Risk Stratification Indices logo

Risk Stratification Indices

Organization
awslabs
risk-stratification-indices

Reasoning skill for clinical risk stratification index selection and interpretation. Use when the user asks about LACE scores, Charlson Comorbidity Index, Elixhauser Index, readmission risk scoring, comorbidity weighting, SDOH Z-codes, Area Deprivation Index, or population health stratification methods.

Overview

Publisherawslabs
Repositoryhcls-agent-skills
Skill namerisk-stratification-indices
Stars
71
Forks
14
Bundled files
Instructions only
LicenseMIT-0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by awslabs on GitHub. Read the source before you install it.

Installation

Install the Risk Stratification Indices AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/awslabs/hcls-agent-skills/tree/main/skills/risk-stratification-indices
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/awslabs/hcls-agent-skills.git /tmp/hcls-agent-skills
mkdir -p .claude/skills
cp -r /tmp/hcls-agent-skills/skills/risk-stratification-indices .claude/skills/risk-stratification-indices
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Risk Stratification Indices in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Risk Stratification Indices on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Risk Stratification Indices is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Risk Stratification Indices Reasoning

Overview

Guide selection and interpretation of clinical risk stratification indices (LACE, Charlson, Elixhauser) and SDOH factors (Z-codes, ADI) for population health management. Based on validated scoring systems from peer-reviewed literature.

Usage

  • Activate when selecting a risk stratification index for a specific use case (readmission, mortality, utilization)
  • Activate when interpreting LACE, Charlson, or Elixhauser scores
  • Activate when incorporating SDOH factors (Z-codes, ADI) into population health stratification

Core Concepts

Response Format

Apply scoring logic internally. Present the recommended index with justification, scoring interpretation, and risk tier. Do not narrate the full scoring calculation unless asked.

1. Choosing a Risk Stratification Method

What is the use case?
├── 30-day readmission prediction
│   └── Use LACE index (designed for readmission)
├── Long-term mortality risk adjustment
│   └── Use Charlson Comorbidity Index
├── Hospital resource utilization / cost prediction
│   └── Use Elixhauser Comorbidity Index
├── Medicare risk adjustment (payment)
│   └── Use CMS-HCC (Hierarchical Condition Categories)
└── Population health stratification
    └── Combine clinical risk (Charlson/Elixhauser) + SDOH factors

2. LACE Index (Readmission Risk)

ComponentScoringRange
L — Length of stay1d=1, 2d=2, 3d=3, 4–6d=4, 7–13d=5, ≥14d=70–7
A — Acuity of admissionEmergent=3, Urgent=2, Elective=00–3
C — Comorbidity (Charlson)0=0, 1=1, 2=2, 3=3, ≥4=50–5
E — ED visits (prior 6 months)0=0, 1=1, 2=2, 3=3, ≥4=40–4
TotalSum of L+A+C+E0–19

Risk tiers: Low (0–4), Moderate (5–9), High (10+)

3. Charlson Comorbidity Index

17 conditions with integer weights:

  • Weight 1: MI, CHF, PVD, CVD, dementia, COPD, connective tissue disease, peptic ulcer, mild liver disease, uncomplicated diabetes
  • Weight 2: complicated diabetes, hemiplegia, renal disease, non-metastatic cancer
  • Weight 3: moderate/severe liver disease
  • Weight 6: metastatic tumor, AIDS/HIV

Total score = sum of all applicable weights.

4. Elixhauser Comorbidity Index

AttributeCharlsonElixhauser
Conditions1731
WeightingFixed integerVaries by model (van Walraven common)
ScopeMortality predictionMortality + resource use
Mental healthLimited (dementia only)Depression, psychoses, substance use
Best forLong-term mortalityHospital utilization, readmission

5. SDOH Risk Factors

ICD-10 Z-Codes for SDOH

Key ranges: Z55 (education/literacy), Z56 (employment), Z57 (occupational exposure), Z59 (housing/economic — Z59.0 homelessness, Z59.41 food insecurity), Z60 (social environment), Z62 (upbringing/abuse), Z63 (family circumstances), Z65 (psychosocial/legal).

Area Deprivation Index (ADI)

ADI PercentileRisk LevelImplication
1–25Low deprivationStandard outreach sufficient
26–50ModerateEnhanced reminder systems
51–75HighCare coordination, transportation assistance
76–100Very highIntensive outreach, community health workers

Incorporating SDOH into Stratification

Weight members higher when:

  1. Any SDOH Z-code documented in claims
  2. High ADI score (≥51st percentile)
  3. Dual-eligible status (Medicare + Medicaid)
  4. Language barrier (non-English preferred)
  5. No PCP visit in 12 months (care disengagement)

Common Mistakes

  • Wrong: Using Charlson for readmission prediction → Right: Use LACE (purpose-built for 30-day readmission)
  • Wrong: Using Elixhauser for long-term mortality → Right: Use Charlson (validated for mortality prediction)
  • Wrong: Ignoring SDOH factors in population stratification → Right: Combine clinical index + SDOH for actionable tiers
  • Wrong: Applying same outreach to all risk tiers → Right: Tailor interventions by barrier type (transportation, literacy, engagement)
  • Wrong: Using ADI alone without clinical risk → Right: ADI indicates access barriers; combine with clinical severity for full picture
  • Wrong: Treating all Z-codes as equivalent risk signals → Right: Weight by relevance to the specific outcome (e.g., Z59.0 homelessness is higher barrier than Z56 employment)

When to Escalate

  • When risk scores drive reimbursement or payment decisions (requires validated, audited implementation)
  • When stratification results will determine resource allocation across populations
  • When combining indices in novel ways not validated in literature

Frequently asked questions

What does the Risk Stratification Indices AI skill do?

Reasoning skill for clinical risk stratification index selection and interpretation. Use when the user asks about LACE scores, Charlson Comorbidity Index, Elixhauser Index, readmission risk scoring, comorbidity weighting, SDOH Z-codes, Area Deprivation Index, or population health stratification methods.

Why use Risk Stratification Indices on TypingMind?

Because you install it once and use it with any model. Risk Stratification Indices is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Risk Stratification Indices in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/awslabs/hcls-agent-skills/tree/main/skills/risk-stratification-indices. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Risk Stratification Indices?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Risk Stratification Indices?

As many as you like. As long as a model supports skills, you can use Risk Stratification Indices with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Risk Stratification Indices AI skill free?

Yes. It is published on GitHub by awslabs under the MIT-0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇