The Banerjee Lab focuses on data from smartphones and other digital wearable devices, the development of digital applications and interventions for mental health using mHealth data, predictors of health outcomes using big data, and clinical trials in mental and behavioral health.
Research
Our lab focuses on developing technology tailored to a population, statistical and machine learning methods to pre-process and analyze mHealth data, and adapting models for digital interventions. We have expertise in digital phenotyping and digital interventions with mHealth data, predictors of health outcomes with big data, identifying sub-groups of treatment responders using machine learning, clinical trials in mental and behavioral health, and multivariate methodology. The lab uses a cross-platform mHealth app development infrastructure to create digital interventions efficiently and at scale.
We have developed a statistical framework and produced open-source software to analyze the massive amount of longitudinal data from wearable and smartphone devices collected in research studies from individuals in their natural environments. We are also developing predictive models on various health outcomes. Through our collaborations with the Institute of Geriatric Psychiatry and ALACRITY Research Center, we have designed and analyzed several randomized trials (including randomized cluster trials) that studied various behavioral interventions, psychotherapies, drugs, and home care management interventions on older adults with depression, psychosis, and bipolar disorder. Our team aims to understand the interplay between multiple correlated outcomes in determining treatment efficacy, mediating treatment effect, and discovering patient sub-groups. This information could be beneficial in predicting treatment effects based on baseline characteristics. We also employ passive sensing data to assess fluctuations in daily functioning in real-time during psychotherapy, work that seeks to promote treatment optimization and improve clinical outcomes.
Current Projects:
- Technology dRiven Enhancement to Engage & Connect (WCM IRB #2404027370)
- PATH-Pain: A Primary Care-Based Psychosocial Intervention To Improve Cognitive and Depression Outcomes in Older Adults with MCI and Early Stage AD (R33MH128516-03)
- Ecological Momentary Assessment to Improve Symptom Management in Palliative Care (K76 AG083287-01A1)
- Gamification to Improve Psychotherapy Adherence and Clinical Outcomes in Depressed Older Adults
- Adherence to Psychotherapy Prediction using Passive and Active Data
- Passive Sensing Activity Levels and Behavioral Activation in Psychotherapies for Late Life Depression
- Algorithms for Processing Passively-Sensed mHealth Data
- Stress Detection using Passively-Sensed mHealth Data
Bio
Dr. Samprit Banerjee received his BStat and MStat from the Indian Statistical Institute, Kolkata, India. He went on to obtain his PhD in biostatistics from the University of Alabama, Birmingham. He has been working at Weill Cornell Medicine in the Division of Biostatistics since 2008, first in the Department of Public Health, then the Department of Healthcare Policy and Research, and currently the Department of Population Health Sciences. He has experience as a biostatistician in biomedical collaborations, which range from randomized clinical trials, observational cohort studies, comparative effectiveness research, analysis of mHealth data (smartphones and wearables), analysis of big data (EHR, claims, large registries and cohorts), statistical genetics, and cancer genomics.
Selected Publications:
- Banerjee S, Wu Y, Bingham KS, Marino P, Meyers BS, Mulsant BH, Neufeld NH, Oliver LD, Power JD, Rothschild AJ, Sirey JA, Voineskos AN, Whyte EM, Alexopoulos GS, Flint AJ; STOP-PD II Study Group. Trajectories of remitted psychotic depression: identification of predictors of worsening by machine learning. Psychol Med. 2023 Oct 11:1-10. doi: 10.1017/S0033291723002945. Epub ahead of print. PMID: 37818656.
- Goyal P, Schenck E, Wu Y, Zhang Y, Visaria A, Orlander D, Xi W, Díaz I, Morozyuk D, Weiner M, Kaushal R, Banerjee S⇞. Influence of social deprivation index on in-hospital outcomes of COVID-19. Sci Rep. 2023 Jan 31;13(1):1746. doi: 10.1038/s41598-023-28362-0. PMID: 36720999; PMCID: PMC9887560.
- Mauer E, Lee J, Choi J, Zhang H, Hoffman K, Easthausen I, Rajan M, Weiner M, Kaushal R, Safford M, Steel P, Banerjee S⇞ (2021) A predictive model of clinical deterioration among hospitalized COVID-19 patients by harnessing hospital course trajectories. J Biomed Inform. 2021 Apr 30;118:103794. doi: 10.1016/j.jbi.2021.103794. Epub ahead of print. PMID: 33933654; PMCID: PMC8084618.
- Banerjee S, Monni S. An Orthogonally Equivariant Estimator of the Covariance Matrix in High Dimensions and for Small Sample Sizes. J Stat Plan Inference. 2021 Jul;213:16-32. doi: 10.1016/j.jspi.2020.10.006. Epub 2020 Nov 16. PMID: 33281277; PMCID: PMC7709931.
- Flint AJ, Meyers BS, Rothschild AJ, Whyte EM, Alexopoulos GS, Rudorfer MV, Marino P, Banerjee S⧫, Pollari CD, Wu Y, Voineskos AN, Mulsant BH; STOP-PD II Study Group. Effect of Continuing Olanzapine vs Placebo on Relapse Among Patients With Psychotic Depression in Remission: The STOP-PD II Randomized Clinical Trial. JAMA. 2019 Aug 20;322(7):622-631. doi: 10.1001/jama.2019.10517. PubMed PMID:31429896.
- Qiu Y, Carter E, Benda N, Sirey JAnne, Kim S, Kim Y, Yu Z, Kiosses D, Marino P, Gunning F et al.. 2025. Improving Adherence to Psychotherapy and Clinical Outcome in Patients With Late-Life Depression Through Gamified mHealth Technology.. Am J Geriatr Psychiatry.
- Kim Y, Basu S, Banerjee S. 2025. A Co-Segmentation Algorithm to Predict Emotional Stress From Passively Sensed mHealth Data.. Stat Med. 44(10-12):e70099.
- Zhang H, Diaz JL, Kim S, Yu Z, Wu Y, Carter E, Banerjee S. 2024. 2SpamH: A Two-Stage Pre-Processing Algorithm for Passively Sensed mHealth Data.. Sensors (Basel). 24(21).