Machine Learning as a Diagnostic and Prognostic Tool for Predicting Thrombosis in Cancer Patients: A Systematic Review
Machine Learning als diagnostisches und prognostisches Werkzeug zur Vorhersage von Thrombose bei Krebspatient:innen: systematische Übersichtsarbeit
Seminars in Thrombosis and Hemostasis · 2024-09 · 50 (06) · 809-816
DOI: 10.1055/s-0044-1785482 ↗Auf einen Blick
Die systematische Übersichtsarbeit zeigt: ML-Modelle konnten die Thrombosevorhersage bei Krebspatient:innen in mehreren Datensätzen besser als der Khorana-Score abschneiden. Am besten schnitt offenbar extreme gradient boosting ab.
Fragestellung
Wie gut eignen sich ML-Algorithmen zur Vorhersage von Thrombose bei Krebspatient:innen im Vergleich zum Khorana-Score?
Methode
Systematische Übersichtsarbeit nach PRISMA; Suche in Medline, EMBASE, Cochrane und ClinicalTrials.gov von Beginn bis 15. September 2023. Eingeschlossen wurden Studien mit erwachsenen Krebspatient:innen und ML-Modellen.
Ergebnisse
8 Studien mit 22.893 Patient:innen wurden eingeschlossen. Die Thrombose wurde als venöse Thromboembolie (n = 6) oder peripher eingeführte Zentralkatheterthrombose (n = 2) beschrieben. Mehrere Modelle übertrafen den KS in ihren Datensätzen.
Schlussfolgerung der Autor:innen
Extreme gradient boosting scheint das leistungsstärkste Modell zu sein; mehrere ML-Modelle übertrafen den Khorana-Score in den jeweiligen Datensätzen.
Kernaussagen
- 8 Studien mit 22.893 Patient:innen eingeschlossen
- Mehrere ML-Modelle waren besser als der Khorana-Score
- Extreme gradient boosting schnitt offenbar am besten ab
Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.
Kurz gefasst
Systematische Übersicht in der Zeitschrift Seminars in Thrombosis and Hemostasis, online erschienen am 11.04.2024. Verfasst von Adham H El-Sherbini und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biomedical and Molecular Sciences, School of Medicine, Queen's University, Kingston, Ontario, Canada. Hauptthemen laut MEDLINE: Machine Learning, Neoplasms, Thrombosis. Die Arbeit wurde bisher 20-mal zitiert (Crossref) und nennt 29 Literaturangaben.
Themen: Künstliche Intelligenz in der Pflege, Onkologische Pflege
Abstract (Originalsprache)
Khorana score (KS) is an established risk assessment model for predicting cancer-associated thrombosis. However, it ignores several risk factors and has poor predictability in some cancer types. Machine learning (ML) is a novel technique used for the diagnosis and prognosis of several diseases, including cancer-associated thrombosis, when trained on specific diagnostic modalities. Consolidating the literature on the use of ML for the prediction of cancer-associated thrombosis is necessary to understand its diagnostic and prognostic abilities relative to KS. This systematic review aims to evaluate the current use and performance of ML algorithms to predict thrombosis in cancer patients. This study was conducted per Preferred Reporting Items for Systematic Reviews and Meta-Analysis guidelines. Databases Medline, EMBASE, Cochrane, and ClinicalTrials.gov, were searched from inception to September 15, 2023, for studies evaluating the use of ML models for the prediction of thrombosis in cancer patients. Search terms “machine learning,” “artificial intelligence,” “thrombosis,” and “cancer” were used. Studies that examined adult cancer patients using any ML model were included. Two independent reviewers conducted study selection and data extraction. Three hundred citations were screened, of which 29 studies underwent a full-text review, and ultimately, 8 studies with 22,893 patients were included. Sample sizes ranged from 348 to 16,407 patients. Thrombosis was characterized as venous thromboembolism (n = 6) or peripherally inserted central catheter thrombosis (n = 2). The types of cancer included breast, gastric, colorectal, bladder, lung, esophageal, pancreatic, biliary, prostate, ovarian, genitourinary, head–neck, and sarcoma. All studies reported outcomes on the ML's predictive capacity. The extreme gradient boosting appears to be the best-performing model, and several models outperform KS in their respective datasets.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Biomedical and Molecular Sciences, School of Medicine, Queen's University, Kingston, Ontario, Canada.
- School of Baccalaureate Nursing, St Lawrence College, Kingston, Ontario, Canada.
- Faculty of Medicine, Mansoura University, Mansoura, Egypt.
Zitieren
APA
El-Sherbini, A. H., Coroneos, S., Zidan, A., & Othman, M. (2024). Machine Learning as a Diagnostic and Prognostic Tool for Predicting Thrombosis in Cancer Patients: A Systematic Review. Seminars in Thrombosis and Hemostasis, 50(06), 809-816. https://doi.org/10.1055/s-0044-1785482
Vancouver
El-Sherbini AH, Coroneos S, Zidan A, Othman M. Machine Learning as a Diagnostic and Prognostic Tool for Predicting Thrombosis in Cancer Patients: A Systematic Review. Seminars in Thrombosis and Hemostasis. 2024;50(06):809-816. doi:10.1055/s-0044-1785482
BibTeX
@article{ElSherbini2024,
author = {El-Sherbini, Adham H and Coroneos, Stefania and Zidan, Ali and Othman, Maha},
title = {Machine Learning as a Diagnostic and Prognostic Tool for Predicting Thrombosis in Cancer Patients: A Systematic Review},
journal = {Seminars in Thrombosis and Hemostasis},
year = {2024},
volume = {50},
number = {06},
pages = {809--816},
doi = {10.1055/s-0044-1785482}
}
EUVIMED