EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Early prediction and risk stratification of ovarian cancer based on clinical data using machine learning approaches

Ting Gui iD, Dongyan Cao iD, Jiaxin Yang iD, Zhenhao Wei iD, Jiatong Xie iD, Wei Wang iD, Yang Xiang iD, Peng Peng iD

Journal of Gynecologic Oncology · 2025

DOI: 10.3802/jgo.2025.36.e53 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Gynecologic Oncology, 2025. Verfasst von Ting Gui und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Obstetrics and Gynecology, National Clinical Research Center for Obstetric and Gynecologic Diseases, State Key Laboratory of Complex Se…. Hauptthemen laut MEDLINE: Ovarian Neoplasms, Machine Learning. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: National High Level Hospital Clinical Research Funding.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

OBJECTIVE: Our study was aimed to construct a predictive model to advance ovarian cancer diagnosis by machine learning. METHODS: A retrospective analysis of patients with pelvic/adnexal/ovarian mass was performed. Potential features related to ovarian cancer were obtained as many as possible. The optimal machine learning algorithm was selected among six candidates through 5-fold cross validation. Top 20 features having the most powerful predictive significance were ranked by Shapley Additive Interpretation (Shap) method. Clinical validation was further performed to confirm whether our model could advance diagnosis of ovarian cancer. RESULTS: A total of 9,799 patients were collected. The inclusion criteria included age >18 years old, the first diagnosis being pelvic/adnexal/ovarian mass of undetermined significance, and pathological report indispensable. Four hundred and thirty-eight dimensional features were obtained after filtration. LightGBM showed the best performance with accuracy 88%. Among the top 20 features, 55% belonged to laboratory test report, 35% came from imaging examination report, and 10% were attributed to basic demographics and main symptom. Age, CA125, and risk of ovarian malignancy algorithm were the top three. Our predictive model performed stably in testing and clinical validation datasets, and was found to advance the diagnosis of ovarian cancer about 17 days before clinical pathological examination. CONCLUSION: LightGBM was the optimal algorithm for our predictive model with accuracy of 88%. Laboratory test and imaging examination played essential roles in diagnosing ovarian cancer. Our model could advance the diagnosis of ovarian cancer before clinical pathological examination.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Ovarian NeoplasmsMachine LearningHumansFemaleRetrospective StudiesMiddle AgedRisk AssessmentAdultCA-125 AntigenAgedAlgorithmsPredictive Value of Tests

Stichwörter der Autor:innen

Machine LearningMachine Prediction MethodsOvarian CancerPredictive Learning ModelsRisk Factors

Substanzen

CA-125 Antigen

Autor:innen und Institutionen

  • Department of Obstetrics and Gynecology, National Clinical Research Center for Obstetric and Gynecologic Diseases, State Key Laboratory of Complex Severe and Rare Diseases, Peking Union Medical College Hospital, Chinese…
  • Goodwill Hessian Health Technology Co. Ltd, Beijing, People's Republic of China.

ORCID-Profile: Ting Gui, Dongyan Cao, Jiaxin Yang, Zhenhao Wei, Jiatong Xie, Wei Wang, Yang Xiang, Peng Peng

Förderung

  • National High Level Hospital Clinical Research Funding

Zitieren

APA

Gui, T., Cao, D., Yang, J., Wei, Z., Xie, J., Wang, W., Xiang, Y., & Peng, P. (2025). Early prediction and risk stratification of ovarian cancer based on clinical data using machine learning approaches. Journal of Gynecologic Oncology. https://doi.org/10.3802/jgo.2025.36.e53

Vancouver

Gui T, Cao D, Yang J, Wei Z, Xie J, Wang W, et al. Early prediction and risk stratification of ovarian cancer based on clinical data using machine learning approaches. Journal of Gynecologic Oncology. 2025. doi:10.3802/jgo.2025.36.e53

BibTeX
@article{Gui2025,
  author = {Gui, Ting and Cao, Dongyan and Yang, Jiaxin and Wei, Zhenhao and Xie, Jiatong and Wang, Wei and Xiang, Yang and Peng, Peng},
  title = {Early prediction and risk stratification of ovarian cancer based on clinical data using machine learning approaches},
  journal = {Journal of Gynecologic Oncology},
  year = {2025},
  doi = {10.3802/jgo.2025.36.e53}
}
Kostenlos starten →