Chronic Kidney Disease Prognosis Prediction Using Transformer
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917086280810496 |
|---|---|
| author | Lee, Yohan Kang, DongGyun Park, SeHoon Park, Sa-Yoon Kim, Kwangsoo |
| author_facet | Lee, Yohan Kang, DongGyun Park, SeHoon Park, Sa-Yoon Kim, Kwangsoo |
| contents | Chronic Kidney Disease (CKD) affects nearly 10\% of the global population and often progresses to end-stage renal failure. Accurate prognosis prediction is vital for timely interventions and resource optimization. We present a transformer-based framework for predicting CKD progression using multi-modal electronic health records (EHR) from the Seoul National University Hospital OMOP Common Data Model. Our approach (\textbf{ProQ-BERT}) integrates demographic, clinical, and laboratory data, employing quantization-based tokenization for continuous lab values and attention mechanisms for interpretability. The model was pretrained with masked language modeling and fine-tuned for binary classification tasks predicting progression from stage 3a to stage 5 across varying follow-up and assessment periods. Evaluated on a cohort of 91,816 patients, our model consistently outperformed CEHR-BERT, achieving ROC-AUC up to 0.995 and PR-AUC up to 0.989 for short-term prediction. These results highlight the effectiveness of transformer architectures and temporal design choices in clinical prognosis modeling, offering a promising direction for personalized CKD care. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_02340 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Chronic Kidney Disease Prognosis Prediction Using Transformer Lee, Yohan Kang, DongGyun Park, SeHoon Park, Sa-Yoon Kim, Kwangsoo Artificial Intelligence Other Quantitative Biology Chronic Kidney Disease (CKD) affects nearly 10\% of the global population and often progresses to end-stage renal failure. Accurate prognosis prediction is vital for timely interventions and resource optimization. We present a transformer-based framework for predicting CKD progression using multi-modal electronic health records (EHR) from the Seoul National University Hospital OMOP Common Data Model. Our approach (\textbf{ProQ-BERT}) integrates demographic, clinical, and laboratory data, employing quantization-based tokenization for continuous lab values and attention mechanisms for interpretability. The model was pretrained with masked language modeling and fine-tuned for binary classification tasks predicting progression from stage 3a to stage 5 across varying follow-up and assessment periods. Evaluated on a cohort of 91,816 patients, our model consistently outperformed CEHR-BERT, achieving ROC-AUC up to 0.995 and PR-AUC up to 0.989 for short-term prediction. These results highlight the effectiveness of transformer architectures and temporal design choices in clinical prognosis modeling, offering a promising direction for personalized CKD care. |
| title | Chronic Kidney Disease Prognosis Prediction Using Transformer |
| topic | Artificial Intelligence Other Quantitative Biology |
| url | https://arxiv.org/abs/2511.02340 |