TRACE: Transformer-based Risk Assessment for Clinical Evaluation
This work addresses clinical risk assessment for healthcare professionals, presenting an incremental improvement with a novel method for a known bottleneck in handling diverse data types.
The paper tackles clinical risk assessment by proposing TRACE, a Transformer-based method that handles multiple data modalities and missing values, outperforming existing baselines and offering interpretable results via attention weights.
We present TRACE (Transformer-based Risk Assessment for Clinical Evaluation), a novel method for clinical risk assessment based on clinical data, leveraging the self-attention mechanism for enhanced feature interaction and result interpretation. Our approach is able to handle different data modalities, including continuous, categorical and multiple-choice (checkbox) attributes. The proposed architecture features a shared representation of the clinical data obtained by integrating specialized embeddings of each data modality, enabling the detection of high-risk individuals using Transformer encoder layers. To assess the effectiveness of the proposed method, a strong baseline based on non-negative multi-layer perceptrons (MLPs) is introduced. The proposed method outperforms various baselines widely used in the domain of clinical risk assessment, while effectively handling missing values. In terms of explainability, our Transformer-based method offers easily interpretable results via attention weights, further enhancing the clinicians' decision-making process.