Estimating individualized treatment effects from observational data presents a persistent challenge due to unmeasured confounding and structural bias. Causal Machine Learning (causal ML) methods, such as causal trees and doubly robust estimators, provide tools for estimating conditional average treatment effects. These methods have limited effectiveness in complex real-world environments due to the presence of latent confounders or those described in unstructured formats. Moreover, reliance on domain experts for confounder identification and rule interpretation introduces high annotation cost and scalability concerns. In this work, we proposed Large Language Model-based agents for automated confounder discovery and subgroup analysis that integrate agents into the causal ML pipeline to simulate domain expertise. Our framework systematically performs subgroup identification and confounding structure discovery by leveraging the reasoning capabilities of LLM-based agents, which reduces human dependency while preserving interpretability. Experiments on real-world medical datasets show that our proposed approach enhances treatment effect estimation robustness by narrowing confidence intervals and uncovering unrecognized confounding biases. Our findings suggest that LLM-based agents offer a promising path toward scalable, trustworthy, and semantically aware causal inference.

Recent advancements in Large Language Models offer promising capabilities to simulate complex human social interactions. We investigate whether LLM-based multi-agent simulations can reproduce core human social dynamics observed in online forums. We evaluate conformity dynamics, group polarization, and fragmentation across different model scales and reasoning capabilities using a structured simulation framework. Our findings indicate that smaller models exhibit higher conformity rates, whereas models optimized for reasoning are more resistant to social influence.

Detecting pulmonary nodules in chest X-rays (CXRs) is essential for early lung disease screening. This study developed a lightweight Convolutional Neural Network (CNN)-based Computer-Aided Detection (CAD) system leveraging YOLOv2 and YOLOv8 to operate efficiently in resource-constrained medical environments. The models were trained and validated using datasets from the NIH and Vietnamese medical centers, with annotations verified by radiologists from a southern Taiwan medical center. The proposed system demonstrated high accuracy and efficiency, effectively detecting pulmonary nodules, including nodular opacities from both abnormalities and overlapping anatomical structures. YOLOv2 showed particular strength in handling complex regions, such as retrocardiac and clavicular overlaps. Its lightweight design makes it suitable for primary care facilities, remote clinics, and as an auxiliary tool in larger hospitals to enhance diagnostic efficiency. Future work will expand datasets, optimize model structures, and conduct clinical trials to validate real-world applications. Efforts will also focus on model compression and hardware acceleration to further reduce computational costs. While this study targets CXRs, the system’s architecture can be adapted for other medical imaging modalities, ensuring broad applicability and clinical relevance.

Accurate and interpretable prediction of estimated glomerular filtration rate (eGFR) is essential for managing chronic kidney disease (CKD) and supporting clinical decisions. Recent advances in Large Multimodal Models (LMMs) have shown strong potential in clinical prediction tasks due to their ability to process visual and textual information. However, challenges related to deployment cost, data privacy, and model reliability hinder their adoption. In this study, we propose a collaborative framework that enhances the performance of open-source LMMs for eGFR forecasting while generating clinically meaningful explanations. The framework incorporates visual knowledge transfer, abductive reasoning, and a short-term memory mechanism to enhance prediction accuracy and interpretability. Experimental results show that the proposed framework achieves predictive performance and interpretability comparable to proprietary models. It also provides plausible clinical reasoning processes behind each prediction. Our method sheds new light on building AI systems for healthcare that combine predictive accuracy with clinically grounded interpretability.