Jiho Lee

Dr. Jiho Lee

orcid

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
13 October 2024 in Mathematics
Verified
Journal Article
Open access
PDF file
JHJunhee Hong
Junhee Hong
YSYoungjin Seol
Youngjin Seol
SLSeunghyun Lee
Seunghyun Lee
JYJanghyeok Yoon
Janghyeok Yoon
JLJiho Lee
Jiho Lee
JHJi-Wan Ha
Ji-Wan Ha
Rapid elderly population growth has increased the number of patients with cognitive impairment (CI). Early detection and ongoing medical treatment can slow CI progression and significantly reduce the cost of managing patients. However, distinguishing CI from natural cognitive decline associated with aging is challenging. Previous studies conducted to identify patients with CI using lifelog data did not consider changes in lifelog data over time because each data point was learned individually. This study introduces a model that predicts patients with CI based on sleep lifelog data and analyzes significant sleep factors that influence cognitive decline. This study followed three steps: (1) collecting sleep lifelog data from elderly Korean people and reconstructing sleep lifelog data as time-series data; (2) building a model to classify CI using a time series of sleep lifelog data and a long short-term memory model; and (3) identifying sleep factors that influence the onset of CI using an explainable AI algorithm. The proposed CI classification model achieved a sensitivity of 0.89, a specificity of 0.80, and an area under the receiver operating characteristic curve of 0.92. This study will facilitate the noninvasive screening, diagnosis, and continuous monitoring of CI in the elderly.

17 December 2024 in Diagnostics
Verified
Journal Article
Open access
PDF file
JLJiho Lee
Jiho Lee
NKNayeon Kim
Nayeon Kim
JHJi-Wan Ha
Ji-Wan Ha
KKKyunghun Kang
Kyunghun Kang
EPEunhee Park
Eunhee Park
KPKi-Su Park
Ki-Su Park
Objective: To develop a non-invasive cognitive impairment detection system using speech data analysis, addressing the growing global dementia crisis and enabling accessible early screening through daily health monitoring. Methods: Speech data from 223 Korean patients were collected across eight tasks. Patients were classified based on Korean Mini-Mental State Examination scores. Four machine learning models were tested for three binary classification tasks. Voice acoustic features were extracted and analyzed. Results: The Deep Neural Network model performed best in two classification tasks, with Precision-Recall Area Under the Curve scores of 0.737 for severe vs. no impairment and 0.726 for mild vs. no impairment, while Random Forest achieved 0.715 for severe + mild vs. no impairment. Several acoustic features emerged as potentially important indicators, with DDA shimmer from the /i/ task and stdevF0 from the /puh-tuh-kuh/ task showing consistent patterns across classification tasks. Conclusions: This preliminary study suggests that certain acoustic features may be associated with cognitive status, though demographic factors significantly influence these relationships. Further research with demographically matched populations is needed to validate these findings.

28 December 2024 in Communication Sciences & Disorders
Verified
Journal Article
Open access
PDF file
YCYoo-Jung Cho
Yoo-Jung Cho
NKNayeon Kim
Nayeon Kim
JLJiho Lee
Jiho Lee
KPKi-Su Park
Ki-Su Park
KKKyunghun Kang
Kyunghun Kang
JHJi-Wan Ha
Ji-Wan Ha
Objectives: The purpose of this study was to determine whether a story information retrieval task can be used to sensitively detect cognitive and language decline in patients with Parkinson’s disease (PD) and normal pressure hydrocephalus (NPH) and to differentially diagnose the two groups. Methods: To assess participants’ real-life cognitive and language abilities, we used the story information retrieval task, which involves showing a video of a story and then asking for information about it. The task was administered to 60 participants, 20 each of the healthy elderly (HE), PD patients, and NPH patients. We then compared the performance of story information retrieval among the three groups in terms of full and partial information frequencies, the total score, and scores by information type. And the correlation with the Korean version of the mini-mental state examination, 2nd edition (K-MMSE-2) was analyzed to check the validity of the story information retrieval task. Results: The PD and NPH groups performed significantly worse than the HE group on the story information retrieval, whether measured by frequency or total score. However, when compared by information type, only the NPH and HE groups showed significant differences. Conclusion: By assessing story information retrieval performance, we were able to identify language and cognitive decline in PD and NPH patients. And the study also showed that the two patient populations may perform differently when evaluated by information type.

28 December 2024 in Communication Sciences & Disorders
Verified
Journal Article
Open access
PDF file
YPYu-Min Park
Yu-Min Park
YCYoo-Jung Cho
Yoo-Jung Cho
NKNayeon Kim
Nayeon Kim
JLJiho Lee
Jiho Lee
KPKi-Su Park
Ki-Su Park
JHJi-Wan Ha
Ji-Wan Ha
Objectives: The present study aimed to determine whether stimulus modality, age group, and time of performance differed in story recall performance in normal aging. Methods: Seventy-three healthy older adults were divided into two groups, 65-74 years old and 75+ years old, and randomly assigned to an auditory condition and an audiovisual condition to perform a story recall task. For each independent variable, event sequencing scores and total number of information units (IUs) were compared, and information-finding behaviors were categorized into reformulation, repetition, filler, and insertion in order to compare the frequency of production by type of information-finding behavior.Results: First, there was no significant difference between groups in event sequencing score according to modalities, age, and time interval. Second, there was no significant difference between groups in the total number of IUs according to modalities, age, and time interval, but all groups performed better on average in the second trials than in the first. Third, the frequencies of all types of information-finding behaviors decreased in the second trials compared to the first, and there was a significant difference between time intervals, especially in fillers and insertions. Conclusion: This study provides meaningful information about variables that should be considered when establishing norms for story recall assessment.

27 January 2025 in Applied Sciences
Verified
Journal Article
Open access
PDF file
HKHayeon Ku
Hayeon Ku
JLJiho Lee
Jiho Lee
MLMinseo Lee
Minseo Lee
SKSeulgi Kim
Seulgi Kim
JYJanghyeok Yoon
Janghyeok Yoon
A person’s voice serves as an indicator of age, as it changes with anatomical and physiological influences throughout their life. Although age prediction is a subject of interest across various disciplines, age-prediction studies using Korean voices are limited. The few studies that have been conducted have limitations, such as the absence of specific age groups or detailed age categories. Therefore, this study proposes an optimal combination of speech features and deep-learning models to recognize detailed age groups using a large Korean-speech dataset. From the speech dataset, recorded by individuals ranging from their teens to their 50s, four speech features were extracted: the Mel spectrogram, log-Mel spectrogram, Mel-frequency cepstral coefficients (MFCCs), and ΔMFCCs. Using these speech features, four deep-learning models were trained: ResNet-50, 1D-CNN, 2D-CNN, and a vision transformer. A performance comparison of speech feature-extraction methods and models indicated that MFCCs + ΔMFCCs was the best for both sexes when trained on the 1D-CNN model; it achieved an accuracy of 88.16% for males and 81.95% for females. The results of this study are expected to contribute to the future development of Korean speaker-recognition systems.

30 April 2024 in Journal of The Korean Society of Laryngology, Phoniatrics and Logopedics
Verified
Journal Article
Open access
PDF file
SKSeungtae Kang
Seungtae Kang
SPSu Na Park
Su Na Park
JHJi-Wan Ha
Ji-Wan Ha
KPKi-Su Park
Ki-Su Park
JLJiho Lee
Jiho Lee
GLGil Joon Lee
Gil Joon Lee
Background and Objectives The purpose of this study is to evaluate value of diagnostic tool for vocal cord palsy utilizing artificial intelligence without laryngoscopeMaterials and Method A dataset consisting of recordings from patients with unilateral vocal cord paralysis (n=54) as well as normal individuals (n=163). The dataset included prolonged pronunciations of the vowels /ah/, /u/, /i/, and vocal cord data from paralyzed patients. Various acoustic parameters such as Mel-frequency cepstral coefficients, jitter, shimmer, harmonics-to-noise ratio, and fundamental frequency statistics were analyzed. The classification of vocal cord paralysis encompassed paralysis status, paralysis degree, and paralysis location. The deep learning model employed the leave-one-out method, and the feature set with the highest performance was selected using the following methods.Results Vocal Cord Paralysis Classifier: The classifier accurately distinguished normal voice from vocal cord paralysis, achieving an accuracy and F1 score of 1.0. Paralysis Location Classifier: The classifier accurately differentiated between median and paramedian vocal cord paralysis, achieving an accuracy and micro F1 score of 1.0. Breathiness Degree Classifier: The classifier achieved an accuracy of 0.795 and a mean absolute error of 0.2857 in distinguishing different degrees of breathiness.Conclusion Although the small sample size raises concerns of potential overfitting, this preliminary study highlights distinctive acoustic features in cases of unilateral vocal fold paralysis compared to those of normal individuals. These findings suggest the feasibility of determining the presence, degree, and location of paralysis through the utilization of acoustic parameters. Further research is warranted to validate and expand upon these results.