Advancing AI Trustworthiness Through Patient Simulation: Risk Assessment of Conversational Agents for Antidepressant Selection
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911547808284672 |
|---|---|
| author | Shawon, Md Tanvir Rouf Irbaz, Mohammad Sabik Elyazori, Hadeel R. A. Resapu, Keerti Reddy Lin, Yili Cardenas, Vladimir Franzuela Alemi, Farrokh Lybarger, Kevin |
| author_facet | Shawon, Md Tanvir Rouf Irbaz, Mohammad Sabik Elyazori, Hadeel R. A. Resapu, Keerti Reddy Lin, Yili Cardenas, Vladimir Franzuela Alemi, Farrokh Lybarger, Kevin |
| contents | Objective: This paper introduces a patient simulator for scalable, automated evaluation of healthcare conversational agents, generating realistic, controllable interactions that systematically vary across medical, linguistic, and behavioral dimensions to support risk assessment across populations. Methods: Grounded in the NIST AI Risk Management Framework, the simulator integrates three profile components: (1) medical profiles constructed from All of Us electronic health records using risk-ratio gating; (2) linguistic profiles modeling health literacy and condition-specific communication; and (3) behavioral profiles representing cooperative, distracted, and adversarial engagement. Profiles were evaluated against NIST AI RMF trustworthiness requirements and assessed against an AI Decision Aid for antidepressant selection. Results: Across 500 simulated conversations, the simulator revealed monotonic degradation in AI Decision Aid performance across health literacy levels: Rank-1 concept retrieval ranged from 47.6% (limited) to 81.9% (proficient), with corresponding recommendation degradation. Medical concept fidelity was high (96.6% across 8,210 concepts), validated by human annotators (0.73 kappa) and an LLM judge with comparable agreement (0.78 kappa). Behavioral profiles were reliably distinguished (0.93 kappa), and linguistic profiles showed moderate agreement (0.61 kappa). Conclusions: The simulator exposes measurable performance risks in conversational healthcare AI. Health literacy emerged as a primary risk factor with direct implications for equitable AI deployment. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_11391 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Advancing AI Trustworthiness Through Patient Simulation: Risk Assessment of Conversational Agents for Antidepressant Selection Shawon, Md Tanvir Rouf Irbaz, Mohammad Sabik Elyazori, Hadeel R. A. Resapu, Keerti Reddy Lin, Yili Cardenas, Vladimir Franzuela Alemi, Farrokh Lybarger, Kevin Computation and Language Objective: This paper introduces a patient simulator for scalable, automated evaluation of healthcare conversational agents, generating realistic, controllable interactions that systematically vary across medical, linguistic, and behavioral dimensions to support risk assessment across populations. Methods: Grounded in the NIST AI Risk Management Framework, the simulator integrates three profile components: (1) medical profiles constructed from All of Us electronic health records using risk-ratio gating; (2) linguistic profiles modeling health literacy and condition-specific communication; and (3) behavioral profiles representing cooperative, distracted, and adversarial engagement. Profiles were evaluated against NIST AI RMF trustworthiness requirements and assessed against an AI Decision Aid for antidepressant selection. Results: Across 500 simulated conversations, the simulator revealed monotonic degradation in AI Decision Aid performance across health literacy levels: Rank-1 concept retrieval ranged from 47.6% (limited) to 81.9% (proficient), with corresponding recommendation degradation. Medical concept fidelity was high (96.6% across 8,210 concepts), validated by human annotators (0.73 kappa) and an LLM judge with comparable agreement (0.78 kappa). Behavioral profiles were reliably distinguished (0.93 kappa), and linguistic profiles showed moderate agreement (0.61 kappa). Conclusions: The simulator exposes measurable performance risks in conversational healthcare AI. Health literacy emerged as a primary risk factor with direct implications for equitable AI deployment. |
| title | Advancing AI Trustworthiness Through Patient Simulation: Risk Assessment of Conversational Agents for Antidepressant Selection |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2602.11391 |