Yihuang Kang

• PhD
• Professor (Associate) at National Sun Yat-sen University

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 compare...

Grading programming assignments is crucial for guiding students to improve their programming skills and coding styles. This study presents an automated grading framework, CodEv, which leverages Large Language Models (LLMs) to provide consistent and constructive feedback. We incorporate Chain of Thought (CoT) prompting techniques to enhance the reas...

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...

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 alg...

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 an...

As information systems continuously produce high volumes of user event log data, efficient detection of anomalous activities indicative of insider threats becomes crucial. Typical supervised Machine Learning (ML) methods are often labor- intensive and suffer from the constraints of costly labeled data with unknown anomaly dependencies. Here we intr...

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 Inte...

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 ca...

Dementia in the older population has become a major issue in health research. Given the prevalence of dementia worldwide, various approaches have been applied to examine the causes of dementia incidence and a wide range of factors are captured from many different perspectives. Despite multifaceted data collected from representative samples, most of...

The present study collects a large amount of HRIrelated research studies and analyzes the research trends from 2010 to 2021. Through the topic modeling technique, our developed ML model is able to retrieve the dominant research factors. The preliminary results reveal five important topics, handover, privacy, robot tutor, skin de deformation, and tr...

(1) Background: A disease prediction model derived from real-world data is an important tool for managing type 2 diabetes mellitus (T2D). However, an appropriate prediction model for the Asian T2D population has not yet been developed. Hence, this study described construction details of the T2D Holistic Care model via estimating the probability of...

Drug–drug interactions (DDIs) and drug–disease interactions (DDXs) are critical issues for the healthcare system and clinical physicians. Typical statistical approaches, such as generalized linear models, cannot systematically handle the complexity of DDIs and DDXs. Although deep neural networks can predict DDIs and DDXs with high accuracy, they of...

Machine Learning (ML) and its applications have been transforming our lives but it is also creating issues related to the development of fair, accountable, transparent, and ethical Artificial Intelligence. As the ML models are not fully comprehensible yet, it is obvious that we still need humans to be part of algorithmic decision-making processes....

Researchers have been overwhelmed by the explosion of research articles published by various research communities. Many research scholarly websites, search engines, and digital libraries have been created to help researchers identify potential research topics and keep up with recent progress on research of interests. However, it is still difficult...

Patients with Acute Kidney Injury (AKI) increase mortality, morbidity, and long-term adverse events. Therefore, early identification of AKI may improve renal function recovery, decrease comorbidities, and further improve patients' survival. To control certain risk factors and develop targeted prevention strategies are important to reduce the risk o...

Many Machine Learning algorithms, such as deep neural networks, have long been criticized for being "black-boxes"-a kind of models unable to provide how it arrive at a decision without further efforts to interpret. This problem has raised concerns on model applications' trust, safety, nondiscrimination, and other ethical issues. In this paper, we d...

A mobile social network system is generally complex that it comprises several views, such as data, function, structure, behavior and so on. There are two approaches to design these views. The multiple diagrams approach for mobile social network systems respectively chooses a distinct diagram for each view. The single diagram approach for mobile soc...

The electronic medical records (EMRs) contain information about the patient such as their date of birth and blood type as well as other medical information such as prescription history and previous syndromes. Physicians usually have limited time to identify critical information on medical records and to provide a summary before they make a decision...

Various and ubiquitous information systems are being used in monitoring, exchanging, and collecting information. These systems are generating massive amount of event sequence logs that may help us understand underlying phenomenon. By analyzing these logs, we can learn process models that describe system procedures, predict the development of the sy...

Due to recent explosion of text data, researchers have been overwhelmed by ever-increasing volume of articles produced by different research communities. Various scholarly search websites, citation recommendation engines, and research databases have been created to simplify the text search tasks. However, it is still difficult for researchers to be...

Process Monitoring involves tracking a system's behaviors, evaluating the current state of the system, and discovering interesting events that require immediate actions. In this paper, we consider monitoring temporal system state sequences to help detect the changes of dynamic systems, check the divergence of the system development, and evaluate th...

Background: There is a paucity of literature on the health care expenditures associated with different pharmacologic treatments in older adults with asthma that is not well controlled on inhaled corticosteroids (ICS). Objective: To compare asthma-related and all-cause health care expenditures associated with leukotriene receptor antagonists (LTR...

Objective: The Medicare federal insurance program is the most common United States insurer of patients with systemic vasculitis (SV). We compared healthcare utilization and expenditures for Medicare beneficiaries with versus without SV. Methods: This national, retrospective study used 2010 claims and enrollment data for a 100% cohort of Medicare...

Objectives: To examine racial and ethnic differences in initiation and time to discontinuation of antidementia medication in Medicare beneficiaries. Design: Retrospective cohort study. Setting: Secondary analysis of 2009-10 enrollment, claims, and Part D prescription data for a 10% national sample of U.S. Medicare fee-for-service beneficiaries...

Various and ubiquitous information systems are being used in monitoring, exchanging, and collecting information. These systems are generating massive amount of event sequence logs that may help us understand underlying phenomenon. By analyzing these logs, we can learn process models that describe system procedures, predict the development of the sy...

Process Monitoring involves tracking a system's behaviors, evaluating the current state of the system, and discovering interesting events that require immediate actions. In this paper, we propose a process monitoring approach that helps detect the changes of dynamic systems, monitor the divergence of the system development, and evaluate the signifi...

Background: Few studies have compared the risk of recurrent falls across various antidepressant agents—using detailed dosage and duration data—among community-dwelling older adults, including those who have a history of a fall/fracture. Objective: To examine the association of antidepressant use with recurrent falls, including among those with a hi...

Objectives: To compare the effectiveness and cardiovascular safety of long-acting beta-agonists (LABAs) with those of leukotriene receptor antagonists (LTRAs) as add-on treatments in older adults with asthma already taking inhaled corticosteroids (ICSs). Design: Retrospective cohort study. Setting: Medicare fee-for-service (FFS) claims (2009-1...

Older people with complex health issues and needs for functional support are increasingly living in different types of residential care environments as alternatives to nursing homes. This study aims to compare the demographics and health-care expenditures of Medicare beneficiaries by the setting in which they live: nursing homes, residential care s...

Process Monitoring involves tracking a system's behaviors, evaluating the current state of the system, and discovering interesting events that require immediate actions. In this paper, we propose a process monitoring approach that helps detect the changes of dynamic systems, monitor the divergence of the system development, and evaluate the signifi...

Complex information systems generate large amount of event logs that represent the states of system dynamics. By monitoring these logs, we can learn the process models that describe the underlying business procedures, predict the future development of the systems, and check whether the process models match the expected ones. Most of the existing pr...

Mobility, such as walking 1/4 mile, is a valuable but underutilized health indicator among older adults. For mobility to be successfully integrated into clinical practice and health policy, an easily assessed marker that predicts subsequent health outcomes is required. To determine the association between mobility, defined as self-reported ability...