A clinical decision support tool that predicts the probability of developing anti-drug antibodies against biologics in rheumatic disease patients.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install ada-predictor
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install ada-predictor using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is ADA-Predictor: Biologic Therapy Risk Stratification?
ADA-Predictor is a sophisticated clinical stratification tool designed to calculate the risk of developing anti-drug antibodies (ADA) in patients receiving biologic therapies such as TNF inhibitors. As part of the Openclaw Skills ecosystem, this tool addresses the significant clinical challenge of secondary loss of efficacy, which impacts a substantial percentage of patients on biologic DMARDs. By synthesizing pharmacogenomic data, treatment history, and clinical variables, it provides a data-driven approach to personalized medicine in rheumatology.
The skill utilizes a weighted logistic composite model to produce a risk score between 0 and 100. This score allows healthcare providers to proactively manage treatment through optimized methotrexate co-prescription and tailored Therapeutic Drug Monitoring (TDM) intervals. This Openclaw Skills implementation bridges the gap between clinical literature and bedside application, helping to prevent infusion reactions and costly treatment failures.
ADA-Predictor: Biologic Therapy Risk Stratification Use Cases
- Pre-treatment risk stratification for patients starting adalimumab, infliximab, or etanercept.
- Optimizing methotrexate dosing to minimize the risk of immunogenicity.
- Determining personalized Therapeutic Drug Monitoring (TDM) schedules for high-risk patients.
- Evaluating the impact of HLA-DQA1*05 carrier status on long-term biologic efficacy.
- Assisting in the selection of alternative biologic classes for patients with very high ADA risk scores.
How ADA-Predictor: Biologic Therapy Risk Stratification Works
- The user provides patient-level clinical data, including biologic type, methotrexate dosage, and baseline CRP levels.
- The system validates the patient profile against clinical constraints and identifies the biologic classification (monoclonal antibody vs. fusion protein).
- A weighted logistic regression algorithm processes factors such as HLA-DQA1*05 status, smoking, BMI, and disease duration using coefficients derived from peer-reviewed clinical studies.
- The probability of ADA development is calculated and converted into a normalized risk score.
- The patient is assigned to a risk tier (Low, Moderate, High, or Very High) which triggers specific clinical recommendations and TDM intervals.
- A Monte Carlo sensitivity analysis is optionally performed to provide a 95% confidence interval for the risk score, accounting for parameter uncertainty.
ADA-Predictor: Biologic Therapy Risk Stratification Setup
To deploy this skill within your environment, ensure you have the required dependencies installed and run the predictor script:
pip install numpy
python3 ada_predictor.py
ADA-Predictor: Biologic Therapy Risk Stratification Data Schema & Taxonomy
The skill utilizes a structured PatientProfile input and generates a detailed analytical report. The output follows this schema:
| Attribute | Description | Data Type |
|---|---|---|
ada_probability |
Raw probability of antibody development | Float |
risk_score |
Normalized risk metric (0-100) | Integer |
risk_tier |
Clinical risk classification | String |
recommended_tdm_weeks |
Suggested interval for drug monitoring | Integer |
factors |
Breakdown of clinical variables used in calculation | Object |
ci_95 |
95% Confidence Interval from Monte Carlo simulation | Array |
ADA-Predictor: Biologic Therapy Risk Stratification Advanced Features
- Monte Carlo sensitivity analysis for robust risk estimation under clinical uncertainty.
- Support for pharmacogenomic markers including HLA-DQA1*05 carrier status.
- Comprehensive recommendation engine for methotrexate optimization and biologic switching.
- Integration-ready JSON output for secondary analysis or EHR synchronization within the Openclaw Skills framework.
- Automated risk tiering based on evidence-based Therapeutic Drug Monitoring (TDM) protocols.
SKILL.md
Loading
Related Openclaw Skills
Follow-Through Day (FTD) Detector
A market timing state machine that detects Follow-Through Day signals to confirm market bottoms using the S&P 500 and NASDAQ indices.
Sora 2 Generate
A professional-grade skill for generating high-fidelity AI videos from text prompts or public image URLs using the Sora 2 engine.
Lobster Memory Master
Lobster Memory Master is a comprehensive long-term memory management system that transforms stateless AI into a stateful assistant with persistent recall and automated context compaction.
Smart Answering Framework
A sophisticated reasoning framework that dynamically adapts response structures based on question types to deliver evidence-based, natural-sounding answers.
Feishu Image Sender
A specialized utility for sending inline images directly through the Feishu Open Platform API, bypassing standard file attachment limitations.
MCP Server Chart
A comprehensive data visualization and mapping skill that enables AI agents to generate over 25 types of professional charts and diagrams via the OneKey Gateway.
Featured*
