KeepHealthCare.ORG – Machine learning detects lymphedema in breast cancer survivors
A new study led by NYU Rory Meyers College of Nursing shows that machine learning—combined with the collection of real-time symptom reports using a mHealth system—can provide early detection and help patients to receive timely intervention to effectively manage lymphedema.
It’s one of the most distressing side effects from breast cancer treatment, stemming from the removal of lymph nodes. Lymphedema, which has no cure and comes with lifelong risk, is the build-up of lymph fluid that causes swelling in the arms or legs of patients.
In the study of 355 women from 45 states who had undergone treatment for breast cancer, the performance of five machine learning algorithms were evaluated—artificial neural network (ANN), Decision Tree of C4.5, Decision Tree of C5.0, gradient boosting model and support vector machine.
According to results published in the journal mHealth, all five machine learning approaches outperformed the conventional statistical approach. However, of the five, the ANN achieved the best performance for detecting lymphedema with accuracy of 93.75 percent, sensitivity of 95.65 percent and specificity of 91.03 percent.
“Such detection accuracy is significantly higher than that achievable by current and often-used clinical methods,” says Mei Fu, associate professor of nursing at NYU Meyers and the study’s lead author. “Clinicians often detect or diagnose lymphedema based on their observation of swelling. However, by the time swelling can be observed or measured, lymphedema has typically occurred for some time, which may lead to poor clinical outcomes.”
Also See: Machine learning helps Mass General predict cancerous breast lesions
“A well-trained ANN classifier using real-time symptom report can provide highly accurate detection of lymphedema,” conclude the study’s authors. “Such detection accuracy is significantly higher than that achievable by current and often-used clinical methods such as bio-impedance analysis. Use of a well-trained classification algorithm to detect lymphedema based on symptom features is a highly promising tool that may improve lymphedema outcomes.”