EUVIMEDEUVIMED entdecken
Crossref

Multimodal Machine Learning for Early Prediction of Metastasis in a Swedish Multicancer Cohort

Franco Rugolon iD, Korbinian Randl iD, Braslav Jovanovic iD, Ioanna Miliou iD, Panagiotis Papapetrou iD

JCO Clinical Cancer Informatics · 2026-04 · 10 (2)

DOI: 10.1200/cci-25-00141 ↗

Kurz gefasst

Fachartikel in der Zeitschrift JCO Clinical Cancer Informatics, 2026-04. Verfasst von Franco Rugolon und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer and Systems Sciences, Stockholm University, Stockholm, Sweden. Hauptthemen laut MEDLINE: Machine Learning, Neoplasms. Die Arbeit nennt 46 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

PURPOSE Multimodal machine learning offers a holistic view of a patient's status, integrating structured and unstructured data from electronic health records (EHR). We propose a framework to predict metastasis risk 1 month before diagnosis, using 6 months of clinical history from EHR data. METHODS Data from four cancer cohorts collected at Karolinska University Hospital (Stockholm, Sweden) were analyzed: breast (n = 743), colon (n = 387), lung (n = 870), and prostate (n = 1,890). The data set included demographics, comorbidities, laboratory results, medications, and clinical text. We compared traditional and deep learning (DL) classifiers across single modalities and multimodal combinations, using various fusion strategies and a transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD) 2a design, with an 80-20 development-validation split to ensure a rigorous, repeatable evaluation. Performance was evaluated using AUROC, area under the precision-recall curve, F1 score, sensitivity, and specificity. We then employed a multimodal adaptation of Shapley additive explanations (SHAP) to analyze the classifiers' reasoning. RESULTS Intermediate fusion achieved the highest F1 scores on breast (0.845), colon (0.786), and prostate cancer (0.845), demonstrating strong predictive performance. For lung cancer, the intermediate fusion achieved an F1 score of 0.819, while the text-only model achieved the highest, with an F1 score of 0.829. DL classifiers consistently outperformed traditional models. Colon cancer, the smallest cohort, had the lowest performance, highlighting the importance of sufficient training data. SHAP analysis showed that the relative importance of modalities varied across cancer types. CONCLUSION Fusion strategies offer distinct strengths and weaknesses. Intermediate fusion consistently delivered the best results, but strategy choices should align with data characteristics and organizational needs.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningNeoplasmsHumansSwedenMaleFemalePredictive Learning ModelsPrognosisElectronic Health RecordsNeoplasm MetastasisClassification AlgorithmsPrediction AlgorithmsCohort StudiesMiddle AgedAged

Autor:innen und Institutionen

  • Department of Computer and Systems Sciences, Stockholm University, Stockholm, Sweden.
  • Tema Cancer, Karolinska University Hospital, Stockholm, Sweden.

ORCID-Profile: Franco Rugolon, Korbinian Randl, Braslav Jovanovic, Ioanna Miliou, Panagiotis Papapetrou

Zitieren

APA

Rugolon, F., Randl, K., Jovanovic, B., Miliou, I., & Papapetrou, P. (2026). Multimodal Machine Learning for Early Prediction of Metastasis in a Swedish Multicancer Cohort. JCO Clinical Cancer Informatics, 10(2). https://doi.org/10.1200/cci-25-00141

Vancouver

Rugolon F, Randl K, Jovanovic B, Miliou I, Papapetrou P. Multimodal Machine Learning for Early Prediction of Metastasis in a Swedish Multicancer Cohort. JCO Clinical Cancer Informatics. 2026;10(2). doi:10.1200/cci-25-00141

BibTeX
@article{Rugolon2026,
  author = {Rugolon, Franco and Randl, Korbinian and Jovanovic, Braslav and Miliou, Ioanna and Papapetrou, Panagiotis},
  title = {Multimodal Machine Learning for Early Prediction of Metastasis in a Swedish Multicancer Cohort},
  journal = {JCO Clinical Cancer Informatics},
  year = {2026},
  volume = {10},
  number = {2},
  doi = {10.1200/cci-25-00141}
}
Kostenlos starten →