Upload folder using huggingface_hub

README.md

@@ -0,0 +1,87 @@
+---
+language: en
+license: mit
+library_name: scikit-learn
+tags:
+- tabular-classification
+- healthcare
+- clinical-prediction
+- risk-stratification
+- explainable-ai
+metrics:
+- roc_auc
+- accuracy
+- recall
+- f1
+model-index:
+- name: heart-attack-risk-classifier
+  results:
+  - task:
+      type: tabular-classification
+    metrics:
+    - type: roc_auc
+      value: 0.912
+    - type: recall
+      value: 0.923
+    - type: f1
+      value: 0.884
+---
+
+# ❤️ Clinical Heart Attack Risk Prediction Model
+
+## 📌 Model Overview
+This calibrated tabular gradient boosting classifier predicts acute myocardial infarction (heart attack) probability from non-invasive clinical intake markers. 
+
+The model is tuned for clinical triage sensitivity, achieving **>92% Recall / Sensitivity** to minimize life-threatening false negatives.
+
+---
+
+## 📋 Features Required for Inference
+1. **`age`:** Patient age (years).
+2. **`sex`:** Biological sex (1 = male, 0 = female).
+3. **`cp`:** Chest Pain type (0: Typical Angina, 1: Atypical Angina, 2: Non-Anginal, 3: Asymptomatic).
+4. **`trtbps`:** Resting blood pressure (mm Hg).
+5. **`chol`:** Serum cholesterol (mg/dL).
+6. **`fbs`:** Fasting blood sugar > 120 mg/dL (1 = true, 0 = false).
+7. **`restecg`:** Resting electrocardiographic results (0, 1, 2).
+8. **`thalachh`:** Maximum heart rate achieved during stress test.
+9. **`exng`:** Exercise-induced angina (1 = yes, 0 = no).
+10. **`oldpeak`:** ST depression induced by exercise relative to rest.
+11. **`slp`:** Slope of peak exercise ST segment (0, 1, 2).
+12. **`caa`:** Number of major vessels (0-3) colored by fluoroscopy.
+13. **`thall`:** Thalassemia rate (0-3).
+
+---
+
+## 🚀 Quick Start with Python
+
+```python
+import joblib
+import pandas as pd
+from huggingface_hub import hf_hub_download
+
+# Download model from Hugging Face Hub
+model_path = hf_hub_download(repo_id="Jayan12321/heart-attack-risk-classifier", filename="model.joblib")
+model = joblib.load(model_path)
+
+# Sample Patient Vector (High Risk Profile)
+sample_patient = pd.DataFrame([{
+    'age': 63, 'sex': 1, 'cp': 3, 'trtbps': 145, 'chol': 233, 'fbs': 1,
+    'restecg': 0, 'thalachh': 150, 'exng': 0, 'oldpeak': 2.3, 'slp': 0,
+    'caa': 0, 'thall': 1
+}])
+
+prob = model.predict_proba(sample_patient)[0, 1]
+print(f"Predicted Cardiac Event Probability: {prob * 100:.1f}%")
+```
+
+---
+
+## 🔬 Benchmark Performance (5-Fold Stratified CV)
+* **ROC-AUC:** `0.912`
+* **Sensitivity / Recall:** `0.923`
+* **Precision:** `0.851`
+* **F1-Score:** `0.884`
+
+---
+*Authored and published by [Jayan Gupta](https://huggingface.co/Jayan12321) • Data Scientist & AI Engineer*

model.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09fbad512111272ad9fe4c7a43bac32eaebef44c38befc2567850f926cf6a264
+size 208649