Health trend analyzer

Health Trend Analyzer

Analyze trends and patterns in health data over time; identify changes and correlations and provide data-driven health insights.

Core Functions

1. Multi-dimensional trend analysis

• Weight/BMI trend: track weight and BMI over time, assess the health trend
• Symptom patterns: identify recurring symptoms, frequency changes, potential triggers
• Medication adherence: analyze medication patterns, identify missed-dose patterns and room for improvement
• Lab-result trends: track changes in biochemistry (cholesterol, glucose, blood pressure, etc.)
• Mood and sleep: correlate mood state with sleep quality, identify mental-health trends

2. Correlation-analysis engine

• Medication–symptom correlation: identify whether a new medication relates to symptom changes
• Lifestyle effects: correlate diet/sleep with symptoms and mood
• Treatment-effect assessment: measure whether treatment led to improvement
• Cycle–symptom correlation: cycle correlations in women's health tracking

3. Change detection

• Significant changes: warn about rapid weight change, new symptoms, medication changes
• Worsening patterns: early detection of declining health
• Improvement detection: highlight positive health changes
• Threshold alerts: warn when approaching dangerous levels (radiation, extreme BMI)

4. Predictive insights

• Risk assessment: identify risk factors from trends
• Preventive advice: suggest preventive measures based on patterns
• Early warning: predict before a problem becomes serious

Usage

Triggers

Use this skill when the user mentions scenarios such as:

General queries:

• ✅ "What has changed in my health recently?"
• ✅ "Analyze my health trends"
• ✅ "How has my condition changed?"
• ✅ "Health-status summary"

Specific dimensions:

• ✅ "What is my weight/BMI trend?"
• ✅ "Analyze my symptom patterns"
• ✅ "How is my medication adherence?"
• ✅ "What changed in my lab values?"
• ✅ "My mood and sleep trends"

Correlation analysis:

• ✅ "What are my symptoms related to?"
• ✅ "Are my medications working?"
• ✅ "How does sleep relate to my mood?"

Time range:

• Defaults to the past 3 months
• Supports: "past 1 month", "past 6 months", "past 1 year"
• Supports: "Jan 2025 to now", "last 90 days"

Execution Steps

Step 1: Determine the analysis time range

Extract the time range from user input, or use the default (3 months).

Step 2: Read health data

Read the following data sources:

// 1. Personal profile (BMI, weight)
const profile = readFile('data/profile.json');

// 2. Symptom records
const symptomFiles = glob('data/symptoms/**/*.json');
const symptoms = readAllJson(symptomFiles);

// 3. Mood records
const moodFiles = glob('data/mood/**/*.json');
const moods = readAllJson(moodFiles);

// 4. Diet records
const dietFiles = glob('data/diet/**/*.json');
const diets = readAllJson(dietFiles);

// 5. Medication logs
const medicationLogs = glob('data/medication-logs/**/*.json');

// 6. Women's-health data (if applicable)
const cycleData = readFile('data/cycle-tracker.json');
const pregnancyData = readFile('data/pregnancy-tracker.json');
const menopauseData = readFile('data/menopause-tracker.json');

// 7. Allergy history
const allergies = readFile('data/allergies.json');

// 8. Radiation records
const radiation = readFile('data/radiation-records.json');

Step 3: Filter data

Filter data by time range:

function filterByDate(data, startDate, endDate) {
  return data.filter(item => {
    const itemDate = new Date(item.date || item.created_at);
    return itemDate >= startDate && itemDate <= endDate;
  });
}

Step 4: Trend analysis

Analyze the trend for each data dimension:

4.1 Weight/BMI trend

• Extract historical weight data
• Compute BMI change
• Identify trend direction (up/down/stable)
• Assess the magnitude of change

4.2 Symptom patterns

• Tally symptom frequency
• Identify high-frequency symptoms
• Analyze symptom timing patterns
• Detect symptom triggers

4.3 Medication adherence

• Compute overall adherence rate
• Analyze adherence per medication
• Identify missed-dose patterns
• Assess improvement suggestions

4.4 Lab results

• Track biochemistry across multiple reports
• Compare with reference ranges
• Identify improvement/worsening
• Flag abnormal values

4.5 Mood and sleep

• Correlate mood scores with sleep duration
• Identify mood-fluctuation patterns
• Detect stress level
• Assess mental-health trends

Step 5: Correlation analysis

Identify correlations using statistical methods:

// Pearson correlation coefficient
function pearsonCorrelation(x, y) {
  // Compute the correlation coefficient
  // Range: -1 (negative) to 1 (positive)
}

// Use cases
- Medication start date vs. symptom frequency
- Sleep duration vs. mood score
- Weight change vs. diet records
- Exercise volume vs. mood state

Step 6: Change detection

Identify significant changes:

// Change-point detection
function detectChangePoints(timeSeries) {
  // Use statistical methods to detect significant change points
  // e.g., sudden weight drop, sudden symptom increase
}

// Threshold alerts
function checkThresholds(value, thresholds) {
  // Check whether approaching or exceeding dangerous thresholds
  // e.g., BMI > 30, radiation dose > safe limit
}

Step 7: Generate insights

Generate predictive insights from the results:

// Risk assessment
function assessRisks(trends) {
  // Identify high-risk trends
  // e.g., rapid weight loss, frequent symptoms
}

// Preventive advice
function generateRecommendations(trends, correlations) {
  // Suggest preventive measures based on patterns
  // e.g., improve sleep, improve medication adherence
}

// Early warning
function earlyWarnings(trends) {
  // Predict before a problem becomes serious
  // e.g., rising symptom frequency, persistently low mood
}

Step 8: Generate a visual report

Generate an interactive HTML report:

1. Data summary: produce results in JSON
2. HTML-template rendering: inject data into the HTML template
3. ECharts chart config: configure 6 interactive charts
4. Save the file: save as a standalone HTML file

For detailed output formats, see: data-sources.md

Output Format

Text report (concise)

Health Trend Analysis Report
━━━━━━━━━━━━━━━━━━━━━━━━━━
Generated: 2025-12-31
Analysis period: past 3 months (2025-10-01 to 2025-12-31)

📊 Overall assessment
━━━━━━━━━━━━━━━━━━━━━━━━━━
Improving: weight management, cholesterol level
Stable: glucose control, mood state
Needs attention: medication adherence, sleep quality

📊 Weight/BMI trend
├─ Current weight: 68.5 kg
├─ Current BMI: 23.1 (normal range)
├─ 3-month change: -2.3 kg (-3.2%)
├─ Trend: 📉 gradual weight loss
└─ Assessment: ✅ positive trend, within healthy range

💊 Medication adherence
├─ Current medications: 3
├─ Overall adherence: 78%
├─ Missed doses: 8
├─ Best: Aspirin (95%)
└─ Needs improvement: Amlodipine (65%)

⚠️ Symptom patterns
├─ Most frequent: headache (12 times in 3 months)
├─ Trend: 📉 decreasing frequency (4 fewer than last period)
├─ Potential trigger: moderate correlation with sleep quality (r=0.62)
└─ Suggestion: keep improving sleep patterns

🧪 Lab-result trends
├─ Cholesterol: 240 → 210 mg/dL (improved ✅)
├─ Glucose: 5.6 → 5.4 mmol/L (stable)
├─ Last test: 30 days ago
└─ Suggestion: recheck in 3 months

😊 Mood and sleep
├─ Average mood score: 6.8/10
├─ Average sleep duration: 6.5 hours
├─ Trend: stable mood, slightly improved sleep
└─ Correlation: sleep duration strongly correlates with mood score (r=0.78)

🔗 Correlation analysis
━━━━━━━━━━━━━━━━━━━━━━━━━━
• Sleep duration ↔ mood score: strong positive (r=0.78)
• Weight change ↔ diet records: moderate (r=0.55)
• Medication adherence ↔ symptom frequency: moderate negative (r=-0.62)

💡 Risk assessment and suggestions
━━━━━━━━━━━━━━━━━━━━━━━━━━

🟢 Keep doing
• Current weight-management approach is effective
• Cholesterol level clearly improved

🟡 Needs attention
• Improve Amlodipine adherence (set reminders)
• Increase sleep duration to 7-8 hours

📅 Recheck plan
• Recheck a lipid panel in 3 months
• Reassess medication-adherence improvement in 1 month

━━━━━━━━━━━━━━━━━━━━━━━━━━
⚠️ Disclaimer
This analysis is for reference only and does not replace professional medical diagnosis.
Please consult a physician for professional advice.

HTML visual report (full)

Generates a standalone HTML file with interactive ECharts charts, including:

1. Overall-assessment cards: key metrics at a glance
2. Weight/BMI trend chart: dual-Y-axis line chart (weight + BMI)
3. Symptom-frequency chart: color-coded bar chart (high red / medium yellow / low green)
4. Medication-adherence dashboard: overall adherence + per-medication detail
5. Lab-result trend chart: multi-series line chart + reference lines
6. Correlation heatmap: heatmap of inter-variable correlations
7. Mood-and-sleep area chart: dual-Y-axis area chart

HTML-file features:

• ✅ Fully standalone (all dependencies via CDN)
• ✅ Interactive charts (zoom, export, legend toggle)
• ✅ Responsive design (mobile-friendly)
• ✅ Printable (print-optimized styles)
• ✅ Shareable (send to a physician)

Data Sources

Primary data sources

Data source	File path	Content
Personal profile	data/profile.json	weight, height, BMI history
Symptom records	data/symptoms/**/*.json	symptom name, severity, duration
Mood records	data/mood/**/*.json	mood score, sleep quality, stress level
Diet records	data/diet/**/*.json	meals, foods, calories, nutrients
Medication logs	data/medication-logs/**/*.json	dose times, adherence records
Lab results	data/medical_records/**/*.json	biochemistry, reference ranges

Auxiliary data sources

Data source	File path	Content
Menstrual cycle	data/cycle-tracker.json	cycle length, symptom records
Pregnancy	data/pregnancy-tracker.json	gestational week, weight, check-ups
Menopause	data/menopause-tracker.json	symptoms, HRT use
Allergy history	data/allergies.json	allergen, severity
Radiation records	data/radiation-records.json	cumulative radiation dose

For detailed data structures, see: data-sources.md

Analysis Algorithms

Time-series analysis

• Trend detection (linear regression)
• Seasonality analysis
• Outlier detection

Correlation analysis

• Pearson correlation (continuous variables)
• Spearman correlation (ordinal variables)
• Cross-correlation analysis (time series)

Change-point detection

• CUSUM algorithm
• Sliding-window t-test
• Bayesian change-point detection

Statistical metrics

• Mean, median, standard deviation
• Percentiles (25%, 50%, 75%)
• Rate of change (period-over-period, year-over-year)

For detailed algorithms, see: algorithms.md

Safety and Privacy

Must follow

• ❌ Does not give a medical diagnosis
• ❌ Does not give specific medication advice
• ❌ Does not judge prognosis/mortality
• ❌ Includes a disclaimer (for reference only)

Information accuracy

• ✅ Analysis based only on recorded data
• ✅ Does not guess or infer missing information
• ✅ Clearly notes data source and time range
• ✅ Advice should be reviewed by a medical professional

Privacy protection

• ✅ All data stays local
• ✅ No external API calls
• ✅ Results saved locally only
• ✅ The HTML report runs standalone (no data transmission)

Error Handling

Missing data

• No data: output "No data yet; record [data type] first"
• Insufficient data: output "Not enough data (at least 1 month is needed for trend analysis)"
• Narrow range: use available data; note "Record for longer to get a more accurate trend"

Analysis failure

• Cannot compute a trend: output "Cannot compute a trend; too few data points"
• Correlation failed: output "Correlation analysis needs more data"
• Chart-render failure: fall back to the text report

Usage Examples

Example 1: general health trend

User: "What has changed in my health over the past 3 months?" Output: a full HTML report with trend analysis across all dimensions

Example 2: symptom analysis

User: "Analyze my symptom patterns" Output: focus on symptom frequency, triggers, trends

Example 3: weight trend

User: "What is my weight trend?" Output: focus on weight/BMI change and correlation with diet/exercise

Example 4: medication effectiveness

User: "Is my blood-pressure medication working?" Output: correlate medication start date with BP readings and symptom improvement

For more complete examples, see: examples.md

Related Commands

• /symptom: record a symptom
• /mood: record mood
• /diet: record diet
• /medication: manage medications and dose records
• /query: query a specific data point

Technical Implementation

Tool restrictions

This skill uses only the following tools (no extra permissions):

• Read: read JSON data files
• Grep: search for specific patterns
• Glob: find data files by pattern
• Write: generate the HTML report (saved to data/health-reports/)

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

Extensibility

• Supports adding new data dimensions
• Supports custom chart types
• Supports custom analysis algorithms