Medical Decision-Making Capacity Assessment Constraint Verification Benchmark
#clinical constraint verification #evidence-based reasoning #gap and conflict detection #medical decision-making capacity assessment #clinical competency evaluation #patient autonomy protection
- 5000
- 0.3GB
- JSON
- CATL
MOBIUSI INC
Updated:2026-11-02
AI Analysis & Value Prop
This benchmark presents structured JSON cases containing specific medical decisions, patient interview evidence, clinical context, and claimed decision-making capacity assessments to be verified. Cases focus on the elements required for each decision, enabling evaluation of whether conclusions are supported by the evidence and whether material information gaps or conflicts are identified. It is designed for model evaluation, constraint reasoning research, and clinical AI validation in consultation-liaison psychiatry.
Dataset Insights
Sample Examples
{}
Technical Specifications
| Field | Type | Description |
|---|---|---|
| file_name | string | File name |
| evidence_gaps | array | Material information missing from the record that prevents or limits validation of the assessment. |
| overall_result | string | The overall judgment on whether the claimed assessment is supported by the available decision-specific evidence. |
| clinical_context | object | Relevant clinical and communication information for interpreting the interview evidence. |
| decision_context | object | The medical decision being considered and the stakes specific to that decision. |
| constraint_checks | array | Explicit checks of whether the proposed assessment follows the constraints of a decision-specific capacity evaluation. |
| overall_rationale | string | A concise synthesis of the required elements, constraint checks, evidence gaps, and conflicts supporting the overall result. |
| required_elements | array | Decision-specific capacity elements and an evidence-based assessment of whether each element is addressed. |
| claimed_assessment | object | The capacity determination and supporting rationale to evaluate against the specific decision and interview evidence. |
| evidence_conflicts | array | Material contradictions among the interview evidence, clinical context, and claimed assessment. |
| interview_evidence | array | Patient statements and observations from the interview that may support or challenge capacity elements. |
Compliance Statement
| Authorization Type | Proprietary - Commercial AI Training License (No Redistribution) |
| Commercial Use | Requires exclusive subscription or authorization contract (monthly or per-invocation charging) |
| Privacy and Anonymization | No PII, no real company names, simulated scenarios follow industry standards |
| Compliance System | Compliant with China's Data Security Law / EU GDPR / supports enterprise data access logs |
Frequently Asked Questions
- What does the benchmark contain?
- Cases are organized as JSON and cover specific medical decisions, patient interview evidence, clinical context, claimed capacity assessments, required assessment elements, constraint checks, evidence gaps, evidence conflicts, and overall validation results.
- Which capabilities can this benchmark evaluate?
- It can evaluate whether a model connects a capacity assessment to the specific decision and interview evidence, checks whether required elements are supported, and identifies missing or conflicting information. It is suitable for domain evaluation and clinical reasoning research related to consultation-liaison psychiatry.
- What is the data structure and quality?
- The data uses structured JSON with explicit fields for decision context, interview evidence, clinical context, assessment claims, and validation results, making it suitable for parsing and evaluation workflows. Refer to the product listing for the available sample count, coverage, and version details.
- How can I access the data, and what are the licensing terms?
- Check the product listing for available access methods, delivery formats, and licensing terms. Confirm the permitted scope of use and applicable privacy and clinical compliance requirements before use. Benchmark results are intended for model evaluation research and should not replace professional clinical judgment.
Can't find the data you need?
Post a request and let data providers reach out to you.
Get this Dataset
Verified for Enterprise UseCite this Work
@dataset{Mobiusi2026,
title={Medical Decision-Making Capacity Assessment Constraint Verification Benchmark},
author={MOBIUSI INC},
year={2026},
url={https://www.mobiusi.com/datasets/6b1c42c1d5717471b570e2c8c6b382fd?dataset_task_cate_id=1},
urldate={2026-10-12},
keywords={medical decision-making capacity,capacity assessment benchmark,consultation-liaison psychiatry,constraint verification dataset,clinical evidence reasoning,patient interview analysis,evidence gap detection,medical AI evaluation},
version={1.0}
}Using this in research? Please cite us.
placeholder
placeholder
placeholder
placeholder
placeholder
placeholder
placeholder