Coding Hcc Risk Adjustment

What it does

When your agent uses it

• The user wants to surface risk-adjustable diagnoses from notes
• Map ICD-10-CM codes to HCC categories
• Reconcile a patient/panel RAF
• Find suspected-but-undocumented HCCs

Example prompts

• “/coding-hcc-risk-adjustment”

Requirements

• Python 3

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

1. 1Extract condition spans with OpenMed (Disease/Pathology/Oncology models).
2. 2Code each to ICD-10-CM (see coding-icd10) — HCCs key off ICD-10-CM.
3. 3Map ICD-10-CM → V28 HCC via the CMS crosswalk.
4. 4Apply the hierarchy so only the most severe HCC in each family counts.
5. 5Sum coefficients for the correct model segment + add the demographic factor
6. 6Attach MEAT evidence: for each candidate HCC, cite the note text that
7. 7Emit candidate HCCs + estimated RAF + supporting offsets for human review.

What it can do on your machine

Read from SKILL.md and the folder at commit 9dca507. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md (its code samples are python).

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Links to these hosts (documentation or services it may open):

  • cms.gov

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Coding Hcc Risk Adjustment loads about 2.2k tokens when it runs. Until then it costs about 216 tokens; SKILL.md has 683 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~216

When it runs · the whole SKILL.md, loaded when a task matches

~2.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from maziyarpanahi/openmed at commit 9dca507, republished under its Apache-2.0 licence (© maziyarpanahi). 683 words, ~2,231 tokens.

name

coding-hcc-risk-adjustment

description

Maps chronic conditions extracted by OpenMed to CMS-HCC V28 risk-adjustment categories and estimates a RAF (Risk Adjustment Factor) score as decision support. Use when the user wants to surface risk-adjustable diagnoses from notes, map ICD-10-CM codes to HCC categories, estimate or reconcile a patient/panel RAF, find suspected-but-undocumented HCCs, or check MEAT documentation support. Trigger keywords: HCC, CMS-HCC, V28, RAF score, risk adjustment, Medicare Advantage, hierarchical condition category, MEAT, recapture, suspect HCC, RADV. Pairs after OpenMed NER + ICD-10 coding: consume Disease/Pathology entities from openmed.analyze_text, code them (see coding-icd10), then roll up to HCCs. CMS-HCC mappings and weights are public from CMS. This is a coding-support aid for human review, never autonomous risk-adjustment coding.

license

Apache-2.0

metadata.project

OpenMed

metadata.category

terminology-coding

metadata.pairs

after

metadata.version

1.0

import csv

# 1) ICD-10-CM -> HCC (V28) crosswalk from the CMS Risk Adjustment files.
icd_to_hcc = {}                       # "E1122" -> "HCC38" (Diabetes w/ complication)
with open("cms_hcc_v28_icd_map.csv") as fh:
    for row in csv.DictReader(fh):
        icd_to_hcc[row["icd10cm"].replace(".", "")] = row["hcc_v28"]

# 2) HCC -> RAF coefficient for the relevant model segment (e.g. CNA community).
hcc_weight = {}                       # "HCC38" -> 0.166 (illustrative)
with open("cms_hcc_v28_coefficients.csv") as fh:
    for row in csv.DictReader(fh):
        hcc_weight[row["hcc"]] = float(row["coefficient"])

# 3) Apply the HCC hierarchy: a more severe HCC in a family suppresses milder
#    ones (e.g. acute MI suppresses angina). Load the hierarchy from CMS.
hierarchy = {                         # parent HCC -> HCCs it zeroes out
    # "HCC37": {"HCC38"},  # illustrative; use the official V28 hierarchy file
}

def apply_hierarchy(hccs: set[str]) -> set[str]:
    kept = set(hccs)
    for parent in hccs:
        kept -= hierarchy.get(parent, set())
    return kept

def estimate_raf(icd_codes: list[str], demo_factor: float = 0.0) -> dict:
    hccs = {icd_to_hcc[c] for c in icd_codes if c in icd_to_hcc}
    hccs = apply_hierarchy(hccs)
    disease_raf = sum(hcc_weight.get(h, 0.0) for h in hccs)
    return {"hccs": sorted(hccs),
            "disease_raf": round(disease_raf, 3),
            "estimated_raf": round(disease_raf + demo_factor, 3)}

import openmed

note = ("Problem list: type 2 diabetes with diabetic nephropathy; COPD. "
        "Plan: continue metformin, ordered HbA1c, refer nephrology.")
result = openmed.analyze_text(
    note,
    model_name="disease_detection_superclinical",   # Disease category
    output_format="dict",
)

DX_LABELS = {"DISEASE", "CONDITION", "PATHOLOGY"}
suspects = []
for ent in result["entities"]:
    if ent["label"] in DX_LABELS:
        # 1) code to ICD-10-CM (coding-icd10) -> e.g. "E1122"
        icd = map_to_icd10cm(ent["text"])           # your coding step
        hcc = icd_to_hcc.get(icd)
        if hcc:
            # MEAT: capture the sentence around the span for the reviewer
            sent = note[max(0, ent["start"] - 60): ent["end"] + 80]
            suspects.append({"condition": ent["text"], "icd10cm": icd,
                             "hcc": hcc, "span": (ent["start"], ent["end"]),
                             "meat_context": sent})

raf = estimate_raf([s["icd10cm"] for s in suspects])
print(raf, suspects)        # candidates + estimate, for coder validation

© maziyarpanahi, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/coding-hcc-risk-adjustment of maziyarpanahi/openmed.

Open the folder on GitHubat commit 9dca507