A multimodal neuroimaging classifier for alcohol dependence

Progress and trends in neurological disorders research based on deep learning

In recent years, deep learning (DL) has emerged as a powerful tool in clinical imaging, offering unprecedented opportunities for the diagnosis and treatment of neurological disorders (NDs). This comprehensive review explores the multifaceted role of DL techniques in leveraging vast datasets to advance our understanding of NDs and improve clinical outcomes. Beginning with a systematic literature review, we delve into the utilization of DL, particularly focusing on multimodal neuroimaging data analysis-a domain that has witnessed rapid progress and garnered significant scientific interest. Our study categorizes and critically analyses numerous DL models, including Convolutional Neural Networks (CNNs), LSTM-CNN, GAN, and VGG, to understand their performance across different types of Neurology Diseases. Through particular analysis, we identify key benchmarks and datasets utilized in training and testing DL models, shedding light on the challenges and opportunities in clinical neuroimaging research. Moreover, we discuss the effectiveness of DL in real-world clinical scenarios, emphasizing its potential to revolutionize ND diagnosis and therapy. By synthesizing existing literature and describing future directions, this review not only provides insights into the current state of DL applications in ND analysis but also covers the way for the development of more efficient and accessible DL techniques. Finally, our findings underscore the transformative impact of DL in reshaping the landscape of clinical neuroimaging, offering hope for enhanced patient care and groundbreaking discoveries in the field of neurology. This review paper is beneficial for neuropathologists and new researchers in this field.

Multimodal-based machine learning approach to classify features of internet gaming disorder and alcohol use disorder: A sensor-level and source-level resting-state electroencephalography activity and neuropsychological study

OBJECTIVES

Addictions have recently been classified as substance use disorder (SUD) and behavioral addiction (BA), but the concept of BA is still debatable. Therefore, it is necessary to conduct further neuroscientific research to understand the mechanisms of BA to the same extent as SUD. The present study used machine learning (ML) algorithms to investigate the neuropsychological and neurophysiological aspects of addictions in individuals with internet gaming disorder (IGD) and alcohol use disorder (AUD).

METHODS

We developed three models for distinguishing individuals with IGD from those with AUD, individuals with IGD from healthy controls (HCs), and individuals with AUD from HCs using ML algorithms, including L1-norm support vector machine, random forest, and L1-norm logistic regression (LR). Three distinct feature sets were used for model training: a unimodal-electroencephalography (EEG) feature set combined with sensor- and source-level feature; a unimodal-neuropsychological feature (NF) set included sex, age, depression, anxiety, impulsivity, and general cognitive function, and a multimodal (EEG + NF) feature set.

RESULTS

The LR model with the multimodal feature set used for the classification of IGD and AUD outperformed the other models (accuracy: 0.712). The important features selected by the model highlighted that the IGD group had differential delta and beta source connectivity between right intrahemispheric regions and distinct sensor-level EEG activities. Among the NFs, sex and age were the important features for good model performance.

CONCLUSIONS

Using ML techniques, we demonstrated the neurophysiological and neuropsychological similarities and differences between IGD (a BA) and AUD (a SUD).

White matter diffusion estimates in obsessive-compulsive disorder across 1653 individuals: machine learning findings from the ENIGMA OCD Working Group

White matter pathways, typically studied with diffusion tensor imaging (DTI), have been implicated in the neurobiology of obsessive-compulsive disorder (OCD). However, due to limited sample sizes and the predominance of single-site studies, the generalizability of OCD classification based on diffusion white matter estimates remains unclear. Here, we tested classification accuracy using the largest OCD DTI dataset to date, involving 1336 adult participants (690 OCD patients and 646 healthy controls) and 317 pediatric participants (175 OCD patients and 142 healthy controls) from 18 international sites within the ENIGMA OCD Working Group. We used an automatic machine learning pipeline (with feature engineering and selection, and model optimization) and examined the cross-site generalizability of the OCD classification models using leave-one-site-out cross-validation. Our models showed low-to-moderate accuracy in classifying (1) "OCD vs. healthy controls" (Adults, receiver operator characteristic-area under the curve = 57.19 ± 3.47 in the replication set; Children, 59.8 ± 7.39), (2) "unmedicated OCD vs. healthy controls" (Adults, 62.67 ± 3.84; Children, 48.51 ± 10.14), and (3) "medicated OCD vs. unmedicated OCD" (Adults, 76.72 ± 3.97; Children, 72.45 ± 8.87). There was significant site variability in model performance (cross-validated ROC AUC ranges 51.6-79.1 in adults; 35.9-63.2 in children). Machine learning interpretation showed that diffusivity measures of the corpus callosum, internal capsule, and posterior thalamic radiation contributed to the classification of OCD from HC. The classification performance appeared greater than the model trained on grey matter morphometry in the prior ENIGMA OCD study (our study includes subsamples from the morphometry study). Taken together, this study points to the meaningful multivariate patterns of white matter features relevant to the neurobiology of OCD, but with low-to-moderate classification accuracy. The OCD classification performance may be constrained by site variability and medication effects on the white matter integrity, indicating room for improvement for future research.

Transcriptomic and neuroimaging data integration enhances machine learning classification of schizophrenia

Background

Schizophrenia is a polygenic disorder associated with changes in brain structure and function. Integrating macroscale brain features with microscale genetic data may provide a more complete overview of the disease etiology and may serve as potential diagnostic markers for schizophrenia.

Objective

We aim to systematically evaluate the impact of multi-scale neuroimaging and transcriptomic data fusion in schizophrenia classification models.

Methods

We collected brain imaging data and blood RNA sequencing data from 43 patients with schizophrenia and 60 age- and gender-matched healthy controls, and we extracted multi-omics features of macroscale brain morphology, brain structural and functional connectivity, and gene transcription of schizophrenia risk genes. Multi-scale data fusion was performed using a machine learning integration framework, together with several conventional machine learning methods and neural networks for patient classification.

Results

We found that multi-omics data fusion in conventional machine learning models achieved the highest accuracy (AUC ~0.76-0.92) in contrast to the single-modality models, with AUC improvements of 8.88 to 22.64%. Similar findings were observed for the neural network, showing an increase of 16.57% for the multimodal classification model (accuracy 71.43%) compared to the single-modal average. In addition, we identified several brain regions in the left posterior cingulate and right frontal pole that made a major contribution to disease classification.

Conclusion

We provide empirical evidence for the increased accuracy achieved by imaging genetic data integration in schizophrenia classification. Multi-scale data fusion holds promise for enhancing diagnostic precision, facilitating early detection and personalizing treatment regimens in schizophrenia.

Machine Learning of Functional Connectivity to Biotype Alcohol and Nicotine Use Disorders

BACKGROUND

Magnetic resonance imaging provides noninvasive tools to investigate alcohol use disorder (AUD) and nicotine use disorder (NUD) and neural phenotypes for genetic studies. A data-driven transdiagnostic approach could provide a new perspective on the neurobiology of AUD and NUD.

METHODS

Using samples of individuals with AUD (n = 140), individuals with NUD (n = 249), and healthy control participants (n = 461) from the UK Biobank, we integrated clinical, neuroimaging, and genetic markers to identify biotypes of AUD and NUD. We partitioned participants with AUD and NUD based on resting-state functional connectivity (FC) features associated with clinical metrics. A multitask artificial neural network was trained to evaluate the cluster-defined biotypes and jointly infer AUD and NUD diagnoses.

RESULTS

Three biotypes-primary NUD, mixed NUD/AUD with depression and anxiety, and mixed AUD/NUD-were identified. Multitask classifiers incorporating biotype knowledge achieved higher area under the curve (AUD: 0.76, NUD: 0.74) than single-task classifiers without biotype differentiation (AUD: 0.61, NUD: 0.64). Cerebellar FC features were important in distinguishing the 3 biotypes. The biotype of mixed NUD/AUD with depression and anxiety demonstrated the largest number of FC features (n = 5), all related to the visual cortex, that significantly differed from healthy control participants and were validated in a replication sample (p < .05). A polymorphism in TNRC6A was associated with the mixed AUD/NUD biotype in both the discovery (p = 7.3 × 10-5) and replication (p = 4.2 × 10-2) sets.

CONCLUSIONS

Biotyping and multitask learning using FC features can characterize the clinical and genetic profiles of AUD and NUD and help identify cerebellar and visual circuit markers to differentiate the AUD/NUD group from the healthy control group. These markers support a new growing body of literature.

Sampling inequalities affect generalization of neuroimaging-based diagnostic classifiers in psychiatry

BACKGROUND

The development of machine learning models for aiding in the diagnosis of mental disorder is recognized as a significant breakthrough in the field of psychiatry. However, clinical practice of such models remains a challenge, with poor generalizability being a major limitation.

METHODS

Here, we conducted a pre-registered meta-research assessment on neuroimaging-based models in the psychiatric literature, quantitatively examining global and regional sampling issues over recent decades, from a view that has been relatively underexplored. A total of 476 studies (n = 118,137) were included in the current assessment. Based on these findings, we built a comprehensive 5-star rating system to quantitatively evaluate the quality of existing machine learning models for psychiatric diagnoses.

RESULTS

A global sampling inequality in these models was revealed quantitatively (sampling Gini coefficient (G) = 0.81, p < .01), varying across different countries (regions) (e.g., China, G = 0.47; the USA, G = 0.58; Germany, G = 0.78; the UK, G = 0.87). Furthermore, the severity of this sampling inequality was significantly predicted by national economic levels (β =  - 2.75, p < .001, R²_adj = 0.40; r =  - .84, 95% CI: - .41 to - .97), and was plausibly predictable for model performance, with higher sampling inequality for reporting higher classification accuracy. Further analyses showed that lack of independent testing (84.24% of models, 95% CI: 81.0-87.5%), improper cross-validation (51.68% of models, 95% CI: 47.2-56.2%), and poor technical transparency (87.8% of models, 95% CI: 84.9-90.8%)/availability (80.88% of models, 95% CI: 77.3-84.4%) are prevailing in current diagnostic classifiers despite improvements over time. Relating to these observations, model performances were found decreased in studies with independent cross-country sampling validations (all p < .001, BF₁₀ > 15). In light of this, we proposed a purpose-built quantitative assessment checklist, which demonstrated that the overall ratings of these models increased by publication year but were negatively associated with model performance.

CONCLUSIONS

Together, improving sampling economic equality and hence the quality of machine learning models may be a crucial facet to plausibly translating neuroimaging-based diagnostic classifiers into clinical practice.

Evaluation of Risk of Bias in Neuroimaging-Based Artificial Intelligence Models for Psychiatric Diagnosis: A Systematic Review

IMPORTANCE

Neuroimaging-based artificial intelligence (AI) diagnostic models have proliferated in psychiatry. However, their clinical applicability and reporting quality (ie, feasibility) for clinical practice have not been systematically evaluated.

OBJECTIVE

To systematically assess the risk of bias (ROB) and reporting quality of neuroimaging-based AI models for psychiatric diagnosis.

EVIDENCE REVIEW

PubMed was searched for peer-reviewed, full-length articles published between January 1, 1990, and March 16, 2022. Studies aimed at developing or validating neuroimaging-based AI models for clinical diagnosis of psychiatric disorders were included. Reference lists were further searched for suitable original studies. Data extraction followed the CHARMS (Checklist for Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modeling Studies) and PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-analyses) guidelines. A closed-loop cross-sequential design was used for quality control. The PROBAST (Prediction Model Risk of Bias Assessment Tool) and modified CLEAR (Checklist for Evaluation of Image-Based Artificial Intelligence Reports) benchmarks were used to systematically evaluate ROB and reporting quality.

FINDINGS

A total of 517 studies presenting 555 AI models were included and evaluated. Of these models, 461 (83.1%; 95% CI, 80.0%-86.2%) were rated as having a high overall ROB based on the PROBAST. The ROB was particular high in the analysis domain, including inadequate sample size (398 of 555 models [71.7%; 95% CI, 68.0%-75.6%]), poor model performance examination (with 100% of models lacking calibration examination), and lack of handling data complexity (550 of 555 models [99.1%; 95% CI, 98.3%-99.9%]). None of the AI models was perceived to be applicable to clinical practices. Overall reporting completeness (ie, number of reported items/number of total items) for the AI models was 61.2% (95% CI, 60.6%-61.8%), and the completeness was poorest for the technical assessment domain with 39.9% (95% CI, 38.8%-41.1%).

CONCLUSIONS AND RELEVANCE

This systematic review found that the clinical applicability and feasibility of neuroimaging-based AI models for psychiatric diagnosis were challenged by a high ROB and poor reporting quality. Particularly in the analysis domain, ROB in AI diagnostic models should be addressed before clinical application.

Modern views of machine learning for precision psychiatry

In light of the National Institute of Mental Health (NIMH)'s Research Domain Criteria (RDoC), the advent of functional neuroimaging, novel technologies and methods provide new opportunities to develop precise and personalized prognosis and diagnosis of mental disorders. Machine learning (ML) and artificial intelligence (AI) technologies are playing an increasingly critical role in the new era of precision psychiatry. Combining ML/AI with neuromodulation technologies can potentially provide explainable solutions in clinical practice and effective therapeutic treatment. Advanced wearable and mobile technologies also call for the new role of ML/AI for digital phenotyping in mobile mental health. In this review, we provide a comprehensive review of ML methodologies and applications by combining neuroimaging, neuromodulation, and advanced mobile technologies in psychiatry practice. We further review the role of ML in molecular phenotyping and cross-species biomarker identification in precision psychiatry. We also discuss explainable AI (XAI) and neuromodulation in a closed human-in-the-loop manner and highlight the ML potential in multi-media information extraction and multi-modal data fusion. Finally, we discuss conceptual and practical challenges in precision psychiatry and highlight ML opportunities in future research.

Preoperative data-based deep learning model for predicting postoperative survival in pancreatic cancer patients

BACKGROUND

Pancreatic ductal adenocarcinoma (PDAC) has a poor prognosis even after curative resection. A deep learning-based stratification of postoperative survival in the preoperative setting may aid the treatment decisions for improving prognosis. This study was aimed to develop a deep learning model based on preoperative data for predicting postoperative survival.

METHODS

The patients who underwent surgery for PDAC between January 2014 and May 2015. Clinical data-based machine learning models and computed tomography (CT) data-based deep learning models were developed separately, and ensemble learning was utilized to combine two models. The primary outcomes were the prediction of 2-year overall survival (OS) and 1-year recurrence-free survival (RFS). The model's performance was measured by area under the receiver operating curve (AUC) and was compared with that of American Joint Committee on Cancer (AJCC) 8th stage.

RESULTS

The median OS and RFS were 23 and 10 months in training dataset (n = 229), and 22 and 11 months in test dataset (n = 53), respectively. The AUC of the ensemble model for predicting 2-year OS and 1-year RFS in the test dataset was 0.76 and 0.74, respectively. The performance of the ensemble model was comparable to that of the AJCC in predicting 2-year OS (AUC, 0.67; P = 0.35) and superior to the AJCC in predicting 1-year RFS (AUC, 0.54; P = 0.049).

CONCLUSION

and relevance: Our ensemble model based on routine preoperative variables showed good performance for predicting prognosis for PDAC patients after surgery.

Identifying alcohol misuse biotypes from neural connectivity markers and concurrent genetic associations

Alcohol use behaviors are highly heterogeneous, posing significant challenges to etiologic research of alcohol use disorder (AUD). Magnetic resonance imaging (MRI) provides intermediate endophenotypes in characterizing problem alcohol use and assessing the genetic architecture of addictive behavior. We used connectivity features derived from resting state functional MRI to subtype alcohol misuse (AM) behavior. With a machine learning pipeline of feature selection, dimension reduction, clustering, and classification we identified three AM biotypes-mild, comorbid, and moderate AM biotypes (MIA, COA, and MOA)-from a Human Connectome Project (HCP) discovery sample (194 drinkers). The three groups and controls (397 non-drinkers) demonstrated significant differences in alcohol use frequency during the heaviest 12-month drinking period (MOA > MIA; COA > non-drinkers) and were distinguished by connectivity features involving the frontal, parietal, subcortical and default mode networks. Further, COA relative to MIA, MOA and controls endorsed significantly higher scores in antisocial personality. A genetic association study identified that an alcohol use and antisocial behavior related variant rs16930842 from LINC01414 was significantly associated with COA. Using a replication HCP sample (28 drinkers and 46 non-drinkers), we found that subtyping helped in classifying AM from controls (area under the curve or AUC = 0.70, P < 0.005) in comparison to classifiers without subtyping (AUC = 0.60, not significant) and successfully reproduced the genetic association. Together, the results suggest functional connectivities as important features in classifying AM subgroups and the utility of reducing the heterogeneity in connectivity features among AM subgroups in advancing the research of etiological neural markers of AUD.

Analyzing Hierarchical Multi-View MRI Data With StaPLR: An Application to Alzheimer's Disease Classification

Multi-view data refers to a setting where features are divided into feature sets, for example because they correspond to different sources. Stacked penalized logistic regression (StaPLR) is a recently introduced method that can be used for classification and automatically selecting the views that are most important for prediction. We introduce an extension of this method to a setting where the data has a hierarchical multi-view structure. We also introduce a new view importance measure for StaPLR, which allows us to compare the importance of views at any level of the hierarchy. We apply our extended StaPLR algorithm to Alzheimer's disease classification where different MRI measures have been calculated from three scan types: structural MRI, diffusion-weighted MRI, and resting-state fMRI. StaPLR can identify which scan types and which derived MRI measures are most important for classification, and it outperforms elastic net regression in classification performance.

Machine learning approaches for parsing comorbidity/heterogeneity in antisociality and substance use disorders: A primer

By some accounts, as many as 93% of individuals diagnosed with antisocial personality disorder (ASPD) or psychopathy also meet criteria for some form of substance use disorder (SUD). This high level of comorbidity, combined with an overlapping biopsychosocial profile, and potentially interacting features, has made it difficult to delineate the shared/unique characteristics of each disorder. Moreover, while rarely acknowledged, both SUD and antisociality exist as highly heterogeneous disorders in need of more targeted parcellation. While emerging data-driven nosology for psychiatric disorders (e.g., Research Domain Criteria (RDoC), Hierarchical Taxonomy of Psychopathology (HiTOP)) offers the opportunity for a more systematic delineation of the externalizing spectrum, the interrogation of large, complex neuroimaging-based datasets may require data-driven approaches that are not yet widely employed in psychiatric neuroscience. With this in mind, the proposed article sets out to provide an introduction into machine learning methods for neuroimaging that can help parse comorbid, heterogeneous externalizing samples. The modest machine learning work conducted to date within the externalizing domain demonstrates the potential utility of the approach but remains highly nascent. Within the paper, we make suggestions for how future work can make use of machine learning methods, in combination with emerging psychiatric nosology systems, to further diagnostic and etiological understandings of the externalizing spectrum. Finally, we briefly consider some challenges that will need to be overcome to encourage further progress in the field.

Accelerated Aging of the Amygdala in Alcohol Use Disorders: Relevance to the Dark Side of Addiction

Here we assessed changes in subcortical volumes in alcohol use disorder (AUD). A simple morphometry-based classifier (MC) was developed to identify subcortical volumes that distinguished 32 healthy controls (HCs) from 33 AUD patients, who were scanned twice, during early and later withdrawal, to assess the effect of abstinence on MC-features (Discovery cohort). We validated the novel classifier in an independent Validation cohort (19 AUD patients and 20 HCs). MC-accuracy reached 80% (Discovery) and 72% (Validation). MC features included the hippocampus, amygdala, cerebellum, putamen, corpus callosum, and brain stem, which were smaller and showed stronger age-related decreases in AUD than HCs, and the ventricles and cerebrospinal fluid, which were larger in AUD and older participants. The volume of the amygdala showed a positive association with anxiety and negative urgency in AUD. Repeated imaging during the third week of detoxification revealed slightly larger subcortical volumes in AUD patients, consistent with partial recovery during abstinence. The steeper age-associated volumetric reductions in stress- and reward-related subcortical regions in AUD are consistent with accelerated aging, whereas the amygdalar associations with negative urgency and anxiety in AUD patients support its involvement in the "dark side of addiction".

Promises and pitfalls of deep neural networks in neuroimaging-based psychiatric research

By promising more accurate diagnostics and individual treatment recommendations, deep neural networks and in particular convolutional neural networks have advanced to a powerful tool in medical imaging. Here, we first give an introduction into methodological key concepts and resulting methodological promises including representation and transfer learning, as well as modelling domain-specific priors. After reviewing recent applications within neuroimaging-based psychiatric research, such as the diagnosis of psychiatric diseases, delineation of disease subtypes, normative modeling, and the development of neuroimaging biomarkers, we discuss current challenges. This includes for example the difficulty of training models on small, heterogeneous and biased data sets, the lack of validity of clinical labels, algorithmic bias, and the influence of confounding variables.