Causal-Enhanced AI Agents for Medical Research Screening

• URL: http://arxiv.org/abs/2601.02814v1
• Date: Tue, 06 Jan 2026 08:41:16 GMT
• Title: Causal-Enhanced AI Agents for Medical Research Screening
• Authors: Duc Ngo, Arya Rahgoza,
• Abstract summary: Systematic reviews are essential for evidence-based medicine, but reviewing 1.5 million+ annual publications manually is infeasible.<n>We present a causal graph-enhanced retrieval-augmented generation system integrating explicit causal reasoning with dual-level knowledge graphs.<n>Our approach enforces evidence-first protocols where every causal claim traces to retrieved literature and automatically generates directed acyclic graphs visualizing intervention-outcome pathways.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Systematic reviews are essential for evidence-based medicine, but reviewing 1.5 million+ annual publications manually is infeasible. Current AI approaches suffer from hallucinations in systematic review tasks, with studies reporting rates ranging from 28--40% for earlier models to 2--15% for modern implementations which is unacceptable when errors impact patient care. We present a causal graph-enhanced retrieval-augmented generation system integrating explicit causal reasoning with dual-level knowledge graphs. Our approach enforces evidence-first protocols where every causal claim traces to retrieved literature and automatically generates directed acyclic graphs visualizing intervention-outcome pathways. Evaluation on 234 dementia exercise abstracts shows CausalAgent achieves 95% accuracy, 100% retrieval success, and zero hallucinations versus 34% accuracy and 10% hallucinations for baseline AI. Automatic causal graphs enable explicit mechanism modeling, visual synthesis, and enhanced interpretability. While this proof-of-concept evaluation used ten questions focused on dementia exercise research, the architectural approach demonstrates transferable principles for trustworthy medical AI and causal reasoning's potential for high-stakes healthcare.

Related papers

• PathReasoner-R1: Instilling Structured Reasoning into Pathology Vision-Language Model via Knowledge-Guided Policy Optimization [6.821738567680833]
  We construct PathReasoner, the first large-scale dataset of whole-slide image (WSI) reasoning.<n>PathReasoner-R1 synergizes supervised fine-tuning with reasoning-oriented reinforcement learning to instill structured chain-of-thought capabilities.<n>Experiments demonstrate that PathReasoner-R1 achieves state-of-the-art performance on both PathReasoner and public benchmarks across various image scales.
  arXiv  Detail & Related papers  (2026-01-29T12:21:16Z)
• Learning to reason about rare diseases through retrieval-augmented agents [10.380898352925213]
  RADAR is an agentic system for rare disease detection in brain MRI.<n>Our approach uses AI agents with access to external medical knowledge by embedding both case reports and literature.<n>The agent retrieves clinically relevant evidence to guide diagnostic decision making on unseen diseases, without the need of additional training.
  arXiv  Detail & Related papers  (2025-11-06T10:27:52Z)
• DispatchMAS: Fusing taxonomy and artificial intelligence agents for emergency medical services [49.70819009392778]
  Large Language Models (LLMs) and Multi-Agent Systems (MAS) offer opportunities to augment dispatchers.<n>This study aimed to develop and evaluate a taxonomy-grounded, multi-agent system for simulating realistic scenarios.
  arXiv  Detail & Related papers  (2025-10-24T08:01:21Z)
• Evaluating Large Language Models for Evidence-Based Clinical Question Answering [4.101088122511548]
  Large Language Models (LLMs) have demonstrated substantial progress in biomedical and clinical applications.<n>We curate a benchmark drawing from Cochrane systematic reviews and clinical guidelines.<n>We observe consistent performance patterns across sources and clinical domains.
  arXiv  Detail & Related papers  (2025-09-13T15:03:34Z)
• Design and Validation of a Responsible Artificial Intelligence-based System for the Referral of Diabetic Retinopathy Patients [65.57160385098935]
  Early detection of Diabetic Retinopathy can reduce the risk of vision loss by up to 95%.<n>We developed RAIS-DR, a Responsible AI System for DR screening that incorporates ethical principles across the AI lifecycle.<n>We evaluated RAIS-DR against the FDA-approved EyeArt system on a local dataset of 1,046 patients, unseen by both systems.
  arXiv  Detail & Related papers  (2025-08-17T21:54:11Z)
• Medical Reasoning in the Era of LLMs: A Systematic Review of Enhancement Techniques and Applications [59.721265428780946]
  Large Language Models (LLMs) in medicine have enabled impressive capabilities, yet a critical gap remains in their ability to perform systematic, transparent, and verifiable reasoning.<n>This paper provides the first systematic review of this emerging field.<n>We propose a taxonomy of reasoning enhancement techniques, categorized into training-time strategies and test-time mechanisms.
  arXiv  Detail & Related papers  (2025-08-01T14:41:31Z)
• Automated Retinal Image Analysis and Medical Report Generation through Deep Learning [3.4447129363520337]
  The increasing prevalence of retinal diseases poses a significant challenge to the healthcare system. Traditional methods of generating medical reports from retinal images rely on manual interpretation. This thesis investigates the potential of Artificial Intelligence to automate medical report generation for retinal images.
  arXiv  Detail & Related papers  (2024-08-14T07:47:25Z)
• Explainable AI and Machine Learning Towards Human Gait Deterioration Analysis [0.0]
  We objectively analyze gait data and associate findings with clinically relevant biomarkers. We achieve classification accuracies of 98% F1 sc ores for each PhysioNet.org dataset and 95.5% F1 scores for the combined PhysioNet dataset.
  arXiv  Detail & Related papers  (2023-06-12T14:53:00Z)
• HINT: Hierarchical Interaction Network for Trial Outcome Prediction Leveraging Web Data [56.53715632642495]
  Clinical trials face uncertain outcomes due to issues with efficacy, safety, or problems with patient recruitment. In this paper, we propose Hierarchical INteraction Network (HINT) for more general, clinical trial outcome predictions.
  arXiv  Detail & Related papers  (2021-02-08T15:09:07Z)
• BiteNet: Bidirectional Temporal Encoder Network to Predict Medical Outcomes [53.163089893876645]
  We propose a novel self-attention mechanism that captures the contextual dependency and temporal relationships within a patient's healthcare journey. An end-to-end bidirectional temporal encoder network (BiteNet) then learns representations of the patient's journeys. We have evaluated the effectiveness of our methods on two supervised prediction and two unsupervised clustering tasks with a real-world EHR dataset.
  arXiv  Detail & Related papers  (2020-09-24T00:42:36Z)
• Finding Patient Zero: Learning Contagion Source with Graph Neural Networks [67.3415507211942]
  Locating the source of an epidemic can provide critical insights into the infection's transmission course. Existing methods use graph-theoretic measures and expensive message-passing algorithms. We revisit this problem using graph neural networks (GNNs) to learn P0.
  arXiv  Detail & Related papers  (2020-06-21T21:12:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.