CoChat
Sign Up
Cited by 68Mental Health Research TopicsDigital Mental Health InterventionsHuman Mobility and Location-Based Analysis

Predicting depressive symptom severity through individuals’ nearby Bluetooth device count data collected by mobile phones: preliminary longitudinal study

Open access
Zhang, Yuezhou, Folarin, Amos A, Sun, Shaoxiong, Cummins, Nicholas, Ranjan, Yatharth, Rashid, Zulqarnain, Conde, Pauline, Stewart, Callum +17 more·2021·JMIR mHealth and uHealth
DOI 10.2196/29840PMC PMC8367113

Published version of a preprint

Open this paper in CoChat — free accountOpen PDF

Abstract

Background: Research in mental health has found associations between depression and individuals’ behaviors and statuses, such as social connections and interactions, working status, mobility, and social isolation and loneliness. These behaviors and statuses can be approximated by the nearby Bluetooth device count (NBDC) detected by Bluetooth sensors in mobile phones. Objective: This study aimed to explore the value of the NBDC data in predicting depressive symptom severity as measured via the 8-item Patient Health Questionnaire (PHQ-8). Methods: The data used in this paper included 2886 biweekly PHQ-8 records collected from 316 participants recruited from three study sites in the Netherlands, Spain, and the United Kingdom as part of the EU Remote Assessment of Disease and Relapse-Central Nervous System (RADAR-CNS) study. From the NBDC data 2 weeks prior to each PHQ-8 score, we extracted 49 Bluetooth features, including statistical features and nonlinear features for measuring the periodicity and regularity of individuals’ life rhythms. Linear mixed-effect models were used to explore associations between Bluetooth features and the PHQ-8 score. We then applied hierarchical Bayesian linear regression models to predict the PHQ-8 score from the extracted Bluetooth features. Results: A number of significant associations were found between Bluetooth features and depressive symptom severity. Generally speaking, along with depressive symptom worsening, one or more of the following changes were found in the preceding 2 weeks of the NBDC data: (1) the amount decreased, (2) the variance decreased, (3) the periodicity (especially the circadian rhythm) decreased, and (4) the NBDC sequence became more irregular. Compared with commonly used machine learning models, the proposed hierarchical Bayesian linear regression model achieved the best prediction metrics (R2=0.526) and a root mean squared error (RMSE) of 3.891. Bluetooth features can explain an extra 18.8% of the variance in the PHQ-8 score relative to the baseline model without Bluetooth features (R2=0.338, RMSE=4.547). Conclusions: Our statistical results indicate that the NBDC data have the potential to reflect changes in individuals’ behaviors and statuses concurrent with the changes in the depressive state. The prediction results demonstrate that the NBDC data have a significant value in predicting depressive symptom severity. These findings may have utility for the mental health monitoring practice in real-world settings.

AI snapshot

Written from the paper’s full text.

TL;DR

This preliminary longitudinal study used mobile phone nearby Bluetooth device count (NBDC) data from 316 participants in the RADAR-MDD study to predict depressive symptom severity measured by the PHQ-8. A hierarchical Bayesian linear regression using 49 Bluetooth features achieved the best prediction metrics (leave-all-out R²=0.526, RMSE=3.891), explaining an extra 18.8% of PHQ-8 variance over a baseline model without Bluetooth features.

Key findings

  • From 2886 PHQ-8 intervals in 316 participants, 10 second-order statistical features were significantly negatively associated with PHQ-8 score; Min_Max had the strongest association (z=−4.431, P<.001). MSE_1, MSE_2, and MSE_3 were positively associated, while MSE_16 and MSE_22 were negatively associated. Five frequency-domain features were significant, with MF_sum strongest (z=−4.766, P<.001).
  • Along with worsening depressive symptoms, the preceding 2 weeks of NBDC data showed decreased amount, decreased variance, decreased periodicity (especially circadian rhythm), and a more irregular sequence.
  • The hierarchical Bayesian linear model with all Bluetooth features achieved the best leave-all-out performance (R²=0.526, RMSE=3.891) versus baseline (R²=0.338, RMSE=4.547), an extra 18.8% variance explained; nonlinear Bluetooth features added 4.5% variance. In leave-one-out validation, the same model had R²=0.387 and RMSE=4.426.
  • Likelihood ratio tests showed Bluetooth features improved model fit: model C vs model A χ²=135.19, P<.001; model C vs model B χ²=104.15, P<.001.

Methods

  • Data came from the EU RADAR-CNS/RADAR-MDD study across the Netherlands, Spain, and the United Kingdom. PHQ-8 was collected every 2 weeks; NBDC was scanned hourly. Analyses were restricted to records before February 2020, with valid days having at least 12 hours of NBDC data and PHQ-8 intervals having at least 10 valid days.
  • From the 14-day NBDC sequence before each PHQ-8 score, 49 features were extracted: 16 second-order statistical features, 24 multiscale entropy features (scales 1–24), and 9 frequency-domain features. Linear mixed-effect models with random participant intercepts tested associations, adjusting for baseline age, gender, and years in education, with Benjamini-Hochberg correction.
  • Prediction used hierarchical Bayesian linear regression, LASSO, and XGBoost, with demographics and last observed PHQ-8 score as baseline predictors. Evaluation used leave-all-out and leave-one-out time-series cross-validation with R² and RMSE; the prediction subset included 183 participants.

Limitations

  • The paper states that hourly NBDC scanning may lose dynamic information compared with past studies suggesting 5-minute scanning; MAC addresses and device types were not recorded, so phones cannot be distinguished from other Bluetooth devices or strangers from acquaintances; frequency-domain interval boundaries were manually specified; and the linear Bayesian model may miss nonlinear relationships.
  • The text makes evident that the sample was 74.1% female, had a median baseline age of 51.0 years, and was recruited from a cohort with a history of recurrent major depressive disorder, so generalizability to other populations is not established. The paper also notes that leave-one-out validation used only the first two PHQ-8 intervals per participant for training, which may have caused underfitting at the participant level.

Model-written summary. Check it against the paper before relying on it.

Integrity signals

Registry

Crossref · 10.2196/29840

Cites

Statistics

Claims the paper makes

0 of 56 cited sources checked · 0 supported · 0 flagged

  • Findingown data

    A number of significant associations were found between Bluetooth features and depressive symptom severity.

    “A number of significant associations were found between Bluetooth features and depressive symptom severity.”
    Quote in the paperSubstantial claim
  • Findingown data

    MSE at scales 16 and 22 were significantly negatively associated with depressive symptom severity.

    “while MSE at scale 16 and scale 22 (MSE_16 and MSE_22) were significantly and negatively associated with depressive symptom severity.”
    Quote in the paperSubstantial claim
  • Findingown data

    HF_se was significantly positively associated with depression.

    “The spectral entropy of HF (HF_se) was significantly and positively associated with depression.”
    Quote in the paperSubstantial claim
  • Findingown data

    Bluetooth features can explain an extra 18.8% of the variance in the PHQ-8 score relative to the baseline model without Bluetooth features (R2=0.338, RMSE=4.547).

    “Bluetooth features can explain an extra 18.8% of the variance in the PHQ-8 score relative to the baseline model without Bluetooth features (R2=0.338, RMSE=4.547).”
    Quote in the paperSubstantial claim
  • Findingown data

    89.62% of days have 50% (12 hours) or more of the NBDC data.

    “In our data set, 89.62% of days have 50% (12 hours) or more of the NBDC data.”
    Quote in the paperSubstantial claim
  • May combine two claims. 20
  • Classified as probably not a substantial claim. 35

  • May combine two claims.

    Findingown data

    LF_sum, MF_sum, and HF_sum were all significantly negatively associated with PHQ-8 score.

    “Therefore, the spectrum power of three frequency intervals (LF_sum, MF_sum, and HF_sum) were all significantly and negatively associated with the PHQ-8 score.”
    Quote in the paperSubstantial claim

  • May combine two claims.

    Findingown data

    Model B and model C fitted the data significantly better than model A.

    “Model B (with second-order statistical Bluetooth features) and model C (with all Bluetooth features) fitted data significantly better than model A (without Bluetooth features)”
    Quote in the paperSubstantial claim

  • May combine two claims.

    Findingown data

    MSE at scales 1, 2, and 3 were significantly positively associated with PHQ-8 score.

    “MSE at scale 1, scale 2, and scale 3 (MSE_1, MSE_2, and MSE_3) were significantly and positively associated with the PHQ-8 score”
    Quote in the paperSubstantial claim

  • May combine two claims.

    Findingown data

    Along with depressive symptom worsening, one or more of the following changes were found in the preceding 2 weeks of the NBDC data: the amount decreased, the variance decreased, the periodicity (especially the circadian rhythm) decreased, and the NBDC sequence became more irregular.

    “Generally speaking, along with depressive symptom worsening, one or more of the following changes were found in the preceding 2 weeks of the NBDC data: (1) the amount decreased, (2) the variance decreased, (3) the periodicity (especially the circadian rhythm) decreased, and (4) the NBDC sequence became more irregular.”
    Quote in the paperSubstantial claim

  • May combine two claims.

    Findingown data

    Compared with commonly used machine learning models, the proposed hierarchical Bayesian linear regression model achieved the best prediction metrics (R2=0.526) and a root mean squared error (RMSE) of 3.891.

    “Compared with commonly used machine learning models, the proposed hierarchical Bayesian linear regression model achieved the best prediction metrics (R2=0.526) and a root mean squared error (RMSE) of 3.891.”
    Quote in the paperSubstantial claim

  • May combine two claims.

    Findingown data

    Our study was performed on a larger (N=316) multicenter data set with a longer follow-up (median 4 months) than previous Bluetooth-related studies.

    “Compared with previous Bluetooth-related studies [15-18], our study was performed on a larger (N=316) multicenter data set with a longer follow-up (median 4 months).”
    Quote in the paperNot a substantial claim0 of 4 sources checked
    • cites [15] source

      Not checked in the free run.

    • cites [16] source

      Not checked in the free run.

    • cites [17] source

      Not checked in the free run.

    • cites [18] source

      Not checked in the free run.

  • May combine two claims.

    Findingown data

    The hierarchical Bayesian linear regression model with all Bluetooth features achieved the best result (R2=0.526, RMSE=3.891), beating LASSO and XGBoost.

    “The hierarchical Bayesian linear regression model with all Bluetooth features achieved the best result (R2=0.526, RMSE=3.891), beating the LASSO and XGBoost regression models.”
    Quote in the paperSubstantial claim

  • May combine two claims.

    Findingown data

    The hierarchical Bayesian linear model with all Bluetooth features had the best performance in LOO (R2=0.387, RMSE=4.426), close to XGBoost (R2=0.346, RMSE=4.523).

    “The hierarchical Bayesian linear model with all Bluetooth features had the best performance (R2=0.387, RMSE=4.426), but the result was close to that of the XGBoost regression model (R2=0.346, RMSE=4.523).”
    Quote in the paperSubstantial claim

  • Classified as probably not a substantial claim.

    Premisecitation

    Moturu et al found that individuals with lower sociability (estimated by the NBDC) tend to report lower mood more often.

    “Moturu et al found that individuals with lower sociability (estimated by the NBDC) tend to report lower mood more often [16].”
    Quote in the paperSubstantial claim0 of 1 sources checked
    • cites [16] source

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.

    Premisecitation

    The unemployment rate in depression is high because depressive mood and medical comorbidity can make people unable to work.

    “As the depressive mood and medical comorbidity can make people unable to work, the unemployment rate in depression is high [2].”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [2] source

      Not checked in the free run.

  • Classified as probably not a substantial claim.

    Premisecitation

    Individuals reporting fewer social network connections or less social support tend to have higher depressive symptomatology.

    “For example, individuals reporting fewer social network connections or less social support tend to have higher depressive symptomatology [1].”
    Quote in the paperSubstantial claim0 of 1 sources checked
    • cites [1] source

      Not checked in the free run.

  • Classified as probably not a substantial claim.

    Premisecitation

    Loneliness is a specific risk factor for depression.

    “Loneliness is a specific risk factor for depression, and a significant proportion of suicides have a history of social isolation [1,4].”
    Quote in the paperSubstantial claim0 of 2 sources checked
    • cites [1] source

      Not checked in the free run.

    • cites [4] source

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Premisecitation

    A significant proportion of suicides have a history of social isolation.

    “Loneliness is a specific risk factor for depression, and a significant proportion of suicides have a history of social isolation [1,4].”
    Quote in the paperNot a substantial claim0 of 2 sources checked
    • cites [1] source

      Not checked in the free run.

    • cites [4] source

      Not checked in the free run.

  • May combine two claims.

    Premisecitation

    Studies on depression and behaviors/statuses relied on participant self-report, which is susceptible to recall bias and typically does not capture dynamic information.

    “Although these findings have been replicated in different populations, these studies relied on participant self-report, which is susceptible to recall bias and typically does not capture dynamic information [5].”
    Quote in the paperSubstantial claim0 of 1 sources checked
    • cites [5] source

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.

    Premisecitation

    Boonstra et al illustrated the feasibility of collecting nearby Bluetooth device information for the depression recognition task, but they did not provide further findings.

    “Boonstra et al illustrated the feasibility of collecting nearby Bluetooth device information for the depression recognition task, but they did not provide further findings [5].”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [5] source

      Not checked in the free run.

  • Classified as probably not a substantial claim.

    Premisecitation

    Wang et al found a negative association (r=−0.362, P=.03) between the NBDC and self-reported depressive symptoms on the StudentLife data set, which contained mobile phone data from 48 students across a 10-week term at Dartmouth College.

    “Wang et al found a negative association (r=−0.362, P=.03) between the NBDC and self-reported depressive symptoms on the StudentLife data set, which contained mobile phone data from 48 students across a 10-week term at Dartmouth College [15].”
    Quote in the paperSubstantial claim0 of 1 sources checked
    • cites [15] source

      Not checked in the free run.

  • Classified as probably not a substantial claim.

    Premisecitation

    Reduced mobility and physical activity are associated with depressive symptoms.

    “Reduced mobility and physical activity are associated with depressive symptoms [3].”
    Quote in the paperSubstantial claim0 of 1 sources checked
    • cites [3] source

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Premisecitation

    MSE analysis has been used to provide insights into the complexity and periodicity of signals over a range of timescales since the method was proposed by Costa et at [31].

    “MSE analysis has been used to provide insights into the complexity and periodicity of signals over a range of timescales since the method was proposed by Costa et at [31].”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [31] source

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Premisecitation

    Compared with other entropy techniques (eg, sample entropy and approximate entropy), the advantage of MSE analysis is that the assessments of complexity at shorter and longer timescales can be analyzed separately.

    “Compared with other entropy techniques (eg, sample entropy and approximate entropy), the advantage of MSE analysis is that the assessments of complexity at shorter and longer timescales can be analyzed separately [36].”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [36] source

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.

    Premisecitation

    Bogomolov et al established machine learning models to recognize happiness and stress with features of Bluetooth records, calls, and text messages, which obtained accuracy rates of 80.81% and 72.28%, respectively.

    “Bogomolov et al established machine learning models to recognize happiness and stress with features of Bluetooth records, calls, and text messages, which obtained accuracy rates of 80.81% and 72.28%, respectively [17,18].”
    Quote in the paperNot a substantial claim0 of 2 sources checked
    • cites [17] source

      Not checked in the free run.

    • cites [18] source

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S2 (checkable).

    Interpretationreasoning

    The associations between the NBDC data and depression are yet to be fully explored.

    “Therefore, the associations between the NBDC data and depression are yet to be fully explored.”
    Quote in the paperNot a substantial claim

  • Classified as probably not a substantial claim. May combine two claims.

    Interpretationreasoning

    The power in MF represents the circadian rhythm; the power in LF represents the long-term (>1 day) rhythm; the power in HF represents the short-term (<1 day) rhythm.

    “The power in MF represents the circadian rhythm. Similarly, the power in LF represents the long-term (>1 day) rhythm, while the power in HF represents the short-term (<1 day) rhythm.”
    Quote in the paperSubstantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Premisecitation

    Studies have shown that whether feeling comfortable in the presence of strangers is related to the intensity of social connections.

    “Studies have shown that whether feeling comfortable in the presence of strangers is related to the intensity of social connections [26].”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [26] source

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S2 (checkable).

    Interpretationreasoning

    These findings may have utility for the mental health monitoring practice in real-world settings.

    “These findings may have utility for the mental health monitoring practice in real-world settings.”
    Quote in the paperNot a substantial claim

  • Classified as probably not a substantial claim. May combine two claims.

    Premisecitation

    The linear mixed-effect model contains both fixed and random effects, allowing for both within-participant and between-participants variations over repeated measurements.

    “The linear mixed-effect model contains both fixed and random effects, allowing for both within-participant and between-participants variations over repeated measurements [39].”
    Quote in the paperSubstantial claim0 of 1 sources checked
    • cites [39] Laird, NM, 1982, Biometrics source

      Not checked in the free run.

  • May combine two claims.

    Interpretationreasoning

    The NBDC data contain information about participants' social connections and interactions with family, friends, co-workers, and strangers, and can reflect participants' time at home, mobility, social isolation, and working status, as well as the number of other Bluetooth devices in the house and working environment.

    “Therefore, the NBDC data contain information about participants’ social connections and interactions with family, friends, co-workers, and strangers, and the data can also reflect participants’ time at home, mobility, social isolation, and working status, as well as the number of other Bluetooth devices in the house and working environment.”
    Quote in the paperSubstantial claim

  • Classified as probably not a substantial claim.

    Premisecitation

    The likelihood ratio test is a statistical test of goodness of fit between two nested models.

    “The likelihood ratio test is a statistical test of goodness of fit between two nested models [41].”
    Quote in the paperSubstantial claim0 of 1 sources checked
    • cites [41] source

      Not checked in the free run.

  • Classified as probably not a substantial claim.

    Premisecitation

    To test whether the model can predict variability of depression severity, the difference of one participant's PHQ-8 scores should be more than or equal to 5 (clinically meaningful change).

    “To test whether the model can predict variability of depression severity, the difference of one participant’s PHQ-8 scores should be more than or equal to 5 (clinically meaningful change) [42].”
    Quote in the paperSubstantial claim0 of 1 sources checked
    • cites [42] source

      Not checked in the free run.

  • May combine two claims.

    Premisereasoning

    Previous studies [15-18] have been performed on relatively small (approximately 100 participants) homogeneous (eg, university students) cohorts of participants over relatively short periods (8-10 weeks), which may limit their generalizability.

    “Previous studies [15-18] have been performed on relatively small (approximately 100 participants) homogeneous (eg, university students) cohorts of participants over relatively short periods (8-10 weeks), which may limit their generalizability.”
    Quote in the paperSubstantial claim0 of 4 sources checked
    • cites [15] source

      Not checked in the free run.

    • cites [16] source

      Not checked in the free run.

    • cites [17] source

      Not checked in the free run.

    • cites [18] source

      Not checked in the free run.

  • Classified as probably not a substantial claim.

    Premisecitation

    If the model with more parameters fits the data significantly better, it indicates that additional parameters provide more information and improve the model's fitness.

    “If the model with more parameters fits the data significantly better, it indicates that additional parameters provide more information and improve the model’s fitness [41].”
    Quote in the paperSubstantial claim0 of 1 sources checked
    • cites [41] source

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S4 (based).

    Premisenone given

    The second-order statistical features can only reflect the amount and variance of the NBDC data.

    “The second-order statistical features can only reflect the amount (max, min, and mean) and variance (standard deviation) of the NBDC data.”
    Quote in the paperNot a substantial claim

  • Classified as probably not a substantial claim. May combine two claims.

    Premisenone given

    The above three studies were all performed on the "Friends and Family" data set, including 8 weeks of mobile phone data from 117 participants living in a major US university's married graduate student residency.

    “The above three studies were all performed on the “Friends and Family” data set, including 8 weeks of mobile phone data from 117 participants living in a major US university’s married graduate student residency.”
    Quote in the paperSubstantial claim0 of 3 sources checked
    • cites [16] source

      Not checked in the free run.

    • cites [17] source

      Not checked in the free run.

    • cites [18] source

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Premisecitation

    FD analysis has been widely used in the signal processing field, especially for signals with periodic characteristics.

    “FD analysis has been widely used in the signal processing field, especially for signals with periodic characteristics [32].”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [32] Broughton, S, 2008, Discrete Fourier Analysis and Wavelets: Applications to Signal and Image Processing source

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Premisecitation

    Saeb et al [29] and Farhan et al [30] used 50% as each day's completeness threshold for passive data.

    “Saeb et al [29] and Farhan et al [30] used 50% as each day’s completeness threshold for passive data.”
    Quote in the paperNot a substantial claim0 of 2 sources checked
    • cites [29] source

      Not checked in the free run.

    • cites [30] source

      Not checked in the free run.

  • Classified as probably not a substantial claim.

    Premisecitation

    Spectrum power around 1 cycle per day reflects the participant's circadian rhythm (approximately 24-hour rhythm).

    “According to the spectrum’s definition, spectrum power around 1 cycle per day reflects the participant’s circadian rhythm (approximately 24-hour rhythm) [19].”
    Quote in the paperSubstantial claim0 of 1 sources checked
    • cites [19] source

      Not checked in the free run.

  • Classified as probably not a substantial claim.

    Premisereasoning

    As we used the temporal data, "future data" should not predict "past data."

    “As we used the temporal data, “future data” should not predict “past data.””
    Quote in the paperSubstantial claim

  • Classified as probably not a substantial claim.

    Interpretationreasoning

    Only the data observed before test data can be included in the training set.

    “Therefore, only the data observed before test data can be included in the training set.”
    Quote in the paperSubstantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Premisecitation

    The hierarchical Bayesian approach is an intermediate method compared to the completely pooled model and individualized model, capturing the whole population's characteristics while allowing individual differences.

    “The hierarchical Bayesian approach is an intermediate method compared to the completely pooled model and individualized model, capturing the whole population’s characteristics while allowing individual differences [43].”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [43] Gelman, A, 2013, Bayesian Data Analysis source

      Not checked in the free run.

  • May combine two claims.

    Interpretationreasoning

    Reduced periodicity and increased irregularity of the NBDC sequence can reflect misalignment of circadian rhythm and more irregular life rhythms.

    “This can be reflected in reduced periodicity and increased irregularity of the NBDC sequence.”
    Quote in the paperSubstantial claim
    • Rests on an assumption: NBDC data are related to individuals' movement and location information.
    • Rests on an assumption: The periodicity and irregularity of NBDC reflect circadian rhythm and life rhythms.

  • Classified as probably not a substantial claim.

    Interpretationreasoning

    The hierarchical Bayesian model is an appropriate prediction model for predicting depression with longitudinal data, as both participant-level and population-level characteristics are considered.

    “The hierarchical Bayesian model is an appropriate prediction model for predicting depression with longitudinal data, as both participant-level and population-level characteristics are considered in the model.”
    Quote in the paperSubstantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Interpretationreasoning

    The decreased mobility and engagement in activities may be possible reasons why participants with higher PHQ-8 scores have lower variance-related features (Max_Std, Min_Std, Mean_Std, and Std_Std).

    “The decreased mobility and engagement in activities may be possible reasons why participants with higher PHQ-8 scores have lower variance-related features (Max_Std, Min_Std, Mean_Std, and Std_Std).”
    Quote in the paperNot a substantial claim
    • Rests on an assumption: NBDC data are related to individuals' movement and location information.
    • Rests on an assumption: The variance of NBDC reflects mobility and engagement in activities.

  • May combine two claims.

    Interpretationreasoning

    It was impossible to distinguish between mobile phones and other Bluetooth devices, and between strangers' and acquaintances' devices.

    “This made it impossible to distinguish between mobile phones and other Bluetooth devices (such as headphones, printers, and laptops), and between strangers’ and acquaintances’ devices.”
    Quote in the paperSubstantial claim

  • Classified as probably not a substantial claim.

    Study design and conductreasoning

    MAC addresses and types of Bluetooth devices were not recorded.

    “the MAC addresses and types of Bluetooth devices were not recorded for private issues.”
    Quote in the paperSubstantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Study design and conductreasoning

    It is difficult to explain the specific reasons for changes in the NBDC.

    “The disadvantage is that it is difficult to explain the specific reasons for changes in the NBDC, that is, we cannot know whether the changes in the NBDC are caused by social interactions, working status, traveling, or isolation.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Interpretationreasoning

    The increased time at home, inability to work or study, and diminished social interactions are reflected in the reduced amount of the NBDC sequence.

    “The increased time at home, inability to work or study, and diminished social interactions are reflected in the reduced amount of the NBDC sequence.”
    Quote in the paperSubstantial claim
    • Rests on an assumption: NBDC data are related to individuals' movement and location information.
    • Rests on an assumption: The amount of NBDC reflects daily social activities (social interactions and traveling).

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Study design and conductnone given

    The frequency interval boundaries for FD features were manually specified by experience.

    “the division of the frequency intervals of the spectrum of the NBDC sequence in this paper was manually specified by our experience.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Interpretationreasoning

    The LOO cross-validation's lower performance may be because only the first two PHQ-8 intervals of one participant were used for training, causing underfitting at participant level.

    “One potential reason is that only the first two PHQ-8 intervals of one participant were used for training in the LOO cross-validation, which may have caused the model to underfit the patterns at the participant level.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S2 (checkable).

    Interpretationreasoning

    These findings may support the mental health monitoring practice in real-world settings.

    “These findings may support the mental health monitoring practice in real-world settings.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Study design and conductreasoning

    Lower data resolution (hourly NBDC) may cause the loss of some dynamic information.

    “Although hourly NBDC data can also reflect individuals’ behaviors and statuses, our lower data resolution may cause the loss of some dynamic information.”
    Quote in the paperNot a substantial claim
49 of 49

  • The paper relies on this without support.

    The NBDC data collected before February 2020 are unaffected by the COVID-19 pandemic.

    “To exclude the impact of the COVID-19 pandemic, we performed a preliminary analysis with the data before February 2020.”

  • The paper relies on this without support.

    NBDC data are related to individuals' movement and location information.

    “As the NBDC data are related to individuals’ movement and location information, we will combine the NBDC data with GPS and acceleration data for future analysis to understand the context of the Bluetooth data.”

  • The paper relies on this without support.

    The amount of NBDC reflects daily social activities (social interactions and traveling).

    “which indicated that participants with a lower PHQ-8 score tended to have more daily social activities (such as social interactions and traveling) in the past 2 weeks.”

  • The paper relies on this without support.

    The variance of NBDC reflects mobility and engagement in activities.

    “The decreased mobility and engagement in activities may be possible reasons why participants with higher PHQ-8 scores have lower variance-related features (Max_Std, Min_Std, Mean_Std, and Std_Std).”

  • The paper relies on this without support.

    The periodicity and irregularity of NBDC reflect circadian rhythm and life rhythms.

    “This can be reflected in reduced periodicity and increased irregularity of the NBDC sequence.”
5 of 5

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Statistics recomputed

Every reported test result, recomputed from its test statistic and degrees of freedom. A result shows as not adding up only once an independent check has confirmed it.

  • Consistentz = -4.431reported p < .001 · recomputed p < .001

    “(z=−4.431, p < .001”

  • Consistentz = -4.766reported p < .001 · recomputed p < .001

    “(z=−4.766, p < .001”

2 of 2

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

Each contradiction between two passages listed here was confirmed by an independent check.

  • A reported adjusted P value is below its unadjusted P value

    Minor

    A z score of 1.985 has a two-sided unadjusted P value of about .047. The table reports .04 as its Benjamini-Hochberg-adjusted P value, but that adjustment cannot make the P value smaller than the unadjusted value.

1 of 1

The citation lists haven’t been fetched yet

References 58 · Cited by 68

Research works printed but not linked: 1

  1. Pedregosa, F, 2011, The Journal of Machine Learning Research, 12, 2825

Authors
Zhang, Y., Folarin, A. A., Sun, S., Cummins, N., Ranjan, Y., Rashid, Z., Conde, P., Stewart, C., Laiou, P., Matcham, F., Oetzmann, C., Lamers, F., Siddi, S., Simblett, S., Rintala, A., Mohr, D. C., Myin-Germeys, I., Wykes, T., Haro, J. M., Penninx, B. W. J. H., Narayan, V. A., Annas, P., Hotopf, M., Dobson, R. J. B., & RADAR-CNS Consortium
Affiliations
  • King's College London (GB)
  • University College London Hospitals NHS Foundation Trust (GB)
  • Amsterdam Neuroscience (NL)
  • Centro de Investigación Biomédica en Red de Salud Mental (ES)
  • LAB University of Applied Sciences (FI)
  • Northwestern University (US)
  • Lundbeck (Denmark) (DK)
Corresponding author
Dobson, Richard J B
ORCID
Venue
JMIR mHealth and uHealth
Publisher
JMIR Publications Inc.
Published
2021-07-30
Volume
9
Issue
7
Pages
e29840
ISSN
2291-5222 (ISSN-L)
DOI
10.2196/29840
PMC
PMC8367113
OpenAlex
W3172601496
Cited by
68
References
58
Citations by year
2026: 11 · 2025: 15 · 2024: 17 · 2023: 10 · 2022: 12 · 2021: 3
FWCI
10.14
Type
journal article
Language
en
Open access
Licence
cc-by
Locations
  • JMIR mhealth and uhealth (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • Amsterdam UMC (VU Amsterdam) - Institutional Repository (publishedVersion, other-oa)
  • arXiv (Cornell University) (submittedVersion)
  • Lirias (KU Leuven) (submittedVersion, other-oa)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
  • UCL Discovery (University College London) (submittedVersion)
  • Figshare (submittedVersion, cc-by)
  • Research Portal (King's College London) (submittedVersion, other-oa)
  • Data Archiving and Networked Services (DANS) (submittedVersion, cc-by)
  • arXiv (Cornell University)
Funders
  • South London and Maudsley NHS Foundation Trust
  • Wellcome Trust
  • King's College Hospital NHS Foundation Trust
  • Scottish Government
  • European Federation of Pharmaceutical Industries and Associations (116074)
  • UK Research and Innovation
  • Alzheimer's Society
  • National Institute for Health and Care Research (NF-SI-0514-10028, NIHR-INF-0684)
  • British Heart Foundation
  • Department of Health and Social Care
  • King's College London
  • University College London
  • European Commission (115902, 116074, HORIZON2020)
  • European Society of Cardiology
  • Public Health Agency
  • ZonMw (73305095003)
  • Innovative Medicines Initiative (116074, 115902)
  • Institut Català de la Salut
  • GIESKES-STRIJBIS FONDS
  • Chief Scientist Office, Scottish Government Health and Social Care Directorate
  • NIHR Maudsley Biomedical Research Centre
  • Medical Research Council (MC_PC_17214)
  • Engineering and Physical Sciences Research Council
  • Economic and Social Research Council
  • Health and Social Care Research and Development Division
  • National Institute for Health Research Applied Research Collaboration South London
  • National Institute of Mental Health (R01MH111610, P50MH119029)
  • Health Data Research UK
Topics
  • Social Sciences › Psychology › Experimental and Cognitive Psychology › Mental Health Research Topics
  • Social Sciences › Psychology › Applied Psychology › Digital Mental Health Interventions
  • Social Sciences › Transportation › Human Mobility and Location-Based Analysis
Keywords
depression severity, smartphone sensors, PHQ-8, depression prediction, circadian rhythm, mental health monitoring
MeSH terms
Bayes Theorem, Depression, Humans, Longitudinal Studies, Social Isolation, Cell Phone

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Claims read by deepseek-v4.1-flash under definition version 3 (extract-v3) on 2026-10-10.

Classified by jev-1.13-20260917 (gold-guideline-v0.2) on 2026-10-10.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review