Depression screening using mobile phone usage metadata: a machine learning approach
Open accessThe DOI matches its Crossref record; 21 of the 21 references it cites were found in a registry or an index.
Abstract
Objective: Depression is currently the second most significant contributor to non-fatal disease burdens globally. While it is treatable, depression remains undiagnosed in many cases. As mobile phones have now become an integral part of daily life, this study examines the possibility of screening for depressive symptoms continuously based on patients’ mobile usage patterns. Materials and Methods: 412 research participants reported a range of their mobile usage statistics. Beck Depression Inventory—2nd ed (BDI-II) was used to measure the severity of depression among participants. A wide array of machine learning classification algorithms was trained to detect participants with depression symptoms (ie, BDI-II score ≥ 14). The relative importance of individual variables was additionally quantified. Results: Participants with depression were found to have fewer saved contacts on their devices, spend more time on their mobile devices to make and receive fewer and shorter calls, and send more text messages than participants without depression. The best model was a random forest classifier, which had an out-of-sample balanced accuracy of 0.768. The balanced accuracy increased to 0.811 when participants’ age and gender were included. Discussions/Conclusion: The significant predictive power of mobile usage attributes implies that, by collecting mobile usage statistics, mental health mobile applications can continuously screen for depressive symptoms for initial diagnosis or for monitoring the progress of ongoing treatments. Moreover, the input variables used in this study were aggregated mobile usage metadata attributes, which has low privacy sensitivity making it more likely for patients to grant required application permissions.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Kuhn, M., & Johnson, K. (2013) · doi:10.1007/978-1-4614-6849-3 · Cited by 6,788 · cited 4×
“To ensure that the performance of the models was assessed on a sufficient number of samples and that the reported prediction performance was not specific to a single test subset, the above process was repeated 10 times, each time with new random training and test partitions and performance results were subsequently av…”
BackgroundMethodInfluentialWhy is depression more prevalent in women?
Albert, P. R. (2015) · Journal of Psychiatry and Neuroscience · doi:10.1503/jpn.150205 · Cited by 1,785
Thomée, S., Härenstam, A., & Hagberg, M. (2011) · BMC Public Health · doi:10.1186/1471-2458-11-66 · Cited by 1,269 · cited 2×
“13,15,16,18,19 Understanding the predictive power of mobile usage attributes is required to assess the feasibility, reliability, and accuracy of using these attributes for depression screening.”
BackgroundAwad, N. F., & Krishnan, M. S. (2006) · MIS Quarterly · doi:10.2307/25148715 · Cited by 1,252
Clinical diagnosis of depression in primary care: a meta-analysis
Mitchell, A. J., Vaze, A., & Rao, S. (2009) · The Lancet · doi:10.1016/s0140-6736(09)60879-5 · Cited by 1,251 · cited 1×
“2,42 Upon diagnosis of depression, various Internet-based interventions can be delivered by the mobile health application, where many of these interventions have been found to be promising.”
BackgroundGhassemzadeh, H., Mojtabai, R., Karamghadiri, N., & Ebrahimkhani, N. (2005) · Depression and Anxiety · doi:10.1002/da.20070 · Cited by 813
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 · cited 1×
“…could be detected with relatively good accuracy (ie, balanced accuracy ¼ 0.768) even with aggregated metadata usage attributes, which are less privacy-sensitive compared to other attributes such as the exact users’ location information 3 or the content of their social media posts and activities.”
BackgroundInfluentialHarnessing context sensing to develop a mobile intervention for depression
Burns, M. N., Begale, M., Duffecy, J., Gergle, D., Karr, C. J., Giangrande, E., & Mohr, D. C. (2011) · Journal of Medical Internet Research · doi:10.2196/jmir.1838 · Cited by 646 · cited 1×
“Table 2 shows the variations of demographics and mobile usage attributes for depressed (ie, BDI-II score (cid:2) 14) and not-depressed (ie, BDI-II score (cid”
BackgroundCross-cultural validation of the Beck Depression Inventory-II in Japan
Kojima, M., Furukawa, T. A., Takahashi, H., Kawai, M., Nagaya, T., & Tokudome, S. (2002) · Psychiatry Research · doi:10.1016/s0165-1781(02)00106-3 · Cited by 496 · cited 1×
“The validity and reliability of BDI-II has been examined and confirmed in several studies including studies considering individuals in different age groups, 24,25 in different cultures, 26,27 and among individuals with various disorders.”
MethodTitov, N., Andrews, G., Davies, M., McIntyre, K., Robinson, E., & Solley, K. (2010) · PLoS ONE · doi:10.1371/journal.pone.0010939 · Cited by 406
Berger, T., Hämmerli, K., Gubser, N., Andersson, G., & Caspar, F. (2011) · Cognitive Behaviour Therapy · doi:10.1080/16506073.2011.616531 · Cited by 383
Josephine, K., Josefine, L., Philipp, D., David, E., & Harald, B. (2017) · Journal of Affective Disorders · doi:10.1016/j.jad.2017.07.021 · Cited by 341 · cited 1×
“47 The study 49 provides a systematic review and comparison of mobile-based interventions for depression, where many of these interventions have been found to be highly effective.”
BackgroundSegal, D. L., Coolidge, F. L., Cahill, B. S., & O'Riley, A. A. (2008) · Behavior Modification · doi:10.1177/0145445507303833 · Cited by 335
Torous, J., Friedman, R., & Keshavan, M. (2014) · JMIR mHealth and uHealth · doi:10.2196/mhealth.2994 · Cited by 287 · cited 1×
“13,15,16,18,19 Understanding the predictive power of mobile usage attributes is required to assess the feasibility, reliability, and accuracy of using these attributes for depression screening.”
BackgroundLy, K. H., Trüschel, A., Jarl, L., Magnusson, S., Windahl, T., Johansson, R., Carlbring, P., & Andersson, G. (2014) · BMJ Open · doi:10.1136/bmjopen-2013-003440 · Cited by 269 · cited 2×
“47 The study 49 provides a systematic review and comparison of mobile-based interventions for depression, where many of these interventions have been found to be highly effective.”
BackgroundDehling, T., Gao, F., Schneider, S., & Sunyaev, A. (2015) · JMIR mHealth and uHealth · doi:10.2196/mhealth.3672 · Cited by 243 · cited 1×
“Considering the increasing importance of privacy for adopting mobile health applications by users, 21 the sensitivity of the information collected by such applications is likely to influence their adoption rate by users.”
BackgroundConstantly connected–The effects of smart-devices on mental health
Harwood, J., Dooley, J. J., Scott, A. J., & Joiner, R. (2014) · Computers in Human Behavior · doi:10.1016/j.chb.2014.02.006 · Cited by 236
WELLS, J. E., & HORWOOD, L. J. (2004) · Psychological Medicine · doi:10.1017/s0033291703001843 · Cited by 199
Lipschitz, J., Miller, C. J., Hogan, T. P., Burdick, K. E., Lippin-Foster, R., Simon, S. R., & Burgess, J. (2019) · JMIR Mental Health · doi:10.2196/11334 · Cited by 183
Thomée, S., Dellve, L., Härenstam, A., & Hagberg, M. (2010) · BMC Public Health · doi:10.1186/1471-2458-10-66 · Cited by 181 · cited 3×
“11 19 For example, depressed users have been found to make fewer calls and browse the internet on their mobile phones less frequently.”
BackgroundCarlbring, P., Hägglund, M., Luthström, A., Dahlin, M., Kadowaki, Å., Vernmark, K., & Andersson, G. (2013) · Journal of Affective Disorders · doi:10.1016/j.jad.2012.12.020 · Cited by 177
Cited by
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
“Recent studies with larger and more diverse samples using classi fi cation machine learning techniques have found that a low average number and duration of calls made daily predicted depression state 63 .”
ResultMeyerhoff, 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
Richter, T., Fishbain, B., Richter-Levin, G., & Okon-Singer, H. (2021) · Journal of Personalized Medicine · doi:10.3390/jpm11100957 · Cited by 52
Metadata
- Authors
- Razavi, R., Gharipour, A., & Gharipour, M.
- Venue
- Journal of the American Medical Informatics Association
- Publisher
- Oxford University Press (OUP)
- Published
- 2020-01-24
- Volume
- 27
- Issue
- 4
- Pages
- 522-530
- ISSN
- 1067-5027 (ISSN-L)
- 1527-974X
- OpenAlex
- W3003035376
- Cited by
- 74
- References
- 21
- FWCI
- 6.97
- Type
- journal article
- Language
- en
- Open access
- green
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.
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.