tooluniverse-clinical-risk-scoring

Clinical Risk Scoring

Turn a clinical scenario into the right validated risk score, compute it with a deterministic calculator tool, and interpret the number into a clinical action. All 10 backing tools are pure-compute (no network, no API key) and return {status, data:{score, interpretation, components, ...}}.

This skill is decision-support only — see LIMITATIONS. It does not replace clinical judgment.

Step 1 — Map the scenario to the score(s)

When the scenario names a pair, always run both — one alone is misleading (e.g. stroke risk without bleeding risk, or Child-Pugh without MELD-Na).

Step 2 — Gather the required inputs

Required vs optional inputs per tool (omitted booleans default to false/absent; omitted scalars are rejected when required):

If a required value is missing, ask the user for it — do not guess. State explicitly which booleans you assumed false.

Step 3 — Compute

tu run ClinicalCalc_CHA2DS2_VASc '{"age":76,"female":true,"hypertension":true,"diabetes":true}'

Every tool returns data.score plus a human-readable data.interpretation and a data.components breakdown (per-factor points). MELD/eGFR/ASCVD also return unit; Child-Pugh returns child_pugh_class; Wells PE returns three_tier and two_tier. Echo the components so the user can audit which factors drove the score.

Step 4 — Interpret (per-score tables)

CHA2DS2-VASc (stroke risk in AF, 0–9)

HAS-BLED (major bleeding on anticoagulation, 0–9)

How to weigh CHA2DS2-VASc + HAS-BLED together

A high HAS-BLED does not by itself withhold anticoagulation. If CHA2DS2-VASc meets the threshold, the stroke benefit usually outweighs bleeding risk; HAS-BLED instead flags modifiable risk factors to fix and patients needing closer monitoring. Only a very high, non-modifiable bleeding risk shifts the decision against anticoagulation.

CURB-65 (CAP severity, 0–5)

qSOFA (sepsis screen, 0–3)

Child-Pugh (cirrhosis severity, class A/B/C)

MELD-Na (90-day mortality / transplant priority, 6–40)

Wells DVT (pretest probability)

Wells PE (pretest probability)

ASCVD 10-year risk (%)

eGFR CKD-EPI (mL/min/1.73m^2) → CKD stage

Worked example A — Atrial fibrillation, weigh anticoagulation (paired)

76-year-old woman with AF, hypertension, type 2 diabetes; on an NSAID; no prior stroke/bleed, BP controlled, stable INR.

tu run ClinicalCalc_CHA2DS2_VASc '{"age":76,"female":true,"hypertension":true,"diabetes":true}'
# -> score 5: "Elevated risk (5) — oral anticoagulation recommended"
#    components: Age>=75 2, Hypertension 1, Diabetes 1, Female 1

tu run ClinicalCalc_HAS_BLED '{"age":76,"hypertension":true,"drugs":true}'
# -> score 3: "High bleeding risk (3) — caution, review reversible factors"
#    components: Hypertension_uncontrolled 1, Elderly_>65 1, Drugs_antiplatelet_NSAID 1

Interpretation. CHA2DS2-VASc 5 (>=3 for a woman) → anticoagulation recommended. HAS-BLED 3 is high but driven by modifiable factors: stop the NSAID and control BP and 2 of the 3 points disappear, lowering bleeding risk. The high HAS-BLED does not cancel anticoagulation — it directs you to fix reversible risks and monitor more closely.

Worked example B — Cirrhosis severity and transplant priority (paired)

Cirrhotic patient: bilirubin 3.5 mg/dL, albumin 2.5 g/dL, INR 2.4, moderate ascites, grade 1–2 encephalopathy; creatinine 2.0, sodium 128, not on dialysis.

tu run ClinicalCalc_Child_Pugh '{"bilirubin":3.5,"albumin":2.5,"inr":2.4,"ascites":"moderate","encephalopathy":"grade1-2"}'
# -> score 14, child_pugh_class "C": "Class C (score 14): decompensated disease"

tu run ClinicalCalc_MELD_Na '{"creatinine":2.0,"bilirubin":5.0,"inr":2.0,"sodium":128,"dialysis":false}'
# -> score 31: "MELD-Na 31: very high ... 90-day mortality risk"

Interpretation. Child-Pugh class C (14) = decompensated cirrhosis, very high surgical/anesthetic risk — avoid elective surgery. MELD-Na 31 implies roughly a third-or-higher 90-day mortality and a high transplant-allocation priority. Together they justify urgent hepatology / transplant evaluation. (Note MELD uses bilirubin 5.0 and INR 2.0 from this patient's labs; lower bounds of 1.0 are applied internally.)

Completeness checklist

• Picked the score(s) that match the scenario — ran both members of a pair (CHA2DS2-VASc+HAS-BLED, Child-Pugh+MELD-Na)
• Confirmed all required inputs; asked for missing ones rather than guessing
• Stated which optional booleans were assumed false
• Reported score, interpretation, and the components breakdown
• Mapped the score to a clinical action using the interpretation table
• For pairs, explained how to weigh the two scores together
• Stated the LIMITATIONS caveat (decision-support, validated population, ASCVD age 40–79)

LIMITATIONS

• Decision-support only. These scores inform, but do not replace, clinical judgment and the full clinical picture. Do not present output as a treatment directive.
• Validated populations. Each score was derived/validated in specific cohorts and may not transfer to children, pregnancy, valvular AF (CHA2DS2-VASc is for non-valvular AF), or other excluded groups.
• ASCVD Pooled Cohort Equations are validated only for ages 40–79 and the White / African-American coefficient sets; they can mis-estimate for other ancestries and are for primary prevention (no prior ASCVD event).
• eGFR CKD-EPI assumes stable kidney function (steady-state creatinine); it is unreliable in acute kidney injury, extremes of muscle mass, or amputees, and a single value does not stage CKD on its own.
• qSOFA / CURB-65 / Wells are screening / pretest-probability tools — a reassuring score does not exclude the diagnosis; combine with clinical gestalt and confirmatory testing.
• MELD-Na / Child-Pugh apply to chronic liver disease; they do not capture acute liver failure or hepatocellular-carcinoma exception points.
• Inputs are taken at face value — garbage in, garbage out. Verify lab units (mg/dL vs mmol/L, BUN vs urea) before entry.
• Not a substitute for institutional protocols, guideline updates, or specialist consultation.