Bipolar Disorder

State space model multiple imputation for missing data in non-stationary multivariate time series with application in digital psychiatry

FNIBI / Featured publications / Bipolar Disorder, Digital phenotyping, Ecological Momentary Assessment, Smartphone /

June 29, 2022

Mobile technology enables unprecedented continuous monitoring of an individual’s behavior, social interactions, symptoms, and other health conditions, presenting an enormous opportunity for therapeutic advancements and scientific discoveries regarding the etiology of psychiatric illness. Continuous collection of mobile data results in the generation of a new type of data: entangled multivariate time series of outcome, exposure, and covariates. Missing data is a pervasive problem in biomedical and social science research, and the Ecological Momentary Assessment (EMA) using mobile devices in psychiatric research is no exception. However, the complex structure of multivariate time series introduces new challenges in handling missing data for proper causal inference. Data imputation is commonly recommended to enhance data utility and estimation efficiency. The majority of available imputation methods are either designed for longitudinal data with limited follow-up times or for stationary time series, which are incompatible with potentially non-stationary time series.

For more information:

https://arxiv.org/abs/2206.14343

Linking bipolar disorders to metabolism through machine learning-based behavioral analysis

FNIBI / Past Projects / Bipolar Disorder, Metabolism, Motion Sequencing, Mouse Models /

April 1, 2022

In collaboration with the Harvard Brain Initiative Bipolar Seed Grant Program, the goals of this project were to use Motion Sequencing, an unsupervised behavioral discovery platform, to characterize the behavior of two mouse models of bipolar disorder in which behavioral deficits are linked to metabolic changes (hyperthyroid and AKAP11 deleted mice), and to characterize the behavior of patients with bipolar disorder in which endocrine and metabolic parameters are measured.

Context-Adaptive Multimodal Informatics for Psychiatric Discharge Planning

FNIBI / Current Projects / Actigraphy, Audio Diary Recording, Bipolar Disorder, Current Projects, Depression, Discharge Planning, Dyadic Recording, Ecological Momentary Assessment, Electronic Health Record, Facial Recording, Inpatient, Longitudinal, Road to Recovery, Schizophrenia, Smartphone, Social Signal Processing Algorithms /

January 1, 2022

Determining when a patient is ready for discharge is an open problem, as currently 20% of those hospitalized for psychiatric illness will be hospitalized again within 30 days. To address this issue, we are working to identify behavioral biomarkers for severe mental illness in 400 inpatients hospitalized for psychosis at McLean. The Multisense project is a collaboration with Dr. with LP Morency‘s team at Carnegie Mellon University, where information is extracted from both audio and video of both clinician and patient during a series of semi-structured inpatient interviews. Multimodal analysis techniques are used both to predict clinical scale and discharge-readiness scores, as well as to visualize a summary of each interview and extract relevant interpretable features.

Smartphone-Based Markers of Social Activity in Schizophrenia and Bipolar Disorder

FNIBI / Featured publications / Bipolar Disorder, Digital phenotyping, Schizophrenia, Smartphone /

March 23, 2021

The-link-between-artificial-intelligence-and-psychology.

Loneliness of Schizophrenia and Bipolar Disorder Patients in a Multi-Year mHealth Study is a research study recently published by members in the fNIBI lab.

Background

Social impairment and isolation are indicators of progression and predictors of relapse in psychiatric disorders. Little research has been done to measure these constructs using digital technologies in this population. We investigate the feasibility of collecting active and passive information about the social activity phenotype, in the long-term, using the Beiwe smartphone application.

Methods

Our study enrolled 47 patients with schizophrenia and bipolar disorder. Subjects completed daily surveys on digital and in-person social activity, and feeling outgoing or lonely. We described trends and variability of the mobile communication (passive) and survey (active) data streams. We conducted cluster analysis using dynamic time warping distance to explore the similarity of active and passive features of social activity.

For more information:

https://www.biologicalpsychiatryjournal.com/article/S0006-3223(21)00664-8/abstract

Computational Analysis of Spoken Language in Acute Psychosis and Mania

FNIBI / Featured publications / Bipolar Disorder, Facial Recording, Inpatient, Schizophrenia /

February 11, 2021

Objectives:

This study aimed to (1) determine the feasibility of collecting behavioral data from participants hospitalized with acute psychosis and (2) begin to evaluate the clinical information that can be computationally derived from such data.

Methods:

Behavioral data was collected across 99 sessions from 38 participants

recruited from an inpatient psychiatric unit. Each session started with a semi-structured interview modeled on a typical “clinical rounds” encounter and included administration of the Positive and Negative Syndrome

Scale (PANSS).

For more information:

https://osf.io/preprints/psyarxiv/zc47p

Neurogenetic analysis in unipolar and bipolar depression

FNIBI / Current Projects / Bipolar Disorder, Current Projects, Depression, Facial Recording, fMRI, Neurocognitive Tasks, Neuroimaging, Schizophrenia, SCID /

December 1, 2019

This is a neuroimaging study conducted in collaboration with Avram Holmes’ lab at Yale University focusing on neurogenetic factors related to unipolar and bipolar depression.

Circuit dynamics underlying longitudinal fluctuations in mood and cognition in bipolar patients

FNIBI / Current Projects / A Year in the Life, Actigraphy, Arterial Spin Labeling, Audio Diary Recording, Bipolar Disorder, Completed Projects, Depression, Dyadic Recording, Ecological Momentary Assessment, Eye-tracking, Facial Recording, Functional MRI, Neurocognitive Tasks, Neuroimaging, Schizophrenia, Smartphone, Social Signal Processing Algorithms /

January 1, 2018

Research on affective disorders, such as bipolar disorder, and on psychotic disorders is hampered by a lack of basic understanding of the course of dynamic circuit properties that might underlie fluctuations in mood and cognition.Bipolar and psychotic disorders at its core are unstable clinical conditions: at its extremes, it can result in periods of profound changes in mood and cognition (i.e., mania, major depression, and psychosis). And yet, remarkably little has been done to understand the basic mechanisms underlying the fluctuating course common to these individuals. We hope to better understand and characterize the natural course of changes in mood and cognition and associated environmental variables in individuals with severe affective and psychotic disorders using mobile behavioral technology. We believe that this will further enable advances in our understanding of how these disorders develop, paving the way for the development and evaluation of new treatment strategies.

Functional Biomarkers of Psychotic State, Trait, and Compensation in Schizophrenia and Related Disorders Using Resting State Imaging

FNIBI / Past Projects / Bipolar Disorder, Functional MRI, Neuroimaging, Schizophrenia /

April 1, 2013

The major goals of this study were to characterize the state-dependent nature of brain abnormalities in individuals with schizophrenia and bipolar disorder using functional imaging, and to define biological biomarkers of clinical state, trait, and compensation.

Neuroimaging Correlates of Genetic and Clinical Variables in Schizophrenia and Bipolar Disorder

FNIBI / Past Projects / Bipolar Disorder, Functional MRI, Genetics, Neuroimaging, Schizophrenia /

April 1, 2008

In collaboration with Dost Ongur, the major goals of this study were to characterize any brain system abnormalities present in patients who are experiencing psychotic or manic symptoms, and relate these patterns to specific genetic variables (e.g., single nucleotide polymorphisms) and clinical findings (e.g., presence or absence of hallucinations or delusions).