Using machine learning to predict patients with polycystic ovary disease in Chinese women
Objective: With an estimated global frequency ranging from5 % to 21 %, polycystic ovary syndrome (PCOS) is one of the most prevalent hormonal disorders. There are many factors found to be related to PCOS. However, most of these researches used traditional methods such as multiple logistic regression...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-01-01
|
| Series: | Taiwanese Journal of Obstetrics & Gynecology |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1028455924002791 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841553928093696000 |
|---|---|
| author | Chen-Yu Wang Dee Pei Chun-Kai Wang Jyun-Cheng Ke Siou-Ting Lee Ta-Wei Chu Yao-Jen Liang |
| author_facet | Chen-Yu Wang Dee Pei Chun-Kai Wang Jyun-Cheng Ke Siou-Ting Lee Ta-Wei Chu Yao-Jen Liang |
| author_sort | Chen-Yu Wang |
| collection | DOAJ |
| description | Objective: With an estimated global frequency ranging from5 % to 21 %, polycystic ovary syndrome (PCOS) is one of the most prevalent hormonal disorders. There are many factors found to be related to PCOS. However, most of these researches used traditional methods such as multiple logistic regression (LR). Nowadays, machine learning (Mach-L) emerges as a new method and can be used in medical researches. In the present study, there were two goals: 1. Compare the accuracy of five alternative Mach-L techniques with that of conventional LR. 2. Use Mach-L to forecast PCOS and prioritize the risk factors. Materials and methods: Totally, 170 PCOS patients and 950 control participants were included. We collected information on demographics, biochemistry, and lifestyle. PCOS was identified using Rotterdam criteria. Random Forest (RF), stochastic gradient boosting (SGB), multivariate adaptive regression splines (MARS), extreme gradient boosting (XGBoost), and gradient boosting with categorical features support (CatBoost) are five Mach-L algorithms that were used. Models with lower estimation errors were better. Results: By using t-test, we found subjects with PCOS were younger, glutamic oxaloacetic transaminase (GOT), glutamic pyruvic transaminase (GPT), γ-Glutamyl transferase (γ-GT), Triglyceride (TG), and educational levels were higher. All the five Mach-L methods had lower estimation errors compared to LR. The average of the AUC derived from Mach-L was mean AUC of 0.6669, higher than the that of LR (0.5908). Finally, age, TG, GPT, white blood cell count (WBC), uric acid (UA), and platelet (Plt) were the six most important risk factors selected by Mach-L. Conclusion: Mach-L methods overtook conventional LR and age was the most significant factor, followed by TG, GPT, WBC, UA, and Plt in a cohort of Chinese women. |
| format | Article |
| id | doaj-art-e544d3dbebe94751a20cb324c1d1b688 |
| institution | Kabale University |
| issn | 1028-4559 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Taiwanese Journal of Obstetrics & Gynecology |
| spelling | doaj-art-e544d3dbebe94751a20cb324c1d1b6882025-01-09T06:12:50ZengElsevierTaiwanese Journal of Obstetrics & Gynecology1028-45592025-01-016416875Using machine learning to predict patients with polycystic ovary disease in Chinese womenChen-Yu Wang0Dee Pei1Chun-Kai Wang2Jyun-Cheng Ke3Siou-Ting Lee4Ta-Wei Chu5Yao-Jen Liang6Department of Obstetrics and Gynecology, Tri-Service General Hospital, National Defense Medical Center, Taipei, Taiwan; Graduate Institute of Applied Science and Engineering, Fu Jen Catholic University, New Taipei City, TaiwanDepartment of Medicine, Medical School, Fu Jen Catholic University, Department of Endocrinology and Metabolism, Fu Jen Catholic University Hospital, New Taipei City, TaiwanDepartment of Obstetrics and Gynecology, Zuoying Branch of Kaohsiung Armed Forces General Hospital, Kaohsiung, TaiwanDepartment of Obstetrics and Gynecology, Tri-Service General Hospital, National Defense Medical Center, Taipei, TaiwanDepartment of Obstetrics and Gynecology, Tri-Service General Hospital, National Defense Medical Center, Taipei, Taiwan; Department of Obstetrics and Gynecology, Taoyuan Armed Forces General Hospital, Taoyuan, TaiwanDepartment of Obstetrics and Gynecology, Tri-Service General Hospital, National Defense Medical Center, Taipei, Taiwan; MJ Health Research Foundation, Taipei, TaiwanGraduate Institute of Applied Science and Engineering, Fu Jen Catholic University, New Taipei City, Taiwan; Corresponding author. Department of Life Science, Graduate Institute of Applied Science and Engineering, Fu-Jen Catholic University, No. 510, Zhongzheng Rd., Xinzhuang Dist., New Taipei City, 24205, Taiwan.Objective: With an estimated global frequency ranging from5 % to 21 %, polycystic ovary syndrome (PCOS) is one of the most prevalent hormonal disorders. There are many factors found to be related to PCOS. However, most of these researches used traditional methods such as multiple logistic regression (LR). Nowadays, machine learning (Mach-L) emerges as a new method and can be used in medical researches. In the present study, there were two goals: 1. Compare the accuracy of five alternative Mach-L techniques with that of conventional LR. 2. Use Mach-L to forecast PCOS and prioritize the risk factors. Materials and methods: Totally, 170 PCOS patients and 950 control participants were included. We collected information on demographics, biochemistry, and lifestyle. PCOS was identified using Rotterdam criteria. Random Forest (RF), stochastic gradient boosting (SGB), multivariate adaptive regression splines (MARS), extreme gradient boosting (XGBoost), and gradient boosting with categorical features support (CatBoost) are five Mach-L algorithms that were used. Models with lower estimation errors were better. Results: By using t-test, we found subjects with PCOS were younger, glutamic oxaloacetic transaminase (GOT), glutamic pyruvic transaminase (GPT), γ-Glutamyl transferase (γ-GT), Triglyceride (TG), and educational levels were higher. All the five Mach-L methods had lower estimation errors compared to LR. The average of the AUC derived from Mach-L was mean AUC of 0.6669, higher than the that of LR (0.5908). Finally, age, TG, GPT, white blood cell count (WBC), uric acid (UA), and platelet (Plt) were the six most important risk factors selected by Mach-L. Conclusion: Mach-L methods overtook conventional LR and age was the most significant factor, followed by TG, GPT, WBC, UA, and Plt in a cohort of Chinese women.http://www.sciencedirect.com/science/article/pii/S1028455924002791Machine learningLogistic regressionPolycystic ovary syndrome |
| spellingShingle | Chen-Yu Wang Dee Pei Chun-Kai Wang Jyun-Cheng Ke Siou-Ting Lee Ta-Wei Chu Yao-Jen Liang Using machine learning to predict patients with polycystic ovary disease in Chinese women Taiwanese Journal of Obstetrics & Gynecology Machine learning Logistic regression Polycystic ovary syndrome |
| title | Using machine learning to predict patients with polycystic ovary disease in Chinese women |
| title_full | Using machine learning to predict patients with polycystic ovary disease in Chinese women |
| title_fullStr | Using machine learning to predict patients with polycystic ovary disease in Chinese women |
| title_full_unstemmed | Using machine learning to predict patients with polycystic ovary disease in Chinese women |
| title_short | Using machine learning to predict patients with polycystic ovary disease in Chinese women |
| title_sort | using machine learning to predict patients with polycystic ovary disease in chinese women |
| topic | Machine learning Logistic regression Polycystic ovary syndrome |
| url | http://www.sciencedirect.com/science/article/pii/S1028455924002791 |
| work_keys_str_mv | AT chenyuwang usingmachinelearningtopredictpatientswithpolycysticovarydiseaseinchinesewomen AT deepei usingmachinelearningtopredictpatientswithpolycysticovarydiseaseinchinesewomen AT chunkaiwang usingmachinelearningtopredictpatientswithpolycysticovarydiseaseinchinesewomen AT jyunchengke usingmachinelearningtopredictpatientswithpolycysticovarydiseaseinchinesewomen AT sioutinglee usingmachinelearningtopredictpatientswithpolycysticovarydiseaseinchinesewomen AT taweichu usingmachinelearningtopredictpatientswithpolycysticovarydiseaseinchinesewomen AT yaojenliang usingmachinelearningtopredictpatientswithpolycysticovarydiseaseinchinesewomen |