4.6 Article

Individual-Level Prediction of Exposure Therapy Outcome Using Structural and Functional MRI Data in Spider Phobia: A Machine-Learning Study

相关参考文献

注意:仅列出部分参考文献,下载原文获取全部文献信息。
Article Neurosciences

Moment-to-Moment Brain Signal Variability Reliably Predicts Psychiatric Treatment Outcome

Kristoffer N. T. Mansson et al.

Summary: Task-based brain signal variability has been found to be the most reliable indicator for predicting treatment outcomes of psychiatric disorders, outperforming self-reports and other neural measures. This suggests that moment-to-moment fMRI signal variability may serve as a prognostic indicator for clinical outcomes.

BIOLOGICAL PSYCHIATRY (2022)

Article Neurosciences

Behavioral and Magnetoencephalographic Correlates of Fear Generalization Are Associated With Responses to Later Virtual Reality Exposure Therapy in Spider Phobia

Kati Roesmann et al.

Summary: The study found that pretreatment differences in behavioral and neural markers of fear generalization in spider-phobic patients may impact their response to exposure therapy. These findings suggest that fear generalization could be a potential predictive marker to identify patients who may not benefit from exposure therapy, helping personalize and optimize treatment strategies for vulnerable patient groups.

BIOLOGICAL PSYCHIATRY-COGNITIVE NEUROSCIENCE AND NEUROIMAGING (2022)

Review Health Care Sciences & Services

Machine learning for medical imaging: methodological failures and recommendations for the future

Gael Varoquaux et al.

Summary: Research in computer analysis of medical images has the potential to improve patients' health, but systematic challenges are impeding progress. From data limitations to research incentives, many issues hinder advancements. However, there are ongoing efforts to address these problems and recommendations for future improvement.

NPJ DIGITAL MEDICINE (2022)

Review Psychology, Clinical

Can we predict who will benefit from cognitive-behavioural therapy? A systematic review and meta-analysis of machine learning studies

Sandra Vieira et al.

Summary: Cognitive-behavioural therapy (CBT) is the first line of treatment for several mental health disorders, but not all patients respond to it. Machine learning has shown promise in predicting the clinical response to CBT. A literature review identified 24 studies that used machine learning to predict clinical response, with an overall accuracy of 74.0%. The accuracy varied among different diagnostic groups, with PTSD, AD, and OCD showing the highest accuracy.

CLINICAL PSYCHOLOGY REVIEW (2022)

Article Neuroimaging

Predicting escitalopram treatment response from pre-treatment and early response resting state fMRI in a multi-site sample: A CAN-BIND-1 report

Jacqueline K. Harris et al.

Summary: Previous intervention studies have used fMRI data to predict the antidepressant response of patients with MDD. However, the limited scope of these studies may not accurately reflect real-world situations. This study suggests that collecting fMRI data before and shortly after treatment initiation can lead to improved predictive models.

NEUROIMAGE-CLINICAL (2022)

Article Neuroimaging

Neural correlates of fear conditioning are associated with treatment-outcomes to behavioral exposure in spider phobia-Evidence from magnetoencephalography

Kati Roesmann et al.

Summary: This study found that pre-treatment fear ratings of conditioned safety and threat cues, as well as neural markers of safety-learning and fear inhibition, were not predictive of the outcomes of behavioral exposure therapy. However, the study also found that neural activity in the bilateral dorsolateral prefrontal cortex and left ventromedial prefrontal cortex before treatment was associated with symptom reductions and remission status.

NEUROIMAGE-CLINICAL (2022)

Editorial Material Psychiatry

Prediction, Not Association, Paves the Road to Precision Medicine

Danilo Bzdok et al.

JAMA PSYCHIATRY (2021)

Article Psychiatry

The Overlapping Neurobiology of Induced and Pathological Anxiety: A Meta-Analysis of Functional Neural Activation

Alice Chavanne et al.

Summary: This meta-analysis reveals a consistent pattern of activation across induced and pathological anxiety, suggesting some overlapping neurobiological mechanisms and indicating that induced anxiety could potentially serve as a model for certain anxiety disorders. However, it may be a more suitable model for some disorders than others.

AMERICAN JOURNAL OF PSYCHIATRY (2021)

Article Psychiatry

Centromedial amygdala is more relevant for phobic confrontation relative to the bed nucleus of stria terminalis in patients with spider phobia

N. Siminski et al.

Summary: Through investigating the involvement of CM and BNST in individuals with spider phobia, it was found that CM plays a more significant role in phobic confrontation in patients.

JOURNAL OF PSYCHIATRIC RESEARCH (2021)

Review Medicine, General & Internal

Anxiety disorders

Brenda W. J. H. Penninx et al.

Summary: Anxiety disorders are the most common group of mental disorders, characterized by excessive fear, anxiety, and avoidance of perceived threats. Risk factors include genetic and environmental influences, with high rates of comorbidity with other mental disorders. Timely and accurate treatment is crucial for reducing the burden of anxiety disorders.

LANCET (2021)

Article Clinical Neurology

Disruption of functional and structural networks in first -episode, drug -nave adolescents with generalized anxiety disorder

Xiaotong Guo et al.

Summary: Our study identified disruptions in both functional networks and structural networks in individuals with GAD, as well as aberrant couplings between the two networks. These network alterations were associated with anxiety severity in GAD patients.

JOURNAL OF AFFECTIVE DISORDERS (2021)

Article Neurosciences

Systematic misestimation of machine learning performance in neuroimaging studies of depression

Claas Flint et al.

Summary: A study in psychiatry machine learning found that larger datasets do not necessarily lead to better results, with smaller studies often performing better. When classifying patients with depression and healthy controls, accuracies of up to 95% were observed for small sample sizes (N = 20), while accuracies of around 75% were found for medium sample sizes (N = 100).

NEUROPSYCHOPHARMACOLOGY (2021)

Article Psychology, Clinical

Clinical predictors of treatment response towards exposure therapy in virtuo in spider phobia: A machine learning and external cross-validation approach

Elisabeth J. Leehr et al.

Summary: The study found that virtual reality exposure therapy is highly effective for patients with spider phobia, but individual treatment response prediction still poses challenges, indicating the need for further research and improved models.

JOURNAL OF ANXIETY DISORDERS (2021)

Article Psychiatry

The promise of machine learning in predicting treatment outcomes in psychiatry

Adam M. Chekroud et al.

Summary: In psychiatry, there is a growing interest in using machine learning to develop personalized treatment models, shifting focus from experimental studies to predictive models. Key studies have explored prediction of treatment outcomes using various data sources, and discussions have included the ethical challenges of applying machine learning in mental health care.

WORLD PSYCHIATRY (2021)

Article Psychology, Clinical

Neural processing of emotional facial stimuli in specific phobia: An fMRI study

Joscha Boehnlein et al.

Summary: Patients with specific phobia (SP) showed altered brain activation when presented with phobia-specific stimuli, but no differences were found in response to nonspecific aversive facial stimuli compared to healthy controls. However, machine learning techniques were able to differentiate between the two groups with a high accuracy rate. This suggests that patients with SP may have subtle differences in processing nonspecific emotional stimuli.

DEPRESSION AND ANXIETY (2021)

Article Health Care Sciences & Services

Predicting therapy outcome in a digital mental health intervention for depression and anxiety: A machine learning approach

Silvan Hornstein et al.

Summary: This study evaluates the performance of machine learning in predicting treatment response in a digital mental health intervention for depression and anxiety, finding that a random forest classifier achieved a good accuracy. Predicted non-responders showed less reduction in symptoms compared to responders. The variables used for prediction include pre-treatment symptom assessments, self-reported motivation, and type of referral into the programme.

DIGITAL HEALTH (2021)

Review Psychiatry

Establishment of Best Practices for Evidence for Prediction A Review

Russell A. Poldrack et al.

JAMA PSYCHIATRY (2020)

Article Psychiatry

Theranostic markers for personalized therapy of spider phobia: Methods of a bicentric external cross-validation machine learning approach

Hanna Schwarzmeier et al.

INTERNATIONAL JOURNAL OF METHODS IN PSYCHIATRIC RESEARCH (2020)

Review Behavioral Sciences

I tried a bunch of things: The dangers of unexpected overfitting in classification of brain data

Mahan Hosseini et al.

NEUROSCIENCE AND BIOBEHAVIORAL REVIEWS (2020)

Article Psychiatry

Symptom trajectories of early responders and remitters among youth with OCD

Megan Rech et al.

JOURNAL OF OBSESSIVE-COMPULSIVE AND RELATED DISORDERS (2020)

Review Clinical Neurology

Neuroimaging findings as predictors of treatment outcome of psychotherapy in anxiety disorders

Veruska Andrea Santos et al.

PROGRESS IN NEURO-PSYCHOPHARMACOLOGY & BIOLOGICAL PSYCHIATRY (2019)

Article Psychiatry

Altered Brain Signal Variability in Patients With Generalized Anxiety Disorder

Liyuan Li et al.

FRONTIERS IN PSYCHIATRY (2019)

Review Psychiatry

The Science of Prognosis in Psychiatry A Review

Paolo Fusar-Poli et al.

JAMA PSYCHIATRY (2018)

Article Psychology, Clinical

The predictive value of early response in patients with depressive disorders

Henrike Stephanie Schlagert et al.

PSYCHOTHERAPY RESEARCH (2017)

Article Biochemistry & Molecular Biology

Brain connectomics predict response to treatment in social anxiety disorder

S. Whitfield-Gabrieli et al.

MOLECULAR PSYCHIATRY (2016)

Article Psychology, Clinical

SPIDER OR NO SPIDER? NEURAL CORRELATES OF SUSTAINED AND PHASIC FEAR IN SPIDER PHOBIA

Anna Luisa Muensterkoetter et al.

DEPRESSION AND ANXIETY (2015)

Article Psychology, Clinical

Response rates for CBT for anxiety disorders: Need for standardized criteria

Amanda G. Loerinc et al.

CLINICAL PSYCHOLOGY REVIEW (2015)

Review Neurosciences

Reproducibility of Graph-Theoretic Brain Network Metrics: A Systematic Review

Thomas Welton et al.

BRAIN CONNECTIVITY (2015)

Article Neurosciences

Single-Subject Anxiety Treatment Outcome Prediction using Functional Neuroimaging

Tali M. Ball et al.

NEUROPSYCHOPHARMACOLOGY (2014)

Article Psychology, Clinical

Patterns of Early Change and Their Relationship to Outcome and Early Treatment Termination in Patients With Panic Disorder

Wolfgang Lutz et al.

JOURNAL OF CONSULTING AND CLINICAL PSYCHOLOGY (2014)

Review Behavioral Sciences

Moment-to-moment brain signal variability: A next frontier in human brain mapping?

Douglas D. Garrett et al.

NEUROSCIENCE AND BIOBEHAVIORAL REVIEWS (2013)

Review Psychology, Clinical

The Efficacy of Cognitive Behavioral Therapy: A Review of Meta-analyses

Stefan G. Hofmann et al.

COGNITIVE THERAPY AND RESEARCH (2012)

Article Neurosciences

Conn: A Functional Connectivity Toolbox for Correlated and Anticorrelated Brain Networks

Susan Whitfield-Gabrieli et al.

BRAIN CONNECTIVITY (2012)

Article Geriatrics & Gerontology

Early Response to Psychotherapy and Long-Term Change in Worry Symptoms in Older Adults With Generalized Anxiety Disorder

Andrea Bradford et al.

AMERICAN JOURNAL OF GERIATRIC PSYCHIATRY (2011)

Article Neurosciences

The Importance of Being Variable

Douglas D. Garrett et al.

JOURNAL OF NEUROSCIENCE (2011)

Article Neurosciences

Blood Oxygen Level-Dependent Signal Variability Is More than Just Noise

Douglas D. Garrett et al.

JOURNAL OF NEUROSCIENCE (2010)

Article Neurosciences

Complex network measures of brain connectivity: Uses and interpretations

Mikail Rubinov et al.

NEUROIMAGE (2010)

Article Computer Science, Artificial Intelligence

Inference for the generalization error

C Nadeau et al.

MACHINE LEARNING (2003)