Yihuang Kang

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.

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.

Objective: Machine learning (ML) algorithms are promising tools for managing anemia in hemodialysis (HD) patients. However, their efficacy in predicting erythropoiesis-stimulating agents (ESAs) doses remains uncertain. This study aimed to evaluate the effectiveness of a contemporary artificial intelligence (AI) model in prescribing ESA doses compared to physicians for HD patients. Materials and Methods: This double-blinded control trial randomized participants into traditional doctor (Dr) and AI groups. In the Dr group, doses of ESA were determined by following clinical guideline recommendations, while in the AI group, they were predicted by the developed models named Random effects (REEM) trees, Mixed-effect random forest (MERF), Long short-term memory (LSTM) networks-I, and LSTM-II. The primary outcome was the capability to maintain patients’ hemoglobin (Hb) value near 11 g/dL with a margin of 0.25 g/dL after treating the suggested ESA, with the secondary outcome being Hb value between 10 and 12 g/dL. Results: A total of 124 participants were enrolled, with 104 completing the study. The mean Hb values were 10.8 and 10.9 g/dL in the AI and Dr groups, respectively, with 69.7% and 73.5% of participants in the respective groups maintaining Hb levels between 10 and 12 g/dL. Only the REEM trees model passed the non-inferiority test for the primary outcome with a margin of 0.25 g/dL and the secondary outcome with a margin of 15%. There was no difference in severe adverse events between the 2 groups. Conclusion: The REEM trees AI model demonstrated non-inferiority to physicians in prescribing ESA doses for HD patients, maintaining Hb levels within the therapeutic target. ClinicalTrials.gov Identifier: NCT04185519.

This study proposes an improved methodology based on life cycle assessment (LCA), which is used to calculate the carbon footprint of agriculture, provides a simple and feasible calculation path, and constructs a streamlined framework for calculating the carbon footprint based on the agricultural traceability system records. Using important economic crop (Onion) as research subject, and choose the largest planting area in R.O.C. (southern Taiwan) as a case study. A total of 64 farm production history records have been collected, includes all of farms certified with a traceable agricultural products (TAP) label. Through a detailed analysis of the traditional carbon footprint calculation method, found that agricultural traceability system records could replace the data source in carbon footprint verification (CFV) process, and system records could be used as activity data after being organized. With our method, no need to go through a complicated CFV process, just download the existing data on agricultural traceability system, can start calculating carbon footprint as soon as possible. To compared to traditional assessment method, results show a margin of error is less than 6% compared to traditional assessment methods. Advantages of improved method were be found, such as easy data acquisition, simplified calculation steps, and improved data transparency and accuracy. From statistical data, show that at least seven categories of carbon emission sources for carbon footprints, the most significant of carbon emission impact are fertilizers. The result of improved methodology based on life cycle assessment (LCA), show that using the improved methods can help promote the carbon footprint management efficiency of agricultural organizations such as Farmers’ Association or Agricultural Production Marketing Group, promptly monitor the carbon footprint status of their fields and adjust strategies to reduce carbon footprints in real-time, advancing towards the goal of net-zero carbon emissions.

The estimated Glomerular Filtration Rate (eGFR) is an essential indicator of kidney function in clinical practice. Although traditional equations and Machine Learning (ML) models using clinical and laboratory data can estimate eGFR, accurately predicting future eGFR levels remains a significant challenge for nephrologists and ML researchers. Recent advances demonstrate that Large Language Models (LLMs) and Large Multimodal Models (LMMs) can serve as robust foundation models for diverse applications. This study investigates the potential of LMMs to predict future eGFR levels with a dataset consisting of laboratory and clinical values from 50 patients. By integrating various prompting techniques and ensembles of LMMs, our findings suggest that these models, when combined with precise prompts and visual representations of eGFR trajectories, offer predictive performance comparable to existing ML models. This research extends the application of foundation models and suggests avenues for future studies to harness these models in addressing complex medical forecasting challenges.

Machine learning models are often criticized for their black-box nature, raising concerns about their applicability in critical decision-making scenarios. Consequently, there is a growing demand for interpretable models in such contexts. In this study, we introduce Model-based Deep Rule Forests (mobDRF), an interpretable representation learning algorithm designed to extract transparent models from data. By leveraging IF-THEN rules with multi-level logic expressions, mobDRF enhances the interpretability of existing models without compromising accuracy. We apply mobDRF to identify key risk factors for cognitive decline in an elderly population, demonstrating its effectiveness in subgroup analysis and local model optimization. Our method offers a promising solution for developing trustworthy and interpretable machine learning models, particularly valuable in fields like healthcare, where understanding differential effects across patient subgroups can lead to more personalized and effective treatments.

Understanding and inferencing Heterogeneous Treatment Effects (HTE) and Conditional Average Treatment Effects (CATE) are vital for developing personalized treatment recommendations. Many state-of-the-art approaches achieve inspiring performance in estimating HTE on benchmark datasets or simulation studies. However, the indirect predicting manner and complex model architecture reduce the interpretability of these approaches. To mitigate the gap between predictive performance and heterogeneity interpretability, we introduce the Causal Rule Forest (CRF), a novel approach to learning hidden patterns from data and transforming the patterns into interpretable multi-level Boolean rules. By training the other interpretable causal inference models with data representation learned by CRF, we can reduce the predictive errors of these models in estimating HTE and CATE, while keeping their interpretability for identifying subgroups that a treatment is more effective. Our experiments underscore the potential of CRF to advance personalized interventions and policies, paving the way for future research to enhance its scalability and application across complex causal inference challenges.

In this study, we address the interpretability issue in complex, black-box Machine Learning models applied to sequence data. We introduce the Model-Based tree Hidden Semi-Markov Model (MOB-HSMM), an inherently interpretable model aimed at detecting high mortality risk events and discovering hidden patterns associated with the mortality risk in Intensive Care Units (ICU). This model leverages knowledge distilled from Deep Neural Networks (DNN) to enhance predictive performance while offering clear explanations. Our experimental results indicate the improved performance of Model-Based trees (MOB trees) via employing LSTM for learning sequential patterns, which are then transferred to MOB trees. Integrating MOB trees with the Hidden Semi-Markov Model (HSMM) in the MOB-HSMM enables uncovering potential and explainable sequences using available information.

The concept of chronic kidney disease (CKD) originated in the 2000s, and an estimated 850 million patients are currently suffering from health threats from different degrees of CKD. However, it is unclear whether the existing CKD care systems are optimal for improving patient prognosis and outcomes, so this review summarizes the burden, existing care models, effectiveness, challenges, and developments of CKD care. Even under the general care principles, there are still significant gaps in our understanding of the causes of CKD, prevention or care resources, and care burdens between countries worldwide. Receiving care from multidisciplinary teams rather than only a nephrologist shows potential profits in comprehensive and preferable outcomes. In addition, we propose a novel CKD care structure that combines modern technologies, biosensors, longitudinal data visualization, machine learning algorithms, and mobile care. The novel care structure could simultaneously change the care process, significantly reduce human contact, and make the vulnerable population less likely to be exposed to infectious diseases such as COVID-19. The information offered should be beneficial, allowing us to rethink future CKD care models and applications to reach the goals of health equality and sustainability.