Symptom modeling in head and neck cancer is challenged by the complexity of heterogeneous patient data, leading to an interest in deep learning approaches. Although Long Short-Term Memory Networks (LSTMs) have shown great results in patient risk prediction, their low interpretability requires data modelers to collaborate with clinical experts to validate the results. We present L-VISP, a human–machine solution that uses visual analytics for LSTM modeling in clinical research. L-VISP uses custom visual encodings to make multiple LSTM variants interpretable, supporting a full range of analysis, from understanding model operations and evaluating performance to interpreting results in a clinical context. We evaluate L-VISP with data modelers and a clinical oncologist and present the takeaways from this multidisciplinary collaboration.

Keywords: medical XAI, LSTM modeling, multidisciplinary visual analytics, temporal visualization

CCS Concepts: Human-centered computing - Scientific visualization; Computing methodologies - Machine learning; Applied computing - Life and medical sciences

PDF

Floricel, C., Wang, Y., Wentzel, A., Fuller, C. D., Marai, G. E., Papka, M. E., Canahuate, G., L-VISP: LSTM Visualization for Interpretable Symptom Prediction in Patient Cohorts, Computer Graphics Forum, Eurographics, March 1st, 2026.