Individual differences in computational psychiatry: A review of current challenges

Neuroscience & Biobehavioral Reviews, Journal Year: 2023, Volume and Issue: 148, P. 105137 - 105137

Published: March 20, 2023

Bringing precision to the understanding and treatment of mental disorders requires instruments for studying clinically relevant individual differences. One promising approach is development computational assays: integrating models with cognitive tasks infer latent patient-specific disease processes in brain computations. While recent years have seen many methodological advancements modelling cross-sectional patient studies, much less attention has been paid basic psychometric properties (reliability construct validity) measures provided by assays. In this review, we assess extent issue examining emerging empirical evidence. We find that suffer from poor properties, which poses a risk invalidating previous findings undermining ongoing research efforts using assays study (and even group) provide recommendations how address these problems and, crucially, embed them within broader perspective on key developments are needed translating clinical practice.

Language: Английский

---

A Systematic Evaluation of Machine Learning–Based Biomarkers for Major Depressive Disorder

JAMA Psychiatry, Journal Year: 2024, Volume and Issue: 81(4), P. 386 - 386

Published: Jan. 10, 2024

Biological psychiatry aims to understand mental disorders in terms of altered neurobiological pathways. However, for one the most prevalent and disabling disorders, major depressive disorder (MDD), no informative biomarkers have been identified.

Language: Английский

---

Functional magnetic resonance imaging in schizophrenia: current evidence, methodological advances, limitations and future directions

World Psychiatry, Journal Year: 2024, Volume and Issue: 23(1), P. 26 - 51

Published: Jan. 12, 2024

Functional neuroimaging emerged with great promise and has provided fundamental insights into the neurobiology of schizophrenia. However, it faced challenges criticisms, most notably a lack clinical translation. This paper provides comprehensive review critical summary literature on functional neuroimaging, in particular magnetic resonance imaging (fMRI), We begin by reviewing research fMRI biomarkers schizophrenia high risk phase through historical lens, moving from case-control regional brain activation to global connectivity advanced analytical approaches, more recent machine learning algorithms identify predictive features. Findings studies negative symptoms as well neurocognitive social cognitive deficits are then reviewed. neural markers these may represent promising treatment targets Next, we summarize related antipsychotic medication, psychotherapy psychosocial interventions, neurostimulation, including response resistance, therapeutic mechanisms, targeting. also utility data-driven approaches dissect heterogeneity schizophrenia, beyond comparisons, methodological considerations advances, consortia precision fMRI. Lastly, limitations future directions field discussed. Our suggests that, order for be clinically useful care patients should address potentially actionable decisions that routine treatment, such which prescribed or whether given patient is likely have persistent impairment. The potential influenced must weighed against cost accessibility factors. Future evaluations prognostic consider health economics analysis.

Language: Английский

---

MRI economics: Balancing sample size and scan duration in brain wide association studies

bioRxiv (Cold Spring Harbor Laboratory), Journal Year: 2024, Volume and Issue: unknown

Published: Feb. 18, 2024

Abstract A pervasive dilemma in neuroimaging is whether to prioritize sample size or scan time given fixed resources. Here, we systematically investigate this trade-off the context of brain-wide association studies (BWAS) using functional magnetic resonance imaging (fMRI). We find that total duration (sample × per participant) robustly explains individual-level phenotypic prediction accuracy via a logarithmic model, suggesting and are broadly interchangeable up 20-30 min data. However, returns diminish relative size, which explain with principled theoretical derivations. When accounting for overhead costs associated each participant (e.g., recruitment, non-imaging measures), many small-scale some large-scale BWAS might benefit from longer than typically assumed. These results generalize across domains, scanners, acquisition protocols, racial groups, mental disorders, age as well resting-state task-state connectivity. Overall, our study emphasizes importance time, ignored standard power calculations. Standard calculations maximize at expense can result sub-optimal accuracies inefficient use Our empirically informed reference available future design: WEB_APPLICATION_LINK

Language: Английский

---

Relationship between prediction accuracy and feature importance reliability: An empirical and theoretical study

NeuroImage, Journal Year: 2023, Volume and Issue: 274, P. 120115 - 120115

Published: April 23, 2023

There is significant interest in using neuroimaging data to predict behavior. The predictive models are often interpreted by the computation of feature importance, which quantifies relevance an imaging feature. Tian and Zalesky (2021) suggest that importance estimates exhibit low split-half reliability, as well a trade-off between prediction accuracy reliability across parcellation resolutions. However, it unclear whether universal. Here, we demonstrate that, with sufficient sample size, (operationalized Haufe-transformed weights) can achieve fair excellent reliability. With size 2600 participants, weights average intra-class correlation coefficients 0.75, 0.57 0.53 for cognitive, personality mental health measures respectively. much more reliable than original regression univariate FC-behavior correlations. Original not even participants. Intriguingly, strongly positively correlated phenotypes. Within particular behavioral domain, there no clear relationship performance models. Furthermore, show mathematically necessary, but sufficient, error. In case linear models, lower error related Therefore, higher might yield accuracy. Finally, discuss how our theoretical results relate features measures. Overall, current study provides empirical insights into

Language: Английский

---

Insights from personalized models of brain and behavior for identifying biomarkers in psychiatry

Neuroscience & Biobehavioral Reviews, Journal Year: 2023, Volume and Issue: 152, P. 105259 - 105259

Published: June 1, 2023

Language: Английский

---

Study design features increase replicability in brain-wide association studies

Nature, Journal Year: 2024, Volume and Issue: unknown

Published: Nov. 27, 2024

Abstract Brain-wide association studies (BWAS) are a fundamental tool in discovering brain–behaviour associations 1,2 . Several recent have shown that thousands of study participants required for good replicability BWAS 1–3 Here we performed analyses and meta-analyses robust effect size index using 63 longitudinal cross-sectional MRI from the Lifespan Brain Chart Consortium 4 (77,695 total scans) to demonstrate optimizing design is critical increasing standardized sizes BWAS. A meta-analysis brain volume with age indicates larger variability covariate reported size. Analysing effects on global regional measures UK Biobank Alzheimer’s Disease Neuroimaging Initiative, showed modifying through sampling schemes improves replicability. To ensure our results generalizable, further evaluated cognitive, psychopathology demographic structural functional outcome Adolescent Cognitive Development dataset. We demonstrated commonly used models, which assume equal between-subject within-subject changes can, counterintuitively, reduce Explicitly modelling avoids conflating them enables each separately. Together, these provide guidance designs improve

Language: Английский

---

Psychiatric neuroimaging designs for individualised, cohort, and population studies

Neuropsychopharmacology, Journal Year: 2024, Volume and Issue: 50(1), P. 29 - 36

Published: Aug. 14, 2024

Abstract Psychiatric neuroimaging faces challenges to rigour and reproducibility that prompt reconsideration of the relative strengths limitations study designs. Owing high resource demands varying inferential goals, current designs differentially emphasise sample size, measurement breadth, longitudinal assessments. In this overview perspective, we provide a guide landscape psychiatric with respect balance scientific goals constraints. Through heuristic data cube contrasting key design features, discuss resulting trade-off among small sample, precision studies (e.g., individualised cohorts) large minimally longitudinal, population studies. Precision support tests within-person mechanisms, via intervention tracking course. Population generalisation across multifaceted individual differences. A proposed reciprocal validation model (RVM) aims recursively leverage these complementary in sequence accumulate evidence, optimise strengths, build towards improved long-term clinical utility.

Language: Английский

---

Sample size matters when estimating test–retest reliability of behaviour

Behavior Research Methods, Journal Year: 2025, Volume and Issue: 57(4)

Published: March 21, 2025

Intraclass correlation coefficients (ICCs) are a commonly used metric in test-retest reliability research to assess measure's ability quantify systematic between-subject differences. However, estimates of differences also influenced by factors including within-subject variability, random errors, and measurement bias. Here, we use data collected from large online sample (N = 150) (1) behavioural computational measures reversal learning using ICCs, (2) our dataset as the basis for simulation study investigating effects size on variance component estimation association between components ICC measures. In line with previously published work, find reliable learning, assay flexibility. Reliable between-subject, (across-session), error (with ± .05 precision 80% confidence) required sizes ranging 10 over 300 (behavioural median N: 167, 34, 103; 68, 20, 45). These exceed those often studies, suggesting that larger than studies (circa 30) robustly estimate task performance Additionally, found showed highly positive negative correlations components, respectively, might be expected, which remained relatively stable across sizes. were weakly or not correlated variance, providing evidence importance decomposition studies.

Language: Английский

---

Impact of analytic decisions on test-retest reliability of individual and group estimates in functional magnetic resonance imaging: a multiverse analysis using the monetary incentive delay task

bioRxiv (Cold Spring Harbor Laboratory), Journal Year: 2024, Volume and Issue: unknown

Published: March 20, 2024

Empirical studies reporting low test-retest reliability of individual blood oxygen-level dependent (BOLD) signal estimates in functional magnetic resonance imaging (fMRI) data have resurrected interest among cognitive neuroscientists methods that may improve fMRI. Over the last decade, several reported modeling decisions, such as smoothing, motion correction and contrast selection, BOLD estimates. However, it remains an empirical question whether certain analytic decisions

Language: Английский

---