菜单
Teaches agents clinical reference ranges, condition codes, quality measure definitions, drug classifications, and regulatory context so they can flag abnormal values and identify care gaps.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | clinical-knowledge |
| description | Teaches agents clinical reference ranges, condition codes, quality measure definitions, drug classifications, and regulatory context so they can flag abnormal values and identify care gaps. |
| metadata | {"openclaw":{"requires":{"bins":["python3"]}}} |
The 21st Century Cures Act (2016) and ONC's Interoperability Final Rule (2020) require US healthcare organizations to expose patient data through standardized FHIR APIs. As of 2024, ~70% of US hospitals support FHIR R4 (source: ONC). CMS ties quality measure reporting to reimbursement through programs like MIPS (Merit-based Incentive Payment System) and the Hospital Value-Based Purchasing Program. Failure to report -- or poor performance -- results in payment adjustments of up to 9%.
HIPAA (Health Insurance Portability and Accountability Act) prohibits transmitting Protected Health Information (PHI) to external services without a BAA (Business Associate Agreement). This is the primary reason clinical AI must run locally: cloud LLM APIs are not BAA-covered by default, and even those that offer BAAs (e.g., Azure OpenAI) face institutional resistance from hospital compliance teams.
These are general adult reference ranges. Values vary by lab, assay, and patient characteristics. Always defer to the performing laboratory's reference range when available via FHIR referenceRange.
| Lab | Normal Range | Concerning | Unit | Notes |
|---|---|---|---|---|
| HbA1c | < 5.7% (non-diabetic), < 7.0% (diabetic target) | > 9.0% = poor control | % | ADA 2024 guidelines; target may be relaxed to < 8.0% for elderly/frail |
| Fasting Glucose | 70-100 | 100-125 = prediabetes, >= 126 = diabetic | mg/dL | Must be fasting; random glucose >= 200 also diagnostic |
| Creatinine | 0.7-1.3 (male), 0.6-1.1 (female) | > 1.5 = impaired renal | mg/dL | Affected by muscle mass; less reliable in elderly |
| eGFR | > 90 (normal), 60-89 (mild decrease) | 30-59 = moderate CKD, 15-29 = severe, < 15 = kidney failure | mL/min/1.73m2 | CKD-EPI 2021 equation (race-neutral) |
| BUN | 7-20 | > 20 with rising creatinine = renal concern | mg/dL | Elevated by dehydration, high protein diet |
| Total Cholesterol | < 200 | 200-239 = borderline, >= 240 = high | mg/dL | |
| LDL | < 100 (general), < 70 (high-risk ASCVD) | > 160 = high | mg/dL | ACC/AHA 2018 |
| HDL | > 40 (male), > 50 (female) | < 40 = cardiovascular risk factor | mg/dL | |
| Triglycerides | < 150 | 150-499 = elevated, >= 500 = severe (pancreatitis risk) | mg/dL | |
| Systolic BP | < 120 (normal), 120-129 (elevated) | 130-139 = Stage 1 HTN, >= 140 = Stage 2 HTN | mmHg | ACC/AHA 2017; CMS165 uses 140/90 threshold |
| Diastolic BP | < 80 | 80-89 = Stage 1 HTN, >= 90 = Stage 2 HTN | mmHg | |
| BNP | < 100 | 100-400 = possible HF, > 400 = likely HF | pg/mL | Age-adjusted: higher cutoffs in elderly; obesity lowers BNP |
| NT-proBNP | < 300 (rule-out) | Age-stratified: >450 (<50y), >900 (50-75y), >1800 (>75y) | pg/mL | More stable than BNP; renal clearance affects levels |
| Potassium | 3.5-5.0 | < 3.5 = hypokalemia, > 5.5 = hyperkalemia (cardiac risk) | mEq/L | Critical for patients on ACEi/ARB/spironolactone |
| Sodium | 136-145 | < 130 = moderate hyponatremia | mEq/L | Common in HF patients |
| ALT | 7-56 | > 3x ULN = significant hepatotoxicity | U/L | Monitor with statin therapy |
| Hemoglobin | 13.5-17.5 (male), 12.0-16.0 (female) | < 12 (male) or < 11 (female) = anemia | g/dL | Common in CKD (erythropoietin deficiency) |
When reporting lab values:
referenceRange, use that instead of the table above| Code | Condition | ICD-10 Equivalent | Prevalence (US adults) |
|---|---|---|---|
| 44054006 | Type 2 Diabetes Mellitus | E11.x | ~11% (37M) |
| 46635009 | Type 1 Diabetes Mellitus | E10.x | ~0.5% (1.6M) |
| 38341003 | Essential Hypertension | I10 | ~47% (116M) |
| 84114007 | Heart Failure | I50.x | ~2.4% (6.7M) |
| 40055000 | Chronic Kidney Disease | N18.x | ~15% (37M) |
| 53741008 | Coronary Artery Disease | I25.x | ~7% (20M) |
| 13645005 | COPD | J44.x | ~6% (16M) |
| 195967001 | Asthma | J45.x | ~8% (25M) |
| 49436004 | Atrial Fibrillation | I48.x | ~2% (6M) |
| 73211009 | Diabetes (unspecified) | E11.9 | Used in older records |
When FHIR Condition resources use ICD-10 coding (system http://hl7.org/fhir/sid/icd-10-cm), map as follows:
Note: A Condition resource may have both SNOMED and ICD-10 codes in the coding array. Always check all entries, not just coding[0].
| Component | Definition |
|---|---|
| Denominator | Patients 18-75 with diabetes (Type 1 or Type 2) and at least 2 encounters during the measurement period |
| Numerator | Patients with most recent HbA1c > 9.0%, OR no HbA1c recorded during the measurement period |
| Exclusions | Hospice care, palliative care, advanced illness with frailty (2+ encounters for advanced illness AND frailty diagnosis), dementia medications (donepezil, rivastigmine, memantine, galantamine) |
| Performance rate | Lower is better (inverse measure) |
| Payment impact | Part of MIPS quality reporting; affects Medicare reimbursement |
| Component | Definition |
|---|---|
| Denominator | Patients 18-85 with essential hypertension diagnosed before or during the measurement period |
| Numerator | Patients with most recent BP < 140/90 mmHg |
| Exclusions | Hospice, palliative care, ESRD, kidney transplant, advanced illness with frailty, pregnancy |
| Performance rate | Higher is better |
| Note | BP must be measured during an outpatient encounter; home BP readings are not counted in the standard measure |
| Component | Definition |
|---|---|
| Denominator | Patients 18+ with heart failure AND documented LVEF < 40% (HFrEF) |
| Numerator | Patients prescribed ACE inhibitor, ARB, or ARNI (sacubitril/valsartan) |
| Exclusions | Hospice, allergy/intolerance to all three classes, bilateral renal artery stenosis, pregnancy, hyperkalemia > 5.5 |
| Note | LVEF data often in DiagnosticReport or CarePlan, not always queryable via Condition alone |
| Component | Definition |
|---|---|
| Denominator | Patients 18-75 with diabetes |
| Numerator | Patients with nephropathy screening (urine albumin test) OR evidence of nephropathy treatment (ACEi/ARB) OR nephropathy diagnosis |
| Exclusions | Hospice, palliative care, advanced illness with frailty |
When checking medication coverage, recognize these drug class groupings. Matching should be case-insensitive partial string matching on the medication name from FHIR medicationCodeableConcept.text or .coding[].display.
| Class | Drugs | Notes |
|---|---|---|
| Biguanide | metformin | First-line therapy |
| Sulfonylureas | glipizide, glyburide, glimepiride | Hypoglycemia risk |
| Insulin | insulin lispro, insulin glargine, insulin aspart, insulin detemir, insulin degludec, NPH insulin | Match any string containing "insulin" |
| GLP-1 Receptor Agonists | liraglutide (Victoza), semaglutide (Ozempic/Wegovy/Rybelsus), dulaglutide (Trulicity), exenatide (Byetta/Bydureon), tirzepatide (Mounjaro) | Weight loss benefit; cardiovascular benefit |
| SGLT2 Inhibitors | empagliflozin (Jardiance), dapagliflozin (Farxiga), canagliflozin (Invokana), ertugliflozin (Steglatro) | Cardiovascular + renal benefit; monitor for DKA |
| DPP-4 Inhibitors | sitagliptin (Januvia), saxagliptin, linagliptin, alogliptin | Weight-neutral |
| Thiazolidinediones | pioglitazone, rosiglitazone | HF risk; edema |
| Class | Drugs | Notes |
|---|---|---|
| ACE Inhibitors | lisinopril, enalapril, ramipril, benazepril, fosinopril, quinapril | Cough side effect; monitor K+ and creatinine |
| ARBs | losartan, valsartan, irbesartan, olmesartan, telmisartan, candesartan, azilsartan | Alternative if ACEi cough |
| ARNIs | sacubitril/valsartan (Entresto) | HFrEF guideline-directed; do NOT combine with ACEi |
| CCBs | amlodipine, nifedipine, diltiazem, verapamil | Diltiazem/verapamil contraindicated in HFrEF |
| Beta-Blockers | metoprolol (tartrate or succinate), atenolol, carvedilol, bisoprolol, propranolol, nebivolol | Only carvedilol, metoprolol succinate, bisoprolol for HF |
| Thiazide Diuretics | hydrochlorothiazide (HCTZ), chlorthalidone, indapamide | First-line for HTN |
| Loop Diuretics | furosemide, bumetanide, torsemide | Volume management in HF, not primary HTN therapy |
| Aldosterone Antagonists | spironolactone, eplerenone | HF benefit; monitor K+ |
| Intensity | Drugs |
|---|---|
| High | atorvastatin 40-80mg, rosuvastatin 20-40mg |
| Moderate | atorvastatin 10-20mg, rosuvastatin 5-10mg, simvastatin 20-40mg, pravastatin 40-80mg |
| Low | simvastatin 10mg, pravastatin 10-20mg, lovastatin 20mg |
The four pillars of HFrEF therapy (ACC/AHA 2022):
medication_name = fhir_med_text.lower()
is_on_insulin = "insulin" in medication_name
is_on_glp1 = any(drug in medication_name for drug in
["liraglutide", "semaglutide", "dulaglutide", "exenatide", "tirzepatide",
"victoza", "ozempic", "trulicity", "byetta", "mounjaro", "rybelsus"])
is_on_sglt2 = any(drug in medication_name for drug in
["empagliflozin", "dapagliflozin", "canagliflozin", "ertugliflozin",
"jardiance", "farxiga", "invokana", "steglatro"])
is_on_acei = any(drug in medication_name for drug in
["lisinopril", "enalapril", "ramipril", "benazepril", "fosinopril", "quinapril"])
is_on_arb = any(drug in medication_name for drug in
["losartan", "valsartan", "irbesartan", "olmesartan", "telmisartan",
"candesartan", "azilsartan"])
is_on_betablocker = any(drug in medication_name for drug in
["metoprolol", "atenolol", "carvedilol", "bisoprolol", "propranolol", "nebivolol"])
is_on_statin = any(drug in medication_name for drug in
["atorvastatin", "rosuvastatin", "simvastatin", "pravastatin", "lovastatin"])
Common co-occurring conditions to watch for during analysis:
Configure NVIDIA MIG (Multi-Instance GPU) partitions on the DGX Station GB300, including enabling MIG mode, choosing a profile layout, creating instances, and retrieving MIG UUIDs. Use when the user asks to partition the GB300, set up MIG, run multiple models in isolation on one GPU, or reconfigure existing MIG instances.
Diagnose common DGX Station GB300 issues — CUDA crashes, wrong-GPU targeting, vLLM/SGLang container bugs, MIG state problems, NVLink/Fabric Manager errors, X/Vulkan failures, HuggingFace auth, and port conflicts. Use when the user reports a GPU error, inference server crash, MIG problem, or any unexplained DGX Station failure.
Deploy an SGLang inference server on an NVIDIA DGX Station GB300 with the cu130 container, RadixAttention prefix caching, and structured JSON output support. Use when the user asks to serve a model with SGLang, start an SGLang endpoint, or needs structured-output inference on DGX Station.
Deploy a vLLM inference server on an NVIDIA DGX Station GB300 with validated container, GPU targeting, and tuning parameters. Use when the user asks to serve a model with vLLM, start a vLLM endpoint, or set up OpenAI-compatible inference on DGX Station.
Teaches the analyst agent how to write correct, robust Python analysis code for FHIR clinical data using pandas, matplotlib, and scipy.
Prepare a complete clinical case summary for a patient from FHIR endpoints. Use when asked to summarize a patient, compile a case, or prepare for tumor board.