HLHaejung Lee

Haejung Lee

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

Haejung Lee has a total of 6 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Week-Ahead Prediction of High-Risk Drinking Episodes Among Young Adults Using Wearable Biosignals and Psychological Vulnerabilities: Prospective Observational Machine Learning Study

    by Jae Seok Kwak, Hae Kook Lee, Sun-Jin Jo, Jun Hyuk Kwon, Sun Jung Kwon, Yena Kim, Haejung Lee

    Background: Although machine learning has increasingly been used to predict mental health symptoms and maladaptive behaviors, real-world prediction of addiction-related risk remains limited. Emotional and temperamental vulnerabilities are established correlates of alcohol-related problems, yet few studies have integrated these factors with wearable-derived biosignals in alcohol-risk prediction models. Objective: This study evaluated whether machine learning models could predict weekly high-risk drinking episodes among young adults with elevated alcohol-use risk by integrating wearable-derived health data with baseline emotional and personality vulnerability indicators. Methods: In this prospective observational study, adults in their 20s completed weekly self-report surveys and wore Fitbit devices for 4 weeks. Features from week t were used to predict the Alcohol Use Disorders Identification Test-Korean version (AUDIT-K)–based high-risk drinking label at week t+1. Positive labels were defined using AUDIT-K high-risk drinking cutoffs, with scores of ≥20 for men and ≥10 for women. Extreme gradient boosting (XGBoost) and random forest models were evaluated across self-report-only, wearable-only, and integrated feature sets using 5-fold participant-level grouped cross-validation. Results: A total of 206 participants contributed 620 week-level observations, of which 85 (13.7%) were labeled as positive high-risk drinking episodes. In participant-level grouped cross-validation, the integrated random forest model showed the most favorable sensitivity-oriented performance, with a mean accuracy of 0.617 (SD 0.078), recall/sensitivity of 0.653 (SD 0.144), area under the receiver operating characteristic curve (ROC AUC) of 0.681 (SD 0.079), and area under the precision-recall curve (PR AUC) of 0.255 (SD 0.090). The integrated XGBoost model achieved an accuracy of 0.670 (SD 0.089), recall/sensitivity of 0.399 (SD 0.174), ROC AUC of 0.651 (SD 0.089), and PR AUC of 0.228 (SD 0.074). Shapley additive explanations analyses indicated that both baseline vulnerability indicators and wearable-derived weekly summaries contributed to model predictions. Conclusions: Integrating baseline emotional and personality vulnerability indicators with wearable-derived weekly health signals may provide useful information for week-ahead prediction of high-risk drinking episodes. These findings provide preliminary support for wearable-assisted alcohol-risk stratification, although the modest positive predictive performance indicates that external validation and more proximal within-person measures are needed before real-world early-warning or just-in-time adaptive intervention applications.

  • Open Access

    Unintended positive behavioral changes during self-report and wearable data collection on digital media use in young adults

    by Sun-Jin Jo, Hae Kook Lee, Sun Jung Kwon, Yena Kim, Jae Seok Kwak, Haejung Lee

    Background and aims: The use of mobile devices is increasingly recognized as a valuable tool for interventions targeting mental health issues. This brief report aims to share insights into the unexpected positive changes observed during the data collection process for predicting addictive behaviors using mobile technology. Methods: We analyze self-reported baseline and 4-week follow-up data collected to develop an algorithm for predicting addictive digital media use. Two hundred and six adults in their 20 s completed a smartphone self-report survey on digital media use behaviors and emotion, while their step and heart rate data was passively collected via Fitbit. Results: Despite the absence of any interventional feedback beyond the data collection process, positive changes were observed, including time spent on digital media use ( p = 0.031), a reduction in high-risk digital media use score ( p < 0.001), and depressive symptom score ( p = 0.004). Conclusions: When collecting data on digital media use and related emotion via mobile devices, it is important to recognize that positive changes may occur in participants even without planed intervention. Failing to consider this phenomenon could lead to an overestimation of the effects of interventions provided through smart devices.

  • Open Access

    Week-Ahead Prediction of High-Risk Drinking Episodes Among Young Adults Using Wearable Biosignals and Psychological Vulnerabilities: Prospective Observational Machine Learning Study (Preprint)

    by Jae Seok Kwak, Hae Kook Lee, Sun-Jin Jo, Jun Hyuk Kwon, Sun Jung Kwon, Yena Kim, Haejung Lee

    BACKGROUND Although machine learning has increasingly been used to predict mental health symptoms and maladaptive behaviors, real-world prediction of addiction-related risk remains limited. Emotional and temperamental vulnerabilities are established correlates of alcohol-related problems, yet few studies have integrated these factors with wearable-derived biosignals in alcohol-risk prediction models. OBJECTIVE This study evaluated whether machine learning models could predict weekly high-risk drinking episodes among young adults with elevated alcohol-use risk by integrating wearable-derived health data with baseline emotional and personality vulnerability indicators. METHODS In this prospective observational study, adults in their 20s completed weekly self-report surveys and wore Fitbit devices for 4 weeks. Features from week t were used to predict the Alcohol Use Disorders Identification Test-Korean version (AUDIT-K)–based high-risk drinking label at week t+1. Positive labels were defined using AUDIT-K high-risk drinking cutoffs, with scores of ≥20 for men and ≥10 for women. Extreme gradient boosting (XGBoost) and random forest models were evaluated across self-report-only, wearable-only, and integrated feature sets using 5-fold participant-level grouped cross-validation. RESULTS A total of 206 participants contributed 620 week-level observations, of which 85 (13.7%) were labeled as positive high-risk drinking episodes. In participant-level grouped cross-validation, the integrated random forest model showed the most favorable sensitivity-oriented performance, with a mean accuracy of 0.617 (SD 0.078), recall/sensitivity of 0.653 (SD 0.144), area under the receiver operating characteristic curve (ROC AUC) of 0.681 (SD 0.079), and area under the precision-recall curve (PR AUC) of 0.255 (SD 0.090). The integrated XGBoost model achieved an accuracy of 0.670 (SD 0.089), recall/sensitivity of 0.399 (SD 0.174), ROC AUC of 0.651 (SD 0.089), and PR AUC of 0.228 (SD 0.074). Shapley additive explanations analyses indicated that both baseline vulnerability indicators and wearable-derived weekly summaries contributed to model predictions. CONCLUSIONS Integrating baseline emotional and personality vulnerability indicators with wearable-derived weekly health signals may provide useful information for week-ahead prediction of high-risk drinking episodes. These findings provide preliminary support for wearable-assisted alcohol-risk stratification, although the modest positive predictive performance indicates that external validation and more proximal within-person measures are needed before real-world early-warning or just-in-time adaptive intervention applications.