Medication Reconciliation

Compare patient pre-admission medication lists with inpatient orders to automatically identify omitted or duplicated medications and improve medication safety.

Medical Disclaimer: This tool is for reference only. Final medication decisions must be confirmed by qualified medical staff. All patient data must comply with applicable data protection regulations (e.g., HIPAA).

Quick Check

python -m py_compile scripts/main.py
python scripts/main.py --help

When to Use

• Use this skill when comparing pre-admission medication lists against inpatient orders to detect omissions or duplicates.
• Use this skill when generating structured reconciliation reports for clinical handover or pharmacy review.
• Do not use this skill as a substitute for pharmacist or physician review of medication orders.

Workflow

1. PHI Check: Before processing, prompt the user to confirm data has been de-identified: "Please confirm that the input files have been de-identified or that you have authorization to process this patient data under applicable regulations (e.g., HIPAA) before proceeding."
2. Confirm patient ID, pre-admission medication list, and inpatient orders are available.
3. Validate that both input files are well-formed and patient IDs match.
4. Run the reconciliation script or apply the manual comparison path.
5. Return a structured report separating continued, discontinued, new, and duplicate medications.
6. Dose-change detection: When a drug appears in both lists with different dose strings, flag it as dose_changed with a warning: "Dose change detected — verify with prescribing physician before proceeding."
7. Flag warnings for critical drug classes (anticoagulants, hypoglycemics, antihypertensives, antiepileptics).
8. If inputs are incomplete, state exactly which fields are missing and request only the minimum additional information.

Usage

# Basic usage
python scripts/main.py --pre-admission pre_meds.json --inpatient orders.json --output report.json

# Use example data
python scripts/main.py --example

# Verbose output
python scripts/main.py --pre-admission pre_meds.json --inpatient orders.json --verbose

Parameters

Output Format