LGCLJun 9, 2023

Transformer-based Time-to-Event Prediction for Chronic Kidney Disease Deterioration

arXiv:2306.05779v117 citationsh-index: 6
Originality Incremental advance
AI Analysis

This work addresses time-to-event prediction for chronic kidney disease patients, offering potential improvements in clinical targeting, though it is incremental as it adapts transformers to a specific domain.

The authors tackled the problem of predicting time-to-event for chronic kidney disease deterioration using a novel transformer-based architecture called STRAFE, which outperformed other algorithms on a dataset of over 130,000 individuals and improved the positive predictive value for high-risk patients by 3-fold.

Deep-learning techniques, particularly the transformer model, have shown great potential in enhancing the prediction performance of longitudinal health records. While previous methods have mainly focused on fixed-time risk prediction, time-to-event prediction (also known as survival analysis) is often more appropriate for clinical scenarios. Here, we present a novel deep-learning architecture we named STRAFE, a generalizable survival analysis transformer-based architecture for electronic health records. The performance of STRAFE was evaluated using a real-world claim dataset of over 130,000 individuals with stage 3 chronic kidney disease (CKD) and was found to outperform other time-to-event prediction algorithms in predicting the exact time of deterioration to stage 5. Additionally, STRAFE was found to outperform binary outcome algorithms in predicting fixed-time risk, possibly due to its ability to train on censored data. We show that STRAFE predictions can improve the positive predictive value of high-risk patients by 3-fold, demonstrating possible usage to improve targeting for intervention programs. Finally, we suggest a novel visualization approach to predictions on a per-patient basis. In conclusion, STRAFE is a cutting-edge time-to-event prediction algorithm that has the potential to enhance risk predictions in large claims datasets.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes