plutoa386 commited on
Commit
4897642
Β·
1 Parent(s): e5330d0

updated README again

Browse files
Files changed (1) hide show
  1. README.md +14 -7
README.md CHANGED
@@ -10,10 +10,13 @@ pinned: false
10
  ---
11
 
12
  # 🧠 NMS Dementia Risk Assessment API
13
- **AI Backend for the NMS Mobile App & Web Platform**
 
14
 
15
  This repository contains the **agentic AI backend** powering dementia risk assessment and personalized news delivery for the NMS ecosystem. Built on [**CrewAI**](https://crewai.com), it provides scalable, explainable, and audience-aware intelligence for patients, caregivers, and clinicians.
16
 
 
 
17
  ---
18
 
19
  ## βœ… Core Capabilities
@@ -39,8 +42,8 @@ The system uses **4 specialized agents**, each with dedicated tools and LLMs:
39
  |-------|------|-----|-------|
40
  | `Risk Calculator (Audio)` | Runs XGBoost model + SHAP on speech features | `gpt-oss-120b` | `calculate_dementia_risk_audio`, `explain_dementia_risk_audio` |
41
  | `Risk Calculator (Lifestyle)` | Runs XGBoost model + SHAP on lifestyle data | `gpt-oss-120b` | `calculate_dementia_risk_lifestyle`, `explain_dementia_risk_lifestyle` |
42
- | `Patient News Agent` | Fetches, scrapes, and summarizes news for patients/caregivers | `Llama-3.1-8B-Instruct` | `gather_news_patient` |
43
- | `Doctor News Agent` | Fetches, scrapes, and summarizes research for clinicians | `Llama-3.1-8B-Instruct` | `gather_news_doctor` |
44
 
45
  > πŸ”‘ **Why agents?**
46
  > - Separation of concerns (prediction vs. information retrieval)
@@ -52,9 +55,9 @@ The system uses **4 specialized agents**, each with dedicated tools and LLMs:
52
  ## πŸ› οΈ Key Technologies
53
 
54
  - **Machine Learning**: XGBoost (v3.0.5) for high-accuracy binary classification
55
- - **Explainability**: SHAP TreeExplainer for model-agnostic, global + local interpretability
56
  - **Web Scraping**: `requests` + `BeautifulSoup4` (with fallbacks for dynamic sites)
57
- - **LLM Orchestration**: LiteLLM + Hugging Face Inference API (`meta-llama/Llama-3.1-8B-Instruct`, `openai/gpt-oss-120b`)
58
  - **Data Pipeline**: Firebase (Firestore for lifestyle, Storage for audio/transcripts)
59
  - **Deployment**: Hugging Face Spaces (Gradio frontend + CrewAI backend)
60
 
@@ -72,11 +75,15 @@ The system uses **4 specialized agents**, each with dedicated tools and LLMs:
72
  ## πŸ” Ethical & Technical Notes
73
 
74
  - All predictions undergo **SHAP-based validation** to ensure model fairness and transparency.
75
- - News scraping respects `robots.txt` and uses rate-limiting; open-access/Europe PMC sources prioritized.
76
  - No personally identifiable information (PII) leaves Firebase β€” all processing is anonymized.
77
 
 
 
 
 
 
78
  ---
79
 
80
  > πŸ’‘ **Developed by** [plutoa386](https://huggingface.co/plutoa386)
81
- > 🌐 **Live Demo**: [Hugging Face Space](https://huggingface.co/spaces/plutoa386/nms-dementia-api)
82
  > πŸ“¦ **Models**: `modelAudiov8_ML.json`, `modelLifestyleV3_ML.json` (XGBoost + SHAP-compatible)
 
10
  ---
11
 
12
  # 🧠 NMS Dementia Risk Assessment API
13
+ **AI Backend for the NMS Mobile App & NMS Web Platform**
14
+ **3rd Year Uni Project**
15
 
16
  This repository contains the **agentic AI backend** powering dementia risk assessment and personalized news delivery for the NMS ecosystem. Built on [**CrewAI**](https://crewai.com), it provides scalable, explainable, and audience-aware intelligence for patients, caregivers, and clinicians.
17
 
18
+ This is my contribution to the NMS group project.
19
+
20
  ---
21
 
22
  ## βœ… Core Capabilities
 
42
  |-------|------|-----|-------|
43
  | `Risk Calculator (Audio)` | Runs XGBoost model + SHAP on speech features | `gpt-oss-120b` | `calculate_dementia_risk_audio`, `explain_dementia_risk_audio` |
44
  | `Risk Calculator (Lifestyle)` | Runs XGBoost model + SHAP on lifestyle data | `gpt-oss-120b` | `calculate_dementia_risk_lifestyle`, `explain_dementia_risk_lifestyle` |
45
+ | `Patient News Agent` | Fetches, scrapes, and summarizes news for patients/caregivers | `Qwen3-4B-Thinking-2507` | `gather_news_patient` |
46
+ | `Doctor News Agent` | Fetches, scrapes, and summarizes research for clinicians | `Qwen3-4B-Thinking-2507` | `gather_news_doctor` |
47
 
48
  > πŸ”‘ **Why agents?**
49
  > - Separation of concerns (prediction vs. information retrieval)
 
55
  ## πŸ› οΈ Key Technologies
56
 
57
  - **Machine Learning**: XGBoost (v3.0.5) for high-accuracy binary classification
58
+ - **XAI (Explainable AI)**: SHAP TreeExplainer for model-agnostic, global + local interpretability
59
  - **Web Scraping**: `requests` + `BeautifulSoup4` (with fallbacks for dynamic sites)
60
+ - **LLM Orchestration**: LiteLLM + Hugging Face Inference API (`Qwen/Qwen3-4B-Thinking-2507`, `openai/gpt-oss-120b`)
61
  - **Data Pipeline**: Firebase (Firestore for lifestyle, Storage for audio/transcripts)
62
  - **Deployment**: Hugging Face Spaces (Gradio frontend + CrewAI backend)
63
 
 
75
  ## πŸ” Ethical & Technical Notes
76
 
77
  - All predictions undergo **SHAP-based validation** to ensure model fairness and transparency.
 
78
  - No personally identifiable information (PII) leaves Firebase β€” all processing is anonymized.
79
 
80
+
81
+ ## ‼️ Disclaimer
82
+ - **This README was generated by AI**
83
+ - The webscraping is mid
84
+
85
  ---
86
 
87
  > πŸ’‘ **Developed by** [plutoa386](https://huggingface.co/plutoa386)
88
+ > 🌐 **Live Demo**: [Hugging Face Space](https://huggingface.co/spaces/plutoa386/nms-ai-dev)
89
  > πŸ“¦ **Models**: `modelAudiov8_ML.json`, `modelLifestyleV3_ML.json` (XGBoost + SHAP-compatible)