EUVIMEDEUVIMED entdecken
VergleichsstudieOpen Access · CC BY 4.0

Comparison of Predictive Models for Keloid Recurrence Based on Machine Learning

Yan Hao, Mengjie Shan, Hao Liu, Yijun Xia, Xinwen Kuang, Kexin Song, Youbin Wang iD

Journal of Cosmetic Dermatology · 2025-02 · 24 (2)

DOI: 10.1111/jocd.70008 ↗

Kurz gefasst

Vergleichsstudie in der Zeitschrift Journal of Cosmetic Dermatology, online erschienen am 07.02.2025. Verfasst von Yan Hao und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Plastic and Cosmetic Surgery, Peking Union Medical College Hospital, Beijing, China. Hauptthemen laut MEDLINE: Postoperative Complications, Recurrence, Keloid, Decision Trees. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Beijing Municipal Commission of Science and Technology, the Clinical Research Special Fund of Peking Union Medical College Hospital.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objectives

To establish, evaluate and compare three recurrence prediction models for keloid patients using machine learning methods.

Methods

We enrolled 301 keloid patients who underwent surgery and postoperative radiotherapy, dividing them into a training set (70%) and a validation set (30%). Three recurrence prediction models were established in the training set: the logistic regression model, the decision tree model, and the random forest model. We then evaluated and compared the performance of these models in the validation set, using metrics such as accuracy, sensitivity, specificity, recall, precision, kappa coefficient, and the area under the ROC curve (AUC).

Results

We developed three machine learning‐based prediction models for keloid recurrence. KAAS, mean arterial pressure levels, postoperative complications, and the proportion of inflammatory cells played crucial roles in these models. The decision tree model outperformed both the random forest and logistic regression models in terms of accuracy, and it also exhibited the highest overall precision. Regarding AUC, logistic regression performed the best, followed by random forest and decision trees.

Conclusions

This study established three prediction models for keloid recurrence using machine learning techniques, highlighting the significance of KAAS, blood pressure levels, postoperative complications, and inflammatory cell proportions. When compared from various dimensions, the logistic regression model demonstrated the most favorable prognostic performance in terms of AUC.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Postoperative ComplicationsRecurrenceKeloidDecision TreesPredictive Learning ModelsPrognosisROC CurveMachine LearningHumansMaleFemaleAdolescentAdultMiddle Aged

Stichwörter der Autor:innen

keloidmachine learningprediction modelrecurrencerisk factors

Autor:innen und Institutionen

  • Department of Plastic and Cosmetic Surgery, Peking Union Medical College Hospital, Beijing, China.
  • Peking Union Medical College, Chinese Academy of Medical Sciences, Peking Union Medical College Hospital, Beijing, China.

ORCID-Profile: Youbin Wang

Förderung

  • Beijing Municipal Commission of Science and Technology
  • the Clinical Research Special Fund of Peking Union Medical College Hospital

Zitieren

APA

Hao, Y., Shan, M., Liu, H., Xia, Y., Kuang, X., Song, K., & Wang, Y. (2025). Comparison of Predictive Models for Keloid Recurrence Based on Machine Learning. Journal of Cosmetic Dermatology, 24(2). https://doi.org/10.1111/jocd.70008

Vancouver

Hao Y, Shan M, Liu H, Xia Y, Kuang X, Song K, et al. Comparison of Predictive Models for Keloid Recurrence Based on Machine Learning. Journal of Cosmetic Dermatology. 2025;24(2). doi:10.1111/jocd.70008

BibTeX
@article{Hao2025,
  author = {Hao, Yan and Shan, Mengjie and Liu, Hao and Xia, Yijun and Kuang, Xinwen and Song, Kexin and Wang, Youbin},
  title = {Comparison of Predictive Models for Keloid Recurrence Based on Machine Learning},
  journal = {Journal of Cosmetic Dermatology},
  year = {2025},
  volume = {24},
  number = {2},
  doi = {10.1111/jocd.70008}
}
Kostenlos starten →