Artificial intelligence in lymphedema: A systematic review of diagnostic and clinical applications.
Authors
Affiliations (5)
Affiliations (5)
- School of Medicine, Acibadem Mehmet Ali Aydinlar University, Istanbul, Turkey.
- Department of Plastic Surgery, Cleveland Clinic, Cleveland, OH, USA.
- Department of Family Medicine, Istanbul University, Istanbul, Turkey.
- Hamidiye International School of Medicine, University of Health Sciences, Istanbul, Turkey.
- Department of Plastic Surgery, Cleveland Clinic, Cleveland, OH, USA. Electronic address: [email protected].
Abstract
Lymphedema is a chronic, progressive condition characterized by impaired lymphatic drainage and fluid accumulation. Conventional diagnostic and monitoring tools remain operator-dependent or insensitive to early disease. Artificial intelligence (AI) offers opportunities to address these limitations through multimodal data integration and automated, reproducible analysis. This systematic review followed the PRISMA guidelines and was registered in PROSPERO (CRD420251133232). PubMed and Google Scholar were searched for clinical studies published between January 2015 and July 2025 by applying AI to lymphedema diagnosis, risk prediction, monitoring, or surgical planning. Data extraction included study design, population, methodology, predictors, and performance metrics. Risk of bias was assessed using PROBAST and QUADAS-2. Eighteen studies involving 8720 patients were included. Applications covered risk prediction, imaging-based diagnosis, volumetric assessment, and clinical decision support. Reported performance ranged as follows: AUC, 0.80-0.99 and accuracy, 77-98%. Machine learning models integrating demographic and clinical data achieved AUCs up to 0.89, whereas deep learning models applied to ultrasound, CT, MRI, and clinical photographs achieved diagnostic accuracies up to 98%. Volumetric tools using dual-camera or 3D imaging correlated strongly with gold-standard water displacement (R = 0.99). External validation was absent and methodological heterogeneity was substantial. AI in lymphedema shows promise for early detection, risk stratification, and longitudinal monitoring; however, current evidence remains preliminary. Larger, multi-institutional validation studies are essential to confirm generalizability and demonstrate clinical utility.