Ethics

All research studies conducted by Sahha, either independently or in collaboration, have undergone rigorous ethical review process. This study was reviewed and approved by the University of Otago Human Ethics Committee, under Reference Number 21/074.

Executive summary

• This study aims to explore the reported associations between activity patterns and depression level as measured by the PHQ-9 using smartphone-based activity tracking.

• Our results are consistent with reported associations between depression level and the activity patterns derived from wrist worn trackers.

• We observed sex-specific differences in the associations, activity regularity statistically significant in males but not females, while activity in the early morning was statistically significant in females but not males.

• Our findings indicate that the inference of depression levels from activity data captured from smartphones and wearable data is scientifically feasible.

Introduction

Background

Our mission at Sahha is to empower technologies with robust and scalable health analytics solutions using passively collected data. We aim to provide organizations with reliable measurements and inferences of their user’s health parameters. To achieve this, strong scientific bases behind our methods are necessary. Mental wellness is a key aspect of overall health, and the drive to monitor and enhance it is rapidly gaining traction in the health-tech sector. A growing array of solutions is emerging to help users improve their mental well-being. Examples of this trend include guided meditation and mindfulness apps, which have become increasingly popular among users seeking to enhance their mental well-being (Neary and Schueller, 2018).

With the rising adoption of wearable technology and the greater precision of smartphone sensor suites, it is now possible to capture a user's activity and sleep patterns with impressive accuracy. A recent meta-analysis found that activity tracking improves activity levels equivalent to an additional 1800 steps per day and reductions of approximately 1 kg in bodyweight (Ferguson et al., 2022). Another study on the use of sleep tracker apps found that the use of sleep tracker apps is associated with Improved perceive mental well-being (Attie and Meyer-Waarden, 2023). These findings suggest that activity and sleep tracking have verifiable impact on a user’s physical and mental wellbeing. A natural progression in the technology would be the inference of a user’s mental states using activity and sleep pattern data. While wearables still tend to be more accurate than smartphones based methods, the activity tracking capabilities and accuracies of smartphone based sensors are rapidly catching up (Caputo et al., 2022; Modave et al., 2017; Piccinini et al., 2020). Tracking mental state tracking using activity patterns Multiple studies examining the associations between activity and mental states have emerged over recent years. While the methodologies used vary, a trend of participants with higher level of depressive symptoms exhibiting lower overall activity levels and a higher proportion of their activity at night relative is consistent across studies.

A study by (Banihashemi et al., 2016) recruited 168 participants with a history of affective disorders and 68 control participants. Diagnosis was determined using DSM4 criteria (American Psychiatric Association, 1994). Activity was measured via wrist worn actigraphy over a mean period of 14 days. Using functional smoothing and function linear analysis, the investigators found that higher depression severity was associated with higher nighttime activity level. A study by (Difrancesco et al., 2019) recruited 359 participants with a history of affective disorders from the Netherlands Study of Depression and Anxiety (NESDA) cohort (Penninx et al., 2008). Activity was measured via wrist worn actigraphy over 14 days. Depression and anxiety levels were assessed using the inventory of depressive symptomatology (IDS) and Beck anxiety inventory (BAI) (Beck et al., 1988; Rush et al., 1996) respectively. Using a linear regression analysis, the investigators found that higher levels of depressive and anxiety symptoms were associated with lower gross motor activity (measured in milli-gravity [mg], 1g = 9.81 m/s2) and greater proportion of the daily activity taking place at night. (Difrancesco et al., 2019). A follow-up study utilizing 121 (63 control) participants from the NESDA cohort examined depressive symptoms specifically. Using a linear mixed effect model, they found that the depression group exhibited a reduced difference between peak and mean activity level, and a preference for nighttime activity (Minaeva et al., 2020). Another study (Smagula et al., 2022) utilised 1800 participants from the 2011-2014 National Health and Nutrition Examination Survey (NHANES) (Chen et al., 2018). Smagula et al. measured activity using wrist worn actigraphy and depression levels using the patient Health Questionnaire (PHQ-9) (Kroenke et al., 2001). The investigators performed clustering analysis and found that the clusters containing the highest proportion of participants with high PHQ-9 scores (>10) are characterised by lower and later activity patterns along with more fragmented and unstable patterns (Smagula et al., 2022).

Thus, there is growing literature indicating an individual’s mental state is often reflected in their activity, most notably, higher depression levels are associated with a lower overall activity level and a preference for nighttime activities. These findings suggest that inferring a user’s mental state using activity is possible. Exploring the association between mental state and smartphone derived activity patterns Existing studies examining the association between mental states and activity patterns using wrist worn activity trackers and (Banihashemi et al., 2016; Difrancesco et al., 2021, 2019; Minaeva et al., 2020; Smagula et al., 2022). Is unknown if this association can be detected using smartphone-based activity trackers.

The aim of this study is to examine whether mental state; specifically, depression level is associated with activity patterns data tracking using smartphone-based methods. In this study, depression level was measured via the PHQ-9 (Kroenke et al., 2001). The PHQ-9 (Patient Health Questionnaire-9) is a self-report psychometric instrument for screening and measuring the level of depression experienced by the individual (Kroenke et al., 2001). It consists of nine items that assess various symptoms of depression, such as mood, interest in activities, and sleep pattern. Each item is scored based on the frequency of symptoms on a scale of 0-3, where 0 being “not at all” and 3 being “nearly every day”. A final score is calculated by summing the individual items. A score of 0–4 indicates minimal depression, 5–9 mild depression, 10–14 moderate depression, 15–19 moderately severe depression, and 20–27 severe depression.

While commonly used to screen for clinical depression in a primary care and research setting, the PHQ-9 score has also been shown that to be a reliable dimensional measure of depression level (Bianchi et al., 2022; Martin et al., 2006). Through this study, we seek examine the scientific basis of the using of using smartphone sensors to infer depression level. We believe that the findings of this study will contribute materially to the field of mood tracking using smartphones

data.

Methodology

Participants recruitment

Participants were recruited from participant recruitment services. Inclusion criteria include i) age from 18-65, ii) has a smartphone (at least Android version 8+ or iPhone with internet connection, iii) proficient in English. Participants were recruited across 13 recruitments over a 1-year period from February 2022 to February 2023.

Data collection

After informed consent and acknowledgement of our data collection and privacy policies which can be found here, participants were required to install the Sahha Research App on their smartphone. The participants were then required to complete the enrollment procedure by providing information on Age, Sex, Ethnicity, Education Attainment, Income, Country, and Living Arrangement. The Sahha Research App collects information provided by Apple HealthKit (iOS) or

Health Connect (Android), this information includes steps counts and sleep duration. Screen lock and unlock events were also logged for Android users. The study period was 1 month, in which participants were required to complete

PHQ-9 on a weekly basis. All data collected in this study were anonymized in accordance with the data collection and privacy policies.

Activity patterns measurements

Using the step count data collected, we derived 7 variables describing an individual’s daily activity pattern: average active hours based on duration (hours with more than 1 minute of physical activity), average active hours based on steps (hours with more than 100 steps), activity regularity (consistency in active hours across days), and the average number of steps in the early morning (5 am to 9 am), day (9 am to 6 pm), evening (6 pm to 9 pm), and night (9 pm to 5 am) respectively.

Statistical analysis

We performed multivariate linear regression analysis with activity patterns measurements as predictor variables and the PHQ-9 scores as the response variable. Distributions of variables were checked on normality with QQ plots. Linearity and

homoskedasticity was checked using predicted vs residual plots. Residual normality, linearity, and homoskedasticity were found to be within acceptable ranges. To account for potential sex-specific differences in the associations, we performed

the analysis separately for male and female participants. Age was included as a covariate in the models to account reported associations between age and depression levels (Hawthorne et al., 2008). Statistical significance was defined at α=0.05. All analysis was performed on Python 3.10 with the statsmodel package 0.14.1 (Seabold and Perktold, 2010).

Results

Participants demographics

A total of 2,864 participants were recruited and participated in the study. After filtering out those with insufficient activity data and those who did not perform at least 1 PHQ-9 survey, the measurements from 2,068 participants were retained for the analysis. Across the 2,068 participants, a total of 26,888 PHQ-9 surveys were collected, the median number of surveys collected per participant was 12. A demographic breakdown of these participants is available in Table 1.

Table 1: Participant demographics

Statistical analysis

3 variables were found to be statistically significant within the male participants,

namely: average active hours (duration) (p=0.045), activity regularity (p=0.045), and

average night-time activity (p=0.021) (Table 2).

Table 2: Multivariate regression results - Male

In our female participants, 4 variables were found to be statistically significant within the male participants, namely: average active hours (duration) (p=0.0278), average night-time activity (p=4.31E-06), average early activity (p=0.00817), and age (p=1.01E-05) (Table 3).

Table 3: Multivariate regression results - Female

Discussion

To our knowledge, this is the first study examining an association between activity patterns tracked via smartphones and depression levels within the general population. These associations are consistent with those found by studies utilising

wrist-worn trackers and (Banihashemi et al., 2016; Difrancesco et al., 2021, 2019; Minaeva et al., 2020; Smagula et al., 2022). Additionally, our results suggest sexspecific differences in the association. For males, the coefficients of average active hours (duration) and activity regularity were negative while the coefficient for Average night activity was positive. These

results suggest that a higher average active hour (duration) and activity regularity are associated with a lower depression level while a higher level of night-time activity was associated a higher depression level in our male participants.

For females, the coefficients of average active hours (duration), Average early activity, and age were negative, while the coefficients of Average night activity were positive. These results suggest that higher average active hours (duration), activity in the early hours, and older age were associated with a lower depression level while a higher level of night-time activity was associated a higher depression level in our female participants. These findings are consistent with reported findings of lower levels of physical activity in the day and higher level of activity at night (Banihashemi et al., 2016;

Difrancesco et al., 2019). The negative association between age and depression level is consistent with findings of a greater prevalence of depressive disorders within younger women (Hawthorne et al., 2008). The different significant activity markers between male and female participants suggest that sex-specific models are necessary when designing mental health tracking models.

Conclusion

Our study found that the reported associations observed between depression levels and activity patterns is also present in the general population. Additionally, this association can be observed using smartphone-based data. The findings here support a move for smartphone-based technology in mental health tracking. The observed sex differences in these associations emphasize the importance of tailoring mental health strategies to account for gender-specific patterns.