Miwoo Lee
Research Subjects
Miwoo Lee has a total of 42 co-authors. Here are the top co-authors by number of shared publications:
- HyunKyung Shin
Research Institute of Minds.AI, Co. Ltd., Seoul, Republic of Korea
5 shared publications - Jeong-Ho Seok
Institute of Behavioral Science in Medicine, Yonsei University College of Medicine, Seoul, Republic of Korea
5 shared publications - Sooah Jang
Research Institute of Minds.AI, Co. Ltd., Seoul, Republic of Korea
5 shared publications - Jun Ho Seo
Department of Psychiatry, Yonsei University Wonju College of Medicine, Wonju, Republic of Korea
2 shared publications - Sin Young Ko
Department of Psychiatry, Gangnam Severance Hospital, Yonsei University College of Medicine, Seoul, Korea
2 shared publications - Sun-Woo Choi
Institute of Behavioral Science in Medicine, Yonsei University College of Medicine, Seoul, Korea
2 shared publications
Latest Publications
- Open Access
- 25 July 2026
- Published by Korean Neuropsychiatric Association in Psychiatry Investigation
- Vol. 23 (7) , 837-850
Development of a Machine Learning-Based Model for Classifying Depression Using Physiological and Psychological Indicators
Objective This study aimed to develop and evaluate machine learning-based models for classifying depression symptoms using salivary hormone markers (cortisol and dehydroepiandrosterone [DHEA]) and psychological indicators from depression screening devices, and to determine the extent to which salivary hormone markers contribute to depression symptom classification.Methods Two models were developed, a multi-class classification (four degrees of depression) and a binary classification model (normal vs. depression), using psychological indicators that assess depression symptoms, protective and vulnerability factors, and physiological indicators including salivary cortisol and DHEA. Each model was evaluated both with and without physiological indicators. Data from 368 individuals were used for model training, with 92 individuals reserved for independent testing. Out of 36 variables, including psychological indicators from the PROtective and Vulnerable factors battEry test and physiological markers (e.g., salivary cortisol and DHEA), 24 non-demographic variables with independent contributions were selected, excluding demographic information. To ensure model robustness, overfitting risks were mitigated using k-fold cross-validation, class weight balancing, and grid search optimization. Model performance was evaluated based on accuracy, precision, recall, and receiver operating characteristic values.Results The multi-class classification model achieved 85.9% and 76.1% accuracy with and without physiological indicators, respectively. The binary classification model (depression presence or absence) achieved 97.8% accuracy both with and without physiological indicators.Conclusion The machine learning models demonstrated high accuracy in depression classification, showing a noteworthy improvement in classification performance when integrating psychological and physiological markers. Future clinical trials will be conducted to secure additional clinical data to verify the model’s reliability and clinical validity.
- 25 July 2026
- Published by Korean Neuropsychiatric Association in Psychiatry Investigation
- Vol. 23 (7) , 837-850
Open AccessDevelopment of a Machine Learning-Based Model for Classifying Depression Using Physiological and Psychological Indicators
Objective This study aimed to develop and evaluate machine learning-based models for classifying depression symptoms using salivary hormone markers (cortisol and dehydroepiandrosterone [DHEA]) and psychological indicators from depression screening devices, and to determine the extent to which salivary hormone markers contribute to depression symptom classification.Methods Two models were developed, a multi-class classification (four degrees of depression) and a binary classification model (normal vs. depression), using psychological indicators that assess depression symptoms, protective and vulnerability factors, and physiological indicators including salivary cortisol and DHEA. Each model was evaluated both with and without physiological indicators. Data from 368 individuals were used for model training, with 92 individuals reserved for independent testing. Out of 36 variables, including psychological indicators from the PROtective and Vulnerable factors battEry test and physiological markers (e.g., salivary cortisol and DHEA), 24 non-demographic variables with independent contributions were selected, excluding demographic information. To ensure model robustness, overfitting risks were mitigated using k-fold cross-validation, class weight balancing, and grid search optimization. Model performance was evaluated based on accuracy, precision, recall, and receiver operating characteristic values.Results The multi-class classification model achieved 85.9% and 76.1% accuracy with and without physiological indicators, respectively. The binary classification model (depression presence or absence) achieved 97.8% accuracy both with and without physiological indicators.Conclusion The machine learning models demonstrated high accuracy in depression classification, showing a noteworthy improvement in classification performance when integrating psychological and physiological markers. Future clinical trials will be conducted to secure additional clinical data to verify the model’s reliability and clinical validity.
- Open Access
- 13 November 2025
- Published by JMIR Publications Inc. in JMIR Preprints
Efficacy and Usability of a Virtual Reality-Based Cognitive Behavioral Therapy Program (CHEEU. Forest N) for Patients with Major Depressive Disorder: A Randomized, Non-inferiority Confirmatory Trial (Preprint)
BACKGROUND Major depressive disorder (MDD) poses a substantial global health burden, with a high suicide risk and limited treatment accessibility. Although cognitive behavioral therapy (CBT) shows robust efficacy, practical barriers, including therapist availability and time constraints, limit its implementation. Virtual reality (VR)-based interventions offer an immersive and accessible alternative. However, rigorous evidence for VR-based CBT for depression remains limited. OBJECTIVE To evaluate the efficacy and usability of CHEEU. Forest N, a VR-based CBT program integrating components of mindfulness-based cognitive, mentalization-based, and dialectical behavior therapies, compared with standard pharmacotherapy in patients with MDD. METHODS This multicenter, randomized, parallel-group, assessor-blinded, non-inferiority confirmatory trial enrolled 134 adults aged between 19 and 55 years who met the DSM-5 criteria for MDD with Patient Health Questionnaire-9 scores ≥7 and moderate suicidality. The participants were randomized 1:1 to receive 6 weekly VR-based CBT sessions (VR group, n=67) or standard antidepressant treatment with brief clinical interviews (treatment-as-usual; TAU group, n=67). The primary outcome was the change in the Korean version of the Quick Inventory of Depressive Symptomatology-Clinician-Rated (K-QIDS-C) scores from baseline to post-treatment (week 6), with a non-inferiority comparison. The secondary outcomes included self-reported depression, anxiety, stress, suicidality, quality of life, presence, and usability. The per-protocol analysis included 116 participants (58 in each group). RESULTS Both groups demonstrated a significant reduction in the severity of their depressive symptoms. The adjusted between-group difference in K-QIDS-C scores was 0.13 points (SE=0.91, 95% CI: –1.66 to 1.93, p=.883), confirming non-inferiority of VR to TAU (upper CI bound 1.93<5.0). Response rates were comparable between the VR (44.8%) and TAU (43.1%) groups (χ²=0.04, p=.852), as were the remission rates (25.9% vs. 27.6%, χ²=0.04, p=.834). For suicidality, 50% of the VR participants achieved remission compared with 43% in TAU (χ²=0.55, p=.457). No significant between-group differences emerged for the secondary outcomes, including anxiety, stress, or quality of life. Usability ratings were high (mean composite score 3.73±0.62/5.0), with participants reporting increased depression literacy (7.43±1.94/10) and willingness to recommend the program (7.47±2.01/10). Simulator sickness decreased significantly with repeated exposure. Baseline presence was correlated with usability (r=0.46, p<.001) but not with clinical outcomes. No serious adverse events occurred. CONCLUSIONS The VR-based CBT intervention demonstrated therapeutic efficacy equivalent to that of standard pharmacotherapy in treating depression, particularly in reducing suicidal ideation and increasing user satisfaction. These findings support VR-based digital therapeutics as safe, effective, and accessible alternatives or adjunctive treatment options for depression, warranting further investigation of long-term outcomes. CLINICALTRIAL This trial was registered with the Clinical Research Information Service (KCT0009868).
- 13 November 2025
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessEfficacy and Usability of a Virtual Reality-Based Cognitive Behavioral Therapy Program (CHEEU. Forest N) for Patients with Major Depressive Disorder: A Randomized, Non-inferiority Confirmatory Trial (Preprint)
BACKGROUND Major depressive disorder (MDD) poses a substantial global health burden, with a high suicide risk and limited treatment accessibility. Although cognitive behavioral therapy (CBT) shows robust efficacy, practical barriers, including therapist availability and time constraints, limit its implementation. Virtual reality (VR)-based interventions offer an immersive and accessible alternative. However, rigorous evidence for VR-based CBT for depression remains limited. OBJECTIVE To evaluate the efficacy and usability of CHEEU. Forest N, a VR-based CBT program integrating components of mindfulness-based cognitive, mentalization-based, and dialectical behavior therapies, compared with standard pharmacotherapy in patients with MDD. METHODS This multicenter, randomized, parallel-group, assessor-blinded, non-inferiority confirmatory trial enrolled 134 adults aged between 19 and 55 years who met the DSM-5 criteria for MDD with Patient Health Questionnaire-9 scores ≥7 and moderate suicidality. The participants were randomized 1:1 to receive 6 weekly VR-based CBT sessions (VR group, n=67) or standard antidepressant treatment with brief clinical interviews (treatment-as-usual; TAU group, n=67). The primary outcome was the change in the Korean version of the Quick Inventory of Depressive Symptomatology-Clinician-Rated (K-QIDS-C) scores from baseline to post-treatment (week 6), with a non-inferiority comparison. The secondary outcomes included self-reported depression, anxiety, stress, suicidality, quality of life, presence, and usability. The per-protocol analysis included 116 participants (58 in each group). RESULTS Both groups demonstrated a significant reduction in the severity of their depressive symptoms. The adjusted between-group difference in K-QIDS-C scores was 0.13 points (SE=0.91, 95% CI: –1.66 to 1.93, p=.883), confirming non-inferiority of VR to TAU (upper CI bound 1.93<5.0). Response rates were comparable between the VR (44.8%) and TAU (43.1%) groups (χ²=0.04, p=.852), as were the remission rates (25.9% vs. 27.6%, χ²=0.04, p=.834). For suicidality, 50% of the VR participants achieved remission compared with 43% in TAU (χ²=0.55, p=.457). No significant between-group differences emerged for the secondary outcomes, including anxiety, stress, or quality of life. Usability ratings were high (mean composite score 3.73±0.62/5.0), with participants reporting increased depression literacy (7.43±1.94/10) and willingness to recommend the program (7.47±2.01/10). Simulator sickness decreased significantly with repeated exposure. Baseline presence was correlated with usability (r=0.46, p<.001) but not with clinical outcomes. No serious adverse events occurred. CONCLUSIONS The VR-based CBT intervention demonstrated therapeutic efficacy equivalent to that of standard pharmacotherapy in treating depression, particularly in reducing suicidal ideation and increasing user satisfaction. These findings support VR-based digital therapeutics as safe, effective, and accessible alternatives or adjunctive treatment options for depression, warranting further investigation of long-term outcomes. CLINICALTRIAL This trial was registered with the Clinical Research Information Service (KCT0009868).
- Open Access
- 1 January 2025
- Published by XMLink in Journal of Korean Neuropsychiatric Association
- Vol. 64 (4) , 266-276
A Preliminary Study on the Validation of a Contactless Mental Health Assessment Service for Disaster Related Distress: Focusing on the Relationship Between Insomnia and Stress Sensitivity
이미우, et al. J Korean Neuropsychiatr Assoc. 2025 Nov;64(4):266-276. https://doi.org/10.4306/jknpa.2025.64.4.266
- 1 January 2025
- Published by XMLink in Journal of Korean Neuropsychiatric Association
- Vol. 64 (4) , 266-276
Open AccessA Preliminary Study on the Validation of a Contactless Mental Health Assessment Service for Disaster Related Distress: Focusing on the Relationship Between Insomnia and Stress Sensitivity
이미우, et al. J Korean Neuropsychiatr Assoc. 2025 Nov;64(4):266-276. https://doi.org/10.4306/jknpa.2025.64.4.266
- Open Access
- 1 January 2025
- Published by XMLink in Journal of Korean Neuropsychiatric Association
- Vol. 64 (2) , 58-76
Development of the Battery Test for Screening of Depression and Mental Health: PROtective and Vulnerable factors battEry test–Light version
이주열, et al. J Korean Neuropsychiatr Assoc. 2025 May;64(2):58-76. https://doi.org/10.4306/jknpa.2025.64.2.58
- 1 January 2025
- Published by XMLink in Journal of Korean Neuropsychiatric Association
- Vol. 64 (2) , 58-76
Open AccessDevelopment of the Battery Test for Screening of Depression and Mental Health: PROtective and Vulnerable factors battEry test–Light version
이주열, et al. J Korean Neuropsychiatr Assoc. 2025 May;64(2):58-76. https://doi.org/10.4306/jknpa.2025.64.2.58
- Open Access
- 1 January 2025
- Published by XMLink in Yonsei Medical Journal
- Vol. 66 (1) , 25-36
Virtual Reality-Based Cognitive Behavior Therapy for Major Depressive Disorder: An Alternative to Pharmacotherapy for Reducing Suicidality
Lee M, et al. Yonsei Med J. 2025 Jan;66(1):25-36. https://doi.org/10.3349/ymj.2024.0002
- 1 January 2025
- Published by XMLink in Yonsei Medical Journal
- Vol. 66 (1) , 25-36
Open AccessVirtual Reality-Based Cognitive Behavior Therapy for Major Depressive Disorder: An Alternative to Pharmacotherapy for Reducing Suicidality
Lee M, et al. Yonsei Med J. 2025 Jan;66(1):25-36. https://doi.org/10.3349/ymj.2024.0002
- Open Access
- 1 January 2004
- Published by Medical Journals Sweden AB in Acta Dermato-Venereologica
- Vol. -1 (1) , 1
Successful Treatment of Multicentric Reticulohistiocytosis with a Combination of Infliximab, Prednisolone and Methotrexate
- 1 January 2004
- Published by Medical Journals Sweden AB in Acta Dermato-Venereologica
- Vol. -1 (1) , 1
Open AccessSuccessful Treatment of Multicentric Reticulohistiocytosis with a Combination of Infliximab, Prednisolone and Methotrexate