Academic Journal
Predicting polycystic ovary syndrome with machine learning algorithms from electronic health records.
| Τίτλος: | Predicting polycystic ovary syndrome with machine learning algorithms from electronic health records. |
|---|---|
| Συγγραφείς: | Zad Z; Division of Systems Engineering, Center for Information and Systems Engineering (CISE), Boston University, Brookline, MA, United States., Jiang VS; Division of Reproductive Endocrinology and Infertility, Department of Obstetrics and Gynecology, Massachusetts General Hospital, Boston, MA, United States., Wolf AT; Icahn School of Medicine at Mount Sinai, New York, NY, United States., Wang T; Division of Systems Engineering, Center for Information and Systems Engineering (CISE), Boston University, Brookline, MA, United States., Cheng JJ; Department of Biostatistics and Medical Informatics, University of Wisconsin, Madison, WI, United States., Paschalidis IC; Division of Systems Engineering, Center for Information and Systems Engineering (CISE), Boston University, Brookline, MA, United States.; Department of Electrical & Computer Engineering, Department of Biomedical Engineering, and Faculty for Computing & Data Sciences, Boston University, Boston, MA, United States., Mahalingaiah S; Division of Reproductive Endocrinology and Infertility, Department of Obstetrics and Gynecology, Massachusetts General Hospital, Boston, MA, United States.; Department of Environmental Health, Harvard T. H. Chan School of Public Health, Boston, MA, United States. |
| Πηγή: | Frontiers in endocrinology [Front Endocrinol (Lausanne)] 2024 Jan 30; Vol. 15, pp. 1298628. Date of Electronic Publication: 2024 Jan 30 (Print Publication: 2024). |
| Τύπος έκδοσης: | Journal Article; Research Support, N.I.H., Extramural; Research Support, U.S. Gov't, Non-P.H.S.; Research Support, Non-U.S. Gov't |
| Γλώσσα: | English |
| Στοιχεία περιοδικού: | Publisher: Frontiers Research Foundation] Country of Publication: Switzerland NLM ID: 101555782 Publication Model: eCollection Cited Medium: Print ISSN: 1664-2392 (Print) Linking ISSN: 16642392 NLM ISO Abbreviation: Front Endocrinol (Lausanne) Subsets: MEDLINE |
| Imprint Name(s): | Original Publication: [Lausanne : Frontiers Research Foundation] |
| Ιατρικοί όροι (MeSH): | Polycystic Ovary Syndrome*/diagnosis, Humans ; Female ; Retrospective Studies ; Artificial Intelligence ; Electronic Health Records ; Luteinizing Hormone ; Algorithms ; Machine Learning |
| Περίληψη: | Introduction: Predictive models have been used to aid early diagnosis of PCOS, though existing models are based on small sample sizes and limited to fertility clinic populations. We built a predictive model using machine learning algorithms based on an outpatient population at risk for PCOS to predict risk and facilitate earlier diagnosis, particularly among those who meet diagnostic criteria but have not received a diagnosis. Methods: This is a retrospective cohort study from a SafetyNet hospital's electronic health records (EHR) from 2003-2016. The study population included 30,601 women aged 18-45 years without concurrent endocrinopathy who had any visit to Boston Medical Center for primary care, obstetrics and gynecology, endocrinology, family medicine, or general internal medicine. Four prediction outcomes were assessed for PCOS. The first outcome was PCOS ICD-9 diagnosis with additional model outcomes of algorithm-defined PCOS. The latter was based on Rotterdam criteria and merging laboratory values, radiographic imaging, and ICD data from the EHR to define irregular menstruation, hyperandrogenism, and polycystic ovarian morphology on ultrasound. Results: We developed predictive models using four machine learning methods: logistic regression, supported vector machine, gradient boosted trees, and random forests. Hormone values (follicle-stimulating hormone, luteinizing hormone, estradiol, and sex hormone binding globulin) were combined to create a multilayer perceptron score using a neural network classifier. Prediction of PCOS prior to clinical diagnosis in an out-of-sample test set of patients achieved an average AUC of 85%, 81%, 80%, and 82%, respectively in Models I, II, III and IV. Significant positive predictors of PCOS diagnosis across models included hormone levels and obesity; negative predictors included gravidity and positive bHCG. Conclusion: Machine learning algorithms were used to predict PCOS based on a large at-risk population. This approach may guide early detection of PCOS within EHR-interfaced populations to facilitate counseling and interventions that may reduce long-term health consequences. Our model illustrates the potential benefits of an artificial intelligence-enabled provider assistance tool that can be integrated into the EHR to reduce delays in diagnosis. However, model validation in other hospital-based populations is necessary. (Copyright © 2024 Zad, Jiang, Wolf, Wang, Cheng, Paschalidis and Mahalingaiah.) |
| Competing Interests: | The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest. |
| Σχόλια: | Update of: medRxiv. 2023 Oct 01:2023.07.27.23293255. doi: 10.1101/2023.07.27.23293255.. (PMID: 37577593) |
| References: | Fertil Res Pract. 2019 Dec 01;5:13. (PMID: 31827874) Clin Endocrinol (Oxf). 2019 Oct;91(4):544-552. (PMID: 31301251) Proc IEEE Inst Electr Electron Eng. 2018 Apr;106(4):690-707. (PMID: 30886441) Clin Epidemiol. 2013 Dec 18;6:1-13. (PMID: 24379699) Front Endocrinol (Lausanne). 2023 Sep 18;14:1106625. (PMID: 37790605) Fertil Steril. 2021 Jan;115(1):229-237. (PMID: 33077236) PLoS One. 2015 Mar 04;10(3):e0118432. (PMID: 25738806) Hum Reprod. 2000 Oct;15(10):2098-102. (PMID: 11006180) Gynecol Endocrinol. 2015;31(8):625-9. (PMID: 26190534) Fertil Steril. 2009 Feb;91(2):456-88. (PMID: 18950759) Front Endocrinol (Lausanne). 2022 Jan 12;12:799871. (PMID: 35095766) Metabolism. 2018 Sep;86:33-43. (PMID: 29024702) Fertil Steril. 2004 Jan;81(1):19-25. (PMID: 14711538) Obes Rev. 2019 Feb;20(2):339-352. (PMID: 30339316) J Am Med Inform Assoc. 2022 Jun 14;29(7):1191-1199. (PMID: 35438796) Stat Methods Med Res. 2019 Dec;28(12):3667-3682. (PMID: 30474497) J Clin Endocrinol Metab. 2004 Jun;89(6):2745-9. (PMID: 15181052) J Clin Endocrinol Metab. 2020 Jun 1;105(6):. (PMID: 31917831) J Clin Endocrinol Metab. 2017 Feb 1;102(2):604-612. (PMID: 27906550) Hum Reprod Update. 2020 Nov 1;26(6):942-960. (PMID: 32995872) Eur J Radiol Open. 2019 Jun 05;6:206-211. (PMID: 31194104) Clin Endocrinol (Oxf). 2019 Jan;90(1):162-169. (PMID: 30339716) J Clin Endocrinol Metab. 2022 Jan 18;107(2):575-585. (PMID: 34546364) J Am Med Inform Assoc. 2021 Jan 15;28(1):155-166. (PMID: 33164082) Hum Reprod Update. 2014 Sep-Oct;20(5):748-58. (PMID: 24688118) J Diabetes Metab Disord. 2018 Nov 13;17(2):277-285. (PMID: 30918863) Hum Reprod. 2015 Sep;30(9):2222-33. (PMID: 26202922) Front Endocrinol (Lausanne). 2022 Mar 17;13:821368. (PMID: 35370993) Reprod Biol Endocrinol. 2015 Oct 29;13:116. (PMID: 26510685) |
| Grant Information: | R01 GM135930 United States GM NIGMS NIH HHS |
| Contributed Indexing: | Keywords: artificial intelligence; disease prediction; machine learning; polycystic ovary syndrome (PCOS); predictive model |
| Substance Nomenclature: | 9002-67-9 (Luteinizing Hormone) |
| Entry Date(s): | Date Created: 20240215 Date Completed: 20240216 Latest Revision: 20240305 |
| Update Code: | 20260130 |
| PubMed Central ID: | PMC10866556 |
| DOI: | 10.3389/fendo.2024.1298628 |
| PMID: | 38356959 |
| Βάση Δεδομένων: | MEDLINE |
καταχωρήστε σχόλιο πρώτοι!