Real-time assessment comparing mood changes and machine learning in adults with mild-moderate depression and a group of healthy volunteers

Intervention - All participants with depression will be provided study-specific smartphones and smartwatches at the start of the study (once off) that will passively acquire physiological and behavioural data through the built-in sensors in these smartdevices. Participants would not have otherwise been given these devices in the absence of the study. Materials - Each participant will be provided with a commercially available smartphone (OneNord) based on the Android platform and a commercially available wearable smartwatch/fitness tracker manufactured by Fitbit. Data captured - Physiological data captured passively includes breathing/heart rates, heart rate variability, sleep quality, and step activity. Behavioural data includes the acoustic features of speech when participants complete daily 2-5 minute audio diaries. Procedures - Participants will complete an initial screening in person to assess for suitability to participate in this study. If considered suitable, there will be a demonstration of how to use the devices (both smartwatch and smartphone). They will then be provided with the smartdevices and a SIM card for the study-supplied smartphone. They will also be provided with the Fitbit smartwatch to wear during sleep and for most of the day. Fitbit smartwatches will potentially capture physiological data continuously and passively (as long as the participant is wearing it) - given the potential confounder of movement artefacts during the day, overnight measurements will be of particular interest. The smartphones will be used to capture interactive data - these include daily audio diaries (once a day) and ecological momentary assessments (up to five times daily). Participants are expected to record short audio diaries (2-5 mins in length) once a day on their smartphone. Tasks they would have to complete as part of the audio diaries include describing their day in general and then specific questions on bad aspects of the day and good aspects of the day respectively. These tasks will capture unstructured speech rather than structured speech (e.g. reading a stock sentence out loud daily). Ecological momentary assessments (EMAs) will be captured up to 5 times a day and will take less than a minute each to complete. EMAs will be on a Likert scale which the participant can select indicating how they are feeling at the time of completing the EMA. Who will provide the smartdevices - Clinical screening will be undertaken by the clinicians in the team with mental health expertise while the demonstration of how to use the smartdevices and support during the study will be provided by team members with a computer and software engineering background. Mode of delivery - Smartdevices will be provided to individual participants face to face and will be collected from participants at the end of the study. Location of intervention - Participants will come in for a face to face initial clinical screening assessment at the start of the study at the Clinical Research Centre of the University of Auckland which is in an urban centre. If considered suitable to participate, they will be provided with the smartdevices which they will have with them for a period of 1 month of data collection. The 1 month of data collection will be in the participants' own environment e.g. home, workplace, gym, etc. as they will be carrying these smartdevices with them. Refer to the Procedures section for details of the data captured. Adherence - Participants will be individually contacted weekly into the study after they are recruited to check whether they are able to use the smartdevices confidently and troubleshoot should they be encountering any technical challenges. Study duration - Total of 1 year. Data from individual participants will be gathered over a period of 1 month.