Updating the readme file
Browse files
README.md
CHANGED
|
@@ -3,7 +3,48 @@ license: apache-2.0
|
|
| 3 |
base_model:
|
| 4 |
- ncbi/MedCPT-Query-Encoder
|
| 5 |
tags:
|
| 6 |
-
-
|
| 7 |
-
-
|
| 8 |
-
-
|
| 9 |
-
--
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
base_model:
|
| 4 |
- ncbi/MedCPT-Query-Encoder
|
| 5 |
tags:
|
| 6 |
+
- federated-learning
|
| 7 |
+
- blockchain
|
| 8 |
+
- healthcare
|
| 9 |
+
- clinical-nlp
|
| 10 |
+
- semantic-search
|
| 11 |
+
- privacy-preserving
|
| 12 |
+
pipeline_tag: feature-extraction
|
| 13 |
+
---
|
| 14 |
+
|
| 15 |
+
# Global Model: Decentralized Federated Learning for Distributed Hospitals
|
| 16 |
+
|
| 17 |
+
This repository hosts the global model weights aggregated during the decentralized federated learning process across distributed clinical institutions. The aggregation coordination, model integrity verification, and round participation are orchestrated via a blockchain network to ensure auditability, zero data leakage, and Byzantine fault tolerance.
|
| 18 |
+
|
| 19 |
+
## Model Details
|
| 20 |
+
|
| 21 |
+
### Model Description
|
| 22 |
+
|
| 23 |
+
- **Model type:** Biomedical Query Encoder / Text Feature Extraction
|
| 24 |
+
- **Language(s) (NLP):** English
|
| 25 |
+
- **License:** Apache-2.0
|
| 26 |
+
- **Finetuned from model:** `ncbi/MedCPT-Query-Encoder`
|
| 27 |
+
- **Federated Scheme:** Decentralized On-Chain Aggregation (e.g., FedAvg / Smart Contract Consensus)
|
| 28 |
+
|
| 29 |
+
### Model Sources
|
| 30 |
+
|
| 31 |
+
- **Repository:** [GitHub: Decentralized-Systems-and-Applications/Federated_Learning_with_Blockchain_for_Distributed_Hospitals](https://github.com/Decentralized-Systems-and-Applications/Federated_Learning_with_Blockchain_for_Distributed_Hospitals)
|
| 32 |
+
- **Demo :** [ Demo Video (https://drive.google.com/file/d/11C0rO3Zjp7459Yn7012KK0VBu-refau_/view)]
|
| 33 |
+
|
| 34 |
+
---
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
### Direct Use
|
| 39 |
+
Generating dense clinical embeddings for biomedical text retrieval, semantic document matching, and hospital query classification without exposing institutional private training data.
|
| 40 |
+
|
| 41 |
+
### Downstream Use
|
| 42 |
+
Integrating into distributed clinical decision support systems (CDSS), electronic health record (EHR) cross-search, or zero-trust medical intelligence pipelines.
|
| 43 |
+
|
| 44 |
+
### Out-of-Scope Use
|
| 45 |
+
- Automated diagnosis or medication prescribing without human clinician oversight.
|
| 46 |
+
- Handling tasks completely outside the clinical and biomedical domain without domain-specific re-evaluation.
|
| 47 |
+
|
| 48 |
+
---
|
| 49 |
+
|
| 50 |
+
## Decentralized & Federated Training Architecture
|