AI-Powered Deep Learning Models for Prediction of Musculoskeletal Complications After Breast Cancer Surgery Focusing on Lymphedema, Axillary Web Syndrome, Neuropathy, and Pain

What this Trial Is About

Researchers are studying musculoskeletal complications that can occur after breast cancer surgery, such as lymphedema, axillary web syndrome, neuropathy, and pain-related syndromes. These complications can affect daily activities and the ability to continue cancer treatment. The study aims to develop and validate predictive models using deep learning methods to identify patients at risk for these issues early on, helping clinicians plan preventive care. Four deep learning architectures—ResNet50, AlexNet, GoogleNet, and UNet—will be evaluated for this purpose. The study involves collecting detailed physical and clinical data from female patients scheduled for unilateral breast cancer surgery. Data include demographic information, measurements of upper-extremity circumference and shoulder range of motion, skin and nerve examinations, diagnosis details, treatments received, and laboratory test results. Patients will complete questionnaires on pain, anxiety, depression, and disability. Assessments are done at baseline and during follow-ups at 1, 3, and 6 months post-surgery. Treatment details like chemotherapy and radiotherapy doses are also recorded during monthly visits. Participants will undergo physical examinations and complete questionnaires throughout a 6-month follow-up period. Shoulder range of motion will be measured with a goniometer before treatment and at each follow-up visit. Researchers will analyze changes over time and use this information to build risk prediction tools. The study aims to help clinicians estimate the likelihood of these complications before treatment starts, supporting better management and care for breast cancer patients.

Deep Learning for Musculoskeletal Complications in Breast Cancer