The relationship between mobile phone location sensor data and depressive symptom severity
Open accessAbstract
Background: Smartphones offer the hope that depression can be detected using passively collected data from the phone sensors. The aim of this study was to replicate and extend previous work using geographic location (GPS) sensors to identify depressive symptom severity. Methods: We used a dataset collected from 48 college students over a 10-week period, which included GPS phone sensor data and the Patient Health Questionnaire 9-item (PHQ-9) to evaluate depressive symptom severity at baseline and end-of-study. GPS features were calculated over the entire study, for weekdays and weekends, and in 2-week blocks. Results: The results of this study replicated our previous findings that a number of GPS features, including location variance, entropy, and circadian movement, were significantly correlated with PHQ-9 scores ( r ’s ranging from −0.43 to −0.46, p -values < .05). We also found that these relationships were stronger when GPS features were calculated from weekend, compared to weekday, data. Although the correlation between baseline PHQ-9 scores with 2-week GPS features diminished as we moved further from baseline, correlations with the end-of-study scores remained significant regardless of the time point used to calculate the features. Discussion: Our findings were consistent with past research demonstrating that GPS features may be an important and reliable predictor of depressive symptom severity. The varying strength of these relationships on weekends and weekdays suggests the role of weekend/weekday as a moderating variable. The finding that GPS features predict depressive symptom severity up to 10 weeks prior to assessment suggests that GPS features may have the potential as early warning signals of depression.
AI snapshot
Written from the paper’s full text.
TL;DR
This study replicated and extended prior work showing that passively collected GPS location features are correlated with depressive symptom severity in a 10-week dataset of 48 college students. Weekend-derived GPS features were more strongly related to PHQ-9 scores than weekday features, and some features predicted follow-up depressive symptoms up to 10 weeks earlier.
Key findings
- GPS features including location variance, entropy, and circadian movement were significantly correlated with PHQ-9 scores, with abstract-reported \(r\)’s ranging from −0.43 to −0.46, \(p < .05\).
- In 10-week analyses, follow-up PHQ-9 correlations included location variance \(r = -0.43\), circadian movement \(r = -0.48\), entropy \(r = -0.46\), number of clusters \(r = -0.44\), and home stay \(r = 0.43\).
- Weekend features were generally stronger than weekday features; for example, weekend follow-up correlations included entropy \(r = -0.55\), normalized entropy \(r = -0.54\), circadian movement \(r = -0.51\), and home stay \(r = 0.50\).
- Correlations between baseline PHQ-9 and 2-week GPS features diminished over time, while correlations with end-of-study PHQ-9 remained significant regardless of the time point used to calculate features.
Methods
- Secondary analysis of the StudentLife dataset: 48 college students (38 male, 10 female) followed for 10 weeks, with continuous Android GPS data collected about once every 5 minutes and PHQ-9 administered at baseline and end-of-study.
- Eleven GPS features were calculated, including eight replicated features plus speed mean, speed variance, and raw entropy; features were computed over the entire 10 weeks, separately for weekdays and weekends, and in overlapping 2-week blocks.
- Relationships with PHQ-9 scores were assessed using linear correlations, with 1,000 bootstrap subsamples to estimate correlation coefficients and 95% confidence intervals; significance was set at \(p < 0.05\).
Limitations
- The paper states that many correlation analyses introduced possible alpha slippage, especially for exploratory analyses, and that the study was underpowered to test weekday/weekend differences or differences over time; these findings are therefore preliminary until replicated.
- The paper states that weekday/weekend was only an operationalization for workday/non-workday and may not fit all people, and that the sample size was relatively small with few depression assessment points.
- Evident from the text: the sample was college students in a computer science class, predominantly male, with no inclusion/exclusion criteria based on mental health, and only seven participants had clinically meaningful PHQ-9 change, limiting generalizability and change-score analyses.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
0 of 19 cited sources checked · 0 supported · 0 flagged
- Findingown data
The study replicated previous findings of a relationship between depressive symptom severity and GPS location features (location variance, entropy, and circadian movement) in the StudentLife dataset.
“In this study, we were able to replicate our previous findings of the relationship between severity of depressive symptoms and GPS location features, including location variance, entropy, and circadian movement (Saeb et al., 2015a; Saeb et al., 2015b), in the StudentLife dataset (Wang et al., 2014).”
Quote in the paperSubstantial claim0 of 3 sources checked- cites Saeb et al., 2015a
Not checked in the free run.
- cites Saeb et al., 2015b
Not checked in the free run.
- cites Wang et al., 2014
Not checked in the free run.
- Findingown data
Larger correlations were observed on weekends between many GPS features and depression than on weekdays.
“Indeed, we did see larger correlations on weekends between many of the GPS features and depression, than on weekdays.”
Quote in the paperSubstantial claim - Findingown data
The correlations between 2-week GPS features and depression scores changed over time.
“Overall, while these results were consistent with correlation results in Table 3, they indicated that these correlations changed over time.”
Quote in the paperSubstantial claim - Findingown data
Correlations between baseline PHQ-9 scores and weekend location features were significant in the first weeks immediately following depression assessment, but became non-significant and approached zero at the end of the 10 weeks.
“Furthermore, correlations between baseline PHQ-9 scores and weekend location features were significant in the first weeks immediately following depression assessment, but quickly became non-significant and approached zero at the end of the 10 weeks (Fig. 3C).”
Quote in the paperSubstantial claim - Findingown data
For three out of six weekday features (homestay, entropy, and normalized entropy), correlations with follow-up PHQ-9 scores remained significant regardless of extraction time.
“This was also true for three out of the six features extracted on weekdays (Fig. 3B), including homestay, entropy, and normalized entropy.”
Quote in the paperNot a substantial claim
- Findingown data
Location variance, entropy, and circadian movement were significantly correlated with PHQ-9 scores with r's ranging from −0.43 to −0.46 (p-values < .05).
“The results of this study replicated our previous findings that a number of GPS features, including location variance, entropy, and circadian movement, were significantly correlated with PHQ-9 scores (r’s ranging from −0.43 to −0.46, p-values < .05).”
Quote in the paperSubstantial claim - Findingown data
The magnitude of the relationship between weekend GPS features and PHQ-9 scores was larger than the magnitude of the relationship between 10-week GPS features and PHQ-9 scores.
“The magnitude of the relationship between weekend features and PHQ-9 scores was larger than the magnitude of the relationship between 10-week features and PHQ-9 scores.”
Quote in the paperNot a substantial claim - Findingown data
Correlations between weekend location features and follow-up PHQ-9 scores generally remained significant regardless of the time point at which features were extracted.
“In contrast, correlations between weekend location features and the follow-up PHQ-9 scores generally remained significant regardless of the time point at which features were extracted (Fig. 3D).”
Quote in the paperNot a substantial claim - Findingown data
Correlations of weekend GPS location features with depression scores were generally stronger than correlations of weekday features.
“Consistent with the results in Table 3, correlations of weekend features (Figs. 3C–3D) were generally stronger than weekday features (Figs. 3A–3B).”
Quote in the paperNot a substantial claim - Findingown data
Relationships between GPS features and PHQ-9 scores were stronger when GPS features were calculated from weekend data compared to weekday data.
“We also found that these relationships were stronger when GPS features were calculated from weekend, compared to weekday, data.”
Quote in the paperSubstantial claim - Findingown data
The relationship between depressive symptom severity and subsequent location features was significant for the first weeks, but then rapidly declined over time.
“The relationship between depressive symptom severity and subsequent location features was significant for the first weeks, but then rapidly declined over time.”
Quote in the paperSubstantial claim - Findingown data
Weekday measurement became stronger the closer their extraction occurred to the assessment.
“Nevertheless, weekday measurement did become stronger the closer their extraction occurred to the assessment.”
Quote in the paperSubstantial claim - Findingown data
Some location features, such as location variance and circadian movement, which were strongly predictive of depression 8-10 weeks prior when measured on weekends, showed no significant prediction when measured on weekdays.
“It is also interesting to note that some location features, such as location variance and circadian movement, which were strongly predictive of depression 8–10 weeks prior when measured on weekends, showed no significant prediction when measured on weekdays.”
Quote in the paperSubstantial claim - Findingown data
The decline in the relationship between depressive symptom severity and subsequent location features was most notable when using weekend location features, which were generally stronger predictors.
“This was most notable when using the weekend location features, which were generally stronger predictors.”
Quote in the paperNot a substantial claim - Findingown data
Correlations between weekend location features immediately prior to the assessment of depression symptom severity were very similar to the correlation 8-10 weeks prior.
“In contrast, the correlations between weekend location features immediately prior to the assessment of depression symptom severity were very similar to the correlation 8–10 weeks prior.”
Quote in the paperSubstantial claim - Interpretationown data
The finding that GPS features predict depressive symptom severity up to 10 weeks prior to assessment suggests that GPS features may have potential as early warning signals of depression.
“The finding that GPS features predict depressive symptom severity up to 10 weeks prior to assessment suggests that GPS features may have the potential as early warning signals of depression.”
Quote in the paperSubstantial claim - Interpretationreasoning
There is no single set of sensors that is reliably and consistently sensitive to depression.
“Thus, there is no single set of sensors that is reliably and consistently sensitive to depression.”
Quote in the paperSubstantial claim - Interpretationreasoning
Detection of depression will likely require the development of features that translate mobile phone sensor data into behavioral targets that may be relevant to depression.
“Detection of depression will likely require the development of features that translate mobile phone sensor data into behavioral targets that may be relevant to depression.”
Quote in the paperNot a substantial claim - Premisecitation
A growing body of research has demonstrated the potential of mobile phone sensors to detect a variety of behaviors related to depression, such as activity, sleep, and social interactions.
“A growing body of research has demonstrated the potential of mobile phone sensors to detect a variety of behaviors related to depression, such as activity, sleep, and social interactions (Abdullah et al., 2014; Grunerbl et al., 2015; Kwapisz, Weiss & Moore, 2011; Min et al., 2013; Shoaib et al., 2014; Thomée, Härenstam & Hagberg, 2011; Wiese et al., 2015).”
Quote in the paperSubstantial claim0 of 3 sources checked - Study design and conductown data
The study was not adequately powered to test whether the differences between weekend and 10-week correlations were significant, given the small sample size.
“However, given the small sample size, we were not adequately powered to test if these differences were significant.”
Quote in the paperNot a substantial claim - Interpretationown data
The varying strength of the relationships on weekends and weekdays suggests that weekend/weekday is a moderating variable.
“The varying strength of these relationships on weekends and weekdays suggests the role of weekend/weekday as a moderating variable.”
Quote in the paperSubstantial claim- Rests on an assumption: Movement on workdays is determined to some degree by social roles and expectations, while movement on non-workdays is less determined by external demands and more by the individual’s motivational state.
- Premisecitation
Studies in behavioral sensing using smartphones are usually not cross-validated.
“This is particularly crucial in the field of behavioral sensing using smartphones since studies in this field frequently use small samples, are usually not cross-validated, and failure to replicate has already been observed (Ruwaard et al., 2016).”
Quote in the paperSubstantial claim0 of 1 sources checked- cites Ruwaard et al., 2016 source
Not checked in the free run.
- Premisecitation
Failure to replicate has already been observed in behavioral sensing using smartphones.
“This is particularly crucial in the field of behavioral sensing using smartphones since studies in this field frequently use small samples, are usually not cross-validated, and failure to replicate has already been observed (Ruwaard et al., 2016).”
Quote in the paperSubstantial claim0 of 1 sources checked- cites Ruwaard et al., 2016 source
Not checked in the free run.
- Premisecitation
Studies in behavioral sensing using smartphones frequently use small samples.
“This is particularly crucial in the field of behavioral sensing using smartphones since studies in this field frequently use small samples, are usually not cross-validated, and failure to replicate has already been observed (Ruwaard et al., 2016).”
Quote in the paperSubstantial claim0 of 1 sources checked- cites Ruwaard et al., 2016 source
Not checked in the free run.
- Premisereasoning
Detection of depression using phone sensors is more difficult than detecting behaviors that are observable and more proximal to the sensor data such as physical activity, sleep/wake patterns, and social interaction.
“Detection of depression using phone sensors, however, is a much more difficult task than detecting behaviors that are observable and more proximal to the sensor data such as physical activity, sleep/wake patterns, and social interaction.”
Quote in the paperSubstantial claim - Interpretationcitation
Features of GPS location such as the number of places a person goes, how time is spent in these locations, and the circadian rhythm of movement through geographic space are strongly related to the severity of depressive symptoms.
“Together, these findings provide strong evidence that features of GPS location such as the number of places a person goes, how time is spent in these locations, and the circadian rhythm of movement through geographic space, are strongly related to the severity of depressive symptoms.”
Quote in the paperSubstantial claim - Interpretationown data
The findings are consistent with past research demonstrating that GPS features may be an important and reliable predictor of depressive symptom severity.
“Our findings were consistent with past research demonstrating that GPS features may be an important and reliable predictor of depressive symptom severity.”
Quote in the paperSubstantial claim - Interpretationreasoning
Location features may be early warning detectors of depression.
“This suggests that location features may be early warning detectors of depression.”
Quote in the paperSubstantial claim - Interpretationown data
Our study supports the potential of smartphone sensor technology in providing biomarkers of depression in daily life.
“In conclusion, our study supports the potential of smartphone sensor technology in providing biomarkers of depression in daily life.”
Quote in the paperSubstantial claim
- May combine two claims. 12
- The quote only partly states this claim. 2
- Classified as probably not a substantial claim. 15
May combine two claims. The quote only partly states this claim.
Findingown dataCorrelations between the 10-week GPS features and baseline PHQ-9 scores were weaker than with follow-up scores, and none were statistically significant.
“Correlations between these features and baseline scores were weaker, and none of them were statistically significant.”
Quote in the paperSubstantial claimMay combine two claims.
Findingown dataAll 10-week GPS features significantly related to PHQ-9 scores were also significant when calculated from weekends, whereas only normalized entropy was significantly related as a weekday feature.
“All of those 10-week features that were significantly related to PHQ-9 scores (see Table 2) were also significant when calculated from weekends, whereas only normalized entropy was significantly related to the scores as a weekday feature.”
Quote in the paperNot a substantial claimMay combine two claims.
Findingown dataThe correlation between baseline PHQ-9 scores and 2-week GPS features diminished as the features were calculated further from baseline, while correlations with end-of-study PHQ-9 scores remained significant regardless of the time point used to calculate the features.
“Although the correlation between baseline PHQ-9 scores with 2-week GPS features diminished as we moved further from baseline, correlations with the end-of-study scores remained significant regardless of the time point used to calculate the features.”
Quote in the paperSubstantial claimThe quote only partly states this claim.
Findingown dataIn the 10-week GPS features, location variance, circadian movement, entropy, home stay, and number of clusters had absolute correlation coefficients ≥0.4 with follow-up PHQ-9 scores.
“Particularly, location variance, circadian movement, entropy, home stay, and number of clusters all had absolute correlation coefficients |r| ≥ 0.4 with the follow-up PHQ-9 scores.”
Quote in the paperSubstantial claimMay combine two claims.
Findingown dataAmong the 48 participants, PHQ-9 scores decreased from baseline to follow-up for 20 participants and increased for 16; only seven had a clinically meaningful change (absolute change ≥5).
“For 20 participants, the PHQ-9 scores decreased from baseline to follow-up, while for 16 they increased. However, only seven participants had a change which was clinically meaningful, meaning that the absolute value of the change was greater than or equal to 5.”
Quote in the paperNot a substantial claimClassified as probably not a substantial claim.
PremisecitationThe PHQ-9 is a self-report measure of depression symptom severity.
“including continuous phone GPS data and the Patient Health Questionnaire 9-item (PHQ-9) (Kroenke, Spitzer & Williams, 2001), a self-report measure of depression symptom severity.”
Quote in the paperSubstantial claim0 of 1 sources checked- cites Kroenke, Spitzer & Williams, 2001 source
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
InterpretationcitationThe 10-week GPS results were consistent with previous findings.
“Overall, these results were consistent with our previous findings (Saeb et al., 2015a).”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Saeb et al., 2015a
Not checked in the free run.
May combine two claims.
PremisecitationExploration in small datasets can lead to spurious findings, as seen in the failure to replicate a widely cited paper on phone sensor data to detect mood.
“While exploration is essential to discovery, it is frequently done in small datasets. This can lead to spurious findings, as has recently been seen in the failure to replicate a widely cited paper (Likamwa et al., 2013) on the use of phone sensor data to detect mood (Ruwaard et al., 2016).”
Quote in the paperSubstantial claim0 of 2 sources checked- cites Likamwa et al., 2013
Not checked in the free run.
- cites Ruwaard et al., 2016 source
Not checked in the free run.
May combine two claims.
Premisenone givenThe StudentLife dataset was collected completely independently of this research group and used a very different sample of college students in a small town, as opposed to the general population in a large city (Chicago) from the first study.
“This is particularly notable as the StudentLife dataset was collected completely independently of this research group, using a very different sample that consisted of college students in a small town as opposed to the general population in a large city (Chicago) from our first study.”
Quote in the paperSubstantial claim0 of 1 sources checked- cites Wang et al., 2014
Not checked in the free run.
May combine two claims.
Interpretationown dataWhile it is difficult to relate raw sensor data or their basic statistics directly to depression, features derived from sensor data are more likely to indicate the presence of depressive symptoms.
“Therefore, while it is difficult to relate raw sensor data or their basic statistics directly to depression, their features are more likely to indicate the presence of depressive symptoms.”
Quote in the paperSubstantial claimMay combine two claims.
PremisecitationA third independent group, Canzian and Musolesi, developed very similar location features and had similar findings.
“Furthermore, subsequent to our initial publication, a third independent group, Canzian and Musolesi, developed very similar location features and had similar findings (Canzian & Musolesi, 2015).”
Quote in the paperSubstantial claim0 of 1 sources checked- cites Canzian & Musolesi, 2015
Not checked in the free run.
Classified as probably not a substantial claim.
PremisecitationA recent meta-study showed that only one-third to one-half of experimental results reported in psychological science were replicated in later studies.
“In fact, a recent meta-study showed that only one-third to one-half of experimental results reported in psychological science were replicated in later studies (Open Science, 2015).”
Quote in the paperSubstantial claim0 of 1 sources checked- cites Open Science, 2015 source
Not checked in the free run.
Classified as probably not a substantial claim. May combine two claims.
Study design and conductcitationThe analysis used 1,000 bootstrap subsamples to estimate correlation coefficients and 95% CIs, and only considered coefficients significant if the 95% CI of their associated p-values fell below 0.05.
“In order to reduce the possibility that results were generated by chance, we created 1,000 bootstrap subsamples (Efron & Tibshirani, 1993) to estimate these correlation coefficients and their 95% confidence intervals (CIs). We only considered those coefficients significant for which the 95% CI of their associated p-values fell below 0.05.”
Quote in the paperSubstantial claim0 of 1 sources checked- cites Efron & Tibshirani, 1993 source
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Study design and conductreasoningThe distinction between weekdays and weekend is not necessarily a defining feature for every person.
“Second, the distinction between weekdays and weekend is not necessarily a defining feature for every person.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S2 (checkable).
InterpretationreasoningThe development of effective behavioral sensing prediction models for mental health will likely require a much larger sample size.
“Therefore, the development of effective behavioral sensing prediction models for mental health will likely require a much larger sample size.”
Quote in the paperNot a substantial claimClassified as probably not a substantial claim.
InterpretationreasoningThe relationship between features over time may improve the prediction of depression.
“Thus, the relationship between features over time may improve the prediction.”
Quote in the paperSubstantial claimProbably not a substantial claim: may not pass S2 (checkable).
Interpretationnone givenEven with strong biomarkers, it remains a challenge to develop a system that can passively detect depression with low false positive and false negative rates.
“However, even with strong biomarkers, it remains a challenge to develop a system that can passively detect depression with low false positive and false negative rates.”
Quote in the paperNot a substantial claimClassified as probably not a substantial claim.
Study design and conductnone givenThis study had a relatively small sample size.
“Finally, this study had a relatively small sample size.”
Quote in the paperSubstantial claimProbably not a substantial claim: may not pass S2 (checkable), S3 (load-bearing), S4 (based).
Study design and conductreasoningGiven the consistency across studies and populations, the number of analyses for the replication analyses is not a significant limitation for this study.
“In contrast, given the consistency across studies and populations, the number of analyses for the replication analyses is not a significant limitation for this study.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S2 (checkable), S3 (load-bearing).
Interpretationnone givenBehavioral sensing studies-including ours-require longer periods of time to capture the slow changes in the disease state and in the behavioral features.
“Furthermore, behavioral sensing studies—including ours—require longer periods of time to capture the slow changes in the disease state and in the behavioral features.”
Quote in the paperNot a substantial claim- Rests on an assumption: Most studies of behavioral sensing in depression only have 2 or 3 assessment points for each individual, which makes the dataset underpowered for investigating the longitudinal relationship between sensor data and depression.
Probably not a substantial claim: may not pass S2 (checkable).
Interpretationown dataThe finding of the importance of the workday/non-workday distinction highlights the likely importance of variables that moderate the relationship between sensor data and mental health.
“Our finding of the importance of workday/non-workday distinction highlights the likely importance of the variables that moderate the relationship between sensor data and mental health.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
Study design and conductreasoningThe findings on weekend and weekday features and temporal relationships contain a large number of correlation analyses, which introduce the possibility of alpha slippage, particularly for the exploratory analyses.
“First, the findings on weekend and weekday features and temporal relationships contain a large number of correlation analyses which introduce the possibility of alpha slippage, particularly for the exploratory analyses.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
InterpretationreasoningDepression-related disruption in movement first manifests itself only when there are no social constraints (e.g., on non-workdays), but as the disruption in GPS features shifts to manifest itself on workdays, risk of subsequent depression becomes more immediate.
“This may suggest that depression-related disruption in movement first manifests itself only when there are no social constraints (e.g., on non-workdays), but as the disruption in GPS features shifts to manifest itself on workdays, risk of subsequent depression becomes more immediate.”
Quote in the paperNot a substantial claimMay combine two claims.
PremisereasoningThe StudentLife study extended over 10 weeks, compared to two weeks for the first study, making it a better dataset to explore temporal relationships.
“The StudentLife study extended over 10 weeks, as compared to two weeks for our first study, making it a better dataset to explore temporal relationships.”
Quote in the paperSubstantial claim0 of 1 sources checked- cites Wang et al., 2014
Not checked in the free run.
May combine two claims.
Study design and conductnone givenThe study was not sufficiently powered to detect workday/non-workday differences in the relationship between GPS and depression, nor the differences in these relationships over time.
“Furthermore, we were not sufficiently powered to detect workday/non-workday differences in the relationship between GPS and depression, nor the differences in these relationships over time.”
Quote in the paperSubstantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
PremisecitationIn a previous analysis of the StudentLife dataset, specific aspects about Dartmouth social behavior were used to explore typical 'party' days which did not line up exactly with weekend/weekdays.
“In a previous analysis of the StudentLife dataset, for example, specific aspects about Dartmouth social behavior were used to explore typical “party” days which did not line up exactly with weekend/weekdays (Wang et al., 2015).”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Wang et al., 2015
Not checked in the free run.
The paper relies on this without support.
Movement on workdays is determined to some degree by social roles and expectations, while movement on non-workdays is less determined by external demands and more by the individual’s motivational state.
“Movement on workdays is likely determined to some degree by social roles and expectations, while movement on non-workdays is likely less determined by external demands and more by the individual’s motivational state.”
The paper relies on this without support.
A diagnosis of depression requires the presence of symptoms more days than not for two weeks.
“The 2-week period was selected as a block of time because a diagnosis of depression requires the presence of symptoms more days than not for two weeks.”
The paper relies on this without support.
Some schools have schedules that do not fall cleanly into a 5-day work week and many people work on weekends.
“Some schools might have schedules that do not fall cleanly into a 5-day work week and many people clearly work on weekends.”
The paper relies on this without support.
Most studies of behavioral sensing in depression only have 2 or 3 assessment points for each individual, which makes the dataset underpowered for investigating the longitudinal relationship between sensor data and depression.
“Most studies of behavioral sensing in depression only have 2 or 3 assessment points for each individual, which makes the dataset underpowered for investigating the longitudinal relationship between sensor data—which has much higher frequency—and depression.”
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?
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].”
From Predicting depressive symptom severity through individuals’ nearby Bluetooth device count data collected by mobile phones: preliminary longitudinal study (2021) · cites this paper as [42]
No significant relationship was found between the other smartphone features (total distance, location entropy, normalized location entropy and time spent at home) and mental health measures.
“However, contrary to previous findings (19, 67–69), we did not find a significant relationship between the other smartphone features (total distance, location entropy, normalized location entropy and time spent at home) and mental health measures.”
From Predicting Symptoms of Depression and Anxiety Using Smartphone and Wearable Data (2021) · cites this paper as [68]
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.
Student-year breakdown totals 47, not 48
MinorThe listed Bachelor's, Master's, and PhD student counts sum to 47, one fewer than the stated 48 students.
Reported 48 · recomputed 47
“This dataset, known as StudentLife, was collected from 48 students of a computer science class for a duration of 10 weeks. The students consisted of 38 males and 10 females. Two of them were first-year, 14 second-year, six third-year, and eight fourth-year Bachelor’s students. There were also 13 first-year and one second-year Master’s student, and three PhD students.”
Pew Research Center citation year differs from reference
MinorThe text cites the Pew Research Center as a 2005 source, while the corresponding reference lists 2015.
“(Pew Research Center, 2005)”
“[Pew Research Center (2005] Pew Research Center 2015 http://www.pewinternet.org/2015/04/01/us-smartphone-use-in-2015/ U.S. smartphone use in 2015 Washington, D.C. Pew Research Center”
Abstract's correlation range excludes a reported result
MinorThe abstract gives a range of −0.43 to −0.46 for the significant GPS-feature correlations, but Table 2 reports −0.48 for circadian movement at follow-up.
“r’s ranging from −0.43 to −0.46, p-values < .05”
“| Circadian movement∗ | −0.34 ± 0.006 | −0.48 ± 0.006 | −0.33 ± 0.009 |”
Cites
Diagnostic and Statistical Manual of Mental Disorders
American Psychiatric Association (2013) · doi:10.1176/appi.books.9780890425596 · Cited by 116,369 · see citing works
A Mathematical Theory of Communication
Shannon, C. E. (1948) · Bell System Technical Journal · doi:10.1002/j.1538-7305.1948.tb01338.x · Cited by 88,486 · see citing works
The PHQ-9: Validity of a brief depression severity measure
Kroenke, K., Spitzer, R. L., & Williams, J. B. W. (2001) · Journal of General Internal Medicine · doi:10.1046/j.1525-1497.2001.016009606.x · Cited by 44,910 · see citing works
An Introduction to the Bootstrap
Efron, B., & Tibshirani, R. J. (1993) · doi:10.1007/978-1-4899-4541-9 · Cited by 21,230 · see citing works
Kessler, R. C., Chiu, W. T., Demler, O., & Walters, E. E. (2005) · Archives of General Psychiatry · doi:10.1001/archpsyc.62.6.617 · Cited by 12,052 · see citing works
Estimating the reproducibility of psychological science
Open Science Collaboration (2015) · Science · doi:10.1126/science.aac4716 · Cited by 8,515 · see citing works
Numerical Recipes: The Art of Scientific Computing
Ziegel, E. R., Press, W. H., Flannery, B. P., Teukolsky, S. A., & Vetterling, W. T. (1987) · Technometrics · doi:10.2307/1269484 · Cited by 6,704 · see citing works
Ferrari, A. J., Charlson, F. J., Norman, R. E., Patten, S. B., Freedman, G., Murray, C. J. L., Vos, T., & Whiteford, H. A. (2013) · PLoS Medicine · doi:10.1371/journal.pmed.1001547 · Cited by 3,115 · see citing works
Activity recognition using cell phone accelerometers
Kwapisz, J. R., Weiss, G. M., & Moore, S. A. (2011) · ACM SIGKDD Explorations Newsletter · doi:10.1145/1964897.1964918 · Cited by 2,912 · see citing works
Mathematical Theory of Communication
Binder, M. D., Hirokawa, N., & Windhorst, U. (2008) · Springer eBooks · doi:10.1007/978-3-540-29678-2_3338 · Cited by 2,297 · see citing works
The Economic Burden of Adults With Major Depressive Disorder in the United States (2005 and 2010)
Greenberg, P. E., Fournier, A.-A., Sisitsky, T., Pike, C. T., & Kessler, R. C. (2015) · The Journal of Clinical Psychiatry · doi:10.4088/jcp.14m09298 · Cited by 1,779 · see citing works
ON THE MATHEMATICAL THEORY OF COMMUNICATION
Takada, Y. (1954) · The Japanese journal of psychology · doi:10.4992/jjpsy.25.110 · Cited by 1,662 · see citing works
Screening for Depression in Adults: US Preventive Services Task Force Recommendation Statement
Siu, A. L., and the US Preventive Services Task Force (USPSTF), Bibbins-Domingo, K., Grossman, D. C., Baumann, L. C., Davidson, K. W., Ebell, M., García, F. A. R., Gillman, M., Herzstein, J., et al. (2016) · JAMA · doi:10.1001/jama.2015.18392 · Cited by 1,407 · see citing works
Wang, P. S., Berglund, P., Olfson, M., Pincus, H. A., Wells, K. B., & Kessler, R. C. (2005) · Archives of General Psychiatry · doi:10.1001/archpsyc.62.6.603 · Cited by 1,325 · see citing works
Thomée, S., Härenstam, A., & Hagberg, M. (2011) · BMC Public Health · doi:10.1186/1471-2458-11-66 · Cited by 1,269 · see citing works
Wang, R., Chen, F., Chen, Z., Li, T., Harari, G., Tignor, S., Zhou, X., Ben-Zeev, D., & Campbell, A. T. (2014) · Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing · doi:10.1145/2632048.2632054 · Cited by 1,116 · see citing works
Kessler, R. C., Zhao, S., Blazer, D. G., & Swartz, M. (1997) · Journal of Affective Disorders · doi:10.1016/s0165-0327(97)00056-6 · Cited by 790 · see citing works
Saeb, S., Zhang, M., Karr, C. J., Schueller, S. M., Corden, M. E., Kording, K. P., & Mohr, D. C. (2015) · Journal of Medical Internet Research · doi:10.2196/jmir.4273 · Cited by 782 · see citing works
Self-citationFleeson, W. (2004) · Current Directions in Psychological Science · doi:10.1111/j.0963-7214.2004.00280.x · Cited by 649 · see citing works
The Situational Eight DIAMONDS: A taxonomy of major dimensions of situation characteristics.
Rauthmann, J. F., Gallardo‐Pujol, D., Guillaume, E. M., Todd, E., Nave, C. S., Sherman, R. A., Ziegler, M. D., Jones, A. B., & Funder, D. C. (2014) · Journal of Personality and Social Psychology · doi:10.1037/a0037250 · Cited by 599 · see citing works
Fusion of Smartphone Motion Sensors for Physical Activity Recognition
Shoaib, M., Bosch, S., Incel, O., Scholten, H., & Havinga, P. (2014) · Sensors · doi:10.3390/s140610146 · Cited by 552 · see citing works
Canzian, L., & Musolesi, M. (2015) · Proceedings of the 2015 ACM International Joint Conference on Pervasive and Ubiquitous Computing · doi:10.1145/2750858.2805845 · Cited by 477 · see citing works
MoodScope: building a mood sensor from smartphone usage patterns
LiKamWa, R., Liu, Y., Lane, N. D., & Zhong, L. (2013) · Proceeding of the 11th annual international conference on Mobile systems, applications, and services · doi:10.1145/2462456.2464449 · Cited by 444 · see citing works
Screening and case-finding instruments for depression: a meta-analysis
Gilbody, S., Sheldon, T., & House, A. (2008) · Canadian Medical Association Journal · doi:10.1503/cmaj.070281 · Cited by 443 · see citing works
Smartphone-Based Recognition of States and State Changes in Bipolar Disorder Patients
Grunerbl, A., Muaremi, A., Osmani, V., Bahle, G., Ohler, S., Troster, G., Mayora, O., Haring, C., & Lukowicz, P. (2015) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2014.2343154 · Cited by 384 · see citing works
From depressive symptoms to depressive disorders: the relevance of thresholds
Ayuso‐Mateos, J. L., Nuevo, R., Verdes, E., Naidoo, N., & Chatterji, S. (2010) · The British Journal of Psychiatry · doi:10.1192/bjp.bp.109.071191 · Cited by 348 · see citing works
Perceived barriers to psychological treatments and their relationship to depression
Mohr, D. C., Ho, J., Duffecy, J., Baron, K. G., Lehman, K. A., Jin, L., & Reifler, D. (2010) · Journal of Clinical Psychology · doi:10.1002/jclp.20659 · Cited by 347 · see citing works
Self-citationContinuity and change in personality.
Mischel, W. (1969) · American Psychologist · doi:10.1037/h0028886 · Cited by 344 · see citing works
SmartGPA: how smartphones can assess and predict academic performance of college students
Wang, R., Harari, G., Hao, P., Zhou, X., & Campbell, A. (2015) · Ubiquitous Computing · doi:10.1145/2750858.2804251 · Cited by 219 · see citing works
Asselbergs, J., Ruwaard, J., Ejdys, M., Schrader, N., Sijbrandij, M., & Riper, H. (2016) · Journal of Medical Internet Research · doi:10.2196/jmir.5505 · Cited by 192 · see citing works
Standards for Patient-Reported Outcome–Based Performance Measures
Basch, E., Torda, P., & Adams, K. (2013) · JAMA · doi:10.1001/jama.2013.6855 · Cited by 146 · see citing works
Abdullah, S., Matthews, M. L., Murnane, E. L., Gay, G. K., & Choudhury, T. (2014) · ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) · doi:10.1145/2632048.2632100 · Cited by 125 · see citing works
MoodScope: Building a Mood Sensor from Smartphone Usage Patterns
LiKamWa, R., Liu, Y., Lane, N. D., & Zhong, L. (2012) · Rice Research Repository (Rice University) · Cited by 97 · see citing works
The Relationship between Clinical, Momentary, and Sensor-based Assessment of Depression
Saeb, S., Zhang, M., Kwasny, M., Karr, C., Kording, K., & Mohr, D. (2015) · Proceedings of the 9th International Conference on Pervasive Computing Technologies for Healthcare · doi:10.4108/icst.pervasivehealth.2015.259034 · Cited by 89 · see citing works
Self-citationMining smartphone data to classify life-facets of social relationships
Min, J.-K., Wiese, J., Hong, J., & Zimmerman, J. (2013) · ACM Conference on Computer Supported Cooperative Work (CSCW) · doi:10.1145/2441776.2441810 · Cited by 81 · see citing works
Higginson, D., Τheodoratou, E., Nair, H., Huda, T. M., Zgaga, L., Jadhav, S. S., Omer, S. B., Rudan, I., & Campbell, H. J. (2011) · BMC Public Health · doi:10.1186/1471-2458-11-s3-s31 · Cited by 63 · see citing works
"You Never Call, You Never Write"
Wiese, J., Min, J.-K., Hong, J., & Zimmerman, J. (2015) · ACM Conference on Computer Supported Cooperative Work (CSCW) · doi:10.1145/2675133.2675143 · Cited by 55 · see citing works
Canzian, L., & Musolesi, M. (2015) · Cited by 39 · see citing works
US Preventive Services Task Force Recommendation Statement on Screening for Depression in Adults
Reynolds, C. F., & Frank, E. (2016) · JAMA Psychiatry · doi:10.1001/jamapsychiatry.2015.3281 · Cited by 34 · see citing works
Flagged first, then by citations
Research works printed but not linked: 1
- Pew Research Center, 2015, U.S. smartphone use in 2015
Cited by
Sorted by citations
Digital Phenotyping: Technology for a New Science of Behavior
Insel, T. R. (2017) · JAMA · doi:10.1001/jama.2017.11295 · Cited by 833 · see citing works
Personal Sensing: Understanding Mental Health Using Ubiquitous Sensors and Machine Learning
Mohr, D. C., Zhang, M., & Schueller, S. M. (2017) · Annual Review of Clinical Psychology · doi:10.1146/annurev-clinpsy-032816-044949 · Cited by 802 · see citing works
Self-citationThe promise of machine learning in predicting treatment outcomes in psychiatry
Chekroud, A. M., Bondar, J., Delgadillo, J., Doherty, G., Wasil, A., Fokkema, M., Cohen, Z., Belgrave, D., DeRubeis, R., Iniesta, R., et al. (2021) · World Psychiatry · doi:10.1002/wps.20882 · Cited by 531 · see citing works
Digital biomarkers for Alzheimer’s disease: the mobile/wearable devices opportunity
Kourtis, L. C., Regele, O. B., Wright, J. M., & Jones, G. B. (2019) · npj Digital Medicine · doi:10.1038/s41746-019-0084-2 · Cited by 476 · see citing works
Smartphone Sensors for Health Monitoring and Diagnosis
Majumder, S., & Deen, M. J. (2019) · Sensors · doi:10.3390/s19092164 · Cited by 440 · see citing works
Toward clinical digital phenotyping: a timely opportunity to consider purpose, quality, and safety
Huckvale, K., Venkatesh, S., & Christensen, H. (2019) · npj Digital Medicine · doi:10.1038/s41746-019-0166-1 · Cited by 433 · see citing works
D’Alfonso, S. (2020) · Current Opinion in Psychology · doi:10.1016/j.copsyc.2020.04.005 · Cited by 408 · see citing works
Systematic review of smartphone-based passive sensing for health and wellbeing
Cornet, V. P., & Holden, R. J. (2018) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2017.12.008 · Cited by 406 · see citing works
Digital interventions for the treatment of depression: a meta-analytic review
Moshe, I., Terhorst, Y., Philippi, P., Domhardt, M., Cuijpers, P., Cristea, I., Pulkki-Råback, L., Baumeister, H., & Sander, L. B. (2021) · Psychological Bulletin · doi:10.1037/bul0000334 · Cited by 390 · see citing works
Predicting personality from patterns of behavior collected with smartphones
Stachl, C., Au, Q., Schoedel, R., Gosling, S. D., Harari, G. M., Buschek, D., Völkel, S. T., Schuwerk, T., Oldemeier, M., Ullmann, T., et al. (2020) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1920484117 · Cited by 362 · see citing works
Tracking Depression Dynamics in College Students Using Mobile Phone and Wearable Sensing
Wang, R., Wang, W., daSilva, A., Huckins, J. F., Kelley, W. M., Heatherton, T. F., & Campbell, A. T. (2018) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3191775 · Cited by 340 · see citing works
Predicting Symptoms of Depression and Anxiety Using Smartphone and Wearable Data
Moshe, I., Terhorst, Y., Opoku Asare, K., Sander, L. B., Ferreira, D., Baumeister, H., Mohr, D. C., & Pulkki-Råback, L. (2021) · Frontiers in Psychiatry · doi:10.3389/fpsyt.2021.625247 · Cited by 261 · see citing works
Self-citationAnikwe, C. V., Nweke, H. F., Ikegwu, A. C., Egwuonwu, C. A., Onu, F. U., Alo, U. R., & Teh, Y. W. (2022) · Expert Systems with Applications · doi:10.1016/j.eswa.2022.117362 · Cited by 250 · see citing works
Digital Health Tools for the Passive Monitoring of Depression: A Systematic Review of Methods
de Angel, V., Lewis, S., White, K., Oetzmann, C., Leightley, D., Oprea, E., Lavelle, G., Matcham, F., Pace, A., Mohr, D. C., et al. (2021) · doi:10.1101/2021.07.19.21260786 · Cited by 227 · see citing works
Self-citationStudent engagement and wellbeing over time at a higher education institution
Boulton, C. A., Hughes, E. A., Kent, C., Smith, J. R., & Williams, H. T. P. (2019) · PLoS ONE · doi:10.1371/journal.pone.0225770 · Cited by 231 · see citing works
Torous, J., Larsen, M. E., Depp, C., Cosco, T. D., Barnett, I., Nock, M. K., & Firth, J. (2018) · Current Psychiatry Reports · doi:10.1007/s11920-018-0914-y · Cited by 207 · see citing works
Rohani, D. A., Faurholt-Jepsen, M., Kessing, L. V., & Bardram, J. E. (2017) · doi:10.2196/preprints.9691 · Cited by 195 · see citing works
Chow, P. I., Fua, K., Huang, Y., Bonelli, W., Xiong, H., Barnes, L. E., & Teachman, B. A. (2017) · Journal of Medical Internet Research · doi:10.2196/jmir.6820 · Cited by 172 · see citing works
Harari, G. M., Müller, S. R., Stachl, C., Wang, R., Wang, W., Bühner, M., Rentfrow, P. J., Campbell, A. T., & Gosling, S. D. (2019) · Journal of Personality and Social Psychology · doi:10.1037/pspp0000245 · Cited by 168 · see citing works
Arya, S. S., Dias, S. B., Jelinek, H. F., Hadjileontiadis, L. J., & Pappa, A. (2023) · Biosensors and Bioelectronics · doi:10.1016/j.bios.2023.115387 · Cited by 161 · see citing works
Seppälä, J., De Vita, I., Jämsä, T., Miettunen, J., Isohanni, M., Rubinstein, K., Feldman, Y., Grasa, E., Corripio, I., Berdun, J., et al. (2019) · JMIR Mental Health · doi:10.2196/mental.9819 · Cited by 148 · see citing works
Jacobson, N. C., & Chung, Y. J. (2020) · Sensors · doi:10.3390/s20123572 · Cited by 139 · see citing works
Digital Technologies for Emotion-Regulation Assessment and Intervention: A Conceptual Review
Bettis, A. H., Burke, T. A., Nesi, J. L., & Liu, R. T. (2021) · Clinical Psychological Science · doi:10.1177/21677026211011982 · Cited by 147 · see citing works
Chikersal, P., Doryab, A., Tumminia, M. J., Villalba, D. K., Dutcher, J. M., Liu, X., Cohen, S., Creswell, K. G., Mankoff, J. C., Creswell, J. D., et al. (2021) · ACM Transactions on Computer-Human Interaction · doi:10.1145/3422821 · Cited by 144 · see citing works
Reinertsen, E., & Clifford, G. D. (2018) · Physiological Measurement · doi:10.1088/1361-6579/aabf64 · Cited by 136 · see citing works
Machine learning for the educational sciences
Hilbert, S., Coors, S., Kraus, E., Bischl, B., Lindl, A., Frei, M., Wild, J., Krauß, S., Goretzko, D., & Stachl, C. (2021) · Review of Education · doi:10.1002/rev3.3310 · Cited by 147 · see citing works
Xu, X., Chikersal, P., Doryab, A., Villalba, D. K., Dutcher, J. M., Tumminia, M. J., Althoff, T., Cohen, S., Creswell, K. G., Creswell, J. D., et al. (2019) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3351274 · Cited by 125 · see citing works
Digital phenotyping for mental health of college students: a clinical review
Melcher, J., Hays, R., & Torous, J. (2020) · Evidence Based Mental Health · doi:10.1136/ebmental-2020-300180 · Cited by 121 · see citing works
Pratap, A., Renn, B. N., Volponi, J. J., Mooney, S. D., Gazzaley, A. H., Areán, P. A., & Anguera, J. A. (2018) · Journal of Medical Internet Research · doi:10.2196/10130 · Cited by 116 · see citing works
Ethical Development of Digital Phenotyping Tools for Mental Health Applications: Delphi Study
Martinez‐Martin, N., Greely, H. T., & Cho, M. K. (2021) · JMIR mhealth and uhealth · doi:10.2196/27343 · Cited by 122 · see citing works
Predicting Symptom Trajectories of Schizophrenia using Mobile Sensing
Wang, R., Wang, W., Aung, M. H., Ben‐Zeev, D., Brian, R., Campbell, A. T., Choudhury, T., Hauser, M., Kane, J. M., Scherer, E. A., et al. (2017) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3130976 · Cited by 105 · see citing works
Wang, W., Harari, G. M., Wang, R., Müller, S. R., Mirjafari, S., Masaba, K., & Campbell, A. T. (2018) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3264951 · Cited by 100 · see citing works
Fillekes, M. P., Giannouli, E., Kim, E., Zijlstra, W., & Weibel, R. (2019) · International Journal of Health Geographics · doi:10.1186/s12942-019-0181-0 · Cited by 95 · see citing works
Hur, J., Stockbridge, M. D., Fox, A. S., & Shackman, A. J. (2019) · Progress in brain research · doi:10.1016/bs.pbr.2019.03.012 · Cited by 91 · see citing works
Digital health data-driven approaches to understand human behavior
Marsch, L. A. (2020) · Neuropsychopharmacology · doi:10.1038/s41386-020-0761-5 · Cited by 90 · see citing works
The utility of smartphone-based, ecological momentary assessment for depressive symptoms
Yim, S. J., Lui, L. M. W., Lee, Y. L., Rosenblat, J. D., Ragguett, R., Park, C., Subramaniapillai, M., Cao, B., Zhou, A. J., Rong, C., et al. (2020) · Journal of Affective Disorders · doi:10.1016/j.jad.2020.05.116 · Cited by 82 · see citing works
Sensing Apps and Public Data Sets for Digital Phenotyping of Mental Health: Systematic Review
Mendes, J. P. M., de Moura, I. R., van de Ven, P. W. J., Viana, D., Silva, F., Coutinho, L., Teixeira, S. S., Rodrigues, J. J. P. C., & Teles, A. S. (2021) · Journal of Medical Internet Research · doi:10.2196/28735 · Cited by 85 · see citing works
Grouped feature importance and combined features effect plot
Au, Q., Herbinger, J., Stachl, C., Bischl, B., & Casalicchio, G. (2022) · Data Mining and Knowledge Discovery · doi:10.1007/s10618-022-00840-5 · Cited by 83 · see citing works
Meyerhoff, J., Liu, T., Kording, K. P., Ungar, L. H., Kaiser, S. M., Karr, C. J., & Mohr, D. C. (2021) · Journal of Medical Internet Research · doi:10.2196/22844 · Cited by 82 · see citing works
Self-citationLee, H., Cho, C., Lee, T., Jeong, J., Yeom, J. W., Kim, S., Jeon, S., Seo, J. Y., Moon, E., Baek, J. H., et al. (2022) · Psychological Medicine · doi:10.1017/s0033291722002847 · Cited by 82 · see citing works
Digital Psychiatry: Risks and Opportunities for Public Health and Wellbeing
Burr, C., Morley, J., Taddeo, M., & Floridi, L. (2020) · IEEE Transactions on Technology and Society · doi:10.1109/tts.2020.2977059 · Cited by 78 · see citing works
Nicholas, J., Shilton, K., Schueller, S. M., Gray, E. L., Kwasny, M. J., & Mohr, D. C. (2019) · JMIR mHealth and uHealth · doi:10.2196/12578 · Cited by 77 · see citing works
Self-citationMasud, M. T., Mamun, M. A., Thapa, K., Lee, D. H., Griffiths, M. D., & Yang, S. (2020) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2019.103371 · Cited by 73 · see citing works
Anomalies Detection Through Smartphone Sensors: A Review
Krichen, M. (2021) · IEEE Sensors Journal · doi:10.1109/jsen.2021.3051931 · Cited by 73 · see citing works
Ueafuea, K., Boonnag, C., Sudhawiyangkul, T., Leelaarporn, P., Gulistan, A., Chen, W., Mukhopadhyay, S. C., Wilaiprasitporn, T., & Piyayotai, S. (2020) · IEEE Sensors Journal · doi:10.1109/jsen.2020.3046259 · Cited by 72 · see citing works
Zhang, Y., Folarin, A. A., Sun, S., Cummins, N., Ranjan, Y., Rashid, Z., Conde, P., Stewart, C., Laiou, P., Matcham, F., et al. (2021) · JMIR mHealth and uHealth · doi:10.2196/29840 · Cited by 68 · see citing works
Self-citationHilty, D. M., Armstrong, C. M., Luxton, D. D., Gentry, M. T., & Krupinski, E. A. (2021) · Journal of Technology in Behavioral Science · doi:10.1007/s41347-021-00199-2 · Cited by 68 · see citing works
Leveraging Collaborative-Filtering for Personalized Behavior Modeling
Xu, X., Chikersal, P., Dutcher, J. M., Sefidgar, Y. S., Seo, W., Tumminia, M. J., Villalba, D. K., Cohen, S., Creswell, K. G., Creswell, J. D., et al. (2021) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3448107 · Cited by 65 · see citing works
The relationship between text message sentiment and self-reported depression
Liu, T., Meyerhoff, J., Eichstaedt, J. C., Karr, C. J., Kaiser, S. M., Kording, K. P., Mohr, D. C., & Ungar, L. (2021) · Journal of Affective Disorders · doi:10.1016/j.jad.2021.12.048 · Cited by 67 · see citing works
Self-citationKornfield, R., Zhang, R., Nicholas, J., Schueller, S. M., Cambo, S. A., Mohr, D. C., & Reddy, M. (2020) · Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3313831.3376309 · Cited by 64 · see citing works
Self-citationThe promise of digital mood tracking technologies: are we heading on the right track?
Malhi, G. S., Hamilton, A., Morris, G., Mannie, Z., Das, P., & Outhred, T. (2017) · Evidence Based Mental Health · doi:10.1136/eb-2017-102757 · Cited by 62 · see citing works
Müller, S. R., Peters, H., Matz, S., Wang, W., & Harari, G. M. (2020) · European Journal of Personality · doi:10.1002/per.2262 · Cited by 63 · see citing works
Prasad, T. R., Dhadwal, A. S., Kumar, P., & Sainaba, P. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-022-12315-2 · Cited by 61 · see citing works
Dogrucu, A., Perucic, A., Isaro, A., Ball, D., Toto, E., Rundensteiner, E. A., Agu, E., Davis-Martin, R. E., & Boudreaux, E. D. (2020) · Smart Health · doi:10.1016/j.smhl.2020.100118 · Cited by 62 · see citing works
Sociodemographic characteristics of missing data in digital phenotyping
Kiang, M. V., Chen, J. T., Krieger, N., Buckee, C. O., Alexander, M. J., Baker, J. T., Buckner, R. L., Coombs, G., Rich-Edwards, J. W., Carlson, K. W., et al. (2021) · Scientific Reports · doi:10.1038/s41598-021-94516-7 · Cited by 55 · see citing works
Teepe, G. W., Fonseca, A. D., Kleim, B., Jacobson, N. C., Salamanca-Sanabria, A., Car, L. T., Fleisch, E., & Kowatsch, T. (2021) · Journal of Medical Internet Research · doi:10.2196/29412 · Cited by 60 · see citing works
Sarda, A., Munuswamy, S., Sarda, S., & Subramanian, V. (2019) · JMIR mHealth and uHealth · doi:10.2196/11041 · Cited by 56 · see citing works
Maharjan, S. M., Poudyal, A., van Heerden, A. C., Byanjankar, P., Thapa, A., Islam, C., Kohrt, B. A., & Hagaman, A. K. (2021) · BMC Medical Informatics and Decision Making · doi:10.1186/s12911-021-01473-2 · Cited by 51 · see citing works
Digital Phenotyping and Feature Extraction on Smartphone Data for Depression Detection
Yang, M., Ngai, E. C. ‐., Hu, X., Hu, B., Liu, J., Erol Gelenbe, A., & Leung, V. C. M. (2024) · Proceedings of the IEEE · doi:10.1109/jproc.2025.3542324 · Cited by 54 · see citing works
Zaman, A., Zhang, B., Hoque, M. E., Silenzio, V., & Kautz, H. (2020) · JMIR Mental Health · doi:10.2196/24012 · Cited by 50 · see citing works
Müller, S. R., Chen, X., Peters, H., Chaintreau, A., & Matz, S. C. (2021) · Scientific Reports · doi:10.1038/s41598-021-93087-x · Cited by 51 · see citing works
Using digital phenotyping to understand health-related outcomes: A scoping review
Lee, K., Lee, T. C., Yefimova, M., Kumar, S., Puga, F., Azuero, A., Kamal, A. H., Bakitas, M. A., Wright, A. A., Demiris, G., et al. (2023) · International Journal of Medical Informatics · doi:10.1016/j.ijmedinf.2023.105061 · Cited by 52 · see citing works
Identifying Mobile Sensing Indicators of Stress-Resilience
Adler, D. A., Tseng, V. W.-S., Qi, G., Scarpa, J. R., Sen, S., & Choudhury, T. (2021) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3463528 · Cited by 50 · see citing works
Diagnosis of Depressive Disorder Model on Facial Expression Based on Fast R-CNN
Lee, Y.-S., & Park, W.-H. (2022) · Diagnostics · doi:10.3390/diagnostics12020317 · Cited by 49 · see citing works
Understanding behaviours in context using mobile sensing
Harari, G. M., & Gosling, S. D. (2023) · Nature Reviews Psychology · doi:10.1038/s44159-023-00235-3 · Cited by 56 · see citing works
Digital biomarkers for non-motor symptoms in Parkinson’s disease: the state of the art
Daalen, J. M. J., van den Bergh, R., Prins, E. M., Moghadam, M. S. C., van den Heuvel, R., Veen, J., Mathur, S., Meijerink, H., Mirelman, A., Darweesh, S. K. L., et al. (2024) · npj Digital Medicine · doi:10.1038/s41746-024-01144-2 · Cited by 52 · see citing works
Provider Perspectives on Integrating Sensor-Captured Patient-Generated Data in Mental Health Care
Ng, A., Kornfield, R., Schueller, S. M., Zalta, A. K., Brennan, M. B., & Reddy, M. C. (2019) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3359217 · Cited by 46 · see citing works
Self-citationWang, W., Mirjafari, S., Harari, G. M., Ben‐Zeev, D., Brian, R., Choudhury, T., Hauser, M., Kane, J. M., Masaba, K., Nepal, S. K., et al. (2020) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3313831.3376855 · Cited by 47 · see citing works
Gutiérrez, L. J., Rabbani, K., Ajayi, O. J., Gebresilassie, S. K., Rafferty, J., Castro, L. A., & Baños, O. (2021) · International Journal of Environmental Research and Public Health · doi:10.3390/ijerph18031327 · Cited by 51 · see citing works
Zhang, Y., Folarin, A., Sun, S., Cummins, N., Vairavan, S., Bendayan, R., Ranjan, Y., Rashid, Z., Conde, P., Stewart, C., et al. (2022) · JMIR Mental Health · doi:10.2196/34898 · Cited by 43 · see citing works
Self-citationKim, T., Kim, H., Lee, H. Y., Goh, H., Abdigapporov, S., Jeong, M., Cho, H., Han, K., Noh, Y., Lee, S.-J., et al. (2022) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3491102.3517701 · Cited by 46 · see citing works
Stamatis, C. A., Meyerhoff, J., Meng, Y., Lin, Z. C. C., Cho, Y. M., Liu, T., Karr, C. J., Liu, T., Curtis, B. L., Ungar, L., et al. (2024) · npj Mental Health Research · doi:10.1038/s44184-023-00041-y · Cited by 50 · see citing works
Self-citationBooth, B. M., Mundnich, K., Feng, T., Nadarajan, A., Falk, T. H., Villatte, J. L., Ferrara, E., & Narayanan, S. S. (2019) · Journal of Medical Internet Research · doi:10.2196/12832 · Cited by 46 · see citing works
Precision medicine and digital phenotyping: Digital medicine's way from more data to better health
Baumgartner, R. R. (2021) · Big Data & Society · doi:10.1177/20539517211066452 · Cited by 45 · see citing works
Ji, C., Patil, K. R., Yeo, B. T. T., & Eickhoff, S. B. (2022) · Biological Psychiatry · doi:10.1016/j.biopsych.2022.07.025 · Cited by 43 · see citing works
Technology and Mental Health: State of the Art for Assessment and Treatment
Harvey, P. D., Depp, C. A., Rizzo, A., Strauss, G. P., Spelber, D., Carpenter, L. L., Kalin, N. H., Krystal, J. H., McDonald, W. M., Nemeroff, C. B., et al. (2022) · American Journal of Psychiatry · doi:10.1176/appi.ajp.21121254 · Cited by 46 · see citing works
Matteo, D. D., Fotinos, K., Lokuge, S., Yu, J., Sternat, T., Katzman, M. A., & Rose, J. (2020) · JMIR Formative Research · doi:10.2196/18751 · Cited by 43 · see citing works
AWARE-Light: a smartphone tool for experience sampling and digital phenotyping
van Berkel, N., D’Alfonso, S., Susanto, R., Ferreira, D., & Kostakos, V. (2022) · Personal and Ubiquitous Computing · doi:10.1007/s00779-022-01697-7 · Cited by 39 · see citing works
Turvey, C., & Fortney, J. C. (2017) · Current Psychiatry Reports · doi:10.1007/s11920-017-0844-0 · Cited by 37 · see citing works
Laiou, P., Kaliukhovich, D. A., Folarin, A., Ranjan, Y., Rashid, Z., Conde, P., Stewart, C., Sun, S., Zhang, Y., Matcham, F., et al. (2022) · JMIR mhealth and uhealth · doi:10.2196/28095 · Cited by 39 · see citing works
Social physics: uncovering human behaviour from communication
Bhattacharya, K., & Kaski, K. K. (2018) · Advances in Physics X · doi:10.1080/23746149.2018.1527723 · Cited by 37 · see citing works
Prediction of stress levels with LSTM and passive mobile sensors
Acikmese, Y., & Alptekin, S. E. (2019) · Procedia Computer Science · doi:10.1016/j.procs.2019.09.221 · Cited by 41 · see citing works
Daily mobility patterns in patients with bipolar disorder and healthy individuals
Faurholt‐Jepsen, M., Busk, J., Vinberg, M., Christensen, E. M., Þórarinsdóttir, H., Frost, M. M., Bardram, J. E., & Kessing, L. V. (2020) · Journal of Affective Disorders · doi:10.1016/j.jad.2020.09.087 · Cited by 34 · see citing works
Smith, K. E., Mason, T. B., Juarascio, A., Schaefer, L. M., Crosby, R. D., Engel, S. G., & Wonderlich, S. A. (2019) · International Journal of Eating Disorders · doi:10.1002/eat.23124 · Cited by 34 · see citing works
Zhang, D., Lim, J., Zhou, L., & Dahl, A. A. (2021) · JMIR Mental Health · doi:10.2196/31633 · Cited by 35 · see citing works
Wang, W., Nepal, S. K., Huckins, J. F., Hernandez, L., Vojdanovski, V., Mack, D. L., Plomp, J., Pillai, A., Obuchi, M., DaSilva, A. W., et al. (2022) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3543194 · Cited by 34 · see citing works
He-Yueya, J., Buck, B., Campbell, A. T., Choudhury, T., Kane, J. M., Ben‐Zeev, D., & Althoff, T. (2020) · Schizophrenia · doi:10.1038/s41537-020-00123-2 · Cited by 33 · see citing works
Zhang, Y., Folarin, A., Sun, S., Cummins, N., Ranjan, Y., Rashid, Z., Stewart, C., Conde, P., Sankesara, H., Laiou, P., et al. (2024) · Journal of Medical Internet Research · doi:10.2196/55302 · Cited by 30 · see citing works
Self-citationPassively-sensed Behavioral Correlates of Discrimination Events in College Students
Sefidgar, Y. S., Seo, W., Kuehn, K. S., Althoff, T., Browning, A., Riskin, E. A., Nurius, P. S., Dey, A. K., & Mankoff, J. C. (2019) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3359216 · Cited by 29 · see citing works
Burkhard, O., Becker, H., Weibel, R., & Axhausen, K. W. (2020) · Transportation Research Part C Emerging Technologies · doi:10.1016/j.trc.2020.01.021 · Cited by 31 · see citing works
Predicting Brain Functional Connectivity Using Mobile Sensing
Obuchi, M., Huckins, J. F., Wang, W., daSilva, A., Rogers, C., Murphy, E., Hedlund, E., Holtzheimer, P., Mirjafari, S., & Campbell, A. (2020) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3381001 · Cited by 29 · see citing works
Beames, J. R., Han, J., Shvetcov, A., Zheng, W. Y., Slade, A., Dabash, O., Rosenberg, J., O’Dea, B., Kasthurirathne, S. N., Hoon, L., et al. (2024) · Heliyon · doi:10.1016/j.heliyon.2024.e35472 · Cited by 34 · see citing works
A simple location-tracking app for psychological research
Geyer, K., Ellis, D. A., & Piwek, L. (2018) · Behavior Research Methods · doi:10.3758/s13428-018-1164-y · Cited by 29 · see citing works
Predicting mental health using smart-phone usage and sensor data
Thakur, S. S., & Roy, R. B. (2020) · Journal of Ambient Intelligence and Humanized Computing · doi:10.1007/s12652-020-02616-5 · Cited by 29 · see citing works
A Systematic Review of Location Data for Depression Prediction
Shin, J., & Bae, S. (2023) · International Journal of Environmental Research and Public Health · doi:10.3390/ijerph20115984 · Cited by 29 · see citing works
Mardini, M., Nerella, S., Kheirkhahan, M., Ranka, S., Fillingim, R. B., Hu, Y., Corbett, D. B., Cenko, E., Weber, E., Rashidi, P., et al. (2020) · JMIR mhealth and uhealth · doi:10.2196/19609 · Cited by 31 · see citing works
Digital phenotyping in psychiatry: A scoping review
Chia, A. Z. R., & Zhang, M. W. (2022) · Technology and Health Care · doi:10.3233/thc-213648 · Cited by 26 · see citing works
An Examination of Psychomotor Disturbance in Current and Remitted MDD: An RDoC Study
Shankman, S. A., Mittal, V. A., & Walther, S. (2020) · Journal of Psychiatry and Brain Science · doi:10.20900/jpbs.20200007 · Cited by 26 · see citing works
Palmius, N., Saunders, K. E. A., Carr, O., Geddes, J. R., Goodwin, G. M., & Vos, M. D. (2018) · Journal of Medical Internet Research · doi:10.2196/10194 · Cited by 23 · see citing works
de Arriba-Pérez, F., Santos-Gago, J. M., Rodríguez, M. C., & Merino, M. R. (2019) · Journal of Ambient Intelligence and Humanized Computing · doi:10.1007/s12652-019-01188-3 · Cited by 25 · see citing works
- Authors
- Saeb, S., Lattie, E. G., Schueller, S. M., Kording, K. P., & Mohr, D. C.
- Affiliations
- Northwestern University (US)
- Corresponding author
- Mohr, David C.
- Venue
- PeerJ
- Publisher
- PeerJ
- Published
- 2016-09-29
- Volume
- 4
- Pages
- e2537
- ISSN
- 2167-8359 (ISSN-L)
- PMC
- PMC5361882
- OpenAlex
- W2524967876
- Cited by
- 313
- References
- 39
- Citations by year
- 2026: 21 · 2025: 16 · 2024: 40 · 2023: 19 · 2022: 56 · 2021: 51 · 2020: 59 · 2019: 22 · 2018: 20 · 2017: 9
- FWCI
- 24.13
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Locations
- PeerJ (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- eScholarship (California Digital Library) (submittedVersion)
- eScholarship (California Digital Library) (submittedVersion, cc-by)
- Funders
- US National Institute of Mental Health (P20 MH090318)
- National Institute of Mental Health (K08 MH 102336)
- Topics
- Social Sciences › Psychology › Experimental and Cognitive Psychology › Mental Health Research Topics
- Social Sciences › Transportation › Human Mobility and Location-Based Analysis
- Social Sciences › Psychology › Applied Psychology › Digital Mental Health Interventions
- Keywords
- depression, depression severity, GPS location data, smartphone sensors, passive sensing, PHQ-9, university students, early warning indicators
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
