AI医疗系统

📋 Prerequisites & System Requirements

Before running the application, ensure your environment meets the following specifications:

<img src="docs/assets/divider.svg" alt="AI Healthcare System visual separator divider line" width="100%"/>

Set up python dependencies

python -m pip install -r requirements.txt cp .env.example .env # Update secret keys

Install React portal dependencies

npm --prefix frontend install

☁ 5 Deployment Options

Docker Compose, Enterprise Stack (7 services), Render PaaS, Kubernetes (3-replica HA), Terraform AWS (VPC + EKS + RDS + ElastiCache).

</td> <td width="33%" valign="top">

5. Deployment, Operations & Security

• Performance Benchmarks &mdash; Operational SLAs, response latencies, and high-throughput EKS scaling metrics.
• Real-Time Monitoring Patterns &mdash; Prometheus metrics exporters, Grafana dashboard alerts, and WS broadcast architectures.
• Backup and Restore Readiness &mdash; Disastrous recovery runbooks, Point-in-Time Recovery (PITR) configurations, and replication sets.
• Incident Response Readiness &mdash; Security breach playbooks, reporting procedures, and recovery SLA limits.
• Security Assurance Readiness &mdash; OS hardening playbooks, network firewalls, and credential rotation calendars.
• Security Questionnaire &mdash; Comprehensive institutional questionnaire (HECVAT/HIPAA alignment) for hospital IT boards.

2. Launch with Docker Compose

Launches the complete service container stack (FastAPI backend + React frontend + PostgreSQL + Redis) in a single command:

git clone https://github.com/pavanbadempet/AI-Healthcare-System.git
cd AI-Healthcare-System
cp .env.example .env          # Update GOOGLE_API_KEY & JWT SECRET_KEY
docker compose up --build

🚀 Current Live Serverless Deployment Stack

The platform is currently operating continuously in a multi-cloud serverless production environment. This live topology utilizes 4 major PaaS/SaaS systems interconnected securely:

🌐 AWS Enterprise Production Deployment

For production deployments, the platform utilizes Terraform for Infrastructure as Code (IaC) to provision a secure, scalable, and highly available AWS environment. Applications are containerized and orchestrated inside an Amazon EKS (Elastic Kubernetes Service) cluster.

Deploy to AWS (takes ~15 minutes to spin up EKS, RDS, and ElastiCache)

terraform apply -auto-approve ```

2. EKS Application Deployment (Kubernetes)

Located under the k8s/ directory, the manifests declare: healthcare-backend: A 3-replica High-Availability deployment of the FastAPI server, drawing secrets from healthcare-secrets. healthcare-frontend: A 2-replica deployment of the React SPA served via Nginx. Horizontal Pod Autoscaling: Automatically scales pods between 3 and 10 replicas based on real-time CPU and memory usage (defined in autoscaling.yaml). Ingress Routing: Standardizes path routing (/ to frontend, /v1 to backend) with automated TLS handshakes.

#### Deploy App to EKS: ```bash

4. Deploy all resources

kubectl apply -f k8s/ --namespace healthcare ```

<img src="docs/assets/divider.svg" alt="AI Healthcare System visual separator divider line" width="100%"/>

⚡ Quick Start

⚙ Environment Configuration Reference

Create a .env file in the project root based on the table below:

<img src="docs/assets/divider.svg" alt="AI Healthcare System visual separator divider line" width="100%"/>

🔄 Zero-Configuration Developer Fallback Modes

To allow the platform to run seamlessly on developer machines and thin CI/CD environments (such as GitHub Actions) without requiring the installation of proprietary/external enterprise dependencies (clinical-rag-cache and clinical-fhir-abdm), the backend features a robust local fallback system:

• Fully-Featured Local RAG & Vector Store Fallback: Automatically switches to a persistent JSON-based vector store in backend/rag.py featuring LSH (Locality Sensitive Hashing) Approximate Nearest Neighbor indexing and hybrid similarity scoring.
• Persistent Semantic Cache Fallback: Implements a local file-based SemanticCache using cosine similarity matching over embeddings to optimize and cache LLM responses locally.
• Fully-Schema-Compliant FHIR/ABDM fallbacks: Generates fully validated FHIR R4 Resources (Patient, Observation, MedicationRequest, Invoice, CareEvent, etc.) with local reference resolution and bundle validation, satisfying rigorous automated verification tests out-of-the-box.
• Auto-Initializing Database Schema: Automatically creates and initializes the SQLite schema (Base.metadata.create_all) for all standalone audit runners and tests if a local fallback database is used, guaranteeing that clinical agents can run instantly without manual migrations.

<img src="docs/assets/divider.svg" alt="AI Healthcare System visual separator divider line" width="100%"/>

1. Update your local kubeconfig to point to the new EKS cluster

aws eks update-kubeconfig --name healthcare-prod-cluster --region us-east-1

Run the REST API

uvicorn backend.main:app --reload --host 127.0.0.1 --port 8000

#### Setup Frontend:

📡 Complete REST API Contract

The FastAPI backend exposes the following REST endpoints:

🔑 Commercial Developer Packages (Polar.sh)

If you are a B2B SaaS founder or software developer building products that require offline cryptographic licensing or calibrated machine learning pipelines, you can acquire our production-ready standalone packages directly on Polar.sh with zero-config delivery:

<img src="docs/assets/divider.svg" alt="AI Healthcare System visual separator divider line" width="100%"/>

⚙ 8 CI/CD Pipelines

Pytest + coverage, CodeQL SAST, Docker GHCR builds, HuggingFace sync, Dependabot, release drafter, stale bot, and Render keep-alive.

</td> </tr> </table>

Built for enterprise, built for production. This is a production-grade clinical intelligence platform demonstrating advanced ML engineering, LLM orchestration, RAG architecture, and DevOps maturity in a single cohesive codebase.

<img src="docs/assets/divider.svg" alt="AI Healthcare System visual separator divider line" width="100%"/>

2. Clinical & Medical Workflows

• Diagnostics Workflow &mdash; Clinical lab metric intake, inference pipeline, SHAP interpretability plot rendering, and physician validation.
• Nursing Workflow &mdash; Nurse worklist coordinators, vital sign logs, and shift handover data packets.
• Pharmacy Workflow &mdash; E-prescription fulfillment, drug-drug interaction validation checks, and automatic reorder thresholds.
• Billing Workflow &mdash; Insurance claims verification, double-entry transactional ledgers, and payment processing loops.
• Discharge Workflow &mdash; Inpatient release checklists, outpatient referral summaries, and automatic FHIR serialization.
• Hospital Operations Core &mdash; Inpatient/Outpatient (IPD/OPD) coordinate systems, bed allocation logic, and clinic occupancy algorithms.

Interoperability & Integration Standards

• GET /v1/interop/patient/fhir-bundle: Export patient record as FHIR R4 JSON bundle.
• POST /v1/interop/patient/consents: Grant interoperability access consent.
• POST /v1/interop/patient/consents/{consent_id}/revoke: Revoke granted data consent.
• GET /v1/interop/abdm/readiness: Check India ABDM integration sandbox readiness.
• POST /v1/interop/abdm/consent-callbacks: Ingest ABDM consent lifecycle event.
• GET /v1/interop/dicomweb/readiness: Verify DICOM PACS connection status.
• GET /v1/interop/smart/readiness: Verify SMART on FHIR authorization client status.

<img src="docs/assets/divider.svg" alt="AI Healthcare System visual separator divider line" width="100%"/>

🚀 CI/CD Pipelines Registry

We run 8 structured GitHub Actions workflows for continuous integration and compliance:

<img src="docs/assets/divider.svg" alt="AI Healthcare System visual separator divider line" width="100%"/>

4. GitHub Actions (CI/CD Pipeline Orchestration)

• Application: Fully automated CI/CD pipeline gating every pull request and push to the main branch.
• Architecture: Executes the complete 1,500+ unit test suite using pytest -n auto, verifies UI components with Vitest, runs End-to-End browser tests with Playwright, and checks security vulnerabilities with CodeQL.

<img src="docs/assets/divider.svg" alt="AI Healthcare System visual separator divider line" width="100%"/>

2. Apache Airflow Pipeline Orchestration

The pipeline runs daily data engineering workflows orchestrated via Apache Airflow (airflow/dags/): healthcare_data_pipeline.py (Ingestion & ETL): Manages raw data ingestion, schedules PySpark SparkSubmitOperators to execute ETL tasks, and processes medical data snapshots. healthcare_data_modeling.py (Dimensional Modeling & SCD): Transforms operational EHR data into an optimized star schema (Fact Tables & Dimension Tables). Implements Slowly Changing Dimensions (SCD Type 2) on the patient dimension table to track historical demographic updates over time. * delta_lake_operations.py (Lakehouse Maintenance): Schedules daily OPTIMIZE and Z-ORDER BY (patient_id, timestamp) operations to merge small files and partition the data, alongside VACUUM runs to prune obsolete historical data.

🆚 Competitive Comparison: Why AI Healthcare System?

<img src="docs/assets/divider.svg" alt="AI Healthcare System visual separator divider line" width="100%"/>

❓ FAQ

<details> <summary><strong>Click to expand Frequently Asked Questions</strong></summary>

Q1: How do I run this without an API key? Install Ollama, run ollama pull llama3.2, set OLLAMA_BASE_URL=http://127.0.0.1:11434 in .env, and leave GOOGLE_API_KEY unset. All inference runs locally — free and private.

Q2: How do I deploy this platform to the cloud? The platform is fully containerized and can be deployed to Render using the included render.yaml configuration. For production enterprise environments, you can deploy using the provided Kubernetes manifests (k8s/) or the AWS EKS/RDS Terraform configuration (terraform/).

Q3: Is this HIPAA compliant? This platform implements HIPAA-oriented controls (bcrypt, JWT, RBAC, audit logging, PII-scrubbed errors, per-user consent). Full HIPAA compliance for production requires additional organizational controls, BAAs, and a formal compliance review.

Q4: How do I add a new disease prediction model? Add a training script → register in prediction.py:initialize_models() → add Pydantic schema → add endpoint → add model card in model_cards.py → write unit test.

Q5: How does the chatbot remember my health history? RAG — your health records are embedded with Gemini text-embedding-004, stored in a vector store, retrieved by cosine similarity when you ask a question, and assembled into context before the LLM responds. Your data is scoped to your account only.

Q6: What is FHIR R4 and why does this implement it? FHIR R4 is the international standard for exchanging healthcare data. Implementing it means patient records can be exported to or imported from any FHIR-compatible EHR (Epic, Cerner, etc.) without custom integration.

Q7: How does the model hot-reloader work? The /v1/admin/reload_models route triggers the ModelService state singleton to download or reload .pkl weights from disk into memory atomically. All current sessions use the new weights immediately without API service disruption.

Q8: Why are some ML models scoring low specificity (e.g. Kidney/Lung)? Some datasets (e.g. Lung Cancer / CKD) are heavily imbalanced. In screening applications, we optimize for 100% sensitivity (no false negatives), leading to lower specificity. We discuss these trade-offs in docs/MODEL_AND_DATASET_CARDS.md.

Q9: What is India's ABDM Digital Health Stack integration? It provides standard endpoints to link Health IDs (ABHA), handle consent callbacks, and serialize records into encrypted FHIR packages for exchange over India's National Health Stack.

Q10: How does the turbovec Rust SIMD index work? turbovec is a compiled Rust library that computes cosine similarity between user query embeddings and patient vectors using SIMD instructions. If compilation fails, it automatically falls back to scikit-learn metrics.

Q11: Can I plug in PostgreSQL instead of SQLite? Yes. Define the DATABASE_URL=postgresql://user:password@host:5432/dbname environment variable. The SQLAlchemy database layer automatically scales, handles connection pools, and configures PostgreSQL constraints at startup. </details>

<img src="docs/assets/divider.svg" alt="AI Healthcare System visual separator divider line" width="100%"/>

<img src="docs/assets/divider.svg" alt="AI Healthcare System visual separator divider line" width="100%"/>