Guillermo Cecchi

Title

Principal Research Staff Member - Computational Psychiatry and Neuroimaging

Bio

Academic background

Guillermo Cecchi received an education in Physics (MSc, University of La Plata, Argentina, 1991), Physics and Biology (PhD, The Rockefeller University, 1994-1999), and Imaging in Psychiatry (Postdoctoral Fellow, Cornell University 2000-2001). He has been interested in diverse aspects of theoretical biology, including Brownian transport, molecular computation, spike reliability in neurons, song production and representation in songbirds, statistics of natural images and visual perception, statistics of natural language, and brain imaging. In 2001 he joined IBM Research to work on computational approaches to brain function.

In recent years, Dr. Cecchi has pioneered the use of a computational linguistics approach to quantify psychiatric conditions from short speech samples, applying it successfully to conditions as diverse as schizophrenia, mania, prodromal psychosis, chronic pain, neurodegeneration, drug and alcohol intake, and psychotherapy.

Areas of research

Dr. Cecchi directs the Computational Psychiatry and the Neuroimaging groups in IBM Research, and is Associate Director of Analytics for NIH's Advancing Medicines Partnerships - Schizophrenia. Starting in May 2024, Dr. Cecchi will be co-Director of the PREDiCTOR Center for outcomes forecast across all mental health outpatients in New York City Mt Sinai hospitals (NIH U01 center grant).

Selected Publications

Brain Imaging

Multimodal fusion of brain signals for robust prediction of psychosis transition, Schizophrenia (2024)
Predictive Modeling of Huntington's Disease Unfolds Thalamic and Caudate Longitudinal Atrophy Dissociation, Movement Disorders (2022)
Resting-state connectivity stratifies premanifest Huntington's disease by longitudinal cognitive decline rate, Scientific Reports (2020)
Loss of nucleus accumbens low-frequency fluctuations is a signature of chronic pain, PNAS (2020)
Single-trial classification of awareness state during anesthesia by measuring critical dynamics of global brain activity, Scientific Reports (2019).
Brain and psychological determinants of placebo pill response in chronic pain patients, Nature Comms. (2018).
Loss of consciousness is associated with stabilization of distributed cortical dynamics, Journal of Neuroscience (2015).
Self-organized Dynamical Criticality in Human ECoG, Frontiers Integrative Neuroscience (2012).
Full-brain Auto-Regressive Modeling (FARM) using fMRI, Neuroimage (2011).
Predictive network models of schizophrenia, NIPS (2009).
Scale-free brain functional networks, Physical Review Letters (2005).

Language

People over trust AI-generated medical responses and view them to be as valid as doctors, despite low accuracy. New England Journal of Medicine AI (in press)
Speech and language patterns in autism: towards natural language processing as a research and clinical tool, Psychiatry Research (2024, in press)
Using Large Language Models to Understand Suicidality in a Social Media-based Taxonomy of Mental Health Disorders, JMIR Mental Health (2024)
Are language features associated with psychosis risk universal? A study in Mandarin-speaking youths at clinical high risk for psychosis. World Psychiatry (2023).
Answer ALS: A Large-Scale Resource for Sporadic and Familial ALS Combining Clinical Data with Multi-Omics Data from Induced Pluripotent Cell Lines, Nature Neuroscience (2022)
Quantitative language features identify placebo responders in chronic back pain, Pain (2021)
Linguistic markers predict onset of Alzheimer's disease, The Lancet eClinical (2020)
Modeling Psychotherapy Dialogues with Kernelized Hashcode Representations: A Nonparametric Information-Theoretic Approach, AAAI (2020)
Prediction of psychosis across protocols and risk cohorts using automated language analysis, World Psychiatry (2018).
Automated Analysis of Free Speech Predicts Psychosis Onset in High-Risk Youths, NPJ Schizophrenia (2015).
A Window into the Intoxicated Mind? Speech as an Index of Psychoactive Drug Effects, Neuropsychopharmacology (2014).
Speech Graphs Provide a Quantitative Measure of Thought Disorder in Psychosis, PLoS One (2012).
Global properties of the Wordnet lexicon, PNAS (2002).

Perception

Text-based predictions of COVID-19 diagnosis from self-reported chemosensory descriptions, Communications Medicine (2023)
Expansive linguistic representations to predict interpretable odor mixture discriminability, Chemical Senses (2023)
Predicting natural language descriptions of mono-molecular odorants, Nature Comms. (2018).
Reverse-engineering human olfactory perception from chemical features of odor molecules, Science (2017).
Perceptual basis of evolving Western musical styles, PNAS (2013).
Predictive Dynamics of Pain Perception, PLoS Computational Biology (2012).
On a common circle: natural scenes and Gestalt rules, PNAS (2001).

Neural Systems

Effective Latent Differential Equation Models via Attention and Multiple Shooting. Transactions on Machine Learning Research (2024)
Learning Brain Dynamics with Coupled Low-dimensional Nonlinear Oscillators and Deep Recurrent Networks, Neural Computation (2021)
The relevance of the time domain in neural networks models, Springer (2012).
A theory of loop formation and elimination by STDP, Frontiers in Neuroscience (2010).
Self-tuned critical networks, Physical Review Letters (2009).
Ordered cyclic motifs contribute to dynamic stability in biological and engineered networks, PNAS (2008).
Unsupervised segmentation with dynamical units, IEEE Transactions on Neural Networks (2008).
Unsupervised learning and adaptation in a model of adult neurogenesis, Journal of Computational Neuroscience (2001).
Simple motor gestures for birdsong, Physical Review Letters (2001).
Noise in neurons is message-dependent, PNAS (2000).
Toward a Song Code: Syllabic Representation in the Canary Brain, Neuron (1998).