AI-Driven Prediction of Cancer Pain Episodes: A Hybrid Decision Support Approach

TL;DR

This paper presents a hybrid machine learning and large language model pipeline that predicts cancer pain episodes within 48 and 72 hours, improving sensitivity and interpretability for proactive pain management.

Contribution

The study introduces a novel hybrid approach combining structured data and unstructured clinical notes to predict pain episodes, enhancing accuracy and clinical interpretability.

Findings

Achieved 87.6% accuracy at 48 hours and 91.7% at 72 hours.

Improved sensitivity by over 10% with LLM augmentation.

Demonstrated scalable, interpretable predictions for oncology pain management.

Abstract

Lung cancer patients frequently experience breakthrough pain episodes, with up to 91% requiring timely intervention. To enable proactive pain management, we propose a hybrid machine learning and large language model pipeline that predicts pain episodes within 48 and 72 hours of hospitalization using both structured and unstructured electronic health record data. A retrospective cohort of 266 inpatients was analyzed, with features including demographics, tumor stage, vital signs, and WHO-tiered analgesic use. The machine learning module captured temporal medication trends, while the large language model interpreted ambiguous dosing records and free-text clinical notes. Integrating these modalities improved sensitivity and interpretability. Our framework achieved an accuracy of 0.876 (48h) and 0.917 (72h), with improvements in sensitivity of 10.6% and 10.7%, respectively, attributable to large language model augmentation. This hybrid approach offers a clinically interpretable and scalable tool for early pain episode forecasting, with potential to enhance treatment precision and optimize resource allocation in oncology care.