TLTaeheon Lee

Taeheon Lee

*This is an algorithmically generated author record based on publicly available information.

Taeheon Lee has a total of 25 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    A Clinical Decision Support System for Sleep Staging Tasks With Explanations From Artificial Intelligence: User-Centered Design and Evaluation Study

    by Jeonghwan Hwang, Taeheon Lee, Honggu Lee, Seonjeong Byun

    Background: Despite the unprecedented performance of deep learning algorithms in clinical domains, full reviews of algorithmic predictions by human experts remain mandatory. Under these circumstances, artificial intelligence (AI) models are primarily designed as clinical decision support systems (CDSSs). However, from the perspective of clinical practitioners, the lack of clinical interpretability and user-centered interfaces hinders the adoption of these AI systems in practice. Objective: This study aims to develop an AI-based CDSS for assisting polysomnographic technicians in reviewing AI-predicted sleep staging results. This study proposed and evaluated a CDSS that provides clinically sound explanations for AI predictions in a user-centered manner. Methods: Our study is based on a user-centered design framework for developing explanations in a CDSS that identifies why explanations are needed, what information should be contained in explanations, and how explanations can be provided in the CDSS. We conducted user interviews, user observation sessions, and an iterative design process to identify three key aspects for designing explanations in the CDSS. After constructing the CDSS, the tool was evaluated to investigate how the CDSS explanations helped technicians. We measured the accuracy of sleep staging and interrater reliability with macro-F1 and Cohen κ scores to assess quantitative improvements after our tool was adopted. We assessed qualitative improvements through participant interviews that established how participants perceived and used the tool. Results: The user study revealed that technicians desire explanations that are relevant to key electroencephalogram (EEG) patterns for sleep staging when assessing the correctness of AI predictions. Here, technicians wanted explanations that could be used to evaluate whether the AI models properly locate and use these patterns during prediction. On the basis of this, information that is closely related to sleep EEG patterns was formulated for the AI models. In the iterative design phase, we developed a different visualization strategy for each pattern based on how technicians interpreted the EEG recordings with these patterns during their workflows. Our evaluation study on 9 polysomnographic technicians quantitatively and qualitatively investigated the helpfulness of the tool. For technicians with <5 years of work experience, their quantitative sleep staging performance improved significantly from 56.75 to 60.59 with a P value of .05. Qualitatively, participants reported that the information provided effectively supported them, and they could develop notable adoption strategies for the tool. Conclusions: Our findings indicate that formulating clinical explanations for automated predictions using the information in the AI with a user-centered design process is an effective strategy for developing a CDSS for sleep staging.


  • Open Access

    Spatial Navigation Game in EEG-integrated VR for Screening Cognitive Impairment: Protocol for Feasibility and Pilot Study (Preprint)

    by Hyungsin Jeon, Wanhee Cho, Taeheon Lee, Kanghee Kim, Yongsoo Shim

    BACKGROUND Spatial navigation impairment is recognized as a potential marker of preclinical dementia. Virtual reality (VR) technology has been introduced as a promising framework for dementia research. Recent work has demonstrated further possibilities that integrating electroencephalography (EEG) sensors into VR headsets can provide invaluable information relevant to cognitive impairment. OBJECTIVE The aim of this study is to explore the feasibility of spatial navigation assessment in EEG-integrated VR devices for assessing cognitive impairment. This study will further investigate the neurophysiological characteristics of wearable EEG sensors during a VR spatial navigation game. METHODS Participants recruited for the study will be grouped into three based on their cognitive status (mild Alzheimer’s disease group, mild cognitive impairment group, and healthy controls). The spatial navigation game is designed based on the hidden goal task to assess egocentric and allocentric spatial information processing. As outcome measures, spatial navigation errors, spectral density characteristics of EEG signals, and behavioral responses in VR will be analyzed. RESULTS A spatial navigation game for VR was developed in March 2021. Recruitment commenced in June 2021. CONCLUSIONS The results of this study will provide a comprehensive understanding of VR-based spatial navigation assessment, in terms of cognitive measurement including early screening. If positive, our approach based on EEG-integrated VR devices could constitute an effective cognitive impairment screening test tool that can provide brain dynamic characteristics as well as information on spatial navigation deficits.

  • Open Access

    Deep hierarchical embedding for simultaneous modeling of GPCR proteins in a unified metric space

    by Taeheon Lee, Sangseon Lee, Minji Kang, Sun Kim

    GPCR proteins belong to diverse families of proteins that are defined at multiple hierarchical levels. Inspecting relationships between GPCR proteins on the hierarchical structure is important, since characteristics of the protein can be inferred from proteins in similar hierarchical information. However, modeling of GPCR families has been performed separately for each of the family, subfamily, and sub-subfamily level. Relationships between GPCR proteins are ignored in these approaches as they process the information in the proteins with several disconnected models. In this study, we propose DeepHier, a deep learning model to simultaneously learn representations of GPCR family hierarchy from the protein sequences with a unified single model. Novel loss term based on metric learning is introduced to incorporate hierarchical relations between proteins. We tested our approach using a public GPCR sequence dataset. Metric distances in the deep feature space corresponded to the hierarchical family relation between GPCR proteins. Furthermore, we demonstrated that further downstream tasks, like phylogenetic reconstruction and motif discovery, are feasible in the constructed embedding space. These results show that hierarchical relations between sequences were successfully captured in both of technical and biological aspects.


  • Open Access

    Synergy through Integration of Wearable EEG and Virtual Reality for Mild Cognitive Impairment and Mild Dementia Screening: Protocol Design and Feasibility Study (Preprint)

    by Bohee Lee, Taeheon Lee, Hyungsin Jeon, Songsub Lee, Kibum Kim, Wanhee Cho, Jeonghwan Hwang, Yong-Wook Chae, Jin-Man Jung, Hyo Jin Kang, et al.

    Journal of Medical Internet Research - International Scientific Journal for Medical Research, Information and Communication on the Internet #Preprint #PeerReviewMe: Warning: This is a unreviewed preprint. Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn. Readers with interest and expertise are encouraged to sign up as peer-reviewer, if the paper is within an open peer-review period. Please cite this preprint only for review purposes or for grant applications and CVs (if you are the author). Background: Virtual reality (VR) technologies have shown promising potential in the early diagnosis of dementia by enabling regular assessment thanks to the portability and accessibility of the devices. However, previous VR studies were restricted to the analysis of behavioral responses, so information about degenerated brain dynamics could not be acquired in these studies. One of the possible approaches to enabling inspection of brain dynamics using a portable platform is the application of wearable EEG devices, which provide simple and convenient neuroimaging tools for identifying characteristic neural activities of dementia. Objective: The aim of this study was to develop a cognitive impairment (CI) screening tool based on a wearable EEG device integrated into a VR platform, and to evaluate whether it is feasible and effective to screen for CI using this device. Methods: Subjects were asked to use a hardware setup consisting of a frontal six-channel EEG device mounted on a VR device and to perform tasks designed for assessing cognitive abilities in four domains (focused attention, selective attention, depth perception and working memory). Behavioral response profiles and EEG features were extracted during the tasks, and investigated to determine whether patients with CI could be differentiated from healthy controls (HCs). Furthermore, random forest classifiers were trained on the extracted features to evaluate whether EEG characteristics during the cognitive tasks were helpful for screening subjects with CI. Results: A total of 59 participants (30 HCs and 29 CI) participated in this study. The CI group achieved notably worse cognitive task scores. More importantly, power spectral analysis of the EEG signals revealed notable differences between the two groups. Characteristic observations from participants with CI included reduced alpha activity during the resting-state (P = .03) and other cognitive tasks (P = .04 and .006 for selective attention and depth perception tasks, respectively), which are well-known pathological EEG patterns for dementia. Therefore, the delta-to-alpha ratio (DAR) and theta-to-alpha ratio (TAR), which are well-known biomarkers for dementia screening, were significantly greater in the CI group. The performance of the patient classification consistently improved when EEG characteristics measured during cognitive tasks were additionally included in feature attributes, suggesting that our protocol provides discriminative information that could improve the performance of dementia screening. Conclusions: This study demonstrated that the integration of EEG devices into a VR framework could emerge as a powerful and synergistic strategy for constructing an easily accessible EEG-based dementia screening tool.


  • Open Access

    Synergy through Integration of Wearable EEG and Virtual Reality for Mild Cognitive Impairment and Mild Dementia Screening: Protocol Design and Feasibility Study (Preprint)

    by Bohee Lee, Taeheon Lee, Hyungsin Jeon, Songsub Lee, Kibum Kim, Wanhee Cho, Jeonghwan Hwang, Yong-Wook Chae, Jin-Man Jung, Hyo Jin Kang, et al.

    BACKGROUND Virtual reality (VR) technologies have shown promising potential in the early diagnosis of dementia by enabling regular assessment thanks to the portability and accessibility of the devices. However, previous VR studies were restricted to the analysis of behavioral responses, so information about degenerated brain dynamics could not be acquired in these studies. One of the possible approaches to enabling inspection of brain dynamics using a portable platform is the application of wearable EEG devices, which provide simple and convenient neuroimaging tools for identifying characteristic neural activities of dementia. OBJECTIVE The aim of this study was to develop a cognitive impairment (CI) screening tool based on a wearable EEG device integrated into a VR platform, and to evaluate whether it is feasible and effective to screen for CI using this device. METHODS Subjects were asked to use a hardware setup consisting of a frontal six-channel EEG device mounted on a VR device and to perform tasks designed for assessing cognitive abilities in four domains (focused attention, selective attention, depth perception and working memory). Behavioral response profiles and EEG features were extracted during the tasks, and investigated to determine whether patients with CI could be differentiated from healthy controls (HCs). Furthermore, random forest classifiers were trained on the extracted features to evaluate whether EEG characteristics during the cognitive tasks were helpful for screening subjects with CI. RESULTS A total of 59 participants (30 HCs and 29 CI) participated in this study. The CI group achieved notably worse cognitive task scores. More importantly, power spectral analysis of the EEG signals revealed notable differences between the two groups. Characteristic observations from participants with CI included reduced alpha activity during the resting-state (P = .03) and other cognitive tasks (P = .04 and .006 for selective attention and depth perception tasks, respectively), which are well-known pathological EEG patterns for dementia. Therefore, the delta-to-alpha ratio (DAR) and theta-to-alpha ratio (TAR), which are well-known biomarkers for dementia screening, were significantly greater in the CI group. The performance of the patient classification consistently improved when EEG characteristics measured during cognitive tasks were additionally included in feature attributes, suggesting that our protocol provides discriminative information that could improve the performance of dementia screening. CONCLUSIONS This study demonstrated that the integration of EEG devices into a VR framework could emerge as a powerful and synergistic strategy for constructing an easily accessible EEG-based dementia screening tool.

  • Open Access

    A Clinical Decision Support System for Sleep Staging Tasks With Explanations From Artificial Intelligence: User-Centered Design and Evaluation Study (Preprint)

    by Jeonghwan Hwang, Taeheon Lee, Honggu Lee, Seonjeong Byun

    BACKGROUND Despite the unprecedented performance of deep learning algorithms in clinical domains, full reviews of algorithmic predictions by human experts remain mandatory. Under these circumstances, artificial intelligence (AI) models are primarily designed as clinical decision support systems (CDSSs). However, from the perspective of clinical practitioners, the lack of clinical interpretability and user-centered interfaces hinders the adoption of these AI systems in practice. OBJECTIVE This study aims to develop an AI-based CDSS for assisting polysomnographic technicians in reviewing AI-predicted sleep staging results. This study proposed and evaluated a CDSS that provides clinically sound explanations for AI predictions in a user-centered manner. METHODS Our study is based on a user-centered design framework for developing explanations in a CDSS that identifies why explanations are needed, what information should be contained in explanations, and how explanations can be provided in the CDSS. We conducted user interviews, user observation sessions, and an iterative design process to identify three key aspects for designing explanations in the CDSS. After constructing the CDSS, the tool was evaluated to investigate how the CDSS explanations helped technicians. We measured the accuracy of sleep staging and interrater reliability with macro-F1 and Cohen κ scores to assess quantitative improvements after our tool was adopted. We assessed qualitative improvements through participant interviews that established how participants perceived and used the tool. RESULTS The user study revealed that technicians desire explanations that are relevant to key electroencephalogram (EEG) patterns for sleep staging when assessing the correctness of AI predictions. Here, technicians wanted explanations that could be used to evaluate whether the AI models properly locate and use these patterns during prediction. On the basis of this, information that is closely related to sleep EEG patterns was formulated for the AI models. In the iterative design phase, we developed a different visualization strategy for each pattern based on how technicians interpreted the EEG recordings with these patterns during their workflows. Our evaluation study on 9 polysomnographic technicians quantitatively and qualitatively investigated the helpfulness of the tool. For technicians with <5 years of work experience, their quantitative sleep staging performance improved significantly from 56.75 to 60.59 with a P value of .05. Qualitatively, participants reported that the information provided effectively supported them, and they could develop notable adoption strategies for the tool. CONCLUSIONS Our findings indicate that formulating clinical explanations for automated predictions using the information in the AI with a user-centered design process is an effective strategy for developing a CDSS for sleep staging.


  • Cancer subtype classification and modeling by pathway attention and propagation

    by Sangseon Lee, Sangsoo Lim, Taeheon Lee, Inyoung Sung, Sun Kim

    Motivation: Biological pathway is an important curated knowledge of biological processes. Thus, cancer subtype classification based on pathways will be very useful to understand differences in biological mechanisms among cancer subtypes. However, pathways include only a fraction of the entire gene set, only one-third of human genes in KEGG, and pathways are fragmented. For this reason, there are few computational methods to use pathways for cancer subtype classification. Results: We present an explainable deep-learning model with attention mechanism and network propagation for cancer subtype classification. Each pathway is modeled by a graph convolutional network. Then, a multi-attention-based ensemble model combines several hundreds of pathways in an explainable manner. Lastly, network propagation on pathway–gene network explains why gene expression profiles in subtypes are different. In experiments with five TCGA cancer datasets, our method achieved very good classification accuracies and, additionally, identified subtype-specific pathways and biological functions. Availability and implementation: The source code is available at http://biohealth.snu.ac.kr/software/GCN_MAE. Supplementary information: Supplementary data are available at Bioinformatics online.


  • Ranked k-Spectrum Kernel for Comparative and Evolutionary Comparison of Exons, Introns, and CpG Islands

    by Sangseon Lee, Taeheon Lee, Yung-Kyun Noh, Sun Kim

    Motivation: Existing k-mer based string kernel methods have been successfully used for sequence comparison. However, existing kernel methods have limitations for comparative and evolutionary comparisons of genomes due to the sensitiveness to over-represented k-mers and variable sequence lengths. Results: In this study, we propose a novel ranked k-spectrum string (RKSS) kernel. 1) RKSS kernel utilizes common k-mer sets across species, named landmarks, that can be used for comparing multiple genomes. 2) Based on the landmarks, we can use ranks of k-mers, rather than frequencies, that can produce more robust distances between genomes. To show the power of RKSS kernel, we conducted two experiments using 10 mammalian species with exon, intron, and CpG island sequences. RKSS kernel reconstructed more consistent evolutionary trees than the k-spectrum string kernel. In the subsequent experiment, for each sequence, kernel distance was calculated from 30 landmarks representing exon, intron, and CpG island sequences of 10 genomes. Based on kernel distances, concordance tests were performed and the result suggested that more information is conserved in CpG islands across species than in introns. In conclusion, our analysis suggests that the relational order, exon > CpG island > intron, in terms of evolutionary information contents.