News | Samprit Banerjee Lab

Invited Session at ICHPS

Drs. Samprit Banerjee, Wenna Xi, Jyotishman Pathak, Soohyun Kim, and Younghoon Kim presented at the 2025 International Conference on Health Policy Statistics (ICHPS) Statistical Innovation to Improve Health Equity on January 8th. The session was titled "Maximizing reach of mental health interventions through methodological advances with big and small data: A perspective from Weill Cornell ALACRITY Center."

ICHPS Presentation

In this session, they presented methodological research that has been developed in the context of mid-/late-life depression in an NIMH-funded ALACRITY Center (P50 MH113838). The Center's focus is to develop simplified mental health interventions that can be delivered by community clinicians. These interventions are augmented with digital technology (e.g., smartphones, wearables) and guided by big data analysis that identifies target populations of unmet need. Taken together, the goal of the Center is to shorten the timeline of intervention development to delivery in the community and rapidly inform policy for payment and adoption of these interventions. To support the goals of this Center, the Methods Core is tasked with methodological developments to chart new directions of research in mental health interventions. Specifically, they demonstrated how novel methodologies with "big" (e.g, electronic health records, health insurance claims, clinical notes) and "small" (e.g., data generated actively and passively through mHealth devices such as wearables, smartphones) data can identify populations with unmet need and deliver socially contextual mental health interventions with greater reach. The five presentations were: 1. Overview of methodological focus of the Weill Cornell ALACRITY Center (Presenter: Samprit Banerjee) 2. Predicting preventable and psychiatric hospitalizations in late middle-aged adults with depression (Presenter: Wenna Xi) 3. Words matter: Use of stigmatizing language in clinical notes of patients with opioid use disorder (Presenter: Jyotishman Pathak) 4. Targeted interventions and health policies through identification of patient subtypes with active mHealth data (Presenter: Soohyun Kim) 5. Detecting emotionally stressful periods from passive sensing data via mHeath devices (Presenter: Younghoon Kim).

ICHPS Logo

WCM hosted the 2024 Thomas R. Ten Have Symposium on Statistics in Mental Health on June 28th

Conference History & Overview

Thomas R. Ten Have Symposium to Take Place in May | Amstat News

The 11th Annual Thomas R. Ten Have Symposium on Statistics in Mental Health continues the annual Columbia-Cornell-NYU-Penn-Yale Symposium and is jointly sponsored by the five universities. The idea for a forum on statistics in psychiatry arose in 1998 from informal discussions among Eva Petkova, Ray Carroll, and Tom Ten Have, when Eva visited Ray Carroll at the University of Pennsylvania, where he was a visiting faculty member. The first forum took place in 1999 at the New York State Psychiatric Institute as an informal joint forum with participating statisticians from Columbia University and University of Pennsylvania. Between 1999 and 2003 the forum location rotated between Columbia University and University of Pennsylvania, with each forum consisting of two one-hour presentations on statistics in psychiatry by a member from each school and then ample time for informal discussions before happy hour. In 2004, Yale University joined as the third participating institution. In 2007, New York University became the fourth participating site, and the forum was renamed to symposium in acknowledgement of the growing size and outreach of the event. The symposium continued to expand with adding Cornell University as another participating institution.

In 2001, Thomas Ten Have passed away. To honor his founding role in the symposium and his many contributions to the field of statistics in psychiatry and the broader statistics profession, the symposium was renamed to Tom R. Ten Have Symposium on Statistics in Psychiatry (TTH Symposium). The 2012 symposium was the first renamed TTH symposium, took place at the University of Pennsylvania and culminated in the Ten Have Memorial Lecture given by Professor C. Hendricks Brown. In 2013, the Statistics in Mental Health Section (MHS) of the American Statistical Association and the TTH organizers from the participating universities agreed to jointly sponsor the event.

Agenda

The 2024 Thomas R. Ten Have Symposium on Statistics in Mental Health is scheduled for June 28th at the 3nd floor conference room of the Belfer Research Building (413 E 69th St, New York, NY 10021) in the Upper East Side Campus of Weill Cornell Medicine in NYC.

11:00 – 11:15: Introductory Remarks

11:15 – 12:00: Keynote Address by Dr. Raaz Dwivedi

Affiliation: Assistant Professor, Cornell Tech and Cornell University

Title: "Integrating Double Robustness into Causal Latent Factor Models"

12:00 – 12:30: Invited Speaker: Tse-Hwei Choo

Affiliation: Staff Associate, Columbia University

Title: "RNNs as a Tool for EMA Data Analysis of Suicidal Ideation"

12:30 – 01:30: Lunch (provided)

01:30 – 02:00: Invited Session: Dr. Xiaomeng Ju

Affiliation: Postdoctoral Associate, New York University

Title: "Bayesian scalar-on-network regression with applications to brain functional connectivity"

02:00 – 02:30: Invited Session: Dr. Geyu Zhou

Affiliation: Postdoctoral Associate, Yale University

Title: “Polygenic Prediction of Mental Health Outcomes”

02:30 – 02:50: Coffee Break

02:50 – 03:20: Invited Session: Dr. Nicholas J. Seewald

Affiliation: Assistant Professor, University of Pennsylvania

Title: "Target Trial Emulation for Evaluating Mental Health Policy"

03:20 – 03:50: Invited Session: Dr. Younghoon Kim

Affiliation: Postdoctoral Associate, Cornell University and Weill Cornell Medicine

Title: "Detecting emotionally stressful periods from passive sensing data via mobile devices"

03:50 – 04:20: Speed Presentation Session (6: 5-minute slots)

04:20 – 05:30: Poster Session with Refreshments

06:00 - 08:00: Dinner

Public Transportation (within New York City) - the Belfer Research Building (413 E 69th St, New York, NY 10021) in the Upper East Side Campus of Weill Cornell Medicine is directly accessible through multiple public transit options

Subway – 6 train to East 68th Street – 10-15 minute walk (best option from Grand Central Terminal)
Subway – Q train to 72nd Street-2nd Avenue – 5-10 minute walk (best option from Penn Station)
Bus (M31 to the East 69th Street stop) - 1 minute walk
Bus (M66 and M72 crosstown buses) - 1 minute walk

Presentation at ENAR 2024

Dr. Younghoon Kim gave a presentation at the Eastern North American Region International Biometric Society Spring 2024 Meeting: ENAR – A Home for Every Biostatistician on March 11th in Baltimore, Maryland. His presentation was titled 'Detecting Emotionally Stressful Periods from Passive Sensing Data via Mobile Devices.'

Younghoon presenting at ENAR

Here is the abstract from his presentation: It is crucial for psychotherapy to prevent the negative effects of emotional stress in middle-aged and older adults with chronic pain and depression by detecting the early onset of stressful periods. This study proposes a data-driven emotional stress detection algorithm. The algorithm identifies participants' onset of emotionally stressful periods using passive sensing data related to physical activities, such as step counts and activity duration. The algorithm consists of three separate parts. Firstly, it estimates the time points of changes in the distributions of passive sensing data. Then, the algorithm validates whether the detected changes are statistically associated with changes in the response variable, constructed from self-reported stress levels and stress-related scores. Finally, the algorithm trains a classifier to predict whether the patient is in a stress period at future time points using statistical and physical features computed from each segmented passive sensing data. The algorithm is applied to the ALACRITY Phase 1 data, and its prediction performance and the effectiveness of each step are evaluated using various metrics.

ENAR Banner

Presentation at AAGP 2024

Yuqing Qiu presented in the New Research Oral Presentation session on March 18th 2024 at the American Association for Geriatric Psychiatry (AAGP) Annual Meeting: Reimagining Geriatric Mental Health: Innovations to promote the well-being of patients and caregivers in Atlanta, Georgia. Her presentation was titled 'Gamification via mHealth to Improve Adherence to Psychotherapy and Clinical Outcomes in Depressed Older Adults.

Yuqing presenting at AAGP

Isabel Rollandi from WCM's Deparment of Geriatric Psychiatry also presented at this session, titled 'Suicidal Ideation and Treatment Response Among Depressed Elder Abuse Victims,' a collaboration with our team.

Presentation at UAB Biostatistics Seminar Series 2023

Dr. Samprit Banerjee gave a presenation at the University of Alabama at Birmingham School of Public Health as part of their Biostatistics Seminar Series on November 17th. His presentation was titled 'mHealth in Mental Health: What Smartphones Can Tell Us About Our Mental Health?'

Presentation at the 2023 Thomas R. Ten Have Symposium on Statistics in Mental Health

Dr. Wenna Xi presented on June 9th at the 10th Annual Thomas R. Ten Have Symposium on Statistics in Mental Health in Boston, Massachusetts hosted by the Mental Health Statistics Section of the American Statistical Association, McLean Hospital, and Harvard Medical School. Her presentation was titled 'Analysis of Big Data in Mental Health Research: Opportunities and Challenges.'

Wenna presenting at Tom Ten Have

Tom Ten Have Banner

Presentation at CMStatistics 2023

Dr. Samprit Banerjee gave a presentation at the 16th International Conference of the ERCIM WG on Computational and Methodological Statistics (CMStatistics) on December 16th in Berlin, Germany. His presentation was called 'Semi-supervised learning to predict adherence to psychotherapy with mHealth data.'

CMStatistics Banner

Here is the abstract from his presentation: Smartphones provide an interactive interface that can passively measure various aspects of the users' behaviour from device sensors and actively collect self-ratings (e.g., mood, stress, etc.) obtained via daily ecological momentary assessment. Taken together with traditional clinical assessments, these measures have the potential to provide unique insight into the treatment trajectories of patients with major depressive disorder undergoing psychotherapeutic treatment. Specifically, patient adherence to psychotherapy sessions is a necessary first step to assess barriers to adherence and personalize future sessions in order to improve adherence and, therefore, efficacy. Such predictions have unique challenges due to the noisy nature (missing or under-reporting) of passive and active mHealth data. The nature of missing passive data is unique in the sense that the missed labels are not observed. These and other challenges of mHealth data analysis are introduced, and semi-supervised machine learning algorithms are proposed to address these challenges.