Blackwell: An Explainable Anamnesis-based Multi-Agent Framework for Remote Clinical Diagnosis

Torquato, Lukas (2025) Blackwell: An Explainable Anamnesis-based Multi-Agent Framework for Remote Clinical Diagnosis. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (6MB) | Preview
Preview	PDF (Configuration Manual) Download (640kB) | Preview

Abstract

The adoption of Artificial Intelligence in telemedicine is currently constrained by the ”Black Box” aspect of deep learning models and the lack of autonomous data acquisition mechanisms. This paper presents Blackwell, a Deep Agent Framework designed to automate the complete clinical pipeline—from patient interview to evidence-based treatment planning—while remaining explainable. Powered by LangGraph, LangSmith and Gemini, the system features a novel Anamnesis Agent that autonomously conducts safety-guarded patient interview, feeding a Two-Phase Evaluator that separates diagnostic hypothesis generation from treatment research. On a 250 study cases synthetic dataset Blackwell obtained 84% of symptom Recall, 86.8% of emergency detection and 90.1% of diagnostic accuracy, showing outstanding results for chronic/symptom characteristic diseases. However, the study showed that Text-only diagnosis appeared to be insufficient for conditions based on visual inspections or serological markers (e.g. HIV/AIDS). Blackwell demonstrated that Agentic AI can successfully bridge the gap to cold start a remote clinical diagnosis with only patient conversation, and combine static knowledge base (RAG) with dynamic research (PubMed), offering a transparent, safe support tool for remote clinical assessment.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Haque, Rejwanul UNSPECIFIED
Uncontrolled Keywords:	Artificial Intelligence in Healthcare; Multi-Agent Systems; Deep Agents; Agentic RAG; Large Language Models (LLMs); Clinical Decision Support Systems (CDSS); Medical Diagnostics; LangGraph; Explainable AI (XAI)
Subjects:	Q Science > QH Natural history > QH301 Biology > Methods of research. Technique. Experimental biology > Data processing. Bioinformatics > Artificial intelligence Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Artificial intelligence R Medicine > Healthcare Industry
Divisions:	School of Computing > Master of Science in Artificial Intelligence
Depositing User:	Ciara O'Brien
Date Deposited:	02 Sep 2026 11:00
Last Modified:	02 Sep 2026 11:00
URI:	https://norma.ncirl.ie/id/eprint/9770

Actions (login required)

View Item