Mpn Progression Monitor Agent

name: 'mpn-progression-monitor-agent' description: 'AI-powered myeloproliferative neoplasm monitoring for disease progression prediction, treatment response tracking, and transformation risk assessment in PV, ET, and myelofibrosis.' measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command

MPN Progression Monitor Agent

The MPN Progression Monitor Agent provides comprehensive monitoring of myeloproliferative neoplasms (PV, ET, MF) for disease progression, treatment response, and transformation risk. It integrates molecular profiling, clinical parameters, and AI-based risk models to guide management of chronic phase disease and predict blast transformation.

When to Use This Skill

• When monitoring JAK2/CALR/MPL mutation burden over time.
• For predicting fibrosis progression in PV/ET.
• To assess risk of blast transformation.
• When tracking treatment response to JAK inhibitors.
• For calculating dynamic risk scores (DIPSS, MIPSS70).

Core Capabilities

1. Mutation Monitoring: Track driver and high-risk mutation VAF.

2. Progression Prediction: Model fibrosis and transformation risk.

3. Risk Scoring: Calculate DIPSS, MIPSS70+, MTSS dynamically.

4. Treatment Response: Assess molecular and clinical response.

5. Clone Evolution: Track clonal dynamics and new mutations.

6. Transplant Timing: Optimize allo-HSCT timing decisions.

MPN Classification

High-Risk Mutations

Risk Scores

Workflow

1. Input: Serial molecular testing, CBC, clinical parameters.

2. Baseline Assessment: Calculate initial risk score.

3. Mutation Tracking: Monitor VAF trends over time.

4. Risk Recalculation: Update scores at each timepoint.

5. Progression Detection: Identify molecular/clinical progression.

6. Treatment Assessment: Evaluate response to therapy.

7. Output: Dynamic risk assessment, progression alerts, recommendations.

Example Usage

User: "Monitor this myelofibrosis patient's disease trajectory and update risk scores with new molecular data."

Agent Action:

python3 Skills/Hematology/MPN_Progression_Monitor_Agent/mpn_monitor.py \
    --patient_id MF_001 \
    --molecular_data serial_mutations.csv \
    --cbc_data serial_cbc.csv \
    --clinical_data symptoms.json \
    --mpn_type pmf \
    --baseline_date 2024-01-15 \
    --calculate_scores dipss,mipss70 \
    --output mpn_monitoring/

Input Requirements

Output Components

Progression Criteria

Response Criteria (IWG-MRT)

AI/ML Components

Progression Prediction:

• Survival analysis with molecular features
• Random survival forests
• Deep learning time-to-event

Clone Tracking:

• VAF trajectory modeling
• New clone detection
• Evolutionary tree inference

Transplant Decision:

• Survival benefit modeling
• NRM prediction
• Optimal timing algorithms

Treatment Response Monitoring

Prerequisites

• Python 3.10+
• lifelines, scikit-survival
• Variant annotation tools
• Risk score calculators
• Visualization libraries

Related Skills

• CHIP_Clonal_Hematopoiesis_Agent - Pre-MPN states
• MDS_Classification_Agent - Overlap syndromes
• Bone_Marrow_AI_Agent - Morphology analysis
• Coagulation_Thrombosis_Agent - Thrombosis risk

Thrombosis Risk in MPN

Special Considerations

1. Triple-Negative MPN: Different prognosis, consider other diagnoses
2. Cytogenetic Evolution: High-risk signal, BMB follow-up
3. New Mutations: May indicate disease evolution
4. Treatment Resistance: Consider second-line or transplant
5. Quality of Life: Balance treatment intensity

Transplant Indications

Author

AI Group - Biomedical AI Platform