Application of Single-Nucleotide Polymorphisms in the Diagnosis of Autism Spectrum Disorders: A Preliminary Study with Artificial Neural Networks

A Systematic Review of Genetics- and Molecular-Pathway-Based Machine Learning Models for Neurological Disorder Diagnosis

The process of identification and management of neurological disorder conditions faces challenges, prompting the investigation of novel methods in order to improve diagnostic accuracy. In this study, we conducted a systematic literature review to identify the significance of genetics- and molecular-pathway-based machine learning (ML) models in treating neurological disorder conditions. According to the study's objectives, search strategies were developed to extract the research studies using digital libraries. We followed rigorous study selection criteria. A total of 24 studies met the inclusion criteria and were included in the review. We classified the studies based on neurological disorders. The included studies highlighted multiple methodologies and exceptional results in treating neurological disorders. The study findings underscore the potential of the existing models, presenting personalized interventions based on the individual's conditions. The findings offer better-performing approaches that handle genetics and molecular data to generate effective outcomes. Moreover, we discuss the future research directions and challenges, emphasizing the demand for generalizing existing models in real-world clinical settings. This study contributes to advancing knowledge in the field of diagnosis and management of neurological disorders.

Altered Gut Microbiota and Short-chain Fatty Acids in Chinese Children with Constipated Autism Spectrum Disorder

Gastrointestinal symptoms are more prevalent in children with autism spectrum disorder (ASD) than in typically developing (TD) children. Constipation is a significant gastrointestinal comorbidity of ASD, but the associations among constipated autism spectrum disorder (C-ASD), microbiota and short-chain fatty acids (SCFAs) are still debated. We enrolled 80 children, divided into the C-ASD group (n = 40) and the TD group (n = 40). In this study, an integrated 16S rRNA gene sequencing and gas chromatography-mass spectrometry-based metabolomics approach was applied to explore the association of the gut microbiota and SCFAs in C-ASD children in China. The community diversity estimated by the Observe, Chao1, and ACE indices was significantly lower in the C-ASD group than in the TD group. We observed that Ruminococcaceae_UCG_002, Erysipelotrichaceae_UCG_003, Phascolarctobacterium, Megamonas, Ruminiclostridium_5, Parabacteroides, Prevotella_2, Fusobacterium, and Prevotella_9 were enriched in the C-ASD group, and Anaerostipes, Lactobacillus, Ruminococcus_gnavus_group, Lachnospiraceae_NK4A136_group, Ralstonia, Eubacterium_eligens_group, and Ruminococcus_1 were enriched in the TD group. The propionate levels, which were higher in the C-ASD group, were negatively correlated with the abundance of Lactobacillus taxa, but were positively correlated with the severity of ASD symptoms. The random forest model, based on the 16 representative discriminant genera, achieved a high accuracy (AUC = 0.924). In conclusion, we found that C-ASD is related to altered gut microbiota and SCFAs, especially decreased abundance of Lactobacillus and excessive propionate in faeces, which provide new clues to understand C-ASD and biomarkers for the diagnosis and potential strategies for treatment of the disorder. This study was registered in the Chinese Clinical Trial Registry ( www.chictr.org.cn ; trial registration number ChiCTR2100052106; date of registration: October 17, 2021).

A pilot study on glutamate receptor and carrier gene variants and risk of childhood autism spectrum

Imbalanced glutamate signaling has been implicated in the development of autism spectrum disorder (ASD). This case-control study was to examine single nucleotide polymorphisms (SNPs) in glutamate receptor and carrier genes and determine their association with childhood ASD in a Chinese Han population. A total of 12 SNPs in genes encoding glutamate receptors (GRM7 and GRM8) and carriers (SLC1A1 and SLC25A12) were examined in 249 autistic children and 353 healthy controls. The Childhood Autism Rating Scale (CARS) and its verbal communication domain were applied to evaluate the severity of the disease and language impairment, respectively. The T allele of rs2292813 in the SLC25A12 gene was significantly associated with an increased risk of ASD (odds ratio (OD) = 1.7, 95% confidence interval (CI): 1.1-2.6, P = 0.0107). Neither the genotypes nor allele distributions of other SNPs were associated with the risk of ASD. Notably, rs1800656 and rs2237731 in the GRM8 gene, but not other SNPs, were related to the severity of language impairment. All SNPs were not correlated with the overall severity of ASD. Our findings support associations between the SLC25A12 gene variant and the risk of childhood ASD, and between the GRM8 gene variant and the severity of language impairment in the Chinese Han population.

Association between RIT2 rs16976358 Polymorphism and Autism Spectrum Disorder in Asian Populations: A Meta-analysis

Background

Recent studies have shown that Ras-like without CAAX2 (RIT2) polymorphism is a susceptible factor for Parkinson's disease (PD) and autism spectrum disorder (ASD). SNP rs12456492 and rs16976358 show the emerging evidence of increased risk of PD and ASD, respectively. A meta-analysis examining the relationship between rs12456492 and PD was reported, but the association between rs16976358 and ASD has not been investigated.

Methods

We searched literature from the databases PubMed, Embase, Google Scholar, ScienceDirect, EBSCOhost, OVID, Web of Science, and Wiley up to February 2021. Three studies including 1160 ASD cases and 1367 controls were eventually enrolled in the meta-analysis based on strict inclusion and exclusion criteria.

Results

All genetics models indicate a significant association between rs16976358 polymorphism and ASD susceptibility (C vs. T: p = 0.001; CC vs. TT: p = 0.001; CT vs. TT: p = 0.009; CC+CT vs. TT: p = 0.001; CC vs. CT+TT: p = 0.001; TT+CC vs. CT: p = 0.013). The results of sensitivity analysis and publication bias of Begg's and Egger's tests were stable in the models of allele (C vs. T), codominant (CC vs. TT), dominant (CC+CT vs. TT), and recessive (CC vs. CT+TT).

Conclusions

Our meta-analysis exhibits that the allele C, CC, and CT genotyping of rs16976358 suggest the risk for ASD, but additional studies using a large sample size and ethnically diverse populations need to be included in the future.

Dopaminergic Gene Dosage Reveals Distinct Biological Partitions between Autism and Developmental Delay as Revealed by Complex Network Analysis and Machine Learning Approaches

The neurobiological mechanisms underlying Autism Spectrum Disorders (ASD) remains controversial. One factor contributing to this debate is the phenotypic heterogeneity observed in ASD, which suggests that multiple system disruptions may contribute to diverse patterns of impairment which have been reported between and within study samples. Here, we used SFARI data to address genetic imbalances affecting the dopaminergic system. Using complex network analysis, we investigated the relations between phenotypic profiles, gene dosage and gene ontology (GO) terms related to dopaminergic neurotransmission from a polygenic point-of-view. We observed that the degree of distribution of the networks matched a power-law distribution characterized by the presence of hubs, gene or GO nodes with a large number of interactions. Furthermore, we identified interesting patterns related to subnetworks of genes and GO terms, which suggested applicability to separation of clinical clusters (Developmental Delay (DD) versus ASD). This has the potential to improve our understanding of genetic variability issues and has implications for diagnostic categorization. In ASD, we identified the separability of four key dopaminergic mechanisms disrupted with regard to receptor binding, synaptic physiology and neural differentiation, each belonging to particular subgroups of ASD participants, whereas in DD a more unitary biological pattern was found. Finally, network analysis was fed into a machine learning binary classification framework to differentiate between the diagnosis of ASD and DD. Subsets of 1846 participants were used to train a Random Forest algorithm. Our best classifier achieved, on average, a diagnosis-predicting accuracy of 85.18% (sd 1.11%) on the test samples of 790 participants using 117 genes. The achieved accuracy surpassed results using genetic data and closely matched imaging approaches addressing binary diagnostic classification. Importantly, we observed a similar prediction accuracy when the classifier uses only 62 GO features. This result further corroborates the complex network analysis approach, suggesting that different genetic causes might converge to the dysregulation of the same set of biological mechanisms, leading to a similar disease phenotype. This new biology-driven ontological framework yields a less variable and more compact domain-related set of features with potential mechanistic generalization. The proposed network analysis, allowing for the determination of a clearcut biological distinction between ASD and DD (the latter presenting much lower modularity and heterogeneity), is amenable to machine learning approaches and provides an interesting avenue of research for the future.

Assessment of Expression of Regulatory T Cell Differentiation Genes in Autism Spectrum Disorder

Dysfunction of regulatory T cells (Tregs) has been shown to affect the etiology of autism spectrum disorder (ASD). Differentiation of this group of T cells has been found to be regulated by a group of long non-coding RNAs (lncRNAs). In this study, we have examined the expression of five lncRNAs that regulate this process in the blood samples of ASD cases compared with controls. These lncRNAs were FOXP3 regulating long intergenic non-coding RNA (FLICR), MAF transcriptional regulator RNA (MAFTRR), NEST (IFNG-AS1), RNA component of mitochondrial RNA processing endoribonuclease (RMRP), and Th2 cytokine locus control region (TH2-LCR). Expression of RMRP was significantly lower in total ASD cases compared to controls [expression ratio (95% CI) = 0.11 (0.08–0.18), adjusted P-value < 0.0001]. This pattern was also detected in both men and women cases compared with corresponding controls [expression ratio (95% CI) = 0.15 (0.08–0.29) and 0.08 (0.03–0.2), respectively]. Likewise, expression of NEST was reduced in total cases and cases among men and women compared with corresponding controls [expression ratio (95% CI) = 0.2 (0.14–0.28); 0.22 (0.12–0.37); and 0.19 (0.09–0.43), respectively; adjusted P-value < 0.0001]. Lastly, FLICR was downregulated in total cases and cases among both boys and girls compared with matched controls [expression ratio (95% CI) = 0.1 (0.06–0.19); 0.19 (0.08–0.46); and 0.06 (0.01–0.21), respectively; adjusted P-value < 0.0001]. These three lncRNAs had appropriate diagnostic power for differentiation of ASD cases from controls. Cumulatively, our study supports dysregulation of Treg-related lncRNAs in patients with ASD and suggests these lncRNAs as proper peripheral markers for ASD.

Using Machine Learning to Predict Mortality for COVID-19 Patients on Day 0 in the ICU

Rationale: Given the expanding number of COVID-19 cases and the potential for new waves of infection, there is an urgent need for early prediction of the severity of the disease in intensive care unit (ICU) patients to optimize treatment strategies. Objectives: Early prediction of mortality using machine learning based on typical laboratory results and clinical data registered on the day of ICU admission. Methods: We retrospectively studied 797 patients diagnosed with COVID-19 in Iran and the United Kingdom (U.K.). To find parameters with the highest predictive values, Kolmogorov-Smirnov and Pearson chi-squared tests were used. Several machine learning algorithms, including Random Forest (RF), logistic regression, gradient boosting classifier, support vector machine classifier, and artificial neural network algorithms were utilized to build classification models. The impact of each marker on the RF model predictions was studied by implementing the local interpretable model-agnostic explanation technique (LIME-SP). Results: Among 66 documented parameters, 15 factors with the highest predictive values were identified as follows: gender, age, blood urea nitrogen (BUN), creatinine, international normalized ratio (INR), albumin, mean corpuscular volume (MCV), white blood cell count, segmented neutrophil count, lymphocyte count, red cell distribution width (RDW), and mean cell hemoglobin (MCH) along with a history of neurological, cardiovascular, and respiratory disorders. Our RF model can predict patient outcomes with a sensitivity of 70% and a specificity of 75%. The performance of the models was confirmed by blindly testing the models in an external dataset. Conclusions: Using two independent patient datasets, we designed a machine-learning-based model that could predict the risk of mortality from severe COVID-19 with high accuracy. The most decisive variables in our model were increased levels of BUN, lowered albumin levels, increased creatinine, INR, and RDW, along with gender and age. Considering the importance of early triage decisions, this model can be a useful tool in COVID-19 ICU decision-making.

Unbox the black-box for the medical explainable AI via multi-modal and multi-centre data fusion: A mini-review, two showcases and beyond

Explainable Artificial Intelligence (XAI) is an emerging research topic of machine learning aimed at unboxing how AI systems' black-box choices are made. This research field inspects the measures and models involved in decision-making and seeks solutions to explain them explicitly. Many of the machine learning algorithms cannot manifest how and why a decision has been cast. This is particularly true of the most popular deep neural network approaches currently in use. Consequently, our confidence in AI systems can be hindered by the lack of explainability in these black-box models. The XAI becomes more and more crucial for deep learning powered applications, especially for medical and healthcare studies, although in general these deep neural networks can return an arresting dividend in performance. The insufficient explainability and transparency in most existing AI systems can be one of the major reasons that successful implementation and integration of AI tools into routine clinical practice are uncommon. In this study, we first surveyed the current progress of XAI and in particular its advances in healthcare applications. We then introduced our solutions for XAI leveraging multi-modal and multi-centre data fusion, and subsequently validated in two showcases following real clinical scenarios. Comprehensive quantitative and qualitative analyses can prove the efficacy of our proposed XAI solutions, from which we can envisage successful applications in a broader range of clinical questions.

Machine learning based disease prediction from genotype data

Using results from genome-wide association studies for understanding complex traits is a current challenge. Here we review how genotype data can be used with different machine learning (ML) methods to predict phenotype occurrence and severity from genotype data. We discuss common feature encoding schemes and how studies handle the often small number of samples compared to the huge number of variants. We compare which ML methods are being applied, including recent results using deep neural networks. Further, we review the application of methods for feature explanation and interpretation.

Can Deep Learning Hit a Moving Target? A Scoping Review of Its Role to Study Neurological Disorders in Children

Neurological disorders dramatically impact patients of any age population, their families, and societies. Pediatrics are among vulnerable age populations who differently experience the devastating consequences of neurological conditions, such as attention-deficit hyperactivity disorders (ADHD), autism spectrum disorders (ASD), cerebral palsy, concussion, and epilepsy. System-level understanding of these neurological disorders, particularly from the brain networks' dynamic perspective, has led to the significant trend of recent scientific investigations. While a dramatic maturation in the network science application domain is evident, leading to a better understanding of neurological disorders, such rapid utilization for studying pediatric neurological disorders falls behind that of the adult population. Aside from the specific technological needs and constraints in studying neurological disorders in children, the concept of development introduces uncertainty and further complexity topping the existing neurologically driven processes caused by disorders. To unravel these complexities, indebted to the availability of high-dimensional data and computing capabilities, approaches based on machine learning have rapidly emerged a new trend to understand pathways better, accurately diagnose, and better manage the disorders. Deep learning has recently gained an ever-increasing role in the era of health and medical investigations. Thanks to its relatively more minor dependency on feature exploration and engineering, deep learning may overcome the challenges mentioned earlier in studying neurological disorders in children. The current scoping review aims to explore challenges concerning pediatric brain development studies under the constraints of neurological disorders and offer an insight into the potential role of deep learning methodology on such a task with varying and uncertain nature. Along with pinpointing recent advancements, possible research directions are highlighted where deep learning approaches can assist in computationally targeting neurological disorder-related processes and translating them into windows of opportunities for interventions in diagnosis, treatment, and management of neurological disorders in children.

A Systematic Literature Review on the Application of Machine-Learning Models in Behavioral Assessment of Autism Spectrum Disorder

Autism spectrum disorder (ASD) is associated with significant social, communication, and behavioral challenges. The insufficient number of trained clinicians coupled with limited accessibility to quick and accurate diagnostic tools resulted in overlooking early symptoms of ASD in children around the world. Several studies have utilized behavioral data in developing and evaluating the performance of machine learning (ML) models toward quick and intelligent ASD assessment systems. However, despite the good evaluation metrics achieved by the ML models, there is not enough evidence on the readiness of the models for clinical use. Specifically, none of the existing studies reported the real-life application of the ML-based models. This might be related to numerous challenges associated with the data-centric techniques utilized and their misalignment with the conceptual basis upon which professionals diagnose ASD. The present work systematically reviewed recent articles on the application of ML in the behavioral assessment of ASD, and highlighted common challenges in the studies, and proposed vital considerations for real-life implementation of ML-based ASD screening and diagnostic systems. This review will serve as a guide for researchers, neuropsychiatrists, psychologists, and relevant stakeholders on the advances in ASD screening and diagnosis using ML.

Machine learning for genetic prediction of psychiatric disorders: a systematic review

Machine learning methods have been employed to make predictions in psychiatry from genotypes, with the potential to bring improved prediction of outcomes in psychiatric genetics; however, their current performance is unclear. We aim to systematically review machine learning methods for predicting psychiatric disorders from genetics alone and evaluate their discrimination, bias and implementation. Medline, PsycInfo, Web of Science and Scopus were searched for terms relating to genetics, psychiatric disorders and machine learning, including neural networks, random forests, support vector machines and boosting, on 10 September 2019. Following PRISMA guidelines, articles were screened for inclusion independently by two authors, extracted, and assessed for risk of bias. Overall, 63 full texts were assessed from a pool of 652 abstracts. Data were extracted for 77 models of schizophrenia, bipolar, autism or anorexia across 13 studies. Performance of machine learning methods was highly varied (0.48-0.95 AUC) and differed between schizophrenia (0.54-0.95 AUC), bipolar (0.48-0.65 AUC), autism (0.52-0.81 AUC) and anorexia (0.62-0.69 AUC). This is likely due to the high risk of bias identified in the study designs and analysis for reported results. Choices for predictor selection, hyperparameter search and validation methodology, and viewing of the test set during training were common causes of high risk of bias in analysis. Key steps in model development and validation were frequently not performed or unreported. Comparison of discrimination across studies was constrained by heterogeneity of predictors, outcome and measurement, in addition to sample overlap within and across studies. Given widespread high risk of bias and the small number of studies identified, it is important to ensure established analysis methods are adopted. We emphasise best practices in methodology and reporting for improving future studies.

The role of explainability in creating trustworthy artificial intelligence for health care: A comprehensive survey of the terminology, design choices, and evaluation strategies

Artificial intelligence (AI) has huge potential to improve the health and well-being of people, but adoption in clinical practice is still limited. Lack of transparency is identified as one of the main barriers to implementation, as clinicians should be confident the AI system can be trusted. Explainable AI has the potential to overcome this issue and can be a step towards trustworthy AI. In this paper we review the recent literature to provide guidance to researchers and practitioners on the design of explainable AI systems for the health-care domain and contribute to formalization of the field of explainable AI. We argue the reason to demand explainability determines what should be explained as this determines the relative importance of the properties of explainability (i.e. interpretability and fidelity). Based on this, we propose a framework to guide the choice between classes of explainable AI methods (explainable modelling versus post-hoc explanation; model-based, attribution-based, or example-based explanations; global and local explanations). Furthermore, we find that quantitative evaluation metrics, which are important for objective standardized evaluation, are still lacking for some properties (e.g. clarity) and types of explanations (e.g. example-based methods). We conclude that explainable modelling can contribute to trustworthy AI, but the benefits of explainability still need to be proven in practice and complementary measures might be needed to create trustworthy AI in health care (e.g. reporting data quality, performing extensive (external) validation, and regulation).

Explainable artificial intelligence models using real-world electronic health record data: a systematic scoping review

OBJECTIVE

To conduct a systematic scoping review of explainable artificial intelligence (XAI) models that use real-world electronic health record data, categorize these techniques according to different biomedical applications, identify gaps of current studies, and suggest future research directions.

MATERIALS AND METHODS

We searched MEDLINE, IEEE Xplore, and the Association for Computing Machinery (ACM) Digital Library to identify relevant papers published between January 1, 2009 and May 1, 2019. We summarized these studies based on the year of publication, prediction tasks, machine learning algorithm, dataset(s) used to build the models, the scope, category, and evaluation of the XAI methods. We further assessed the reproducibility of the studies in terms of the availability of data and code and discussed open issues and challenges.

RESULTS

Forty-two articles were included in this review. We reported the research trend and most-studied diseases. We grouped XAI methods into 5 categories: knowledge distillation and rule extraction (N = 13), intrinsically interpretable models (N = 9), data dimensionality reduction (N = 8), attention mechanism (N = 7), and feature interaction and importance (N = 5).

DISCUSSION

XAI evaluation is an open issue that requires a deeper focus in the case of medical applications. We also discuss the importance of reproducibility of research work in this field, as well as the challenges and opportunities of XAI from 2 medical professionals' point of view.

CONCLUSION

Based on our review, we found that XAI evaluation in medicine has not been adequately and formally practiced. Reproducibility remains a critical concern. Ample opportunities exist to advance XAI research in medicine.