An Agentic AI Workflow for Detecting Cognitive Concerns in Real-world Data
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915137051426816 |
|---|---|
| author | Tian, Jiazi Wang, Liqin Fard, Pedram Junior, Valdery Moura Blacker, Deborah Haas, Jennifer S. Patel, Chirag Murphy, Shawn N. Moura, Lidia M. V. R. Estiri, Hossein |
| author_facet | Tian, Jiazi Wang, Liqin Fard, Pedram Junior, Valdery Moura Blacker, Deborah Haas, Jennifer S. Patel, Chirag Murphy, Shawn N. Moura, Lidia M. V. R. Estiri, Hossein |
| contents | Early identification of cognitive concerns is critical but often hindered by subtle symptom presentation. This study developed and validated a fully automated, multi-agent AI workflow using LLaMA 3 8B to identify cognitive concerns in 3,338 clinical notes from Mass General Brigham. The agentic workflow, leveraging task-specific agents that dynamically collaborate to extract meaningful insights from clinical notes, was compared to an expert-driven benchmark. Both workflows achieved high classification performance, with F1-scores of 0.90 and 0.91, respectively. The agentic workflow demonstrated improved specificity (1.00) and achieved prompt refinement in fewer iterations. Although both workflows showed reduced performance on validation data, the agentic workflow maintained perfect specificity. These findings highlight the potential of fully automated multi-agent AI workflows to achieve expert-level accuracy with greater efficiency, offering a scalable and cost-effective solution for detecting cognitive concerns in clinical settings. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_01789 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | An Agentic AI Workflow for Detecting Cognitive Concerns in Real-world Data Tian, Jiazi Wang, Liqin Fard, Pedram Junior, Valdery Moura Blacker, Deborah Haas, Jennifer S. Patel, Chirag Murphy, Shawn N. Moura, Lidia M. V. R. Estiri, Hossein Artificial Intelligence Multiagent Systems Early identification of cognitive concerns is critical but often hindered by subtle symptom presentation. This study developed and validated a fully automated, multi-agent AI workflow using LLaMA 3 8B to identify cognitive concerns in 3,338 clinical notes from Mass General Brigham. The agentic workflow, leveraging task-specific agents that dynamically collaborate to extract meaningful insights from clinical notes, was compared to an expert-driven benchmark. Both workflows achieved high classification performance, with F1-scores of 0.90 and 0.91, respectively. The agentic workflow demonstrated improved specificity (1.00) and achieved prompt refinement in fewer iterations. Although both workflows showed reduced performance on validation data, the agentic workflow maintained perfect specificity. These findings highlight the potential of fully automated multi-agent AI workflows to achieve expert-level accuracy with greater efficiency, offering a scalable and cost-effective solution for detecting cognitive concerns in clinical settings. |
| title | An Agentic AI Workflow for Detecting Cognitive Concerns in Real-world Data |
| topic | Artificial Intelligence Multiagent Systems |
| url | https://arxiv.org/abs/2502.01789 |