EUVIMEDEUVIMED entdecken
Systematische Übersicht

Clinical challenges in the adaptation of AI predictive models in radiation oncology for gynaecological cancer: a systematic review by the radiation oncology-AI MITO group

Amelia Barcellini, Savino Cilla, Michele Aquilano, Paolo Bonome, Alexandra Charalampopoulou, Gaia Giannone, Valentina Lombardo, Federico Mastroleo, Maurizio Polano, Ivano Raimondo, Sandro Pignata, Gabriella Macchia und 1 weitere

La radiologia medica · 25.09.2026 · 131 (10) · 1923-1934

DOI: 10.1007/s11547-026-02272-3 ↗

Kurz gefasst

Systematische Übersicht in der Zeitschrift La radiologia medica, online erschienen am 25.09.2026. Verfasst von Amelia Barcellini und 12 weiteren Autor:innen. Beteiligte Einrichtung: CNAO National Center for Oncological Hadrontherapy, Radiation Oncology Unit, Clinical Department, 27100, Pavia, Italy. Hauptthemen laut MEDLINE: Genital Neoplasms, Female, Predictive Learning Models, Radiation Oncology. Die Arbeit nennt 70 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

INTRODUCTION: The Radiation Oncology-AI MITO group conducted a systematic review to map the current landscape of AI-based predictive modelling in patients with gynaecological malignancies treated with radiotherapy (RT). The aim was to evaluate available evidence, methodological quality, and the clinical applicability of existing models. METHODS: Relevant studies were retrieved from PubMed, EMBASE, and Scopus following PRISMA guidelines. Methodological quality was assessed using the Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modelling Studies (CHARMS) checklist, while risk of bias and applicability were evaluated using the Prediction Model Risk of Bias Assessment Tool (PROBAST). A total of 1402 records were identified, and 1025 unique studies were screened after duplicate removal. RESULTS: Thirty-one studies (1.1%) met eligibility criteria. Of these, 27 (87.0%) focused on cervical cancer, 2 (6.5%) on uterine tumours, and 2 (6.5%) on mixed gynaecological cohorts. Predictive models addressed clinical outcomes (35.5%), treatment-related toxicities (29.0%), or treatment response (29.0%). Studies incorporated 3-114 predictors, using clinical, dosimetric, and radiomic features, mostly from retrospective datasets. LASSO was the most frequent variable-selection method (25.8%). All studies reported internal validation, whereas only two (6.5%) performed external validation. According to CHARMS, 13 studies (41.9%) showed high risk of bias; performance reporting was heterogeneous, commonly limited by small sample sizes and suboptimal predictor selection. CONCLUSIONS: AI-based predictive modelling in gynaecological RT remains constrained by methodological variability, limited external validation, and a lack of clinically deployable tools. Advancing clinical translation requires rigorous model development, transparent reporting, robust validation, and interpretable tools supported by expert consensus.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Genital Neoplasms, FemalePredictive Learning ModelsRadiation OncologyFemaleHumansPrediction Algorithms

Stichwörter der Autor:innen

Artificial intelligenceGynaecological cancerMachine learningPredictive modelsRadiation oncologyRadiotherapy

Autor:innen und Institutionen

  • CNAO National Center for Oncological Hadrontherapy, Radiation Oncology Unit, Clinical Department, 27100, Pavia, Italy.
  • Department of Internal Medicine and Therapeutics, University of Pavia, 27100, Pavia, Italy.
  • Responsible Research Hospital, Medical Physics Unit, Campobasso, Molise, Italy.
  • Radiotherapy Unit, Department of Experimental and Clinical Biomedical Sciences "Mario Serio", Azienda Ospedaliero Universitaria Careggi, 50134, Florence, Italy.
  • Radiation Oncology Unit, Responsible Research Hospital, 86100, Campobasso, Molise, Italy.
  • CNAO National Center for Oncological Hadrontherapy, Radiobiology Unit, 27100, Pavia, Italy. alexandra.charalampopoulou@cnao.it.

Zitieren

APA

Barcellini, A., Cilla, S., Aquilano, M., Bonome, P., Charalampopoulou, A., Giannone, G., Lombardo, V., Mastroleo, F., Polano, M., Raimondo, I., Pignata, S., Macchia, G., & Pezzulla, D. (2026). Clinical challenges in the adaptation of AI predictive models in radiation oncology for gynaecological cancer: a systematic review by the radiation oncology-AI MITO group. La radiologia medica, 131(10), 1923-1934. https://doi.org/10.1007/s11547-026-02272-3

Vancouver

Barcellini A, Cilla S, Aquilano M, Bonome P, Charalampopoulou A, Giannone G, et al. Clinical challenges in the adaptation of AI predictive models in radiation oncology for gynaecological cancer: a systematic review by the radiation oncology-AI MITO group. La radiologia medica. 2026;131(10):1923-1934. doi:10.1007/s11547-026-02272-3

BibTeX
@article{Barcellini2026,
  author = {Barcellini, Amelia and Cilla, Savino and Aquilano, Michele and Bonome, Paolo and Charalampopoulou, Alexandra and Giannone, Gaia and Lombardo, Valentina and Mastroleo, Federico and Polano, Maurizio and Raimondo, Ivano and Pignata, Sandro and Macchia, Gabriella and Pezzulla, Donato},
  title = {Clinical challenges in the adaptation of AI predictive models in radiation oncology for gynaecological cancer: a systematic review by the radiation oncology-AI MITO group},
  journal = {La radiologia medica},
  year = {2026},
  volume = {131},
  number = {10},
  pages = {1923--1934},
  doi = {10.1007/s11547-026-02272-3}
}
Kostenlos starten →