This longitudinal study aims to identify and validate digital phenotypes that can predict recurrence of major depressive episodes using passively collected, real-time sensing data from smartphones and wearable devices. Over a 12-month period, 540 participants-including patients with mood disorders and healthy or high-risk controls-will complete five clinical assessments at 3-month intervals, wear a Fitbit device daily, and log daily mood ratings via a mobile app. The study includes the development of AI-based predictive models and the construction of an anonymized wearable big-data repository for mood disorders.

This is a 12-month longitudinal follow-up study designed to identify digital phenotypes capable of predicting the recurrence of major depressive episodes using passively collected real-time data from smartphones and wearable devices. A total of 540 participants will be enrolled, including 200 patients diagnosed with mood disorders who have experienced at least one depressive episode in the past two years, and 340 healthy or high-risk control participants without a clinical diagnosis.

Clinical interviews and self-report measures will be conducted five times at 3-month intervals. Throughout the study period, participants will wear a Fitbit device daily and use the "My Mental Hero" mobile application to record their mood once a day at a self-selected time. Data collected will be used to develop machine learning models for predicting depressive recurrence and to build a large-scale, anonymized wearable big-data repository for mood disorders.

Participants will receive no interventions beyond data collection, and neither randomization nor blinding will be implemented. Trained psychiatrists, clinical psychologists, or research nurses will conduct the assessments. Initial visits will include informed consent, device setup, and app training, taking approximately 1-2 hours. Subsequent assessments will take about one hour, with additional brief interviews (≤30 minutes) conducted if a mood episode is suspected.

While follow-up assessments for patients and high-risk participants will be conducted in person, those for healthy controls may be conducted remotely (via Zoom or phone) under secure and private conditions without screen recording. Remote assessments may also be used for patient and high-risk groups if necessary.

Inclusion Criteria for Patient Group:

1. Adults aged 19 to 75 years and 11 months.
2. Diagnosed with a major mood disorder (bipolar I or II disorder, or major depressive disorder) based on DSM-5, with a history of psychiatric visits for mood symptoms.
3. Has experienced at least one prior depressive episode (major, minor, or brief).
4. Owns a smartphone with stable internet connectivity, can operate it without difficulty, and agrees to install a digital phenotyping application, wear a Fitbit device daily, and complete daily mood logs throughout the study period.

Inclusion Criteria for Healthy Control Group:

1. Adults aged 19 to 75 years and 11 months.
2. No current or past diagnosis of bipolar disorder or major depressive disorder.
3. Scores below clinical thresholds on both K-MDQ (<7) and PHQ-9 (<5) at baseline assessment.
4. Owns a smartphone with stable internet connectivity, can operate it without difficulty, and agrees to install a digital phenotyping application, wear a Fitbit device daily, and complete daily mood logs throughout the study period.

Inclusion Criteria for Hight Risk Group:

1. Adults aged 19 to 75 years and 11 months.

2. No current or past diagnosis of bipolar disorder or major depressive disorder.

3. Meets either of the following:

   A. Scores above the threshold on K-MDQ (≥7) or PHQ-9 (≥5) at baseline. B. Reports persistent mood symptoms during MINI (e.g., ≥2 weeks of depressive mood/anhedonia, or several days of elevated/irritable mood).

4. Owns a smartphone with stable internet connectivity, can operate it without difficulty, and agrees to install a digital phenotyping application, wear a Fitbit device daily, and complete daily mood logs throughout the study period.

Exclusion Critera (Overall)

1. Inability to provide informed consent due to cognitive impairment, severe psychiatric symptoms, or language barriers.
2. Presence of any neurological or medical condition that may significantly affect mood, cognition, or behavior (e.g., epilepsy, dementia, traumatic brain injury).
3. Current substance use disorder or dependence (excluding nicotine or caffeine) that is either untreated or clinically unstable.
4. Severe suicidal ideation or risk as determined by clinical judgment at screening.
5. Ongoing participation in another interventional clinical trial, particularly those involving psychotropic medications or digital health interventions.
6. Inability or unwillingness to wear a wearable device (Fitbit) or use the required mobile application daily throughout the study.
7. Lack of stable internet access or a compatible smartphone required for digital phenotyping data collection.
8. Any other condition that, in the investigator's judgment, may compromise the participant's safety, compliance, or the integrity of the study data.

This study will recruit a total of 540 participants divided into three groups:

Patient Group (PT, n=200):

Individuals diagnosed with a mood disorder (bipolar I/II or major depressive disorder) who have experienced at least one depressive episode within the past two years.

High-Risk Group (HR):

Individuals with no formal mood disorder diagnosis but who present subclinical mood symptoms or elevated screening scores suggesting potential risk for affective disorders.

Healthy Control Group (HC):

Individuals with no history or current diagnosis of any mood disorder and who do not show clinically significant symptoms on screening assessments.

All participants will undergo 5 clinical assessments over a 12-month period (every 3 months) and will be asked to wear a Fitbit device daily and record their mood daily via a mobile app throughout the study. No therapeutic intervention will be provided, and the study does not involve randomization or blinding.

Some of the data will be shared with the K-BDS (Korea Brain Data Station) after the completion of the study; however, the exact amount and timing of data to be shared have not yet been determined. The expected date of upload to the K-BDS is December 31, 2027.