Skip to main content
ABCT 2024 58th Annual Convention Main banner
Psychology Tools Ad
Final Program


Icon Legend
This session is not in your schedule.
This session is in your schedule. Click again to remove it.
Presentation Icons
Recorded Session
Recorded Session
Ticketed Session
Ticketed Session
Back
Evaluation ViewAttendees 5

Assessment
Symposia

Symposium 111 - New Research Findings in Digital Phenotyping of Psychological Phenomena

Sunday, November 17, 2024
8:30 AM – 10:00 AM EST
Location: Grand Ballroom A, Level 5, Downtown Marriott
CE: 1.5

Keywords: Technology / Mobile Health, Assessment, Depression
Level of Familiarity: Moderate
Recommended Readings: Stamatis, C.A., Meyerhoff, J., Meng, Y. et al. Differential temporal utility of passively sensed smartphone features for depression and anxiety symptom prediction: a longitudinal cohort study. npj Mental Health Res 3, 1 (2024). https://doi.org/10.1038/s44184-023-00041-y,  

Ren B, Balkind EG, Pastro B, Israel ES, Pizzagalli DA, Rahimi-Eichi H, Baker JT, Webb CA. Predicting states of elevated negative affect in adolescents from smartphone sensors: a novel personalized machine learning approach. Psychol Med. 2023 Aug;53(11):5146-5154. doi: 10.1017/S0033291722002161. Epub 2022 Jul 27. PMID: 35894246; PMCID: PMC10650966.

,  

Jacobson, N.C., Weingarden, H. & Wilhelm, S. Digital biomarkers of mood disorders and symptom change. npj Digital Med 2, 3 (2019). https://doi.org/10.1038/s41746-019-0078-0

,   Fedor S, Lewis R, Pedrelli P, Mischoulon D, Curtiss J, Picard RW. Wearable Technology in Clinical Practice for Depressive Disorder. N Engl J Med. 2023 Dec 28;389(26):2457-2466. doi: 10.1056/NEJMra2215898. PMID: 38157501.,   Pedrelli P, Fedor S, Ghandeharioun A, Howe E, Ionescu DF, Bhathena D, Fisher LB, Cusin C, Nyer M, Yeung A, Sangermano L, Mischoulon D, Alpert JE, Picard RW. Monitoring Changes in Depression Severity Using Wearable and Mobile Sensors. Front Psychiatry. 2020 Dec 18;11:584711. doi: 10.3389/fpsyt.2020.584711. PMID: 33391050; PMCID: PMC7775362.

Regular, accurate, and time-sensitive assessment is critical for prevention, early detection, and interventions for mental health symptoms. Yet, traditional clinician and self-report methods of assessment are burdensome for both providers and patients and are thus underutilized. One innovative approach to assessing psychological phenomena is digital phenotyping – that is, using passively collected data that does not require user input to model real-time psychological experiences of interest. Digital phenotyping data can include sensor and physiological data from smartphones or wearable devices and backend user-interaction data collected by digital interventions or apps.
In line with the 2024 conference theme and ABCT goal of innovation, this symposium presents new research from studies across academic and industry settings that use digital phenotyping to assess diverse psychiatric conditions. Our first talk will highlight findings from a study to develop and validate a measure of real-time cognitive change alongside use of a digital therapeutic in adults with MDD. Passively measured cognitive changes correlated significantly with a gold-standard behavioral measure of attention and cognition, showcasing a new, low-burden approach to measuring improvement across treatment. The second talk will highlight research using smartphone sensor data (e.g., GPS, accelerometer) to detect real-time negative emotion states in 87 adults with body dysmorphic disorder (BDD). Negative emotion states such as anxiety and shame are known risk factors for suicide in BDD. Thus, real-time passive detection of negative emotions is critical for developing just-in-time interventions to reduce risk in this serious condition. Our third presenter will discuss the feasibility of monitoring depression passively in an adult sample with MDD, by integrating multiple sensor and physiological data streams. The fourth talk will describe two studies that used passively-collected movement and sleep data to understand depression symptom variability using ensemble machine learning and deep learning approaches. The fifth talk highlights research using passive smartphone sensors to predict negative emotion states using a personalized machine learning approach in adults with depression; as a next step to this work, the authors intend to test just-in-time interventions based on predictions. Finally, our discussant - a leader in digital mental health - will conclude the symposium with highlights from the current presentations, real world implications of results, and next steps for this area of work. Altogether, this symposium will underscore the most current methods and use cases for accurate real-time passive assessment in psychology.

Learning Objectives:

At the end of this session, the learner will be able to:
  1. Discuss the feasibility and accuracy of using digital phenotyping approaches to assess depression, negative affect, and cognition.
  2. Describe the diverse data and features that can be used in digital phenotyping to make inferences about psychological phenomena.
  3. Explain current approaches to building and evaluating digital phenotyping computational models in psychology.
  4. Describe the promise, limitations, ethical considerations, and next steps in digital phenotyping research.
  5. Discuss digital phenotyping work that is being conducted in both academic and applied (industry) settings.

Presentations:

  • 8:30 AM – 10:00 AM EST
    (SYM 111) Detecting Peak Daily Shame in Body Dysmorphic Disorder Using Passive Smartphone Data

    Speaker: Hilary Weingarden, Ph.D. (she/her/hers) – Massachusetts General Hospital

    Co-author: Xiang Meng, MS – Harvard University

    Co-author: Adam Jaroszewski, Ph.D. – Massachusetts General Hospital

    Co-author: Caroline Armstrong, B.A. – Massachusetts General Hospital

    Co-author: Michael Armey, PhD – Warren Alpert Medical School of Brown University

    Co-author: Jukka-Pekka Onnela, DSc – Harvard T.H. Chan School of Public Health

    Co-author: Sabine Wilhelm, Ph.D. (she/her/hers) – Harvard Medical School

  • 8:30 AM – 10:00 AM EST
    (SYM 111) Leveraging Patient-device Interaction Data from AKL-T03, a Digital Therapeutic That Targets Attentional Control in Depression, to Measure Real-time Cognitive Change

    Speaker: Caitlin A. Stamatis, Ph.D. (she/her/hers) – Akili Interactive Labs

    Co-author: Andrew Heusser, PhD (he/him/his) – Akili Interactive Labs

    Co-author: Titiimaea Ala'ilima, MSE – Akili Interactive Labs

    Co-author: Jessica Flannery, PhD (she/her/hers) – Akili Interactive Labs

    Co-author: Tony Simon, PhD – Akili Interactive Labs

    Co-author: Scott Kollins, PhD (he/him/his) – Akili Interactive Labs

  • 8:30 AM – 10:00 AM EST
    (SYM 111) Integrating Digital Phenotyping and Deep Learning to Understand Depression Symptom Variability: A Longitudinal Approach Using Passively-collected Movement and Sleep Data

    Speaker: Nicholas C. Jacobson, Ph.D. (he/him/his) – Geisel School of Medicine, Dartmouth College

    Co-author: George Price, BS – Center for Technology and Behavioral Health, Geisel School of Medicine, Dartmouth College

    Co-author: Anna Langener, BS (she/her/hers) – University of Gronigen

    Co-author: Michael Heinz, MD (he/him/his) – Dartmouth College

    Co-author: Mathew Nemesure, PhD (he/him/his) – Harvard Business School

    Co-author: Daniel Mackin, Sr., Ph.D. – Dartmouth College

    Co-author: Amanda C. Collins, Ph.D. (she/her/hers) – Dartmouth College

    Co-author: Damien Lekkas, M.S. – Dartmouth College

    Co-author: Tess Z. Griffin, Ph.D., M.Ed. – Dartmouth College

    Co-author: Arvind Pillai, M.S. – Dartmouth College

    Co-author: Subigya Nepal, B.S. – Dartmouth College

    Co-author: Andrew Campbell, PhD (he/him/his) – Dartmouth College

  • 8:30 AM – 10:00 AM EST
    (SYM 111) Leveraging Artificial Intelligence for the Assessment of Severity of Depressive Symptoms

    Speaker: Paola Pedrelli, Ph.D. (she/her/hers) – Harvard Medical School

    Co-author: szymon Fedor, PhD (he/him/his) – Massachusetts Institute of Technology

    Co-author: Robert Lewis, MSc (he/him/his) – Massachussetts General Hospital

    Co-author: David Michoulon, MD (he/him/his) – Massachusetts General Hospital

    Co-author: Rosalind Picard, PhD – Massachusetts Institute of Technology

  • 8:30 AM – 10:00 AM EST
    (SYM 111) Harnessing Smartphone Data for Personalized Prediction of States of Heightened Negative Affect

    Speaker: Christian A. Webb, Ph.D. (he/him/his) – Harvard Medical School and McLean Hospital

    Co-author: Christian A. Webb, Ph.D. (he/him/his) – Harvard Medical School and McLean Hospital

    Co-author: Boyu Ren, PhD (he/him/his) – McLean Hospital & Harvard Medical School

    Co-author: Habiballah Rahimi Eichi, PhD – McLean Hospital & Harvard Medical School

    Co-author: Yoonho Chung, PhD – McLean Hospital & Harvard Medical School

    Co-author: Bryce Gillis, PhD – McLean Hospital & Harvard Medical School

    Co-author: Justin Baker, MD, PhD (he/him/his) – McLean Hospital & Harvard Medical School