Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.00738 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909008259973120 |
|---|---|
| author | Mohammadi, Ramin vahdat, Vahab Jain, Sarthak Namin, Amir T. Palacholla, Ramya Kamarthi, Sagar |
| author_facet | Mohammadi, Ramin vahdat, Vahab Jain, Sarthak Namin, Amir T. Palacholla, Ramya Kamarthi, Sagar |
| contents | With the proliferation of Electronic Health Records (EHRs), a critical challenge in building predictive models is determining the optimal historical data time window to maximize accuracy. This study investigates the impact of various observation windows ranging from the day of surgery to three years prior on predicting 30-day readmission following hip and knee arthroplasties. The dataset encompasses both structured encounter records (over 4 million) and unstructured clinical notes (80,000) from 7,174 patients. To extract meaning from the clinical notes, we employed a suite of non neural (BOW, count BOW, TF IDF, LDA) and neural encoders (BERT, 1D CNN, BiLSTM, Average). We subsequently evaluated models utilizing clinical notes alone, structured data alone, and a combination of both modalities. Our results demonstrate that the optimal time window for unstructured clinical notes is significantly shorter than for structured data, maximum predictive performance was achieved using notes from just three to six months prior to surgery. In contrast, performance using structured data improved as the time window lengthened, but strictly plateaued after twelve months. These modality-specific temporal patterns remained consistent regardless of model complexity or encoder type. Ultimately, these findings challenge the general assumption that more historical data inherently yields better machine learning predictions, establishing targeted time-window guidelines for optimizing readmission prediction models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_00738 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Temporal Data Requirement for Predicting Unplanned Hospital Readmissions Mohammadi, Ramin vahdat, Vahab Jain, Sarthak Namin, Amir T. Palacholla, Ramya Kamarthi, Sagar Machine Learning With the proliferation of Electronic Health Records (EHRs), a critical challenge in building predictive models is determining the optimal historical data time window to maximize accuracy. This study investigates the impact of various observation windows ranging from the day of surgery to three years prior on predicting 30-day readmission following hip and knee arthroplasties. The dataset encompasses both structured encounter records (over 4 million) and unstructured clinical notes (80,000) from 7,174 patients. To extract meaning from the clinical notes, we employed a suite of non neural (BOW, count BOW, TF IDF, LDA) and neural encoders (BERT, 1D CNN, BiLSTM, Average). We subsequently evaluated models utilizing clinical notes alone, structured data alone, and a combination of both modalities. Our results demonstrate that the optimal time window for unstructured clinical notes is significantly shorter than for structured data, maximum predictive performance was achieved using notes from just three to six months prior to surgery. In contrast, performance using structured data improved as the time window lengthened, but strictly plateaued after twelve months. These modality-specific temporal patterns remained consistent regardless of model complexity or encoder type. Ultimately, these findings challenge the general assumption that more historical data inherently yields better machine learning predictions, establishing targeted time-window guidelines for optimizing readmission prediction models. |
| title | Temporal Data Requirement for Predicting Unplanned Hospital Readmissions |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2605.00738 |