Patient Risk Assessment and Warning Symptom Detection Using Deep Attention-Based Neural Networks

TL;DR

This paper introduces an attention-based neural network system for patient risk assessment and warning symptom detection, trained on German doctor notes, improving triage accuracy and transparency.

Contribution

It presents a novel attention-based neural network architecture for medical note analysis, including a method for warning symptom detection and model transparency.

Findings

Achieved 85% precision with full text at confidence threshold 0.6

Compared full text and entity-only approaches, showing trade-offs in precision

Implemented a transparent warning symptom detection method

Abstract

We present an operational component of a real-world patient triage system. Given a specific patient presentation, the system is able to assess the level of medical urgency and issue the most appropriate recommendation in terms of best point of care and time to treat. We use an attention-based convolutional neural network architecture trained on 600,000 doctor notes in German. We compare two approaches, one that uses the full text of the medical notes and one that uses only a selected list of medical entities extracted from the text. These approaches achieve 79% and 66% precision, respectively, but on a confidence threshold of 0.6, precision increases to 85% and 75%, respectively. In addition, a method to detect warning symptoms is implemented to render the classification task transparent from a medical perspective. The method is based on the learning of attention scores and a method of automatic validation using the same data.