Saved in:
Bibliographic Details
Main Authors: Zisser, Moshe, Aran, Dvir
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2306.05779
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913338454179840
author Zisser, Moshe
Aran, Dvir
author_facet Zisser, Moshe
Aran, Dvir
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2306_05779
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Transformer-based Time-to-Event Prediction for Chronic Kidney Disease Deterioration
Zisser, Moshe
Aran, Dvir
Machine Learning
Computation and Language
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.
title Transformer-based Time-to-Event Prediction for Chronic Kidney Disease Deterioration
topic Machine Learning
Computation and Language
url https://arxiv.org/abs/2306.05779