EUVIMEDEUVIMED entdecken
Validierungsstudie

Development and validation of a machine learning model to predict moderate-to-severe cancer-related fatigue in breast cancer

Zhen Liu, Guoshuang Shen, Miaozhou Wang, Jiabin Wang, Yongxin Li, Jiuda Zhao

Supportive Care in Cancer · 2026-01 · 34 (1)

DOI: 10.1007/s00520-025-10258-6 ↗

Kurz gefasst

Validierungsstudie in der Zeitschrift Supportive Care in Cancer, online erschienen am 16.12.2025. Verfasst von Zhen Liu und 5 weiteren Autor:innen. Beteiligte Einrichtung: Research Center for High Altitude Medicine, Key Laboratory of High Altitude Medicine (Ministry of Education), Key Laboratory of Application and Found…. Hauptthemen laut MEDLINE: Machine Learning, Breast Neoplasms, Fatigue, Risk Assessment. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 37 Literaturangaben. Gefördert von: the “Flagship” Department Construction Project of the Collaboration of Traditional Chinese and Western Medicine, Office of the Health Commission of Qinghai Pro….

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

PURPOSE: This study aimed to establish and validate a machine learning model for predicting moderate-to-severe cancer-related fatigue (CRF) 2 years after completion of anti-tumor therapy in breast cancer patients. METHODS: Clinical and laboratory data from 183 patients were retrospectively collected. Candidate predictors were screened using multivariate logistic regression, and seven algorithms-logistic regression, decision tree, random forest, support vector machine, extreme gradient boosting (XGBoost), k-nearest neighbor, and naïve Bayes-were constructed in the training cohort and validated in the testing cohort. Model performance was assessed by discrimination, calibration, and decision curve analysis. RESULTS: The 2-year incidence of moderate-to-severe CRF was 54.0%. Eight independent predictors were identified, including age, body mass index, histological grade, menopausal status, hemoglobin, platelet count, neutrophil count, and systemic immune-inflammation index. Models built on these features demonstrated variable performance, with XGBoost showing the most favorable balance. It achieved an AUC of 0.983 in the training set and 0.766 in the validation set, with robust accuracy, sensitivity, and specificity. Calibration plots indicated good agreement between predicted and observed risks, while decision curve analysis confirmed higher net clinical benefit across a wide range of thresholds. CONCLUSION: The XGBoost-based model provided reliable long-term CRF risk prediction, supporting early identification of high-risk patients and informing personalized survivorship care.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningBreast NeoplasmsFatigueRisk AssessmentSeverity of Illness IndexIncidenceCancer SurvivorsSensitivity and SpecificityHumansFemaleRetrospective StudiesRisk FactorsAge FactorsNeoplasm GradingMenopauseAdultMiddle Aged

Stichwörter der Autor:innen

Breast cancerCancer-related fatigueMachine learningPredictive model

Autor:innen und Institutionen

  • Research Center for High Altitude Medicine, Key Laboratory of High Altitude Medicine (Ministry of Education), Key Laboratory of Application and Foundation for High Altitude Medicine Research in Qinghai Province (Qinghai…
  • Breast Disease Diagnosis and Treatment Center of Qinghai University Affiliated Hospital & Affiliated Cancer Hospital of Qinghai University, Chengxi District, No. 29 Tongren Rd, Xining, 810000, China.
  • Qinghai Provincial People's Hospital, Xining, China.
  • Breast Disease Diagnosis and Treatment Center of Qinghai University Affiliated Hospital & Affiliated Cancer Hospital of Qinghai University, Chengxi District, No. 29 Tongren Rd, Xining, 810000, China. jiudazhao@126.com.

Förderung

  • the “Flagship” Department Construction Project of the Collaboration of Traditional Chinese and Western Medicine, Office of the Health Commission of Qinghai Pro…

Zitieren

APA

Liu, Z., Shen, G., Wang, M., Wang, J., Li, Y., & Zhao, J. (2026). Development and validation of a machine learning model to predict moderate-to-severe cancer-related fatigue in breast cancer. Supportive Care in Cancer, 34(1). https://doi.org/10.1007/s00520-025-10258-6

Vancouver

Liu Z, Shen G, Wang M, Wang J, Li Y, Zhao J. Development and validation of a machine learning model to predict moderate-to-severe cancer-related fatigue in breast cancer. Supportive Care in Cancer. 2026;34(1). doi:10.1007/s00520-025-10258-6

BibTeX
@article{Liu2026,
  author = {Liu, Zhen and Shen, Guoshuang and Wang, Miaozhou and Wang, Jiabin and Li, Yongxin and Zhao, Jiuda},
  title = {Development and validation of a machine learning model to predict moderate-to-severe cancer-related fatigue in breast cancer},
  journal = {Supportive Care in Cancer},
  year = {2026},
  volume = {34},
  number = {1},
  doi = {10.1007/s00520-025-10258-6}
}
Kostenlos starten →