Diagnostic and Prognostic Models Based on Electrocardiograms for Rapid Clinical Applications.

Leveraging artificial intelligence (AI) for the analysis of electrocardiograms (ECG) has the potential to transform diagnosis and estimate the prognosis of not only cardiac but, increasingly, non-cardiac conditions. In this review, we summarize clinical studies and AI-enhanced ECG-based clinical applications in the early detection, diagnosis, and estimating prognosis of cardiovascular diseases (CVD) in the last five years (2019-2023). With advancements in deep learning and the rapid increased use of ECG technologies, a large number of clinical studies have been published. However, a majority of these studies are single-center, retrospective, proof-of-concept studies that lack external validation. Prospective studies that progress from development toward deployment in clinical settings account for <15% of the studies. Successful implementations of ECG-based AI applications that have received approval from the Food and Drug Administration (FDA) have been developed through commercial collaborations, with about half of them being for mobile or wearable devices. The field is in its early stages, and overcoming several obstacles is essential, such as prospective validation in multi-center large datasets, addressing technical issues, bias, privacy, data security, model generalizability, and global scalability. This review concludes with a discussion of these challenges and potential solutions. By providing a holistic view of the state of AI in ECG analysis, this review aims to set a foundation for future research directions, emphasizing the need for comprehensive, clinically integrated, and globally deployable AI solutions in CVD management.

Development and validation of machine learning algorithms based on electrocardiograms for cardiovascular diagnoses at the population level.

Artificial intelligence-enabled electrocardiogram (ECG) algorithms are gaining prominence for the early detection of cardiovascular (CV) conditions, including those not traditionally associated with conventional ECG measures or expert interpretation. This study develops and validates such models for simultaneous prediction of 15 different common CV diagnoses at the population level. We conducted a retrospective study that included 1,605,268 ECGs of 244,077 adult patients presenting to 84 emergency departments or hospitals, who underwent at least one 12-lead ECG from February 2007 to April 2020 in Alberta, Canada, and considered 15 CV diagnoses, as identified by International Classification of Diseases, 10th revision (ICD-10) codes: atrial fibrillation (AF), supraventricular tachycardia (SVT), ventricular tachycardia (VT), cardiac arrest (CA), atrioventricular block (AVB), unstable angina (UA), ST-elevation myocardial infarction (STEMI), non-STEMI (NSTEMI), pulmonary embolism (PE), hypertrophic cardiomyopathy (HCM), aortic stenosis (AS), mitral valve prolapse (MVP), mitral valve stenosis (MS), pulmonary hypertension (PHTN), and heart failure (HF). We employed ResNet-based deep learning (DL) using ECG tracings and extreme gradient boosting (XGB) using ECG measurements. When evaluated on the first ECGs per episode of 97,631 holdout patients, the DL models had an area under the receiver operating characteristic curve (AUROC) of <80% for 3 CV conditions (PTE, SVT, UA), 80-90% for 8 CV conditions (CA, NSTEMI, VT, MVP, PHTN, AS, AF, HF) and an AUROC > 90% for 4 diagnoses (AVB, HCM, MS, STEMI). DL models outperformed XGB models with about 5% higher AUROC on average. Overall, ECG-based prediction models demonstrated good-to-excellent prediction performance in diagnosing common CV conditions.

Development and validation of echocardiography-based machine-learning models to predict mortality.

BACKGROUND: Echocardiography (echo) based machine learning (ML) models may be useful in identifying patients at high-risk of all-cause mortality. METHODS: We developed ML models (ResNet deep learning using echo videos and CatBoost gradient boosting using echo measurements) to predict 1-year, 3-year, and 5-year mortality. Models were trained on the Mackay dataset, Taiwan (6083 echos, 3626 patients) and validated in the Alberta HEART dataset, Canada (997 echos, 595 patients). We examined the performance of the models overall, and in subgroups (healthy controls, at risk of heart failure (HF), HF with reduced ejection fraction (HFrEF) and HF with preserved ejection fraction (HFpEF)). We compared the models' performance to the MAGGIC risk score, and examined the correlation between the models' predicted probability of death and baseline quality of life as measured by the Kansas City Cardiomyopathy Questionnaire (KCCQ). FINDINGS: Mortality rates at 1-, 3- and 5-years were 14.9%, 28.6%, and 42.5% in the Mackay cohort, and 3.0%, 10.3%, and 18.7%, in the Alberta HEART cohort. The ResNet and CatBoost models achieved area under the receiver-operating curve (AUROC) between 85% and 92% in internal validation. In external validation, the AUROCs for the ResNet (82%, 82%, and 78%) were significantly better than CatBoost (78%, 73%, and 75%), for 1-, 3- and 5-year mortality prediction respectively, with better or comparable performance to the MAGGIC score. ResNet models predicted higher probability of death in the HFpEF and HFrEF (30%-50%) subgroups than in controls and at risk patients (5%-20%). The predicted probabilities of death correlated with KCCQ scores (all p < 0.05). INTERPRETATION: Echo-based ML models to predict mortality had good internal and external validity, were generalizable, correlated with patients' quality of life, and are comparable to an established HF risk score. These models can be leveraged for automated risk stratification at point-of-care. FUNDING: Funding for Alberta HEART was provided by an Alberta Innovates - Health Solutions Interdisciplinary Team Grant no. AHFMRITG 200801018. P.K. holds a Canadian Institutes of Health Research (CIHR) Sex and Gender Science Chair and a Heart & Stroke Foundation Chair in Cardiovascular Research. A.V. and V.S. received funding from the Mitacs Globalink Research Internship.

Towards artificial intelligence-based learning health system for population-level mortality prediction using electrocardiograms.

The feasibility and value of linking electrocardiogram (ECG) data to longitudinal population-level administrative health data to facilitate the development of a learning healthcare system has not been fully explored. We developed ECG-based machine learning models to predict risk of mortality among patients presenting to an emergency department or hospital for any reason. Using the 12-lead ECG traces and measurements from 1,605,268 ECGs from 748,773 healthcare episodes of 244,077 patients (2007-2020) in Alberta, Canada, we developed and validated ResNet-based Deep Learning (DL) and gradient boosting-based XGBoost (XGB) models to predict 30-day, 1-year, and 5-year mortality. The models for 30-day, 1-year, and 5-year mortality were trained on 146,173, 141,072, and 111,020 patients and evaluated on 97,144, 89,379, and 55,650 patients, respectively. In the evaluation cohort, 7.6%, 17.3%, and 32.9% patients died by 30-days, 1-year, and 5-years, respectively. ResNet models based on ECG traces alone had good-to-excellent performance with area under receiver operating characteristic curve (AUROC) of 0.843 (95% CI: 0.838-0.848), 0.812 (0.808-0.816), and 0.798 (0.792-0.803) for 30-day, 1-year and 5-year prediction, respectively; and were superior to XGB models based on ECG measurements with AUROC of 0.782 (0.776-0.789), 0.784 (0.780-0.788), and 0.746 (0.740-0.751). This study demonstrates the validity of ECG-based DL mortality prediction models at the population-level that can be leveraged for prognostication at point of care.

Resting-state functional connectivity correlates of antipsychotic treatment in unmedicated schizophrenia.

BACKGROUND: Antipsychotics may modulate the resting state functional connectivity(rsFC) to improve clinical symptoms in schizophrenia(Sz). Existing literature has potential confounders like past medication effects and evaluating preselected regions/networks. We aimed to evaluate connectivity pattern changes with antipsychotics in unmedicated Sz using Multivariate pattern analysis(MVPA), a data-driven technique for whole-brain connectome analysis. METHODS: Forty-seven unmedicated patients with Sz(DSM-IV-TR) underwent clinical evaluation and neuroimaging at baseline and after 3-months of antipsychotic treatment. Resting-state functional MRI was analysed using group-MVPA to derive 5-components. The brain region with significant connectivity pattern changes with antipsychotics was identified, and post-hoc seed-to-voxel analysis was performed to identify connectivity changes and their association with symptom changes. RESULTS: Connectome-MVPA analysis revealed the connectivity pattern of a cluster localised to left anterior cingulate and paracingulate gyri (ACC/PCG) (peak coordinates:x = -04,y = +30,z = +26;k = 12;cluster-pFWE=0.002) to differ significantly after antipsychotics. Specifically, its connections with clusters of precuneus/posterior cingulate cortex(PCC) and left inferior temporal gyrus(ITG) correlated with improvement in positive and negative symptoms scores, respectively. CONCLUSION: ACC/PCG, a hub of the default mode network, seems to mediate the antipsychotic effects in unmedicated Sz. Evaluating causality models with data from randomised controlled design using the MVPA approach would further enhance our understanding of therapeutic connectomics in Sz.

Superior temporal gyrus functional connectivity predicts transcranial direct current stimulation response in Schizophrenia: A machine learning study.

Transcranial direct current stimulation (tDCS) is a promising adjuvant treatment for persistent auditory verbal hallucinations (AVH) in Schizophrenia (SZ). Nonetheless, there is considerable inter-patient variability in the treatment response of AVH to tDCS in SZ. Machine-learned models have the potential to predict clinical response to tDCS in SZ. This study aims to examine the feasibility of identifying SZ patients with persistent AVH (SZ-AVH) who will respond to tDCS based on resting-state functional connectivity (rs-FC). Thirty-four SZ-AVH patients underwent resting-state functional MRI at baseline followed by add-on, twice-daily, 20-min sessions with tDCS (conventional/high-definition) for 5 days. A machine learning model was developed to identify tDCS treatment responders based on the rs-FC pattern, using the left superior temporal gyrus (LSTG) as the seed region. Functional connectivity between LSTG and brain regions involved in auditory and sensorimotor processing emerged as the important predictors of the tDCS treatment response. L1-regularized logistic regression model had an overall accuracy of 72.5% in classifying responders vs. non-responders. This model outperformed the state-of-the-art convolutional neural networks (CNN) model-both without (59.41%) and with pre-training (68.82%). It also outperformed the L1-logistic regression model trained with baseline demographic features and clinical scores of SZ patients. This study reports the first evidence that rs-fMRI-derived brain connectivity pattern can predict the clinical response of persistent AVH to add-on tDCS in SZ patients with 72.5% accuracy.

Analyzing biomarker discovery: Estimating the reproducibility of biomarker sets.

Many researchers try to understand a biological condition by identifying biomarkers. This is typically done using univariate hypothesis testing over a labeled dataset, declaring a feature to be a biomarker if there is a significant statistical difference between its values for the subjects with different outcomes. However, such sets of proposed biomarkers are often not reproducible - subsequent studies often fail to identify the same sets. Indeed, there is often only a very small overlap between the biomarkers proposed in pairs of related studies that explore the same phenotypes over the same distribution of subjects. This paper first defines the Reproducibility Score for a labeled dataset as a measure (taking values between 0 and 1) of the reproducibility of the results produced by a specified fixed biomarker discovery process for a given distribution of subjects. We then provide ways to reliably estimate this score by defining algorithms that produce an over-bound and an under-bound for this score for a given dataset and biomarker discovery process, for the case of univariate hypothesis testing on dichotomous groups. We confirm that these approximations are meaningful by providing empirical results on a large number of datasets and show that these predictions match known reproducibility results. To encourage others to apply this technique to analyze their biomarker sets, we have also created a publicly available website, https://biomarker.shinyapps.io/BiomarkerReprod/, that produces these Reproducibility Score approximations for any given dataset (with continuous or discrete features and binary class labels).

Multi-Source Domain Adaptation Techniques for Mitigating Batch Effects: A Comparative Study.

The past decade has seen an increasing number of applications of deep learning (DL) techniques to biomedical fields, especially in neuroimaging-based analysis. Such DL-based methods are generally data-intensive and require a large number of training instances, which might be infeasible to acquire from a single acquisition site, especially for data, such as fMRI scans, due to the time and costs that they demand. We can attempt to address this issue by combining fMRI data from various sites, thereby creating a bigger heterogeneous dataset. Unfortunately, the inherent differences in the combined data, known as batch effects, often hamper learning a model. To mitigate this issue, techniques such as multi-source domain adaptation [Multi-source Domain Adversarial Networks (MSDA)] aim at learning an effective classification function that uses (learned) domain-invariant latent features. This article analyzes and compares the performance of various popular MSDA methods [MDAN, Domain AggRegation Networks (DARN), Multi-Domain Matching Networks (MDMN), and Moment Matching for MSDA (M3SDA)] at predicting different labels (illness, age, and sex) of images from two public rs-fMRI datasets: ABIDE 1and ADHD-200. It also evaluates the impact of various conditions such as class imbalance, the number of sites along with a comparison of the degree of adaptation of each of the methods, thereby presenting the effectiveness of MSDA models in neuroimaging-based applications.

Factors associated with SARS-CoV-2 test positivity in long-term care homes: A population-based cohort analysis using machine learning.

BACKGROUND: SARS-Cov-2 infection rates are high among residents of long-term care (LTC) homes. We used machine learning to identify resident and community characteristics predictive of SARS-Cov-2 infection. METHODS: We linked 26 population-based health and administrative databases to identify the population of all LTC residents tested for SARS-Cov-2 infection in Ontario, Canada. Using ensemble-based algorithms, we examined 484 factors, including individual-level demographics, healthcare use, comorbidities, functional status, and laboratory results; and community-level characteristics to identify factors predictive of infection. Analyses were performed separately for January to April (early wave 1) and May to August (late wave 1). FINDINGS: Among 80,784 LTC residents, 64,757 (80.2%) were tested for SARS-Cov-2 (median age 86 (78-91) years, 30.6% male), of whom 10.2% of 33,519 and 5.2% of 31,238 tested positive in early and late wave 1, respectively. In the late phase (when restriction of visitors, closure of communal spaces, and universal masking in LTC were routine), regional-level characteristics comprised 33 of the top 50 factors associated with testing positive, while laboratory values and comorbidities were also predictive. The c-index of the final model was 0.934, and sensitivity was 0.887. In the highest versus lowest risk quartiles, the odds ratio for infection was 114.3 (95% CI 38.6-557.3). LTC-related geographic variations existed in the distribution of observed infection rates and the proportion of residents at highest risk. INTERPRETATION: Machine learning informed evaluation of predicted and observed risks of SARS-CoV-2 infection at the resident and LTC levels, and may inform initiatives to improve care quality in this setting. FUNDING: Funded by a Canadian Institutes of Health Research, COVID-19 Rapid Research Funding Opportunity grant (# VR4 172736) and a Peter Munk Cardiac Centre Innovation Grant. Dr. D. Lee is the Ted Rogers Chair in Heart Function Outcomes, University Health Network, University of Toronto. Dr. Austin is supported by a Mid-Career investigator award from the Heart and Stroke Foundation. Dr. McAlister is supported by an Alberta Health Services Chair in Cardiovascular Outcomes Research. Dr. Kaul is the CIHR Sex and Gender Science Chair and the Heart & Stroke Chair in Cardiovascular Research. Dr. Rochon holds the RTO/ERO Chair in Geriatric Medicine from the University of Toronto. Dr. B. Wang holds a CIFAR AI chair at the Vector Institute.

Prediction of Obsessive-Compulsive Disorder: Importance of Neurobiology-Aided Feature Design and Cross-Diagnosis Transfer Learning.

BACKGROUND: Machine learning applications using neuroimaging provide a multidimensional, data-driven approach that captures the level of complexity necessary for objectively aiding diagnosis and prognosis in psychiatry. However, models learned from small training samples often have limited generalizability, which continues to be a problem with automated diagnosis of mental illnesses such as obsessive-compulsive disorder (OCD). Earlier studies have shown that features incorporating prior neurobiological knowledge of brain function and combining brain parcellations from various sources can potentially improve the overall prediction. However, it is unknown whether such knowledge-driven methods can provide a performance that is comparable to state-of-the-art approaches based on neural networks. METHODS: In this study, we apply a transparent and explainable multiparcellation ensemble learning framework EMPaSchiz (Ensemble algorithm with Multiple Parcellations for Schizophrenia prediction) to the task of predicting OCD, based on a resting-state functional magnetic resonance imaging dataset of 350 subjects. Furthermore, we apply transfer learning using the features found effective for schizophrenia to OCD to leverage the commonality in brain alterations across these psychiatric diagnoses. RESULTS: We show that our knowledge-based approach leads to a prediction performance of 80.3% accuracy for OCD diagnosis that is better than domain-agnostic and automated feature design using neural networks. Furthermore, we show that a selection of reduced feature sets can be transferred from schizophrenia to the OCD prediction model without significant loss in prediction performance. CONCLUSIONS: This study presents a machine learning framework for OCD prediction with neurobiology-aided feature design using resting-state functional magnetic resonance imaging that is generalizable and reasonably interpretable.

Learning the structure-activity relationship (SAR) of the Wittig reaction from genetically-encoded substrates.

The Wittig reaction can be used for late stage functionalization of proteins and peptides to ligate glycans, pharmacophores, and many other functionalities. In this manuscript, we modified 160 000 N-terminal glyoxaldehyde peptides displayed on phage with the Wittig reaction by using a biotin labeled ylide under conditions that functionalize only 1% of the library population. Deep-sequencing of the biotinylated and input populations estimated the rate of conversion for each sequence. This "deep conversion" (DC) from deep sequencing correlates with rate constants measured by HPLC. Peptide sequences with fast and slow reactivity highlighted the critical role of primary backbone amides (N-H) in accelerating the rate of the aqueous Wittig reaction. Experimental measurement of reaction rates and density functional theory (DFT) computation of the transition state geometries corroborated this relationship. We also collected deep-sequencing data to build structure-activity relationship (SAR) models that can predict the DC value of the Wittig reaction. By using these data, we trained two classifier models based on gradient boosted trees. These classifiers achieved area under the ROC (receiver operating characteristic) curve (ROC AUC) of 81.2 ± 0.4 and 73.7 ± 0.8 (90-92% accuracy) in determining whether a sequence belonged to the top 5% or the bottom 5% in terms of its reactivity. This model can suggest new peptides never observed experimentally with 'HIGH' or 'LOW' reactivity. Experimental measurement of reaction rates for 11 new sequences corroborated the predictions for 8 of them. We anticipate that phage-displayed peptides and related mRNA or DNA-displayed substrates can be employed in a similar fashion to study the substrate scope and mechanisms of many other chemical reactions.

Predictors of mortality among long-term care residents with SARS-CoV-2 infection.

BACKGROUND: While individuals living in long-term care (LTC) homes have experienced adverse outcomes of SARS-CoV-2 infection, few studies have examined a broad range of predictors of 30-day mortality in this population. METHODS: We studied residents living in LTC homes in Ontario, Canada, who underwent PCR testing for SARS-CoV-2 infection from January 1 to August 31, 2020, and examined predictors of all-cause death within 30 days after a positive test for SARS-CoV-2. We examined a broad range of risk factor categories including demographics, comorbidities, functional status, laboratory tests, and characteristics of the LTC facility and surrounding community were examined. In total, 304 potential predictors were evaluated for their association with mortality using machine learning (Random Forest). RESULTS: A total of 64,733 residents of LTC, median age 86 (78, 91) years (31.8% men), underwent SARS-CoV-2 testing, of whom 5029 (7.8%) tested positive. Thirty-day mortality rates were 28.7% (1442 deaths) after a positive test. Of 59,702 residents who tested negative, 2652 (4.4%) died within 30 days of testing. Predictors of mortality after SARS-CoV-2 infection included age, functional status (e.g., activity of daily living score and pressure ulcer risk), male sex, undernutrition, dehydration risk, prior hospital contacts for respiratory illness, and duration of comorbidities (e.g., heart failure, COPD). Lower GFR, hemoglobin concentration, lymphocyte count, and serum albumin were associated with higher mortality. After combining all covariates to generate a risk index, mortality rate in the highest risk quartile was 48.3% compared with 7% in the first quartile (odds ratio 12.42, 95%CI: 6.67, 22.80, p < 0.001). Deaths continued to increase rapidly for 15 days after the positive test. CONCLUSIONS: LTC residents, particularly those with reduced functional status, comorbidities, and abnormalities on routine laboratory tests, are at high risk for mortality after SARS-CoV-2 infection. Recognizing high-risk residents in LTC may enhance institution of appropriate preventative measures.

Pars Triangularis Volume Asymmetry and Schneiderian First Rank Symptoms in Antipsychotic-naïve Schizophrenia.

OBJECTIVE: Schizophrenia is a disorder of language and self, with first-rank symptoms (FRS) as one of the predominant features in a subset of patients. Abnormal language lateralization is hypothesized to underlie the neurobiology of FRS in schizophrenia. The role of Broca's area with its right-hemispheric counterpart, consisting of pars triangularis (PTr) and pars opercularis (POp) of the inferior frontal gyrus in FRS is undetermined. We compared the volumes and asymmetries of PTr & POp in anti-psychotic-naive schizophrenia patients with FRS (FRS[＋]) with those without FRS (FRS[-]) and healthy-controls (HC) using three dimensional, interactive, semi-automated volumetric morphometry. METHODS: Antipsychotic naïve FRS(＋) (n = 27), FRS(-) (n = 24) and HC (n = 51) were carefully assessed with structured and semi-structured clinical tools. T1-weighted images were acquired in a 3T scanner. Volumes of regions of interest were measured independently for both sides using slicer-3D software, and asymmetry indices were calculated. RESULTS: FRS(＋) but not FRS(-) had a significant volume deficit in right PTr after controlling for the potential confounding effects of age, sex, and intracranial volume (p = 0.029). There was a significant leftward asymmetry of PTr in patients with FRS (i.e., leftward asymmetry in patients) (p = 0.026). No significant volume/asymmetry abnormalities were observed in POp. CONCLUSION: Study findings suggest reduced right PTr volume with leftward asymmetry to be associated with FRS in schizophrenia. This is consistent with the loss of Yakovlevian torque in schizophrenia. Role of PTr in the neurobiology of schizophrenia as a disorder of self, speech, and social cognition needs further systematic evaluation in future research.

Antisaccade task performance in obsessive-compulsive disorder and its clinical correlates.

OBJECTIVE: Obsessive-Compulsive Disorder (OCD) is characterized by abnormalities in the cortico-striato-thalamo-cortical (CSTC) circuitry of the brain. Antisaccade eye movement tasks measure aspects of the voluntary control of behaviour that are sensitive to CSTC circuitry dysfunction. METHOD: In this study, we examined antisaccade eye movement parameters of OCD patients in comparison with healthy controls (HC). In addition, we also examined the relationship between the antisaccade eye movement parameters and the severity of OCD. Antisaccade performance among right handed OCD patients (N = 65) was compared to matched right handed HC (N = 57). Eye tracking data during the task performance were collected using an Eye-Link eye-tracker at 1000-Hz sampling rate. OCD symptom severity was evaluated using Yale-Brown obsessive compulsive scale. RESULTS: The antisaccade error percentage was significantly greater in OCD patients than HC (p < 0.001). In addition, OCD patients had less accurate final eye position compared to HC (p < 0.001). There were no significant correlation between antisaccade parameters and OCD severity measures. CONCLUSION: Deficient performance in antisaccade task supports CSTC abnormality in OCD and this appears to be independent of the illness severity. Examining this in remitted participants with OCD and in unaffected first degree relatives could help ascertaining their endophenotype validity.

Impact of NRG1 HapICE gene variants on digit ratio and dermatoglyphic measures in schizophrenia.

Multiple lines of evidence have suggested a potential role of Neuregulin-1 (NRG1) in the neurodevelopmental pathogenesis of schizophrenia. Interaction between genetic risk variants present within NRG1 locus and non-specific gestational putative insults can significantly impair crucial processes of brain development. Such genetic effects can be analyzed through the assessment of digit ratio and dermatoglyphic patterns. We examined the role of two well-replicated polymorphisms of NRG1 (SNP8NRG221533 and SNP8NRG243177) on schizophrenia risk and its probable impact on the digit ratio and dermatoglyphic measures in patients (N = 221) and healthy controls (N = 200). In schizophrenia patients, but not in healthy controls, a significant association between NRG1 SNP8NRG221533 C/C genotype with lower left 2D:4D ratio, as well as with higher FA_TbcRC and DA_TbcRC. The substantial effect of SNP8NRG221533 on both digit ratio and dermatoglyphic measures suggest a potential role for NRG1 gene variants on neurodevelopmental pathogenesis of schizophrenia.

Extending schizophrenia diagnostic model to predict schizotypy in first-degree relatives.

Recently, we developed a machine-learning algorithm "EMPaSchiz" that learns, from a training set of schizophrenia patients and healthy individuals, a model that predicts if a novel individual has schizophrenia, based on features extracted from his/her resting-state functional magnetic resonance imaging. In this study, we apply this learned model to first-degree relatives of schizophrenia patients, who were found to not have active psychosis or schizophrenia. We observe that the participants that this model classified as schizophrenia patients had significantly higher "schizotypal personality scores" than those who were not. Further, the "EMPaSchiz probability score" for schizophrenia status was significantly correlated with schizotypal personality score. This demonstrates the potential of machine-learned diagnostic models to predict state-independent vulnerability, even when symptoms do not meet the full criteria for clinical diagnosis.

Leukocyte mitochondrial DNA copy number in schizophrenia.

OBJECTIVE: Schizophrenia is a complex neuropsychiatric disorder with significant genetic predisposition. In a subset of schizophrenia patients, mitochondrial dysfunction could be explained by the genomic defects like mitochondrial DNA Copy Number Variations, which are considered as a sensitive index of cellular oxidative stress. Given the high energy demands for neuronal functions, altered Mitochondrial DNA copy number (mtDNAcn) and consequent impaired mitochondrial physiology would significantly influence schizophrenia pathogenesis. In this context, we have made an attempt to study mitochondrial dysfunction in schizophrenia by assessing mtDNAcn in antipsychotic-naïve/free schizophrenia patients. METHOD: mtDNAcn was measured in 90 antipsychotic-naïve / free schizophrenia (SCZ) patients and 147 Healthy Controls (HC). The relative mtDNAcn was determined by quantitative real-time polymerase chain reaction (qPCR) using TaqMan® multiplex assay method. RESULT: A statistically significant difference between groups [t = 5.22, P < 0.001] was observed, with significantly lower mtDNAcn in SCZ compared to HC. The group differences persisted even after controlling for age and sex [F (4, 232) = 22.68, P < 0.001, η2 = 0.09]. CONCLUSION: Lower mtDNAcn in SCZ compared to HC suggests that mtDNAcn may hold potential to serve as an important proxy marker of mitochondrial function in antipsychotic-naïve/free SCZ patients.

Differential impact of interleukin-6 promoter gene polymorphism on hippocampal volume in antipsychotic-naïve schizophrenia patients.

BACKGROUND: Differential susceptibility model hypothesizes that a genotype need not be unfavorable all the time as postulated in stress-diathesis model but can be beneficial in a supportive context. Single-nucleotide polymorphism (SNP) (rs18000795) within the promoter region of interleukin-6 (IL-6) gene was earlier noted to have a differential susceptibility on hippocampal volume in schizophrenia (SCZ). MATERIALS AND METHODS: We examined antipsychotic-naïve/free SCZ patients (n = 35) in comparison with healthy controls (n = 68). Hippocampus volumes were assessed in 3 Tesla magnetic resonance imaging using voxel-based morphometry. Region of interest analysis was done using hippocampus mask. IL-6 SNP (rs1800795) was genotyped using TaqMan allelic discrimination assay. RESULTS: A significantly deficient right (T = 3.03; K E= 392; P SVC-FWE= 0.04) and left (T = 3.03; K E= 47; P uncorr= 0.03) hippocampal gray matter volumes were noted in SCZ patients after controlling for the potential confounding effects of age, sex, and total brain volume. There was a significant diagnosis x rs1800795 genotype interaction involving both left (T = 2.17, K E= 95, P uncorr= 0.02) and right (T = 1.82, K E= 29, P uncorr= 0.04) hippocampal volumes. Patients with GG (left: F =5.78; P = 0.02; right: F =6.21; P = 0.01) but not GC/CC genotype (left: F =0.89; P = 0.34; right: F <0.01; P = 0.95) had volume depletion. CONCLUSION: A paradoxical smaller hippocampal volume with GG genotype was noted in SCZ. Further elucidation of its mechanistic basis might have translational implications.

Tolerance of transcranial direct current stimulation in psychiatric disorders: An analysis of 2000+ sessions.

Transcranial direct current stimulation (tDCS), a non-invasive, neuromodulatory technique, is being increasingly applied to several psychiatric disorders. In this study, we describe the side-effect profile of repeated tDCS sessions (N = 2005) that were administered to 171 patients (156 adults and 15 adolescents) with different psychiatric disorders [schizophrenia [N = 109], obsessive-compulsive disorder [N = 28], alcohol dependence syndrome [N = 13], mild cognitive impairment [N = 10], depression [N = 6], dementia [N = 2] and other disorders [N = 3]]. tDCS was administered at a constant current strength of 2 mA with additional ramp-up and ramp-down phase of 20 s each at the beginning and end of the session, respectively. Other tDCS protocol parameters were: schizophrenia and obsessive-compulsive disorder: 5-days of twice-daily 20-min sessions with an inter-session interval of 3-h; Mild cognitive impairment/dementia and alcohol dependence syndrome: at least 5-days of once-daily 20-min session; Depression: 10-days of once-daily 30 min session. At the end of each tDCS session, any adverse event observed by the administrator and/or reported by the patient was systematically assessed using a comprehensive questionnaire. The commonly reported adverse events during tDCS included burning sensations (16.2%), skin redness (12.3%), scalp pain (10.1%), itching (6.7%), and tingling (6.3%). Most of the adverse events were noted to be mild, transient and well-tolerated. In summary, our observations suggest that tDCS is a safe mode for therapeutic non-invasive neuromodulation in psychiatric disorders in adults as well as the adolescent population.

Towards artificial intelligence in mental health by improving schizophrenia prediction with multiple brain parcellation ensemble-learning.

In the literature, there are substantial machine learning attempts to classify schizophrenia based on alterations in resting-state (RS) brain patterns using functional magnetic resonance imaging (fMRI). Most earlier studies modelled patients undergoing treatment, entailing confounding with drug effects on brain activity, and making them less applicable to real-world diagnosis at the point of first medical contact. Further, most studies with classification accuracies >80% are based on small sample datasets, which may be insufficient to capture the heterogeneity of schizophrenia, limiting generalization to unseen cases. In this study, we used RS fMRI data collected from a cohort of antipsychotic drug treatment-naive patients meeting DSM IV criteria for schizophrenia (N = 81) as well as age- and sex-matched healthy controls (N = 93). We present an ensemble model -- EMPaSchiz (read as 'Emphasis'; standing for 'Ensemble algorithm with Multiple Parcellations for Schizophrenia prediction') that stacks predictions from several 'single-source' models, each based on features of regional activity and functional connectivity, over a range of different a priori parcellation schemes. EMPaSchiz yielded a classification accuracy of 87% (vs. chance accuracy of 53%), which out-performs earlier machine learning models built for diagnosing schizophrenia using RS fMRI measures modelled on large samples (N > 100). To our knowledge, EMPaSchiz is first to be reported that has been trained and validated exclusively on data from drug-naive patients diagnosed with schizophrenia. The method relies on a single modality of MRI acquisition and can be readily scaled-up without needing to rebuild parcellation maps from incoming training images.