A fine-tuned Bio_ClinicalBERT model that predicts whether a patient is suitable for Hospital-in-the-Home care based on clinical features.
This model uses a pseudo-note fusion approach (inspired by the MEME paper) to combine structured and unstructured clinical data into a single text input for classification:
All features are serialized into a structured pseudo-note format and classified using Bio_ClinicalBERT with a classification head.
The model expects a single text string in pseudo-note format:
PRESENTING COMPLAINT: [complaint]. WARD: [ward]. LENGTH OF STAY: [days] days. PRIMARY DIAGNOSIS: [diagnosis]. NURSE HANDOVER: [nurse notes] ALLIED HEALTH: [allied health notes]
| Metric | Score |
|---|---|
| AUROC | 1.000 |
| AUPRC | 1.000 |
| F1 | 1.000 |
⚠️ Note: These results are on synthetic training data with clear class separation. Real-world performance will differ and the model should be retrained on actual clinical data before any clinical use.
This is a prototype/research model for exploring HITH eligibility prediction. It is trained on synthetic data and is NOT suitable for clinical decision-making without:
The most predictive features identified by SHAP analysis:
This repository contains the ClinicalBERT model. A companion XGBoost + TF-IDF baseline model is also available, providing:
If you use this model, please cite:
model.safetensors 433 MBtraining_args.bin 5.2 kB