Digital phenotyping explained

Digital phenotyping is a multidisciplinary field of science,[1] [2] [3] first defined in a May 2016 paper in JMIR Mental Health authored by John Torous, Mathew V Kiang, Jeanette Lorme, and Jukka-Pekka Onnela as the "moment-by-moment quantification of the individual-level human phenotype in situ using data from personal digital devices." The data can be divided into two subgroups, called active data and passive data, where the former refers to data that requires active input from the users to be generated, whereas passive data, such as sensor data and phone usage patterns, are collected without requiring any active participation from the user.

Smartphones are well suited for digital phenotyping given their widespread adoption and ownership, the extent to which users engage with the devices, and richness of data that may be collected from them. Smartphone data can be used to study behavioral patterns, social interactions, physical mobility, gross motor activity, and speech production, among others. Smartphone ownership has been in steady rise globally over the past few years. For example, in the U.S., smartphone ownership among adults increased from 35% in 2011 to 64% in 2015,[4] and in 2017 an estimated 95% of Americans own a cellphone of some kind and 77% own a smartphone.[5]

The use of passive data collection from smartphone devices can provide granular information relevant to psychiatric, aging, frailty,[6] and other illness phenotypes.[7] Types of relevant passive data include GPS data to monitor spatial location, accelerometer data to record movement and gross motor activity, and call and messaging logs to document social engagement with others.[8] Passively collected data may also support clinical differentiation between diagnostic groups [9] and monitoring mental health symptoms. [10] [11]

The related term 'digital phenotype' was introduced in Nature Biotechnology by Sachin H. Jain and John Brownstein in 2015.[12]

Research platforms and commercialization

One of the first implementations of digital phenotyping on smart phones was the Funf Open Sensing Framework, developed at the MIT Media Lab and launched on October 5, 2011.[13] Members of the Funf team interested in profiling and predicting human behavior formed a commercial venture called Behavio in 2012.[14] In April 2013, it was announced that the Behavio team had joined Google.[15] The Funf platform has inspired other mobile phone sensor logging platforms for psychology and behavior applications, such as the Purple Robot platform, developed by the CBITS (Center for Behavioral Intervention Technologies) at Northwestern University in 2012,[16] which has since expanded and remains an active GITHUB project.

Among the academic research community, there are now many digital phenotyping platforms. Popular open-source digital phenotyping platforms include Beiwe which was developed in the Onnela lab at Harvard School of Public Health in 2013.[17] Others include AWARE, EARS,[18] mindLAMP,[19] RADAR-CNS among others and there is currently no metric to determine which is most popular.

In terms of commercialization, in 2017, former head of the National Institutes of Mental Health, Tom Insel, joined Rick Klausner and Paul Dagum to form the founding team of MindStrong Health, which uses digital phenotyping methods combined with machine learning to develop new paradigms for mental health assessment and development of new digital biomarkers for mental health.[20] As of 2021 the company's website does not mention digital phenotyping.

Criticisms

The widespread adoption of digital phenotyping across diverse research domains necessitates robust methodological guidelines. Passive data collection, a cornerstone of this approach, poses a significant challenges at every stage of the research process.[21] [22] [23] From the outset, researchers grapple with clearly defining the constructs under investigation, a task complicated by the obscure nature of digital phenomena.[24] [25] [26] Subsequent decisions about data capture devices, applications, and cleaning protocols further amplify the complexity. The analysis phase introduces another layer of challenges, particularly when employing computationally demanding techniques such as machine learning. Optimizing model performance through careful data partitioning and hyperparameter tuning is essential but requires essential knowledge.[27] Recently published templates aim to address these challenges by providing standardized approaches to digital phenotyping research, potentially facilitating greater consistency and comparability across studies.[28]

See also

Further reading

Notes and References

  1. Onnela. Jukka-Pekka. Rauch. Scott L.. June 2016. Harnessing Smartphone-Based Digital Phenotyping to Enhance Behavioral and Mental Health. Neuropsychopharmacology. en. 41. 7. 1691–1696. 10.1038/npp.2016.7. 0893-133X. 4869063. 26818126.
  2. Torous. John. Kiang. Mathew V. Lorme. Jeanette. Onnela. Jukka-Pekka. 2016-05-05. New Tools for New Research in Psychiatry: A Scalable and Customizable Platform to Empower Data Driven Smartphone Research. JMIR Mental Health. 3. 2. e16. 10.2196/mental.5165. 2368-7959. 4873624. 27150677 . free .
  3. Web site: Brown. Karen. 2016-07-19. Your phone knows how you feel. 2019-11-13. Harvard Public Health Magazine. en-us.
  4. Web site: U.S. Smartphone Use in 2015. Smith. Aaron. 2015-04-01. Pew Research Center: Internet, Science & Tech. 2017-06-27.
  5. News: Mobile Fact Sheet. 2017-01-12. Pew Research Center: Internet, Science & Tech. 2017-06-27. en-US.
  6. Pyrkov. Timothy V.. Getmantsev. Evgeny. Zhurov. Boris. Avchaciov. Konstantin. Pyatnitskiy. Mikhail. Menshikov. Leonid. Khodova. Kristina. Gudkov. Andrei V.. Fedichev. Peter O.. 2018-10-26. Quantitative characterization of biological age and frailty based on locomotor activity records. Aging. en. 10. 10. 2973–2990. 10.18632/aging.101603. 1945-4589. 6224248. 30362959.
  7. Gillett. George. 2020. A day in the life of a psychiatrist in 2050: where will the algorithm take us?. BJPsych Bulletin. en. 44. 3. 121–123. 10.1192/bjb.2020.22. 33861188. 8170007. free.
  8. Torous. John. Staples. Patrick. Onnela. Jukka-Pekka. 2015-08-01. Realizing the Potential of Mobile Mental Health: New Methods for New Data in Psychiatry. Current Psychiatry Reports. en. 17. 8. 61. 10.1007/s11920-015-0602-0. 1523-3812. 4608747. 26073363.
  9. Gillett. George. McGowan. Niall. Palmius. Niclas. Bilderbeck. Amy. Goodwin. Guy. Saunders. Kate. 2021. Digital Communication Biomarkers of Mood and Diagnosis in Borderline Personality Disorder, Bipolar Disorder, and Healthy Control Populations. Frontiers in Psychiatry. 12. 610457. 610457. 10.3389/fpsyt.2021.610457. 33897487. 8060643. 1664-0640. free.
  10. Braund . Taylor A. . Zin . May The . Boonstra . Tjeerd W. . Wong . Quincy J. J. . Larsen . Mark E. . Christensen . Helen . Tillman . Gabriel . O’Dea . Bridianne . 2022-05-04 . Smartphone Sensor Data for Identifying and Monitoring Symptoms of Mood Disorders: A Longitudinal Observational Study . JMIR Mental Health . EN . 9 . 5 . e35549 . 10.2196/35549. 35507385 . 9118091 . 247962553 . free .
  11. Braund . Taylor A. . O’Dea . Bridianne . Bal . Debopriyo . Maston . Kate . Larsen . Mark E. . Werner-Seidler. Aliza . Tillman . Gabriel . Christensen . Helen . 2023-05-15 . Associations Between Smartphone Keystroke Metadata and Mental Health Symptoms in Adolescents: Findings From the Future Proofing Study . JMIR Mental Health . EN . 10 . e44986 . 10.2196/44986. 37184904. 10227695 . free.
  12. Jain. Sachin H. Powers. Brian W. Hawkins. Jared B. Brownstein. John S. 2015. The digital phenotype. Nature Biotechnology. 33. 5. 462–463. 10.1038/nbt.3223. 1087-0156. 25965751. 2318642.
  13. Web site: Funf Blog. 2021-01-22. funf-blog.blogspot.com.
  14. Web site: Knight Foundation Bets Mobile Sensor Startup, Behav.io, Is The Future of Journalism. 2021-01-22. TechCrunch. 18 June 2012 . en-US.
  15. Web site: D'Orazio. Dante. 2013-04-12. Google gains team behind Behavio, a startup that uses smartphone data to make predictions. 2021-01-22. The Verge. en.
  16. Web site: 2015-07-16. Your smartphone knows when you're depressed. 2021-01-22. The Daily Dot. en-US.
  17. Web site: Digital Phenotyping and Beiwe Research Platform. 2021-01-22. Onnela Lab. 21 July 2017 . en-us.
  18. Lind. Monika N.. Byrne. Michelle L.. Wicks. Geordie. Smidt. Alec M.. Allen. Nicholas B.. July 2018. The Effortless Assessment of Risk States (EARS) Tool: An Interpersonal Approach to Mobile Sensing. JMIR Mental Health. en. 5. 3. e10334. 10.2196/10334. 30154072. 6134227 . free .
  19. Torous. John. Wisniewski. Hannah. Bird. Bruce. Carpenter. Elizabeth. David. Gary. Elejalde. Eduardo. Fulford. Dan. Guimond. Synthia. Hays. Ryan. Henson. Philip. Hoffman. Liza. 2019-06-01. Creating a Digital Health Smartphone App and Digital Phenotyping Platform for Mental Health and Diverse Healthcare Needs: an Interdisciplinary and Collaborative Approach. Journal of Technology in Behavioral Science. en. 4. 2. 73–85. 10.1007/s41347-019-00095-w. 150589575. 2366-5963. free.
  20. Web site: 2017-05-11. Former Director of the National Institute of Mental Health, Dr. Thomas Insel, Joins Mindstrong Health as President and Co-Founder. 2021-01-22. Mindstrong Health. en-US.
  21. Davidson . Brittany I. . 2022-01-01 . The crossroads of digital phenotyping . General Hospital Psychiatry . 74 . 126–132 . 10.1016/j.genhosppsych.2020.11.009 . 33653612 . 0163-8343.
  22. Hicks . Jennifer L. . Althoff . Tim . Sosic . Rok . Kuhar . Peter . Bostjancic . Bojan . King . Abby C. . Leskovec . Jure . Delp . Scott L. . 2019-06-03 . Best practices for analyzing large-scale health data from wearables and smartphone apps . npj Digital Medicine . en . 2 . 1 . 45 . 10.1038/s41746-019-0121-1 . 2398-6352 . 6550237 . 31304391.
  23. Velozo . Joana De Calheiros . Habets . Jeroen . George . Sandip V. . Niemeijer . Koen . Minaeva . Olga . Hagemann . Noëmi . Herff . Christian . Kuppens . Peter . Rintala . Aki . Vaessen . Thomas . Riese . Harriëtte . Delespaul . Philippe . January 2024 . Designing daily-life research combining experience sampling method with parallel data . Psychological Medicine . en . 54 . 1 . 98–107 . 10.1017/S0033291722002367 . 36039768 . 0033-2917.
  24. Huckvale . Kit . Venkatesh . Svetha . Christensen . Helen . 2019-09-06 . Toward clinical digital phenotyping: a timely opportunity to consider purpose, quality, and safety . npj Digital Medicine . en . 2 . 1 . 88 . 10.1038/s41746-019-0166-1 . 2398-6352 . 6731256 . 31508498.
  25. Mohr . David C. . Zhang . Mi . Schueller . Stephen M. . 2017-05-08 . Personal Sensing: Understanding Mental Health Using Ubiquitous Sensors and Machine Learning . Annual Review of Clinical Psychology . en . 13 . 1 . 23–47 . 10.1146/annurev-clinpsy-032816-044949 . 1548-5943 . 6902121 . 28375728.
  26. Langener . Anna M. . Stulp . Gert . Kas . Martien J. . Bringmann . Laura F. . 2023-03-17 . Capturing the Dynamics of the Social Environment Through Experience Sampling Methods, Passive Sensing, and Egocentric Networks: Scoping Review . JMIR Mental Health . EN . 10 . 1 . e42646 . 10.2196/42646 . free . 10132048 . 36930210.
  27. Yang . Li . Shami . Abdallah . 2020-11-20 . On hyperparameter optimization of machine learning algorithms: Theory and practice . Neurocomputing . 415 . 295–316 . 10.1016/j.neucom.2020.07.061 . 2007.15745 . 0925-2312.
  28. Langener . Anna M. . Siepe . Björn S. . Elsherif . Mahmoud . Niemeijer . Koen . Andresen . Pia K. . Akre . Samir . Bringmann . Laura F. . Cohen . Zachary D. . Choukas . Nathaniel R. . Drexl . Konstantin . Fassi . Luisa . Green . James . Hoffmann . Tabea . Jagesar . Raj R. . Kas . Martien J. H. . 2024-08-07 . A template and tutorial for preregistering studies using passive smartphone measures . Behavior Research Methods . en . 10.3758/s13428-024-02474-5 . 39112740 . 1554-3528. free .