AI Health Analyzer

An AI-based comprehensive health-analysis system that provides intelligent health insights, risk prediction, and personalized advice.

Core Functions

1. Intelligent health analysis

• Multi-dimensional data integration: integrates four data-source categories basic metrics, lifestyle, mental health, and medical history
• Abnormal-pattern detection: uses algorithms such as CUSUM and Z-score to detect outliers and change points
• Correlation analysis: computes correlations between health metrics (Pearson, Spearman)
• Trend prediction: trend analysis and forecasting based on historical data

2. Health-risk prediction

• Hypertension risk: based on the Framingham risk-score model
• Diabetes risk: based on the ADA diabetes risk-score standard
• Cardiovascular-disease risk: based on ACC/AHA ASCVD guidelines
• Nutrient-deficiency risk: based on RDA attainment and dietary-pattern analysis
• Sleep-disorder risk: based on PSQI and sleep-pattern analysis

3. Personalized recommendation engine

• Baseline personalization: based on a static profile (age, sex, BMI, activity level, etc.)
• Recommendation tiers: Level 1 (general), Level 2 (informational), Level 3 (medical advice)
• Evidence base: grounded in medical guidelines and evidence-based medicine
• Actionability: provides specific, feasible improvement suggestions

4. Natural-language interaction

• Intelligent Q&A: supports health-data queries, trend analysis, correlation queries, etc.
• Context understanding: maintains conversation history for multi-turn dialogue
• Intent recognition: identifies user query intent for precise responses

5. AI health-report generation

• Comprehensive report: includes all health-data dimensions, AI insights, and risk assessment
• Quick summary: key-metric overview, anomaly alerts, main recommendations
• Risk-assessment report: disease risks, risk-factor analysis, preventive measures
• Trend-analysis report: multi-dimensional trends, change-point detection, forecasting
• Interactive HTML report: ECharts charts, Tailwind CSS styling

Usage

Triggers

Use this skill when the user mentions scenarios such as:

General queries:

• ✅ "AI-analyze my health"
• ✅ "What health risks do I have?"
• ✅ "Generate an AI health report"
• ✅ "AI-analyze all data"

Risk prediction:

• ✅ "Predict my hypertension risk"
• ✅ "Am I at risk of diabetes?"
• ✅ "Assess my cardiovascular risk"
• ✅ "AI-predict health risks"

Intelligent Q&A:

• ✅ "How is my sleep?"
• ✅ "What effect does exercise have on my health?"
• ✅ "How should I improve my health?"
• ✅ "AI health-assistant Q&A"

Report generation:

• ✅ "Generate an AI health report"
• ✅ "Create a comprehensive analysis report"
• ✅ "AI risk-assessment report"

Execution Steps

#### Step 1: Read AI configuration

const aiConfig = readFile('data/ai-config.json');
const aiHistory = readFile('data/ai-history.json');

Check whether the AI feature is enabled and validate the data-source configuration.

#### Step 2: Read the user profile

const profile = readFile('data/profile.json');

Get basic information: age, sex, height, weight, BMI, etc.

#### Step 3: Read health data

Read the relevant data per the configured data sources:

// Basic health metrics
const indexData = readFile('data/index.json');

// Lifestyle data
const fitnessData = readFile('data-example/fitness-tracker.json');
const sleepData = readFile('data-example/sleep-tracker.json');
const nutritionData = readFile('data-example/nutrition-tracker.json');

// Mental-health data
const mentalHealthData = readFile('data-example/mental-health-tracker.json');

// Medical history
const medications = exists('data/medications.json') ? readFile('data/medications.json') : null;
const allergies = exists('data/allergies.json') ? readFile('data/allergies.json') : null;

#### Step 4: Data integration and preprocessing

Integrate all data sources; perform data cleaning, time alignment, and missing-value handling.

#### Step 5: Multi-dimensional analysis

Correlation analysis: compute associations such as sleep↔mood, exercise↔weight, nutrition↔biochemistry

Trend analysis: identify trend direction using linear regression, moving averages, etc.

Anomaly detection: detect outliers and change points using CUSUM and Z-score algorithms

#### Step 6: Risk prediction

Predict risk using standards such as Framingham, ADA, and ACC/AHA:

• Hypertension risk (10-year probability)
• Diabetes risk (10-year probability)
• Cardiovascular-disease risk (10-year probability)
• Nutrient-deficiency risk
• Sleep-disorder risk

#### Step 7: Generate personalized recommendations

Produce three tiers of recommendations from the analysis results:

• Level 1: general advice (based on standard guidelines)
• Level 2: informational advice (based on personal data)
• Level 3: medical advice (requires physician confirmation, includes a disclaimer)

#### Step 8: Generate the analysis report

Text report: includes overall assessment, risk prediction, key trends, correlation findings, and personalized advice

HTML report: calls scripts/generate_ai_report.py to generate an interactive report with ECharts charts

#### Step 9: Update AI history

Record the analysis results to data/ai-history.json

Data Sources

Algorithm Notes

Correlation analysis

• Pearson correlation: continuous variables (e.g., sleep duration vs. mood score)
• Spearman correlation: ordinal variables (e.g., symptom severity)

Anomaly detection

• CUSUM: change-point detection in time series
• Z-score method: statistical outlier detection (|z| > 2)
• IQR method: interquartile-range outlier detection

Risk prediction

• Framingham risk score: hypertension and cardiovascular-disease risk
• ADA risk score: type-2 diabetes risk
• ASCVD calculator: atherosclerotic cardiovascular-disease risk

Safety and Compliance

Must follow

• ❌ Does not give medical diagnoses
• ❌ Does not give specific medication-dose advice
• ❌ Does not judge prognosis or mortality
• ❌ Does not replace physician advice
• ✅ All analyses must be marked "for reference only"
• ✅ Level 3 advice must include a disclaimer
• ✅ High-risk predictions must recommend consulting a physician

Privacy protection

• ✅ All data stays local
• ✅ No external API calls
• ✅ The HTML report runs standalone

Related Commands

• /ai analyze - comprehensive AI analysis
• /ai predict [risk_type] - health-risk prediction
• /ai chat [query] - natural-language Q&A
• /ai report generate [type] - generate an AI health report
• /ai status - view AI feature status

Technical Implementation

Tool restrictions

This skill uses only the following tools:

• Read: read JSON data files
• Grep: search for specific patterns
• Glob: find data files by pattern
• Write: generate HTML reports and update history

Performance optimization

• Incremental reads: read only data files within the specified time range
• Data caching: avoid re-reading the same file
• Lazy computation: generate chart data on demand