Danilo Bzdok

Why AI Models Hallucinate and How to Fix Them

A tab representation of the Pre trained CLIP Vision Transformer

October 8, 2025

Praneet Suresh

Jack Stanley

Danilo Bzdok

Sonia Joseph

Luca Scimeca

Using LLMs to better understand autism diagnosis

March 25, 2025

Jack Stanley

Danilo Bzdok

Towards Precision Medicine: Understanding Inference and Prediction Divergence in Biomedicine

September 8, 2020

Danilo Bzdok

Publications

Multiscale reorganization of brain and behavior under large-scale electrical perturbation

Sarah Kreuzer

Juergen Dukart

Justine Y. Hansen

Hoang K. Nguyen

Michael Bentsch

Sophia Zieger

Katrin Sakreida

Thomas C. Baghai

Caroline Nothdurfter

Michael Groezinger

Bogdan Draganski

Bratislav Misic

Simon B. Eickhoff

Timm B. Poeppl

2026-03-24

bioRxiv (preprint)

Sex Differences in P-Tau217, Tau Aggregation, and Cognitive Decline

Gillian Coughlan

Valentin Ourry

Diana Townsend

Hannah M Klinger

Jane A. Brown

Madison Cuppels

Tobey Betthauser

Rebecca Langhough

Karly Alex Cody

Mabel Seto

Colin Birkenbihl

Annie Li

Michelle Farrell

Emma G. Thibault

Pia Kivisäkk Webb

S. R. Arnold

Robert A. Rissman

Michael Properzi

Aaron Schultz

Keith Johnson … (see 81 more)

Oliver Langford

Michael C. Donohue

Sylvia Villeneuve

Sterling C. Johnson

Hyun-Sik Yang

JoAnn E. Manson

Reisa Sperling

Rachel F. Buckley

Orest Hurko

Sanra E Black

Rachelle Doody

Murali Doraiswamy

Anthony Gamst

Jeffrey Kaye

Thomas Obisesan

Henry Rusinek

Doug Scharre

Reisa Sperling

Michael W Weiner

R. Green

Paul Aisen

Keith Johnson

Jason Karlawish

Kenneth Marek

Karen Holdridge

REMA RAMAN

R. Yaari

Cheryl Brown

John R. Sims

Robert A. Rissman

Michael C. Donohue

Maria Arampatizdou

Jeremy Pizzola

Mike Rafii

Clifford Jack Jr.

Marybeth Howlett

John Seibyl

Isabella Velon

Paula Cohen

Gustavo Jimenez-Maggiora

Marianne Manire

James B. Brewer

Paul Maruff

Mark Mintun

Alison Belsha

Jennifer Salazar

Cecily Jenkins

Vedeline Torreon

Renarda Jones

Sylvia Villeneuve

Judes Poirier

John C.S. Breitner

Mohamed Badawy

Sylvain Baillet

Andrée‐Ann Baril

Bellec Pierre

Véronique D. Bohbot

Mallar Chakravarty

D. Louis Collins

Mahsa Dadar

Simon Ducharme

Alan C. Evans

Claudine Gauthier

Maiya Geddes

Rick Hoge

Yasser Ituria-Medina

Maxime Montembeault

Gerhard Multhaup

Lisa-Marie Münter

Alexa Pichet Binette

Natasha Rajah

Pedro Rosa-Neto

Taylor W. Schmitz

Jean-Paul Soucy

Nathan R Spreng

Christine Tardif

Etienne Vachon-Presseau

Christian Bocti

Maxime Descoteaux

Pierre Bellec

Importance: Among individuals with high levels of amyloid-β (Aβ), women exhibit higher insoluble tau burden and accumulation than age-matc… (see more)hed men. It remains unclear whether this sex difference is influenced by soluble phosphorylated tau (p-tau), a biomarker that changes early in Alzheimer disease. Objective: To investigate whether sex and aggregated Aβ synergistically predict plasma phosphorylated tau 217 (p-tau217) levels and whether levels of p-tau217 predict cross-sectional and longitudinal tau aggregation in a sex-specific manner (as measured by positron emission tomography [PET]). Design, Setting, and Participants: This longitudinal study analyzed data between September 7, 2024, and October 29, 2025, from 1 clinical trial cohort and 4 observational study cohorts including men and women without cognitive impairment who had undergone multiple assessments via tau PET (18F-flortaucipir or 18F-MK-6240) and plasma p-tau217 assay at baseline. Cognitive performance was measured with the Preclinical Alzheimer Cognitive Composite. Data on cognitive performance were available from 3 of the 5 cohorts for a mean of 4.6 years (SD, 3.1 years). Across the 5 cohorts, the mean follow-up for tau PET was 3.6 years (SD, 1.7 years). Exposures: Self-reported sex (male or female), tau PET, and p-tau217 assay. Main Outcomes and Measures: The primary analyses used linear and mixed-effects models to assess baseline and longitudinal sex × p-tau217 interactions for 9 tau PET regions. The secondary analyses assessed sex × p-tau217 interactions for cognitive change using the Preclinical Alzheimer Cognitive Composite. Results: Across the 5 cohorts, there were a total of 1292 participants (63.6% women; mean age, 70.6 [SD, 6.4] years) with tau PET assessments. Compared with men, women had significantly higher baseline p-tau217 levels at higher aggregated Aβ Centiloid levels (β, -0.21 [95% CI, -0.37 to -0.05], P = .009; highest interaction was found in the Anti-Amyloid Treatment in Asymptomatic Alzheimer's Disease/Longitudinal Evaluation of Amyloid Risk and Neurodegeneration [A4/LEARN] cohort). The sex × p-tau217 interactions at baseline were significant for 1 tau PET region in the Harvard Aging Brain Study (HABS) cohort, for 2 tau PET regions in the A4/LEARN cohort, for 6 tau PET regions in the Wisconsin Registry of Alzheimer's Prevention (WRAP) cohort, and for 4 tau PET regions in the Presymptomatic Evaluation of Experimental or Novel Treatments for Alzheimer's Disease (PREVENT-AD) cohort. Longitudinal interactions were significant for 4 tau PET regions in the A4/LEARN cohort, for 5 tau PET regions in both the Alzheimer's Disease Neuroimaging Initiative (ADNI) cohort and the WRAP cohort, and for 2 PET regions in both the HABS cohort and the PREVENT-AD cohort. Compared with men, women displayed greater tau deposition and accumulation at higher p-tau217 levels. Use of a secondary model showed women with higher p-tau217 levels also exhibited faster rates of cognitive decline relative to men in the both the WRAP cohort and the ADNI cohort. Conclusion and Relevance: These findings add to growing evidence that women have a differential tau response to Aβ that may emerge at the point of p-tau secretion. These findings have implications for the therapeutics and diagnostics of preclinical Alzheimer disease.

2026-02-15

JAMA Neurology (published)

Morphometric dissimilarity in association cortices linked to autism subtype with more severe symptoms

Hongxiu Jiang

Raul Rodriguez-Cruces

Ke Xie

Valeria Kebets

Yezhou Wang

Clara F. Weber

Ying He

Jonah Kember

Hilary Sweatman

Zeus Gracia Tabuenca

Jean-Baptiste Poline

Seok-Jun Hong

Boris Bernhardt

Xiaoqian Chai

Autism spectrum disorder (ASD) is a prevalent and heterogeneous neurodevelopmental condition marked by atypical brain connectivity. Understa… (see more)nding ASD neural subtypes at the network level is critical for clarifying its neuroanatomical heterogeneity. Morphometric similarity networks (MSNs), derived from region-to-region similarity across multiple anatomical features, offer a powerful approach for capturing individual-level neural architecture. In this study, MSNs were estimated from seven anatomical features in 348 individuals with ASD and 452 typically developing (TD) controls. Across all ASD participants, the first principal component of MSN values was negatively correlated with social and communication severity. Three ASD subtypes with distinct MSN patterns were identified. Subtype-1, characterized by weaker morphometric similarity values in frontotemporal association regions compared to TD individuals, exhibited the most severe symptoms in social, communication and repetitive behaviors, and displayed hyperconnectivity between the salience and visual networks, and between language and visual networks. Subtype-2 showed greater values of morphometric similarities than TD and less severe social symptoms compared to subtype-1, along with hyperconnectivity between default and salience networks relative to TD. Subtype-3 displayed morphometric similarity values largely comparable to TD and the least severe symptoms out of the three subtypes. Transcriptomic analysis revealed that GABAergic parvalbumin and glutamatergic intratelencephalic-projecting neurons were key cell types differentiating subtypes. These findings suggest the existence of distinct ASD neuroanatomical subtypes defined by regional morphometric similarity, each linked to unique behavioral, functional, and transcriptomic profiles. Morphometric dissimilarity in association regions may serve as a neural signature for ASD subtypes characterized by more severe clinical manifestations.

2026-01-31

NeuroImage (published)

Threading the needle: Practical considerations for merging theory-driven computational psychiatry with data-driven analytics to enhance precision health at scale

Annie Cheng

Anna Konova

Albert Powers

Philip Corlett

Ifat Levy

Xiaosi Gu

Quentin Huys

Helen Pushkarskya

Sarah Fineberg

Tobias Hauser

Ilan Harpaz-Rotem

Theresa Babuscio

Lisa Nichols

Yize Zhao

Manu Sharma

Daniella Meeker

Hua Xu

Robb B. Rutledge

Godfrey D. Pearlson … (see 2 more)

Christopher Pittenger

Sarah W. Yip

The rapidly evolving field of computational psychiatry enables quantification of specific cognitive processes, and their underlying mechanis… (see more)ms, in a translational and potentially scalable manner, using a combination of data collection via mechanistically informed behavioral tasks and theory-driven mathematical modeling. In parallel, transdiagnostic, dimensional approaches to psychiatric diagnostics, such as RDoC and HiTOP, seek to facilitate links between clinical research and real-world clinical reality, which rarely respects traditional diagnostic boundaries. These two approaches are seldom combined. In addition, while most psychiatric disorders are defined by their longitudinal course, our ability to predict symptom trajectories and tailor treatments to the individual remains limited, in part due to a dearth of longitudinal data collected using assessments sensitive to individual change over time. To address these gaps, the recently launched 'Individually Measured Phenotypes to Advance Computational Translation at Yale' (IMPACT-Y) study is collecting longitudinal data from a transdiagnostic cohort of 2400 individuals, using a combination of 'traditional' clinical research methods (e.g., health records, standardized assessments) and more novel computational approaches (e.g., behavioral tasks with demonstrated sensitivity to latent constructs and to within-person change, spoken narrative data). Here, we discuss unique challenges and opportunities in study design and analysis considerations of IMPACT-Y. Incorporating both theory- and data-driven analytics, we hope that IMPACT-Y will provide an unprecedented resource for characterizing longitudinal trajectories of core computational psychiatry constructs (e.g., reward learning) within and between individuals, for parsing heterogeneity beyond traditional diagnostic categories, and for linking inter- and intra-individual clinical variability to underlying mechanisms.

2026-01-31

Biological Psychiatry: Cognitive Neuroscience and Neuroimaging (published)

Genetic and Causal Insights Into White Matter Hyperintensities Across the Brain‐Body Axis

Manpreet Singh

Kimia Shafighi

Flavie E. Detcheverry

Gabrielle Dagasso

Fanta Dabo

Ikrame Housni

Sridar Narayanan

Nils D. Forkert

Sarah A Gagliano Taliun

AmanPreet Badhwar

White matter hyperintensities (WMHs), visible as bright regions on T2‐weighted FLAIR MRI, are frequent with age and elevated in Alzheimer'… (see more)s disease (AD). Representing axonal damage, demyelination, and edema, WMHs are driven by vascular mechanisms, including endothelial dysfunction and impaired cerebrovascular autoregulation. WMHs also exhibit strong heritability (55–73%), with overlapping genetic pathways shared with AD. Emerging evidence suggests systemic factors across the brain‐body axis influence WMHs, yet these contributions and their genetic overlap with AD remain underexplored. Our study investigated genetic underpinnings specific to WMHs and those shared with AD by assessing partitioned heritability of WMHs and AD across the brain‐body axis with SNP level tissue‐ and cell‐specific annotations; identifying genes associated with WMHs and AD through integration of gene expression data, establishing causal links between SNP‐level findings and imaging‐derived phenotypes (IDPs), particularly structural variations in regional brain volumes. Partitioned heritability was assessed using stratified‐linkage disequilibrium score regression (sLDSC) on GWAS summary statistics ( N = 3 WMH studies; N = 6 AD studies) using human A1) tissue level annotations ( N = 10) and A2) continuous cell‐specific annotations ( N = 64). MAGMA and FUSION analyses highlighted genes associated with WMH and AD for further bioinformatics analysis (using human protein atlas (HPA) and STRING database). MACAW (Vigneshwaran et al, 2024) modeled causal relationships between WMH‐associated SNPs (from FUMA analysis) and IDPs ( N = 172), leveraging directed acyclic graphs to evaluate genetic effects while controlling for confounders (Figure 2). Tissue‐specific analysis revealed significant enrichment of WMH‐associated SNPs in the CNS, liver, cardiovascular system, and kidneys, while AD‐associated SNPs were enriched in the CNS, connective bone, liver, and immune tissues. (Figure 1). Cell‐specific analysis identified vascular endothelial cells as enriched across WMH‐enriched tissues. MAGMA analysis, combined with HPA analysis, corroborated sLDSC tissue‐level findings. MAGMA and FUSION analyses highlighted genes associated with WMHs ( N = 39 and 69) and AD ( N = 291 and 193). MACAW linked WMH‐associated SNP to 172 IDPs, consistently impacting WM hypointensities and regional brain volumes (e.g., left inferior temporal volume). Our findings highlight systemic multi‐tissue contributions (CNS, liver, cardiovascular system, and kidneys) to WMHs, driven by vascular endothelial dysfunction and shared AD genetics, with SNPs across the body also affecting brain imaging derived phenotypes.

2026-01-06

Alzheimer's & Dementia (published)

Carriers of LRRK2 pathogenic variants show a milder, anatomically distinct brain signature of Parkinson's disease

Jakub Kopal

Andrew Vo

Qin Tao

Tanya Simuni

Lana M. Chahine

Alain Dagher

Pathogenic LRRK2 gene variants are a major genetic risk factor for both familial and sporadic Pa… (see more)rkinson’s dissease (PD), opening an unattended window into disease mechanisms and potential therapies. Investigating the influence of pathogenic variants in LRRK2 gene on brain structure is a crucial step toward enabling early diagnosis and personalized treatment. Yet, despite its significance, the ways in which LRRK2 genotype affects brain structure remain largely unexplored. Work in this domain is plagued by small sample sizes and differences in cohort composition, which can obscure genuine distinctions among clinical subgroups. In this study, we overcome such important limitations by combining explicit modeling of population background variation and pattern matching. Specifically, we leverage a cohort of 603 participants (including 370 with a PD diagnosis) to examine MRI-detectable cortical atrophy patterns associated with the LRRK2 pathogenic variants in people with PD and carriers without Parkinson’s symptoms. LRRK2 PD patients exhibit milder cortical thinning compared to sporadic PD, with notable preservation in temporal and occipital regions, suggesting a distinct pattern of neurodegeneration. Non-manifesting LRRK2 carriers show no significant cortical atrophy, indicating no structural signs of subclinical PD. We further analyze the relationship between aggregated alpha-synuclein in cerebrospinal fluid and atrophy. We find that those with evidence of aggregated alpha-synuclein experienced pronounced neurodegeneration and increased cortical thinning, possibly defining another aggressive PD subtype. Our findings highlight genetic avenues for distinguishing PD subtypes, which could lead to more targeted treatment approaches and a more complete understanding of Parkinson’s disease progression.

2026-01-02

Communications Medicine (published)

Quantifying LLM Attention-Head Stability: Implications for Circuit Universality.

Karan Bali

Jack Stanley

Praneet Suresh

In mechanistic interpretability, recent work scrutinizes transformer"circuits"- sparse, mono or multi layer sub computations, that may refle… (see more)ct human understandable functions. Yet, these network circuits are rarely acid-tested for their stability across different instances of the same deep learning architecture. Without this, it remains unclear whether reported circuits emerge universally across labs or turn out to be idiosyncratic to a particular estimation instance, potentially limiting confidence in safety-critical settings. Here, we systematically study stability across-refits in increasingly complex transformer language models of various sizes. We quantify, layer by layer, how similarly attention heads learn representations across independently initialized training runs. Our rigorous experiments show that (1) middle-layer heads are the least stable yet the most representationally distinct; (2) deeper models exhibit stronger mid-depth divergence; (3) unstable heads in deeper layers become more functionally important than their peers from the same layer; (4) applying weight decay optimization substantially improves attention-head stability across random model initializations; and (5) the residual stream is comparatively stable. Our findings establish the cross-instance robustness of circuits as an essential yet underappreciated prerequisite for scalable oversight, drawing contours around possible white-box monitorability of AI systems.

2025-12-31

arXiv (preprint)

arxiv.org

At the Edge of Understanding: Sparse Autoencoders Trace The Limits of Transformer Generalization

Pre-trained transformers have demonstrated remarkable generalization abilities, at times extending beyond the scope of their training data. … (see more)Yet, real-world deployments often face unexpected or adversarial data that diverges from training data distributions. Without explicit mechanisms for handling such shifts, model reliability and safety degrade, urging more disciplined study of out-of-distribution (OOD) settings for transformers. By systematic experiments, we present a mechanistic framework for delineating the precise contours of transformer model robustness. We find that OOD inputs, including subtle typos and jailbreak prompts, drive language models to operate on an increased number of fallacious concepts in their internals. We leverage this device to quantify and understand the degree of distributional shift in prompts, enabling a mechanistically grounded fine-tuning strategy to robustify LLMs. Expanding the very notion of OOD from input data to a model’s private computational processes—a new transformer diagnostic at inference time—is a critical step toward making AI systems safe for deployment across science, business, and government.

2025-12-31

International Conference on Machine Learning (Accept (regular))

openreview.net

Causally informed, multifactorial pathways linking cognition and personality to adolescent mental health

Jiadong Yan

Bin Wan

Paule Joanne Toussaint

Judy Chen

Gleb Bezgin

Yasser Iturria-Medina

Alan Evans

Sherif Karama

Adolescence is a sensitive period for the emergence of psychopathology. During this time, physiological changes and environmental exposures … (see more)jointly shape brain development and influence cognitive and personality maturation, collectively heightening vulnerability to mental disorders. However, the complexity of interactions between these factors has hindered a systems-level understanding of mental health and the causal roles of cognition and personality in psychopathology. In this study, we proposed a multifactorial causal framework integrating brain, pubertal, environmental, and behavioral factors to characterize heterogeneity in adolescent mental health trajectories at the individual level. We then investigated latent causal pathways linking cognition and personality to mental health outcomes and identified potential personalized intervention targets. Leveraging the Adolescent Brain Cognitive Development (ABCD) dataset ( N = 4,501), we analyzed 165 behavioral pairs connecting cognition and personality traits to mental health symptoms. Using cross-sectional multivariate mediation and longitudinal interaction-inclusive analyses, we identified 68 behavioral pairs showing significant causal relationships, with brain and environmental exposures contributing to most pathways, while pubertal factors exhibited limited involvement. Individualized interpretive analyses further revealed 23 pairs suggesting potential interventions with response rates exceeding 50%. Among these, behavioral inhibition, negative urgency, and processing speed emerged as the most common intervention targets, whereas psychosis symptoms and attention problems were the most likely issues to improve. Overall, our study advances a comprehensive framework capturing the multifactorial and heterogeneous nature of adolescent mental health, delineates specific causal pathways from cognitive and personality traits to psychopathology, and provides a principled basis for potential individualized intervention strategies.

2025-12-25

bioRxiv (preprint)

Mitochondria‐nucleus crosstalk characterizes Alzheimer's disease across 1,5 million brain cells

Emerging insight from stem cell research reinforces Alzheimer's disease (AD) to affect mitochondrial protein expression. Compelling new evid… (see more)ence points to mitochondrial reactive oxygen species (ROS) as potential driving player in Aβ toxicity, mediated through glial cells and ultimately impacting neuronal health. A comprehensive understanding of how oxidative phosphorylation variations relate to cell function remains largely unexplored, especially through a cell type lens. Leveraging today's largest single‐nucleus RNA sequencing dataset of AD, we unveil how cell‐type‐specific mitochondrial alterations reverberate in the nuclear transcriptome, in 424 AD patients and healthy controls from ROSMAP. By adopting a supervised latent factor modelling approach, we identified distinct gene modules capturing unique aspects of the mitochondrial crosstalk in 6 major brain cell types across 5,427 nuclear and 13 mitochondrial genes. We found that nuclear‐mitochondrial crosstalk varies distinctly with cell identity, reflecting metabolic demands and functional specialization. In neurons and oligodendrocytes, ATP synthase (complex V) takes a central role, whereas type 1 NADH dehydrogenase (complex I) is more prominent in astrocytes, microglia, and OPCs. Screening across >1 million gene expression profiles from ∼20,000 drug perturbations identified mitochondrial‐nuclear signatures that resemble those activated by parthenolide and niclosamide—two chemical compounds previously associated with oxidative stress and cytotoxicity via ubiquitination—as most predictive of AD. Microglia and OPCs achieved the highest overall classification accuracy, with stronger predictive performance observed in males than in females. Mapping gene module expressions to the Allen Human Brain Atlas revealed shared whole‐brain patterns highlighting the precuneus, which we implicated in ubiquitin‐cascade‐enriched modules. Clinical phenotyping revealed that males with higher AD risk, as indicated by their mitochondrial‐nuclear scores on glial gene modules, exhibited a greater pathological burden, including higher amyloid load, Parkinson's‐like symptoms, and neuroticism‐related traits. Finally, by comparing our findings with 2.5 million CRISPRi‐based perturbations, we identified neural signatures associated with female‐biased transcription factors and fatty acid biosynthesis, while glial signatures were linked to DNA damage and oxidative stress. By integrating multiple layers of biological data from established reference atlases, our analysis of mitochondria‐nuclear crosstalk revealed distinct transcriptional signatures associated with AD risk in glial and neural cells, with these associations exhibiting sex‐biased patterns.

2025-12-22

Alzheimer's & Dementia (published)

Latent brain subtypes of chronotype reveal unique behavioral and health profiles across population cohorts

Julie Carrier

Kai-Florian Storch

Robin I. M. Dunbar

Chronotype is shaped by the complex interplay of endogenous and exogenous factors. This time-enduring trait ties into societal behaviors an… (see more)d is linked to psychiatric and metabolic conditions. Despite its multifaceted nature, prior research has treated chronotype as a monolithic trait across the population, risking overlooking substantial heterogeneity in neural and behavioral fingerprints. To uncover hidden subgroups, we develop a supervised pattern-learning framework integrating three complementary brain-imaging modalities with deep behavioral and health profiling from 27,030 UK Biobank participants. We identify five distinct, biologically valid chronotype subtypes. Each demonstrates unique patterns across brain, behavioral and health profiles. External validation in 10,550 US children from the ABCD Study cohort reveals reversed age distributions and replicates sex-associated brain-behavioral patterns, suggesting that potential divergences between chronotype traits observed throughout adulthood may begin to emerge early in life. These findings highlight underappreciated sources of population variation that echo the rhythm of people’s inner clock.

2025-12-21

Nature Communications (published)