scholarly journals Machine Learning based Autism Grading for Clinical Decision Making

2019 ◽  
Vol 8 (4) ◽  
pp. 7443-7446
Keyword(s):  
Machine Learning ◽  
Decision Making ◽  
Autism Spectrum Disorder ◽  
Clinical Decision Making ◽  
Prediction Models ◽  
Clinical Decision ◽  
Autism Spectrum ◽  
Spectrum Disorder ◽  
Diagnostic Process ◽  
Manhattan Distance

Autism spectrum disorder is a pervasive developmental disorder that affects the behavioral and communication function of the children. It shows poor performance in communication, social and cognitive abilities, which are generally characterized by developmental delays and abnormal activities in their regular work. Early intervention can reduce the autism spectrum disorders. Machine learning techniques are used to detect autistic features in childhood. The prediction models are implemented as classification problem in which model is constructed by using real-time autism dataset. The proposed work is use Backpropagation and learning vector quantization with different distance measures like Euclidean Distance, Manhattan Distance, and City Block Distance to predict whether a child has autism spectrum disorder and also defines the grade of the autism. So that it can be supported for the clinical decision making. It enables automated clinical autism spectrum disorder diagnostic process using machine learning models.

scholarly journals A Protocol for the Diagnosis of Autism Spectrum Disorder Structured in Machine Learning and Verbal Decision Analysis

2021 ◽  
Vol 2021 ◽  
pp. 1-14
Author(s):  
Evandro Andrade ◽  
Samuel Portela ◽  
Plácido Rogério Pinheiro ◽  
Luciano Comin Nunes ◽  
Marum Simão Filho ◽  
...  
Keyword(s):  
Machine Learning ◽  
Autism Spectrum Disorder ◽  
Decision Analysis ◽  
Autism Spectrum ◽  
Machine Learning Algorithms ◽  
Spectrum Disorder ◽  
World Health ◽  
Diagnostic Process ◽  
Icd 10 ◽  
Verbal Decision Analysis

Autism Spectrum Disorder is a mental disorder that afflicts millions of people worldwide. It is estimated that one in 160 children has traces of autism, with five times the higher prevalence in boys. The protocols for detecting symptoms are diverse. However, the following are among the most used: the Diagnostic and Statistical Manual of Mental Disorders, 5th Edition (DSM-5), of the American Psychiatric Association; the Revised Autistic Diagnostic Observation Schedule (ADOS-R); the Autistic Diagnostic Interview (ADI); and the International Classification of Diseases, 10th edition (ICD-10), published by the World Health Organization (WHO) and adopted in Brazil by the Unified Health System (SUS). The application of machine learning models helps make the diagnostic process of Autism Spectrum Disorder more precise, reducing, in many cases, the number of criteria necessary for evaluation, denoting a form of attribute engineering (feature engineering) efficiency. This work proposes a hybrid approach based on machine learning algorithms’ composition to discover knowledge and concepts associated with the multicriteria method of decision support based on Verbal Decision Analysis to refine the results. Therefore, the study has the general objective of evaluating how the mentioned hybrid methodology proposal can make the protocol derived from ICD-10 more efficient, providing agility to diagnosing Autism Spectrum Disorder by observing a minor symptom. The study database covers thousands of cases of people who, once diagnosed, obtained government assistance in Brazil.

Machine Learning Techniques for Analysing and Identifying Autism Spectrum Disorder

2021 ◽  
pp. 69-81
Author(s):  
Jyoti Bhola ◽  
Rubal Jeet ◽  
Malik Mustafa Mohammad Jawarneh ◽  
Shadab Adam Pattekari
Keyword(s):  
Machine Learning ◽  
Autism Spectrum Disorder ◽  
Prediction Models ◽  
Medical Diagnostics ◽  
Autism Spectrum ◽  
Spectrum Disorder ◽  
Machine Learning Techniques ◽  
Autistic Spectrum ◽  
Learning Techniques ◽  
Behavioural Condition

Autism spectrum disorder (ASD) is a neuro disorder in which a person's contact and connection with others has a lifetime impact. In all levels of development, autism can be diagnosed as a “behavioural condition,” since signs generally occur within the first two years of life. The ASD problem begins with puberty and goes on in adolescence and adulthood. In this chapter, an effort is being made to use the supporting vector machine (SVM) and the convolutionary neural network (CNN) for prediction and interpretation of children's ASD problems based on the increased use of machine learning methodology in the research dimension of medical diagnostics. On freely accessible autistic spectrum disorder screening dates in children's datasets, the suggested approaches are tested. Using different techniques of machine learning, the findings clearly conclude that CNN-based prediction models perform more precisely on the dataset for autistic spectrum disorders.

Diagnostic test accuracy for use of machine learning in diagnosis of autism spectrum disorder: A Systematic Review and Meta-Analysis (Preprint)

2019 ◽  
Author(s):  
Sun Jae Moon ◽  
Jin Seub Hwang ◽  
Rajesh Kana ◽  
John Torous ◽  
Jung Won Kim
Keyword(s):  
Machine Learning ◽  
Systematic Review ◽  
Autism Spectrum Disorder ◽  
Meta Analysis ◽  
Learning Algorithms ◽  
Structural Mri ◽  
Autism Spectrum ◽  
Machine Learning Algorithms ◽  
Spectrum Disorder ◽  
Test Accuracy

BACKGROUND Over the recent years, machine learning algorithms have been more widely and increasingly applied in biomedical fields. In particular, its application has been drawing more attention in the field of psychiatry, for instance, as diagnostic tests/tools for autism spectrum disorder. However, given its complexity and potential clinical implications, there is ongoing need for further research on its accuracy. OBJECTIVE The current study aims to summarize the evidence for the accuracy of use of machine learning algorithms in diagnosing autism spectrum disorder (ASD) through systematic review and meta-analysis. METHODS MEDLINE, Embase, CINAHL Complete (with OpenDissertations), PsyINFO and IEEE Xplore Digital Library databases were searched on November 28th, 2018. Studies, which used a machine learning algorithm partially or fully in classifying ASD from controls and provided accuracy measures, were included in our analysis. Bivariate random effects model was applied to the pooled data in meta-analysis. Subgroup analysis was used to investigate and resolve the source of heterogeneity between studies. True-positive, false-positive, false negative and true-negative values from individual studies were used to calculate the pooled sensitivity and specificity values, draw SROC curves, and obtain area under the curve (AUC) and partial AUC. RESULTS A total of 43 studies were included for the final analysis, of which meta-analysis was performed on 40 studies (53 samples with 12,128 participants). A structural MRI subgroup meta-analysis (12 samples with 1,776 participants) showed the sensitivity at 0.83 (95% CI-0.76 to 0.89), specificity at 0.84 (95% CI -0.74 to 0.91), and AUC/pAUC at 0.90/0.83. An fMRI/deep neural network (DNN) subgroup meta-analysis (five samples with 1,345 participants) showed the sensitivity at 0.69 (95% CI- 0.62 to 0.75), the specificity at 0.66 (95% CI -0.61 to 0.70), and AUC/pAUC at 0.71/0.67. CONCLUSIONS Machine learning algorithms that used structural MRI features in diagnosis of ASD were shown to have accuracy that is similar to currently used diagnostic tools.

Machine learning in clinical decision making

Med ◽  
2021 ◽  
Author(s):  
Lorenz Adlung ◽  
Yotam Cohen ◽  
Uria Mor ◽  
Eran Elinav
Keyword(s):  
Machine Learning ◽  
Decision Making ◽  
Clinical Decision Making ◽  
Clinical Decision

scholarly journals Diagnosis despite clinical ambiguity: physicians’ perspectives on the rise in Autism Spectrum disorder incidence

2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Michael Davidovitch ◽  
Dorit Shmueli ◽  
Ran Shmuel Rotem ◽  
Aviva Mimouni Bloch
Keyword(s):  
Autism Spectrum Disorder ◽  
Autism Spectrum ◽  
Mental Illnesses ◽  
Spectrum Disorder ◽  
Medical Community ◽  
Categorical Variables ◽  
Diagnostic Process ◽  
Child Neurology ◽  
Chi Square ◽  
Child Psychiatrists

Abstract Background To provide insight on physicians’ perspectives concerning recent changes in the incidence and diagnostic process of Autism Spectrum Disorder (ASD) compared to other mental and neurodevelopmental disorders. Method A questionnaire was sent to 191 specialists in child neurology and child development, and 200 child psychiatrists in Israel. Information was collected on professional background, as well as on physicians’ opinions concerning the accuracy and rate of ASD diagnosis compared to that of cerebral palsy (CP), mental illness, and Attention Deficit Hyperactivity Disorder (ADHD). For each closed-ended question, a global chi-square test for categorical variables was performed. Results 115 (60.2%) of specialists in child neurology and development, and 59 (29.5%) of child psychiatrists responded. Most physicians (67.2%) indicated that there was a moderate/significant increase in the incidence of ASD, which was higher than similar responses provided for CP (2.9%, p < 0.01) and mental illnesses (14.4%, p < 0.01), and similar to responses provided for ADHD (70.1%, p = 0.56). 52.8% of physicians believed that in more than 10% of clinical assessments, an ASD diagnosis was given despite an inconclusive evaluation (CP: 8.6%, p < 0.01; mental illnesses: 25.8%, p = 0.03; ADHD: 68.4%, p = 0.03). Conclusion The clinicians perceive both ASD and ADHD as over-diagnosed disorders. The shared symptomology between ASD and other disorders, coupled with heightened awareness and public de-stigmatization of ASD and with the availability of ASD-specific services that are not accessible to children diagnosed with other conditions, might lead clinicians to over-diagnose ASD. It is advisable to adopt an approach in which eligibility for treatments is conditional on function, rather than solely on a diagnosis. The medical community should strive for accurate diagnoses and a continuous review of diagnostic criteria.

scholarly journals Parental evaluation of a revised autism spectrum disorder diagnostic process for children under 36 months of age

2021 ◽  
Author(s):  
Jean-François Lemay ◽  
Shauna Langenberger ◽  
Scott McLeod
Keyword(s):  
Autism Spectrum Disorder ◽  
Early Intervention ◽  
Parent Education ◽  
Positive Impact ◽  
Autism Spectrum ◽  
Spectrum Disorder ◽  
Diagnostic Process ◽  
Cross Sectional Survey ◽  
Cross Sectional ◽  
High Level

Abstract Background The Alberta Children’s Hospital-Autism Spectrum Disorder Diagnostic Clinic (ACH-ASDC) was restructured due to long wait times and unsustainable clinic workflow. Major changes included the initiation of pre- and post-ASD parent education sessions and distinct ASD screening appointments before the ASD diagnostic appointment. Methods We conducted a parental program evaluation in summer 2018 of the ACH-ASDC. We used a cross-sectional survey to evaluate key outcomes including parental satisfaction, and the percentage of families obtaining access to government supports and early intervention programs. Results For the 101 eligible patients diagnosed with ASD under 36 months of age 70 (69.3%) parents agreed to participate. The mean diagnostic age of the children diagnosed with ASD was 30.6 months (SD=4.1 months). There were no statistically significant age differences between biological sexes. Ninety-three per cent of parents felt that ASD educational sessions were useful, and 92% of parents were satisfied to very satisfied with the overall ASD diagnostic process. Ninety per cent of parents had access to at least one of the key resources available for ASD early intervention in our province following diagnosis. Parents reported a positive impact on intervention provided to their child in the areas of communication, social interaction, and behaviour. Conclusion Parents of children diagnosed with ASD expressed a high level of satisfaction with the restructured ACH-ASDC process. Implementing parent education sessions was well received and met parents’ needs. Parents were able to access intervention services following diagnosis and reported positive impacts for their child. Re-envisioning program approaches to incorporate novel strategies to support families should be encouraged.

scholarly journals Genotype-Based Deep Learning in Autism Spectrum Disorder: Diagnostic Classification and Prognostic Prediction Using Common Genetic Variants (Preprint)

2020 ◽  
Author(s):  
Haishuai Wang ◽  
Paul Avillach
Keyword(s):  
Machine Learning ◽  
Autism Spectrum Disorder ◽  
Deep Learning ◽  
The United States ◽  
Autism Spectrum ◽  
Repetitive Behaviors ◽  
Spectrum Disorder ◽  
Screening Tools ◽  
Common Variants ◽  
Autism Screening

BACKGROUND In the United States, about 3 million people have autism spectrum disorder (ASD), and around 1 out of 59 children are diagnosed with ASD. People with ASD have characteristic social communication deficits and repetitive behaviors. The causes of this disorder remain unknown; however, in up to 25% of cases, a genetic cause can be identified. Detecting ASD as early as possible is desirable because early detection of ASD enables timely interventions in children with ASD. Identification of ASD based on objective pathogenic mutation screening is the major first step toward early intervention and effective treatment of affected children. OBJECTIVE Recent investigation interrogated genomics data for detecting and treating autism disorders, in addition to the conventional clinical interview as a diagnostic test. Since deep neural networks perform better than shallow machine learning models on complex and high-dimensional data, in this study, we sought to apply deep learning to genetic data obtained across thousands of simplex families at risk for ASD to identify contributory mutations and to create an advanced diagnostic classifier for autism screening. METHODS After preprocessing the genomics data from the Simons Simplex Collection, we extracted top ranking common variants that may be protective or pathogenic for autism based on a chi-square test. A convolutional neural network–based diagnostic classifier was then designed using the identified significant common variants to predict autism. The performance was then compared with shallow machine learning–based classifiers and randomly selected common variants. RESULTS The selected contributory common variants were significantly enriched in chromosome X while chromosome Y was also discriminatory in determining the identification of autistic from nonautistic individuals. The ARSD, MAGEB16, and MXRA5 genes had the largest effect in the contributory variants. Thus, screening algorithms were adapted to include these common variants. The deep learning model yielded an area under the receiver operating characteristic curve of 0.955 and an accuracy of 88% for identifying autistic from nonautistic individuals. Our classifier demonstrated a significant improvement over standard autism screening tools by average 13% in terms of classification accuracy. CONCLUSIONS Common variants are informative for autism identification. Our findings also suggest that the deep learning process is a reliable method for distinguishing the diseased group from the control group based on the common variants of autism.

scholarly journals Vocal markers of Autism Spectrum Disorder: assessing the generalizability of machine learning models

2021 ◽  
Author(s):  
Astrid Rybner ◽  
Emil Trenckner Jessen ◽  
Marie Damsgaard Mortensen ◽  
Stine Nyhus Larsen ◽  
Ruth Grossman ◽  
...  
Keyword(s):  
Machine Learning ◽  
Autism Spectrum Disorder ◽  
Model Performance ◽  
Autism Spectrum ◽  
Spectrum Disorder ◽  
Future Studies ◽  
Out Of Sample ◽  
Biobehavioral Markers ◽  
Similar Task ◽  
Machine Learning Models

Background: Machine learning (ML) approaches show increasing promise to identify vocal markers of Autism Spectrum Disorder (ASD). Nonetheless, it is unclear to what extent such markers generalize to new speech samples collected in diverse settings such as using a different speech task or a different language. Aim: In this paper, we systematically assess the generalizability of ML findings across a variety of contexts. Methods: We re-train a promising published ML model of vocal markers of ASD on novel cross-linguistic datasets following a rigorous pipeline to minimize overfitting, including cross-validated training and ensemble models. We test the generalizability of the models by testing them on i) different participants from the same study, performing the same task; ii) the same participants, performing a different (but similar) task; iii) a different study with participants speaking a different language, performing the same type of task. Results: While model performance is similar to previously published findings when trained and tested on data from the same study (out-of-sample performance), there is considerable variance between studies. Crucially, the models do not generalize well to new similar tasks and not at all to new languages. The ML pipeline is openly shared. Conclusion: Generalizability of ML models of vocal markers - and more generally biobehavioral markers - of ASD is an issue. We outline three recommendations researchers could take in order to be more explicit about generalizability and improve it in future studies.

Sign in / Sign up

Export Citation Format

Share Document