Identifying Subgroups of Patients With Autism by Gene Expression Profiles Using Machine Learning Algorithms

Leveraging AI for the diagnosis and treatment of autism spectrum disorder: Current trends and future prospects

The integration of artificial intelligence (AI) into the diagnosis and treatment of autism spectrum disorder (ASD) represents a promising frontier in healthcare. This review explores the current landscape and future prospects of AI technologies in ASD diagnostics and interventions. AI enables early detection and personalized assessment of ASD through the analysis of diverse data sources such as behavioural patterns, neuroimaging, genetics, and electronic health records. Machine learning algorithms exhibit high accuracy in distinguishing ASD from neurotypical development and other developmental disorders, facilitating timely interventions. Furthermore, AI-driven therapeutic interventions, including augmentative communication systems, virtual reality-based training, and robot-assisted therapies, show potential in improving social interactions and communication skills in individuals with ASD. Despite challenges such as data privacy and interpretability, the future of AI in ASD holds promise for refining diagnostic accuracy, deploying telehealth platforms, and tailoring treatment plans. By harnessing AI, clinicians can enhance ASD care delivery, empower patients, and advance our understanding of this complex condition.

A deep learning model for prediction of autism status using whole-exome sequencing data

Autism is a developmental disability. Research demonstrated that children with autism benefit from early diagnosis and early intervention. Genetic factors are considered major contributors to the development of autism. Machine learning (ML), including deep learning (DL), has been evaluated in phenotype prediction, but this method has been limited in its application to autism. We developed a DL model, the Separate Translated Autism Research Neural Network (STAR-NN) model to predict autism status. The model was trained and tested using whole exome sequencing data from 43,203 individuals (16,809 individuals with autism and 26,394 non-autistic controls). Polygenic scores from common variants and the aggregated count of rare variants on genes were used as input. In STAR-NN, protein truncating variants, possibly damaging missense variants and mild effect missense variants on the same gene were separated at the input level and merged to one gene node. In this way, rare variants with different level of pathogenic effects were treated separately. We further validated the performance of STAR-NN using an independent dataset, including 13,827 individuals with autism and 14,052 non-autistic controls. STAR-NN achieved a modest ROC-AUC of 0.7319 on the testing dataset and 0.7302 on the independent dataset. STAR-NN outperformed other traditional ML models. Gene Ontology analysis on the selected gene features showed an enrichment for potentially informative pathways including calcium ion transport.

Impaired macroautophagy confers substantial risk for intellectual disability in children with autism spectrum disorders

Autism spectrum disorder (ASD) represents a complex of neurological and developmental disabilities characterized by clinical and genetic heterogeneity. While the causes of ASD are still unknown, many ASD risk factors are found to converge on intracellular quality control mechanisms that are essential for cellular homeostasis, including the autophagy-lysosomal degradation pathway. Studies have reported impaired autophagy in ASD human brain and ASD-like synapse pathology and behaviors in mouse models of brain autophagy deficiency, highlighting an essential role for defective autophagy in ASD pathogenesis. To determine whether altered autophagy in the brain may also occur in peripheral cells that might provide useful biomarkers, we assessed activities of autophagy in lympoblasts from ASD and control subjects. We find that lymphoblast autophagy is compromised in a subset of ASD participants due to impaired autophagy induction. Similar changes in autophagy are detected in postmortem human brains from ASD individuals and in brain and peripheral blood mononuclear cells from syndromic ASD mouse models. Remarkably, we find a strong correlation between impaired autophagy and intellectual disability in ASD participants. By depleting the key autophagy gene Atg7 from different brain cells, we provide further evidence that autophagy deficiency causes cognitive impairment in mice. Together, our findings suggest autophagy dysfunction as a convergent mechanism that can be detected in peripheral blood cells from a subset of autistic individuals, and that lymphoblast autophagy may serve as a biomarker to stratify ASD patients for the development of targeted interventions.

Factors mediating pre-existing autism diagnosis and later suicidal thoughts and behaviors: A follow-up cohort study

LAY ABSTRACT

Autistic people are more likely to experience suicidal thoughts and behaviors. The underlying relationships between potential risk factors and suicidal thoughts and behaviors in autistic individuals remain unclear. To understand this, we investigated whether specific factors in childhood/youth explain the effects of pre-existing autism spectrum disorder (ASD) diagnoses on later suicidal thoughts and behaviors in adolescence/adulthood. We assessed internalizing and externalizing problems, bullying experiences, and executive functions (including cognitive flexibility, sustained attention, and spatial working memory) at an average baseline age of 13.4 years and suicidal thoughts and behaviors at an average follow-up age of 19.2 years among 129 autistic and 121 typically developing (TD) individuals. During the follow-up period in adolescence/adulthood, autistic individuals were more likely to report suicidal thoughts than TD individuals. Being bullied partially accounted for the relationship between a pre-existing ASD diagnosis and later-reported higher suicidal thoughts. Contrary to our hypothesis, higher (instead of lower) cognitive flexibility in some autistic young people appeared to partially explain their higher rates of suicidal thoughts compared with typically developing young people. The findings imply that school bullying prevention and tailored intervention programs for autistic people, especially those with higher cognitive flexibility, are warranted to reduce their risks of experiencing suicidal thoughts.

Challenges and prospects in bridging precision medicine and artificial intelligence in genomic psychiatric treatment

Precision medicine is transforming psychiatric treatment by tailoring personalized healthcare interventions based on clinical, genetic, environmental, and lifestyle factors to optimize medication management. This study investigates how artificial intelligence (AI) and machine learning (ML) can address key challenges in integrating pharmacogenomics (PGx) into psychiatric care. In this integration, AI analyzes vast genomic datasets to identify genetic markers linked to psychiatric conditions. AI-driven models integrating genomic, clinical, and demographic data demonstrated high accuracy in predicting treatment outcomes for major depressive disorder and bipolar disorder. This study also examines the pressing challenges and provides strategic directions for integrating AI and ML in genomic psychiatry, highlighting the importance of ethical considerations and the need for personalized treatment. Effective implementation of AI-driven clinical decision support systems within electronic health records is crucial for translating PGx into routine psychiatric care. Future research should focus on developing enhanced AI-driven predictive models, privacy-preserving data exchange, and robust informatics systems to optimize patient outcomes and advance precision medicine in psychiatry.

A face image classification method of autistic children based on the two-phase transfer learning

Autism spectrum disorder (ASD) is a neurodevelopmental disorder, which seriously affects children's normal life. Screening potential autistic children before professional diagnose is helpful to early detection and early intervention. Autistic children have some different facial features from non-autistic children, so the potential autistic children can be screened by taking children's facial images and analyzing them with a mobile phone. The area under curve (AUC) is a more robust metrics than accuracy in evaluating the performance of a model used to carry out the two-category classification, and the AUC of the deep learning model suitable for the mobile terminal in the existing research can be further improved. Moreover, the size of an input image is large, which is not fit for a mobile phone. A deep transfer learning method is proposed in this research, which can use images with smaller size and improve the AUC of existing studies. The proposed transfer method uses the two-phase transfer learning mode and the multi-classifier integration mode. For MobileNetV2 and MobileNetV3-Large that are suitable for a mobile phone, the two-phase transfer learning mode is used to improve their classification performance, and then the multi-classifier integration mode is used to integrate them to further improve the classification performance. A multi-classifier integrating calculation method is also proposed to calculate the final classification results according to the classifying results of the participating models. The experimental results show that compared with the one-phase transfer learning, the two-phase transfer learning can significantly improve the classification performance of MobileNetV2 and MobileNetV3-Large, and the classification performance of the integrated classifier is better than that of any participating classifiers. The accuracy of the integrated classifier in this research is 90.5%, and the AUC is 96.32%, which is 3.51% greater than the AUC (92.81%) of the previous studies.

Are sleep disturbances a cause or consequence of autism spectrum disorder?

Autism spectrum disorder (ASD) is a neurodevelopmental disorder characterized by core symptoms such as atypical social communication, stereotyped behaviors, and restricted interests. One of the comorbid symptoms of individuals with ASD is sleep disturbance. There are two major hypotheses regarding the neural mechanism underlying ASD, i.e., the excitation/inhibition (E/I) imbalance and the altered neuroplasticity hypotheses. However, the pathology of ASD remains unclear due to inconsistent research results. This paper argues that sleep is a confounding factor, thus, must be considered when examining the pathology of ASD because sleep plays an important role in modulating the E/I balance and neuroplasticity in the human brain. Investigation of the E/I balance and neuroplasticity during sleep might enhance our understanding of the neural mechanisms of ASD. It may also lead to the development of neurobiologically informed interventions to supplement existing psychosocial therapies.

Spoken Language Change in Children on the Autism Spectrum Receiving Community-Based Interventions

We assessed the spoken language of 73 preschool aged children on the autism spectrum receiving community-based early intervention at two time points, approximately 7 months apart. Using the Spoken Language Benchmarks, there was a small non-significant change in the proportion of children transitioning from below, to at or above, Phase 3 (word combinations). Using binomial regression, a model comprising seven of nine clinician-proposed child-related predictors explained 64% of the variance. None of the predictors were individually significant, although a large effect size (OR = 16.71) was observed for children's baseline rate of communicative acts. The findings point to substantial unmet clinical need in children with minimal verbal language, but also the relevance of clinician-proposed predictors of their spoken language outcomes.

Why not try to predict autism spectrum disorder with crucial biomarkers in cuproptosis signaling pathway?

The exact pathogenesis of autism spectrum disorder (ASD) is still unclear, yet some potential mechanisms may not have been evaluated before. Cuproptosis is a novel form of regulated cell death reported this year, and no study has reported the relationship between ASD and cuproptosis. This study aimed to identify ASD in suspected patients early using machine learning models based on biomarkers of the cuproptosis pathway. We collected gene expression profiles from brain samples from ASD model mice and blood samples from humans with ASD, selected crucial genes in the cuproptosis signaling pathway, and then analysed these genes with different machine learning models. The accuracy, sensitivity, specificity, and areas under the receiver operating characteristic curves of the machine learning models were estimated in the training, internal validation, and external validation cohorts. Differences between models were determined with Bonferroni's test. The results of screening with the Boruta algorithm showed that FDX1, DLAT, LIAS, and ATP7B were crucial genes in the cuproptosis signaling pathway for ASD. All selected genes and corresponding proteins were also expressed in the human brain. The k-nearest neighbor, support vector machine and random forest models could identify approximately 72% of patients with ASD. The artificial neural network (ANN) model was the most suitable for the present data because the accuracy, sensitivity, and specificity were 0.90, 1.00, and 0.80, respectively, in the external validation cohort. Thus, we first report the prediction of ASD in suspected patients with machine learning methods based on crucial biomarkers in the cuproptosis signaling pathway, and these findings may contribute to investigations of the potential pathogenesis and early identification of ASD.

Subtyping Hyperchloremia among Hospitalized Patients by Machine Learning Consensus Clustering

Background and Objectives: Despite the association between hyperchloremia and adverse outcomes, mortality risks among patients with hyperchloremia have not consistently been observed among all studies with different patient populations with hyperchloremia. The objective of this study was to characterize hyperchloremic patients at hospital admission into clusters using an unsupervised machine learning approach and to evaluate the mortality risk among these distinct clusters. Materials and Methods: We performed consensus cluster analysis based on demographic information, principal diagnoses, comorbidities, and laboratory data among 11,394 hospitalized adult patients with admission serum chloride of >108 mEq/L. We calculated the standardized mean difference of each variable to identify each cluster's key features. We assessed the association of each hyperchloremia cluster with hospital and one-year mortality. Results: There were three distinct clusters of patients with admission hyperchloremia: 3237 (28%), 4059 (36%), and 4098 (36%) patients in clusters 1 through 3, respectively. Cluster 1 was characterized by higher serum chloride but lower serum sodium, bicarbonate, hemoglobin, and albumin. Cluster 2 was characterized by younger age, lower comorbidity score, lower serum chloride, and higher estimated glomerular filtration (eGFR), hemoglobin, and albumin. Cluster 3 was characterized by older age, higher comorbidity score, higher serum sodium, potassium, and lower eGFR. Compared with cluster 2, odds ratios for hospital mortality were 3.60 (95% CI 2.33-5.56) for cluster 1, and 4.83 (95% CI 3.21-7.28) for cluster 3, whereas hazard ratios for one-year mortality were 4.49 (95% CI 3.53-5.70) for cluster 1 and 6.96 (95% CI 5.56-8.72) for cluster 3. Conclusions: Our cluster analysis identified three clinically distinct phenotypes with differing mortality risks in hospitalized patients with admission hyperchloremia.