Hwa-min Lee

While baseline cardiorespiratory fitness (CRF) is inversely associated with mental health disorders, the association of longitudinal CRF changes on depression and anxiety risk remains unclear in large-scale populations. This study investigated the association between changes in estimated CRF (eCRF) and subsequent risk of depressive and anxiety disorders in Korean adults. This nationwide cohort study analysed 7,007,488 Korean adults aged 19 to 64 years using National Health Insurance Service data

분산 이동 시스템은 단순한 통신 기능에서 작업 흐름 관리, 화상회의, 복제 데이타의 관리, 자원 할당 등의 서비스를 제공하는 시스템으로 급속히 확대ㆍ발전하고 있으며, 이러한 서비스를 제공하는 어플리케이션들은 사용자의 요구를 반영하기 위해 메시지를 인과적 순서로 전달해야 한다. 인과적 메시지 전달을 제공하는 기존의 방법들은 많은 피기백(piggyback) 정보로 인한 통신 오버헤드 혹은 어플리케이션으로 전달하는 메시지의 지연, 이동 호스트의 증가에 대한 확장성, 이동 호스트가 계산의 대부분을 수행하는 등의 문제점이 있다. 이 논문은 기지국과 이동 호스트 사이의 종속 정보 행렬을 기지국이 유지하며, 즉각 선행자 메시지(immediate predecessor message)에 대한 종속 정보만을 각 메시지에 피기백하는 방법을 통해 기존 기법의 문제점을 해결하는 효율적인 인과적 메시지 전달 기법을 제안한다. 제안하는 알고리즘은 이전의 알고리즘들과 비교해서 낮은 메시지 오버헤드를 가지며, 메

Background: Depressive disorder affects over 300 million people globally, with only 30% to 40% of patients achieving remission with initial antidepressant monotherapy. This low response rate highlights the critical need for digital mental health tools that can identify treatment response early in the clinical pathway. Objective: This study aimed to evaluate whether reasoning-based large language models (LLMs) could accurately predict 12-week remission in patients with depressive disorder undergo

Abstract Background Clinical prediction models degrade when deployed across hospitals, yet retraining requires technical expertise, labeled data, and regulatory re-approval. We investigated whether post-hoc retrieval augmentation of a frozen model’s output, analogous to retrieval-augmented methods in natural language processing, can mitigate this degradation without any parameter modification. Methods We developed the Post-hoc Retrieval Augmentation Module (PRAM), which combines predictions from

INTRODUCTION/AIMS: Nerve conduction study (NCS) interpretation is labor-intensive, and automation may improve clinical workflow. We developed a dual framework integrating rule-based coding and fine-tuned language models to standardize reporting and enhance diagnostic accuracy. METHODS: The framework combined rule-based coding for converting raw NCS data into structured reports with demyelination parameter evaluation, followed by GPT-4o fine-tuning with structured NCS reports as input and ground-

Major depressive disorder (MDD) is a leading global health burden, yet only one-third of patients achieve remission with initial antidepressant therapy. Inflammatory biomarkers and epigenetic signatures such as DNA methylation have been implicated in treatment response, but their temporal predictive utility remains unclear. We analyzed 821 Korean patients with MDD from the MAKE BETTER study, integrating clinical variables, serum inflammatory biomarkers, and DNA methylation profiles into machine-

Although neuromuscular junction disorders (NMDs) and inflammatory polyneuropathies (IPNs) are biologically distinct, direct genetic comparisons between them remain limited, suggesting that additional underlying biological differences may yet be uncovered. Few studies have explored whether differences in variant patterns within shared biological pathways can be leveraged to distinguish NMDs and IPNs using machine learning (ML). We propose an interpretable ML framework based on Pathway-based Genet

Laryngoscopy is essential for evaluating laryngeal pathology, particularly vocal fold lesions, but large endoscopic datasets often contain low-quality or irrelevant frames that hinder use. We developed and validated a deep learning model to automatically identify high-quality laryngoscopic images that clearly show the vocal folds. This retrospective study included 4711 images from 125 patients. Expert reviewers labeled images as low (3099; 65.8%), mid (698; 14.8%), or high quality (914; 19.4%).

Antibiotic resistance poses a significant global health challenge, with its rapid emergence driven by inappropriate antibiotic use. This study aimed to develop and compare machine learning models to predict resistance to nine antibiotic classes in hospitalized patients, addressing the high-cost labeling challenge of medical data. We conducted a retrospective study using electronic medical records from three Korean tertiary care institutions (n = 59,551). Single-task learning models (Logistic Reg

Dual use of conventional and e-cigarettes is associated with elevated RA risk, even among individuals with lower cumulative smoking exposure. These findings highlight the need for targeted public health strategies addressing dual users and underscore the importance of including e-cigarette use in RA risk assessments.

Fatigue is a multifactorial phenomenon affecting both physical and psychological performance, particularly in high-stress occupations. Although wearable sensors enable continuous monitoring, conventional machine-learning (ML) models can produce unstable, weakly calibrated, and opaque predictions in real-world settings. To improve reliability and interpretability, we developed a selective Retrieval-Augmented Generation (RAG)–enhanced hybrid ML–LLM framework that integrates the efficiency of ML wi

Major depressive disorder (MDD) arises from interacting genetic and physiological factors, yet diagnosis still relies largely on subjective assessments. We present an exploratory deep multi-modal learning framework that integrates wearable time-series, variant-based genomic profiles, and routine clinical variables to enable more objective depression prediction. To encode heterogeneous inputs, we compare sequence encoders for activity and sleep (LSTM, temporal convolutional networks, and 1D-CNN)