Ethan Hyungkeun Kim

Ethan Hyungkeun Kim

Auto-generated profile, based on publicly available information

Ethan Hyungkeun Kim

Affiliations Krembil Centre for Neuroinformatics, Centre for Addiction and Mental Health (CAMH), Toronto, Canada, Institute for Medical Science, University of Toronto, Toronto, Canada

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
24 January 2022 in PLOS ONE
Verified
Journal Article
Open access
PDF file
PAPegah Abed-Esfahani
Pegah Abed-Esfahani
BDBenjamin C. Darwin
Benjamin C. Darwin
DHDerek Howard
Derek Howard
NWNick Wang
Nick Wang
EKEthan Kim
Ethan Kim
LFLeon French
Leon French
High resolution in situ hybridization (ISH) images of the brain capture spatial gene expression at cellular resolution. These spatial profiles are key to understanding brain organization at the molecular level. Previously, manual qualitative scoring and informatics pipelines have been applied to ISH images to determine expression intensity and pattern. To better capture the complex patterns of gene expression in the human cerebral cortex, we applied a machine learning approach. We propose gene re-identification as a contrastive learning task to compute representations of ISH images. We train our model on an ISH dataset of ~1,000 genes obtained from postmortem samples from 42 individuals. This model reaches a gene re-identification rate of 38.3%, a 13x improvement over random chance. We find that the learned embeddings predict expression intensity and pattern. To test generalization, we generated embeddings in a second dataset that assayed the expression of 78 genes in 53 individuals. In this set of images, 60.2% of genes are re-identified, suggesting the model is robust. Importantly, this dataset assayed expression in individuals diagnosed with schizophrenia. Gene and donor-specific embeddings from the model predict schizophrenia diagnosis at levels similar to that reached with demographic information. Mutations in the most discriminative gene, Sodium Voltage-Gated Channel Beta Subunit 4 (SCN4B), may help understand cardiovascular associations with schizophrenia and its treatment. We have publicly released our source code, embeddings, and models to spur further application to spatial transcriptomics. In summary, we propose and evaluate gene re-identification as a machine learning task to represent ISH gene expression images.

14 May 2021 in bioRxiv
Verified
Preprint
Open access
PDF file
EKEthan Kim
Ethan Kim
DHDerek Howard
Derek Howard
YCYuxiao Chen
Yuxiao Chen
STShreejoy J. Tripathy
Shreejoy J. Tripathy
LFLeon French
Leon French
Application of RNA sequencing has enabled the characterization of genome-wide gene expression in the human brain, including distinct layers of the neocortex. Neuroanatomically, the molecular patterns that underlie the laminar organization of the neocortex can help link structure to circuitry and function. To advance our understanding of cortical architecture, we created LaminaRGeneVis , a web application that displays across-layer cortical gene expression from multiple datasets. These datasets were collected using bulk, single-nucleus, and spatial RNA sequencing methodologies and these data were harmonized to facilitate comparisons between datasets. The online resource facilitates single- and multi-gene analyses by providing figures and statistics for user-friendly assessment of laminar gene expression patterns in the adult human neocortex. Availability and implementation: LaminaRGeneVis is available at https://ethanhkim.shinyapps.io/laminargenevis . The source code and data is accessible at https://github.com/ethanhkim/laminargenevis .

3 November 2026 in Journal of Medical Internet Research
Verified
Journal Article
Open access
KCKatherine Anne Comtois
Katherine Anne Comtois
PSPayton Smythe
Payton Smythe
AKAmanda Kerbrat
Amanda Kerbrat
EKEthan H Kim
Ethan H Kim
NCNatalie Crouch
Natalie Crouch
PAPatricia A Arean
Patricia A Arean
Background: Social media and search engine tech companies, such as Google, use the wealth of data at their disposal to create algorithms to predict suicide risk and provide interventions based on company policies and outputs from these algorithms. Neither the details of these algorithms nor their accuracy in risk prediction are shared with the public; thus, research is needed to verify whether algorithms applied to search engine data can accurately predict suicide risk in a platform user. This paper provides new information about the methodological challenges in studying the value of search engine data for suicide prediction. Objective: This paper describes the study methods and experiences regarding recruiting and retaining participants in a year-long, fully remote prospective cohort study of suicide prediction in people with variable risk of suicide, using Google Search data. Methods: We aimed to recruit 1000 United States–dwelling and English-speaking adults with current suicidal ideation who fell into 1 of 3 categories: participants with a suicide attempt in the past year, participants with a lifetime suicide attempt but not one in the past year, and participants with no suicide attempt in their lifetime. Recruitment sources included online advertisements hosted on various websites, to differing levels of success. Participants completed online surveys and an interview via Zoom to enroll in the study and then were sent follow-up surveys every 2 weeks for the year following initial enrollment. Recruitment was conducted from March 2022 to January 2024, with follow-up data being collected through February 2025. Results: Of 15,120 records created in our Research Electronic Data Capture (REDCap) survey system, 485 participants were eligible to participate in the prospective year of the study. Recruitment challenges were mainly due to participant dropout across all enrollment time points, with 63.7% (9636/15,120) of the prescreening sample dropping out or refusing. Other issues included the difficulty of downloading Google Search data (446/3277, 13.6%) and not having enough data to meet the inclusion criteria among those who were able to successfully donate (252/3277, 7.7%). Lastly, the study encountered fraudulent behavior, with 489 of 15,120 records (3.2%) being identified as fraudulent over the course of the study. Conclusions: Despite past success with remote clinical research methods, we found that recruitment can be significantly hampered by fraudulent participation, despite the use of state-of-the-art methods to mitigate this problem. Further, the ability to acquire useful Google Search data is extremely challenging and necessitates the use of technical assistance and continuous monitoring of Google Takeout data structure to ensure accurate and complete data donations. The solutions we provide for this type of research should be helpful for future endeavors. However, research is still limited by the barriers to obtaining data from technology companies. These limitations have significant implications in detecting the accuracy and utility of suicide prediction from search engine data.

8 September 2025 in JMIR Preprints
Verified
Preprint
Open access
KCKatherine Anne Comtois
Katherine Anne Comtois
PSPayton Smythe
Payton Smythe
AKAmanda Kerbrat
Amanda Kerbrat
EKEthan Hyungkeun Kim
Ethan Hyungkeun Kim
NCNatalie Crouch
Natalie Crouch
PAPatricia A Arean
Patricia A Arean
BACKGROUND Social media and search engine tech companies, such as Google, use the wealth of data at their disposal to create algorithms to predict suicide risk, and provide interventions based on company policies and outputs from these algorithms. Neither the details of these algorithms or their accuracy in risk prediction are shared with the public, thus research is needed to verify whether algorithms applied to search engine data can accurately predict suicide risk in a platform user. The onus is on researchers to study the utility of these data for prediction, which requires donation of search data from people with lived experience of suicidal thoughts and behavior. There is little guidance, however, from the research community or tech companies as to how to best assist participants in sharing their data easily and securely. OBJECTIVE This paper describes study methods and experiences recruiting and retaining participants in a year long, fully remote prospective study of suicide prediction in people with variable risk for suicide, using Google Search data. METHODS We have recruited 485 United States dwelling and English-speaking adults who fall into one of 3 categories: participants with a suicide attempt in the past year, participants with a lifetime suicide attempt but not one in the past year, and participants with no lifetime suicide attempt. RESULTS We describe important data supporting the methods we used to recruit a remote sample of participants with risk for suicide, Google Search data quality, amount of fraudulent acting, and retention at each study phase and follow up assessment. CONCLUSIONS Despite past success with remote clinical research methods, we found that recruitment can be significantly hampered by fraudulent acting, despite the use of state-of-the-art methods to mitigate this problem. Further, the ability to acquire useful Google Search data is extremely challenging and necessitates the use of technical assistance and continuous monitoring of Google’s Takeout data structure to ensure accurate data downloads. The solutions we provide for this type of research should be helpful for future endeavors. However, research is still limited by the barriers to obtaining data from technology companies. CLINICALTRIAL Not applicable – not a clinical trial

10 February 2026 in JMIR Preprints
Verified
Preprint
Open access
XRXinyang Ren
Xinyang Ren
AKAmanda H. Kerbrat
Amanda H. Kerbrat
PSPayton Smythe
Payton Smythe
EKEthan H. Kim
Ethan H. Kim
CBCourtney L. Bagge
Courtney L. Bagge
TCTrevor A. Cohen
Trevor A. Cohen
BACKGROUND Suicide is a major global public health concern and a leading cause of death worldwide. However, timely identification of individuals at elevated risk remains challenging. Traditional suicide risk assessment relies heavily on self-report and structured screening tools, which are often limited by infrequent monitoring, social stigma surrounding mental health issues, and restricted access to mental health services. As individuals increasingly rely on web search engines for everyday information seeking, personal search data offer a unique opportunity to capture signals related to suicide risk. OBJECTIVE This study aimed to quantitatively evaluate the utility of personal Google search logs for detecting periods preceding suicide attempts using anomaly detection methods. METHODS A subset of personal Google search data collected in a retrospective-prospective study, focusing on 80 adult participants who reported suicide attempt dates (n=111) with sufficient detail to enable identification of high-risk periods, was used for analysis. Neural language representation techniques were developed to calculate a proximity score between each search query and constructs representing known suicide warning signs, reflecting search behavior related to suicide risk. The semantic feature construction framework, consists of initial proximity based filtering on query-construct relatedness by a smaller-scale language model and further adjudication by a state-of-the-art large language model (Llama 3.1), was feasible for application to large-scale web search data. Anomaly detection methods were applied to semantic and behavioral features of search activity to identify time periods (14 days) preceding the suicide attempts. Models were trained on search data more than 6 months prior to the attempt and evaluated over the 180 days preceding and including the attempt date. The ROC AUC score was used to evaluate how effectively the model distinguished attempt periods from non-attempt periods. RESULTS The majority of analyzed suicide attempts were effectively distinguished from non-attempt periods. The best-performing anomaly detection model achieved a median ROC AUC score of 0.75 across attempts. Individually trained models outperformed generalized models trained on normative data from all participants. Semantic features that characterized search content’s relatedness to constructs contributed more substantially to the anomaly detection performance than behavioral features. Substantial differences in search feature importance were observed across participants, while consistent feature importance was found within the attempt histories of the same participant. Results from the ablation study demonstrated the utility of large language models in adjudicating the validity of construct-to-search relationships. CONCLUSIONS This study showed that personal Google search logs can be a valuable resource for suicide risk detection. The proposed framework has the potential to support the development of automated suicide risk detection tools for more timely identification of individuals at elevated risk.