Machine Learning and Deep Learning in Deep Vein Thrombosis: A Narrative Review of Clinical Applications for Diagnosis, Risk Prediction, and Outcome Management
Maschinelles Lernen und Deep Learning bei tiefer Venenthrombose: Narrative Übersicht zu klinischen Anwendungen für Diagnose, Risikovorhersage und Outcomes-Management
Seminars in Thrombosis and Hemostasis · 17.09.2026
DOI: 10.1055/a-2954-8867 ↗Auf einen Blick
Die Übersichtsarbeit beschreibt ML- und DL-Anwendungen bei tiefer Venenthrombose in 8 klinischen Bereichen. Die Modelle zeigen häufig hohe AUROC-Werte, sind aber meist unzureichend für den Routineeinsatz validiert.
Fragestellung
Welche klinischen Anwendungen von ML und DL bei tiefer Venenthrombose gibt es, und wie reif sind sie für die Umsetzung in die Versorgung?
Methode
Narrative Übersicht mit strukturierter Literaturrecherche in PubMed, Web of Science und Scopus von Januar 2019 bis April 2026; 250 Publikationen in der Synthese.
Ergebnisse
492 Treffer identifiziert, 250 Publikationen in die Synthese aufgenommen. Anwendungen: ultraschallgestützte Diagnostik, CT/MRI, perioperative und stationäre Risikovorhersage, Krebserkrankung, PTS, Lungenembolie, NLP/LLM. Externe Validierung selten, Kalibrierung selten berichtet.
Einschränkungen
Externe Validierung ist selten; Kalibrierungsmaße und Decision-Curve-Analysen werden kaum berichtet; prospektive Implementierungsstudien sind selten.
Schlussfolgerung der Autor:innen
ML und DL zeigen großes Potenzial für Diagnose, Risikostratifizierung und Outcome-Vorhersage bei DVT, sind aber meist noch nicht ausreichend validiert für den Routineeinsatz.
Kernaussagen
- 250 Publikationen in der narrativen Synthese
- Hohe AUROC-Werte, aber selten externe Validierung
- Prospektive Evaluation und Berichtsstandards werden gefordert
Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.
Kurz gefasst
Fachartikel in der Zeitschrift Seminars in Thrombosis and Hemostasis, online erschienen am 17.09.2026. Verfasst von Hyun Yong Lee und 6 weiteren Autor:innen. Beteiligte Einrichtung: Soonchunhyang University Hospital Cheonan, Department of Transplantation and Vascular Surgery, Chungcheongnam-do, South Korea, Cheonan-si. Die Arbeit nennt 40 Literaturangaben. Gefördert von: Soonchunhyang University Research Fund.
Themen: Thromboseprophylaxe, Künstliche Intelligenz in der Pflege
Abstract (Originalsprache)
Machine learning (ML) and deep learning (DL) are increasingly applied across the clinical spectrum of deep vein thrombosis (DVT), from AI-guided ultrasound diagnosis to perioperative and inpatient risk prediction, but methodological progress has outpaced clinical translation. We aimed to narratively synthesize ML and DL applications in DVT across eight clinical domains and assess their performance and translational readiness. We performed a structured literature search of PubMed, Web of Science, and Scopus (January 2019–April 2026) using predefined disease and technology term blocks restricted to Title/Abstract fields. Of 492 records identified, 250 eligible publications were retained as the synthesis pool. Representative studies were purposively selected for detailed appraisal, prioritizing those with external validation, prospective design, or clear linkage to clinical workflows. AI applications span AI-guided ultrasound diagnosis, CT/MRI-based imaging, perioperative risk prediction, medical/ICU risk prediction, cancer-associated DVT, post-thrombotic syndrome and pulmonary embolism outcome prediction, and natural language processing (NLP)/large language model–based surveillance or decision support. Reported AUROC values are frequently high; however, external validation is uncommon, calibration metrics and decision-curve analysis are rarely reported, and prospective implementation studies are scarce. A randomized trial in medical inpatients demonstrated reduced hospital-acquired venous thromboembolism with AI-driven decision support, and AI-guided ultrasound pathways have shown near-expert diagnostic performance when used by non-expert operators. AI shows substantial promise for improving DVT diagnosis, risk stratification, and outcome prediction, but most models remain insufficiently validated for routine use. Prospective multicenter evaluation, standardized reporting of calibration and clinical utility, and structured oversight frameworks will be essential for safe deployment.
Autor:innen und Institutionen
- Soonchunhyang University Hospital Cheonan, Department of Transplantation and Vascular Surgery, Chungcheongnam-do, South Korea, Cheonan-si.
- Soonchunhyang University Hospital, Department of Transplantation and Vascular Surgery, Seoul, South Korea, Yongsan-Gu.
- Soonchunhyang University Hospital Bucheon, Department of Transplantation and Vascular Sugery, Gyeonggi-do, South Korea, Bucheon-si.
- The Catholic University of Korea Seoul St Mary's Hospital, Department of Transplantation and Vascular Surgery, South Korea, Seoul.
- CHA Gangnam Medical Center, Department of Surgery, South Korea, Seoul.
- Ajou University, Department of Mechanical Engineering, South Korea, Suwon-si.
ORCID-Profile: Sangchul Yun
Förderung
- Soonchunhyang University Research Fund
Zitieren
APA
Lee, H. Y., Yun, S., Choi, E., Jin, H., Ohe, H., Cho, S., & Lee, M. G. (2026). Machine Learning and Deep Learning in Deep Vein Thrombosis: A Narrative Review of Clinical Applications for Diagnosis, Risk Prediction, and Outcome Management. Seminars in Thrombosis and Hemostasis. https://doi.org/10.1055/a-2954-8867
Vancouver
Lee HY, Yun S, Choi E, Jin H, Ohe H, Cho S, et al. Machine Learning and Deep Learning in Deep Vein Thrombosis: A Narrative Review of Clinical Applications for Diagnosis, Risk Prediction, and Outcome Management. Seminars in Thrombosis and Hemostasis. 2026. doi:10.1055/a-2954-8867
BibTeX
@article{Lee2026,
author = {Lee, Hyun Yong and Yun, Sangchul and Choi, Eol and Jin, Hana and Ohe, Heangjin and Cho, Sungwoo and Lee, Moon Gu},
title = {Machine Learning and Deep Learning in Deep Vein Thrombosis: A Narrative Review of Clinical Applications for Diagnosis, Risk Prediction, and Outcome Management},
journal = {Seminars in Thrombosis and Hemostasis},
year = {2026},
doi = {10.1055/a-2954-8867}
}
EUVIMED