructingpredictionmodelsforassistedreproductivetechnologyartrelatedlivebirthoutcomes AT xintian machinelearningalgorithmsinconstructingpredictionmodelsforassistedreproductivetechnologyartrelatedlivebirthoutcomes AT xinyiliu machinelearningalgorithmsinconstructingpredictionmodelsforassistedreproductivetechnologyartrelatedlivebirthoutcomes AT yuanyuanxiao machinelearningalgorithmsinconstructingpredictionmodelsforassistedreproductivetechnologyartrelatedlivebirthoutcomes AT yangliu machinelearningalgorithmsinconstructingpredictionmodelsforassistedreproductivetechnologyartrelatedlivebirthoutcomes |