A Population-Specific Ensemble Machine Learning Model for Predicting Borderline or Malignancy Risk of Ovarian Masses in Macao: A Multicenter Retrospective Study.
Background: Preoperative discrimination between benign and malignant ovarian tumors is important. The applicability of published prediction tools may be limited across different health systems. We aim to develop a machine learning model specifically for Macao's population to predict the borderline o...
| Publicado en: | Clinical Medicine Insights: Oncology Vol. 19; pp. 1 - 14 |
|---|---|
| Autores principales: | , , , , , , , , |
| Formato: | research tables/charts Journal Article |
| Publicado: |
Sage Publications Inc.
11/3/2025
|
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=189287375&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 189287375 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 11795549 B3KT jtl: Clinical Medicine Insights: Oncology issn: 11795549 maglogo: Y pubinfo: dt: 11/3/2025 vid: 19 pid: 344 pub: Sage Publications Inc. place: Thousand Oaks, California artinfo: ui: 189287375 189287375 189287375 10.1177/11795549251388312 189287375 ppf: 1 ppct: 13 formats: fmt: – @attributes: type: T – @attributes: type: P tig: atl: A Population-Specific Ensemble Machine Learning Model for Predicting Borderline or Malignancy Risk of Ovarian Masses in Macao: A Multicenter Retrospective Study. aug: au: Chio, Chan-Fong Sin, Lai-Fong Loi, Hoi-Sun Cheang, Hou-Kong Chan, I-San Hong, Shunjia Fong, Wai-Ieng Chan, Kin-Iong Wong, Sio-In affil: Department of Anatomical Pathology, Conde de São Januário Hospital, Macao SAR, China sug: subj: Prediction Models Ovarian Neoplasms Risk Factors Risk Assessment Ovarian Neoplasms Classification Boosting Machine Learning Algorithms Human Macao Multicenter Studies Retrospective Design Record Review Hospitals Macao Oophorectomy Cystectomy Ovarian Neoplasms Surgery Age Factors Menopause Ultrasonography Diagnostic Tests, Routine Female Prospective Studies Blood Cell Count Tumor Markers, Biological Blood Logistic Regression Support Vector Machine Decision Trees Random Forest Mann-Whitney U Test Chi Square Test Fisher's Exact Test Sensitivity and Specificity Predictive Value of Tests ROC Curve Descriptive Statistics Data Analysis Software Platelet Lymphocyte Ratio Neutrophil Lymphocyte Ratio Monocyte Lymphocyte Ratio Female ab: Background: Preoperative discrimination between benign and malignant ovarian tumors is important. The applicability of published prediction tools may be limited across different health systems. We aim to develop a machine learning model specifically for Macao's population to predict the borderline or malignancy risk of ovarian masses using routinely available clinical data in Macao's health system. Methods: The study cohorts were derived from 2 major hospitals in Macao, including 496 patients who underwent oophorectomy or cystectomy for ovarian masses at CHCSJ between January 2014 and December 2023, along with a simulated prospective cohort of 95 patients from CHCSJ between January 2024 and November 2024, and an external validation cohort of 61 patients from KWH between January 2020 and September 2024. Patients' clinical information, ultrasound features, and laboratory test results before initial treatment were collected. LASSO regression was used for feature selection, and classifiers were developed using various machine learning algorithms. The predictions were compared with postoperative pathological diagnoses. The predictive performance was also compared with the RMI-4. Results: Age, menopausal status, 5 ultrasound features, and 7 laboratory tests were identified as predictors of borderline and malignant ovarian tumors. An ensemble learning model based on a voting classifier was selected as the final model. Our model outperformed RMI-4 in the internal test set, simulated prospective cohort, and external validation cohort, achieving an area under the curve (AUC) of 0.923–0.951 (vs 0.810–0.868, P <.05). Decision curve analysis demonstrated superior clinical utility, and SHAP analysis confirmed its interpretability. Conclusions: We propose a machine learning model targeting Macao's population for predicting the borderline or malignancy risk of ovarian masses. Our model is accurate, low-cost, easily accessible, and interpretable. On the basis of no workflow changes, machine learning techniques can maximize the predictive potential of routinely available clinical data in a specific health system. pubtype: Academic Journal doctype: research tables/charts Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|