Elombe Calvert
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Elombe Calvert has a total of 29 co-authors. Here are the top co-authors by number of shared publications:
- John Torous
Beth Israel Deaconess Medical Center, Harvard Medical School, Boston, MA, USA
6 shared publications - Shrutangi Vaidya
Department of Psychiatry, Beth Israel Deaconess Medical Center, Boston, USA
2 shared publications Allison Oh
1 shared publicationAndrew Jin Soo Byun
1 shared publication- Caroline M. Swords
Department of Counseling Psychology, University of Wisconsin-Madison, Madison, USA
1 shared publication Catherine Lager
Department of Psychiatry, Beth Israel Medical Deaconess Center, Boston, MA, USA
1 shared publication
Latest Publications
- Open Access
- 12 September 2026
- Published by JMIR Publications Inc. in JMIR Preprints
Network Analysis in Digital Phenotyping for Mental Health: A Scoping Review (Preprint)
BACKGROUND Despite the rapid expansion of digital phenotyping research, findings remain heterogeneous, with digital phenotyping features showing only modest and inconsistent associations with clinical outcomes. One important reason is that commonly used aggregation-based descriptive and correlational approaches often overlook the temporal dynamics embedded in digital phenotyping data. This has motivated growing interest in network analysis to pair with digital phenotyping, as it enables the modeling of dynamic, within-person interplay among relevant symptoms, behaviors, and contextual factors. However, no scoping review, to our knowledge, has examined the application of network analysis within digital phenotyping research for mental health, despite its theoretical and clinical potential. OBJECTIVE This scoping review aims to synthesize empirical network-based digital phenotyping studies in the mental health field. More specifically, it aims to identify methodological patterns, limitations, and gaps across four domains: 1) study characteristics, 2) digital phenotyping design, 3) network method characteristics, and 4) analytic applications. METHODS Following the PRISMA Extension for Scoping Reviews, this scoping review searched PubMed/MEDLINE, Scopus, Web of Science Core Collection, and PsycINFO (EBSCO) databases. After independent title-and-abstract and full-text screening by two reviewers, 25 data fields were independently extracted from each included study by two reviewers. Finally, descriptive synthesis summarized each extracted field using counts and percentages. RESULTS Among the 1,851 records from database searches, 123 studies published between 2016 and 2026 were finally included. Most samples were young and middle-aged adults from a small set of high-income countries. Active ecological momentary data were included as nodes in all included studies, while passive sensing data were incorporated in only 7.3% of studies. Dynamic multivariate vector autoregressive (VAR) approaches stood out as the dominant method family (74.8%), concentrating on multi-level model fitting and time-invariant parameter estimation. Finally, 91.1% of the studies used network models to describe symptom dynamics or structure, whereas prediction, causal discovery, and clinical application remain rare. CONCLUSIONS The integration of digital phenotyping and network analysis is growing in mental health research, but its broader potential is yet to be realized. Current evidence is concentrated in younger and middle-aged populations in high-income countries, and the predominant approach is to estimate time-invariant VAR models on active self-report data. Future research should therefore broaden population representation and integrate more passive behavioral, physiological, and contextual data to comprehensively map the symptom networks. Also, while group-level and multilevel VAR models have more lenient data requirements, person-specific and time-varying models may better capture individual heterogeneity and evolving symptom dynamics, although their application requires sufficient sampling density and longer observation periods to achieve reliable estimates. Finally, future research should move beyond descriptive analyses toward predictive and causal approaches that better support clinical translation, including risk forecasting, personalized intervention, and clinical decision-making.
- 12 September 2026
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessNetwork Analysis in Digital Phenotyping for Mental Health: A Scoping Review (Preprint)
BACKGROUND Despite the rapid expansion of digital phenotyping research, findings remain heterogeneous, with digital phenotyping features showing only modest and inconsistent associations with clinical outcomes. One important reason is that commonly used aggregation-based descriptive and correlational approaches often overlook the temporal dynamics embedded in digital phenotyping data. This has motivated growing interest in network analysis to pair with digital phenotyping, as it enables the modeling of dynamic, within-person interplay among relevant symptoms, behaviors, and contextual factors. However, no scoping review, to our knowledge, has examined the application of network analysis within digital phenotyping research for mental health, despite its theoretical and clinical potential. OBJECTIVE This scoping review aims to synthesize empirical network-based digital phenotyping studies in the mental health field. More specifically, it aims to identify methodological patterns, limitations, and gaps across four domains: 1) study characteristics, 2) digital phenotyping design, 3) network method characteristics, and 4) analytic applications. METHODS Following the PRISMA Extension for Scoping Reviews, this scoping review searched PubMed/MEDLINE, Scopus, Web of Science Core Collection, and PsycINFO (EBSCO) databases. After independent title-and-abstract and full-text screening by two reviewers, 25 data fields were independently extracted from each included study by two reviewers. Finally, descriptive synthesis summarized each extracted field using counts and percentages. RESULTS Among the 1,851 records from database searches, 123 studies published between 2016 and 2026 were finally included. Most samples were young and middle-aged adults from a small set of high-income countries. Active ecological momentary data were included as nodes in all included studies, while passive sensing data were incorporated in only 7.3% of studies. Dynamic multivariate vector autoregressive (VAR) approaches stood out as the dominant method family (74.8%), concentrating on multi-level model fitting and time-invariant parameter estimation. Finally, 91.1% of the studies used network models to describe symptom dynamics or structure, whereas prediction, causal discovery, and clinical application remain rare. CONCLUSIONS The integration of digital phenotyping and network analysis is growing in mental health research, but its broader potential is yet to be realized. Current evidence is concentrated in younger and middle-aged populations in high-income countries, and the predominant approach is to estimate time-invariant VAR models on active self-report data. Future research should therefore broaden population representation and integrate more passive behavioral, physiological, and contextual data to comprehensively map the symptom networks. Also, while group-level and multilevel VAR models have more lenient data requirements, person-specific and time-varying models may better capture individual heterogeneity and evolving symptom dynamics, although their application requires sufficient sampling density and longer observation periods to achieve reliable estimates. Finally, future research should move beyond descriptive analyses toward predictive and causal approaches that better support clinical translation, including risk forecasting, personalized intervention, and clinical decision-making.
- Open Access
- 1 August 2026
- Published by Center for Open Science in PsyArXiv
Mental Health Benchmarks for Large Language Models: A Systematic Scoping Review
Large language models (LLMs) are increasingly used for mental health support, yet standards for evaluating their safety and competence remain unsettled. Benchmarks, standardized tests with predetermined scoring criteria, are the most common evaluation approach, but this landscape has not been systematically mapped. In this systematic scoping review, we searched four databases, machine-learning repositories, and grey literature through February 2026 and identified 173 publicly available mental health benchmarks for LLMs, extracting 48 fields covering what each benchmark measures, how it was constructed, and how performance is evaluated. The field has grown sharply recently, with more than 70% of benchmarks appearing in 2024 or later, but remains shaped by data availability rather than clinical relevance. Risk and safety, diagnosis, and therapeutic skills dominate, while bias and stigma are nearly absent. Social media and LLM-simulated content are the leading data sources, and data drawn from clinical care are rare. Ethical and methodological safeguards, including ethics review, demographic reporting, human baselines, and hidden test sets, were reported infrequently. Nearly half of the benchmarks involve an LLM in generating items, annotating labels, or judging outputs, a share that reached 90% of new releases by 2026. Shared reporting standards, clinically grounded data, and stronger safeguards are needed for benchmark scores to support claims about safety and clinical capability in mental health care.
- 1 August 2026
- Published by Center for Open Science in PsyArXiv
Open AccessMental Health Benchmarks for Large Language Models: A Systematic Scoping Review
Large language models (LLMs) are increasingly used for mental health support, yet standards for evaluating their safety and competence remain unsettled. Benchmarks, standardized tests with predetermined scoring criteria, are the most common evaluation approach, but this landscape has not been systematically mapped. In this systematic scoping review, we searched four databases, machine-learning repositories, and grey literature through February 2026 and identified 173 publicly available mental health benchmarks for LLMs, extracting 48 fields covering what each benchmark measures, how it was constructed, and how performance is evaluated. The field has grown sharply recently, with more than 70% of benchmarks appearing in 2024 or later, but remains shaped by data availability rather than clinical relevance. Risk and safety, diagnosis, and therapeutic skills dominate, while bias and stigma are nearly absent. Social media and LLM-simulated content are the leading data sources, and data drawn from clinical care are rare. Ethical and methodological safeguards, including ethics review, demographic reporting, human baselines, and hidden test sets, were reported infrequently. Nearly half of the benchmarks involve an LLM in generating items, annotating labels, or judging outputs, a share that reached 90% of new releases by 2026. Shared reporting standards, clinically grounded data, and stronger safeguards are needed for benchmark scores to support claims about safety and clinical capability in mental health care.
- 17 April 2026
- Published by Elsevier in Computers in Human Behavior
- Vol. 182
Smartphone-derived phenotypes of social media use in young adults
- 17 April 2026
- Published by Elsevier in Computers in Human Behavior
- Vol. 182
Smartphone-derived phenotypes of social media use in young adults
- Open Access
A Novel Blended Hybrid Care Model for Maternal Mental Health: Cohort Study of Pregnant and Postpartum Patients
Background: Perinatal mood and anxiety disorders are the most common complications of pregnancy. Given the limited mental health resources, there is a need for novel treatment approaches. Though smartphone applications can increase access to evidence-based care, recent research highlights notable limitations, including varying quality and unclear effectiveness. Blended hybrid care models, which integrate synchronous telehealth services with asynchronous modalities (such as mobile apps), have emerged as an alternative. This pilot study evaluates one such model, the Digital Clinic, to determine its potential to bridge this critical treatment gap and compare outcomes to that of non-peripartum patients in the clinic. Methods: Pregnant and postpartum women referred for anxiety and depression received 8 weeks of synchronous, virtual, evidence-based CBT from a trained clinician. This treatment was complemented by the asynchronous use of the mindLAMP app, providing digital phenotyping, psychoeducation, and CBT skills, with the support of a Digital Navigator. The efficacy of the intervention was evaluated by comparing GAD-7 and PHQ-9 scores from intake to the end of treatment. Results: This secondary analysis included 13 peripartum women from a larger sample of 224 clinic patients. At intake, they reported a mean PHQ-9 score of 9.4 (SD=3.9) and a mean GAD-7 score of 11.69 (SD=6.0). After 8 weeks, participants reported statistically significant decreases of 4.14 points on the GAD-7 (p<.01) and 3.92 points on the PHQ-9 (p<.01). Effect sizes for these reductions were 0.74 (95% CI: 0.20, 1.28) for GAD-7 and 1.10 (95% CI: 0.29, 1.90) for PHQ-9. Conclusion: A novel blended hybrid care model, the Digital Clinic, was successful in reducing depression and anxiety among pregnant and postpartum women. This novel approach to maternal mental health shows promise for delivering accessible, effective, evidence-based care to peripartum patients in real-world settings. Future work should further validate its effectiveness with larger, more diverse patient populations with moderate to severe disease.
Open AccessA Novel Blended Hybrid Care Model for Maternal Mental Health: Cohort Study of Pregnant and Postpartum Patients
Background: Perinatal mood and anxiety disorders are the most common complications of pregnancy. Given the limited mental health resources, there is a need for novel treatment approaches. Though smartphone applications can increase access to evidence-based care, recent research highlights notable limitations, including varying quality and unclear effectiveness. Blended hybrid care models, which integrate synchronous telehealth services with asynchronous modalities (such as mobile apps), have emerged as an alternative. This pilot study evaluates one such model, the Digital Clinic, to determine its potential to bridge this critical treatment gap and compare outcomes to that of non-peripartum patients in the clinic. Methods: Pregnant and postpartum women referred for anxiety and depression received 8 weeks of synchronous, virtual, evidence-based CBT from a trained clinician. This treatment was complemented by the asynchronous use of the mindLAMP app, providing digital phenotyping, psychoeducation, and CBT skills, with the support of a Digital Navigator. The efficacy of the intervention was evaluated by comparing GAD-7 and PHQ-9 scores from intake to the end of treatment. Results: This secondary analysis included 13 peripartum women from a larger sample of 224 clinic patients. At intake, they reported a mean PHQ-9 score of 9.4 (SD=3.9) and a mean GAD-7 score of 11.69 (SD=6.0). After 8 weeks, participants reported statistically significant decreases of 4.14 points on the GAD-7 (p<.01) and 3.92 points on the PHQ-9 (p<.01). Effect sizes for these reductions were 0.74 (95% CI: 0.20, 1.28) for GAD-7 and 1.10 (95% CI: 0.29, 1.90) for PHQ-9. Conclusion: A novel blended hybrid care model, the Digital Clinic, was successful in reducing depression and anxiety among pregnant and postpartum women. This novel approach to maternal mental health shows promise for delivering accessible, effective, evidence-based care to peripartum patients in real-world settings. Future work should further validate its effectiveness with larger, more diverse patient populations with moderate to severe disease.
- Open Access
- 8 September 2025
- Published by Elsevier in International Psychogeriatrics
- Vol. 38 (2) , 100123
Barriers and facilitators to usability of a smartphone-based digital mental health tool in older adults: Insights from a secondary analysis of mindLAMP
- 8 September 2025
- Published by Elsevier in International Psychogeriatrics
- Vol. 38 (2) , 100123
Open AccessBarriers and facilitators to usability of a smartphone-based digital mental health tool in older adults: Insights from a secondary analysis of mindLAMP