Scholarlink

Accurate prediction of disease progression is essential to enable timely clinical interventions and support personalized treatment strategies in both chronic and acute care settings. While recurrent neural networks (RNNs) have traditionally dominated time series modeling in healthcare, transformer-based architectures have recently shown considerable promise. This study evaluates the applicability of the Informer architecture on longitudinal clinical data from the Parkinson’s Progression Markers Initiative (PPMI) dataset. Multiple model variations are explored, including different temporal embedding techniques and multi-task learning configurations. Informers with learnable time-stamp embeddings came up with the lowest mean Mean Squared Error (MSE) and smaller standard deviation (211.6 ± 17.2) with sequence distillation and fixed hyperparameters. However, Multi-Task Learning (MTL) has shown promising results without sequence distillation. To enhance clinical interpretability, explainability methods such as self-attention visualizations, permutation importance, and GradientSHAP are employed. The results show that the Informer architecture can be viable for forecasting tasks within clinical health domains.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

On Explainable Disease Progression Forecasting with Transformer Models

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Umair Aamir Mirza,
  • Faryal Siddique,
  • Faizan Ahmed

摘要

Accurate prediction of disease progression is essential to enable timely clinical interventions and support personalized treatment strategies in both chronic and acute care settings. While recurrent neural networks (RNNs) have traditionally dominated time series modeling in healthcare, transformer-based architectures have recently shown considerable promise. This study evaluates the applicability of the Informer architecture on longitudinal clinical data from the Parkinson’s Progression Markers Initiative (PPMI) dataset. Multiple model variations are explored, including different temporal embedding techniques and multi-task learning configurations. Informers with learnable time-stamp embeddings came up with the lowest mean Mean Squared Error (MSE) and smaller standard deviation (211.6 ± 17.2) with sequence distillation and fixed hyperparameters. However, Multi-Task Learning (MTL) has shown promising results without sequence distillation. To enhance clinical interpretability, explainability methods such as self-attention visualizations, permutation importance, and GradientSHAP are employed. The results show that the Informer architecture can be viable for forecasting tasks within clinical health domains.