Early Detection Of Autism Spectrum Disorder Research Articles

Validation of the French version of the preschool form of the social responsiveness scale-second edition (SRS-2-P)

ObjectivesTo evaluate the psychometric properties of the French form of the preschool social responsiveness scale-2 (SRS-2-P-Fr). ParticipantsA sample of French children aged 2 to 4 years comprising a group of 93 children with autism spectrum disorder (ASD) and a community control group of 201 children. Materials and methodsStudy of internal consistency using Cronbach's α coefficient, convergent validity using correlations with the ADI-R and ADOS-2, and diagnostic accuracy using the receiver operating characteristic curve to determine the best threshold scores useful for screening ASD in preschool children. ResultsGood internal consistency (0.78 to 0.98) according to Cronbach's alpha coefficients for the total score and the sub-scores of the SRS-2-P scale. The study of convergent validity showed strong correlations with the total score of the ADOS-2 Toddlers and the communication and reciprocal social interaction sub-scores of the ADI-R. Diagnostic accuracy indicated that the best cut-off score for detecting ASDs was 56 (area under the curve=0.97, sensitivity 0.925, specificity 0.98). ConclusionThe SRS-2-P-Fr is a valid instrument for the early detection of ASD in preschool children in France and can facilitate diagnosis.

A machine learning model based on CHAT-23 for early screening of autism in Chinese children.

Autism spectrum disorder (ASD) is a neurodevelopmental condition that significantly impacts the mental, emotional, and social development of children. Early screening for ASD typically involves the use of a series of questionnaires. With answers to these questionnaires, healthcare professionals can identify whether a child is at risk for developing ASD and refer them for further evaluation and diagnosis. CHAT-23 is an effective and widely used screening test in China for the early screening of ASD, which contains 23 different kinds of questions. We have collected clinical data from Wuxi, China. All the questions of CHAT-23 are regarded as different kinds of features for building machine learning models. We introduce machine learning methods into ASD screening, using the Max-Relevance and Min-Redundancy (mRMR) feature selection method to analyze the most important questions among all 23 from the collected CHAT-23 questionnaires. Seven mainstream supervised machine learning models were built and experiments were conducted. Among the seven supervised machine learning models evaluated, the best-performing model achieved a sensitivity of 0.909 and a specificity of 0.922 when the number of features was reduced to 9. This demonstrates the model's ability to accurately identify children for ASD with high precision, even with a more concise set of features. Our study focuses on the health of Chinese children, introducing machine learning methods to provide more accurate and effective early screening tests for autism. This approach not only enhances the early detection of ASD but also helps in refining the CHAT-23 questionnaire by identifying the most relevant questions for the diagnosis process.

Fractional whale driving training-based optimization enabled transfer learning for detecting autism spectrum disorder

Autism Spectrum Disorder (ASD) is a neurological illness that degrades communication and interaction among others. Autism can be detected at any stage. Early detection of ASD is important in preventing the communication, interaction and behavioral outcomes of individuals. Hence, this research introduced the Fractional Whale-driving Driving Training-based Based Optimization with Convolutional Neural Network-based Transfer learning (FWDTBO-CNN_TL) for identifying ASD. Here, the FWDTBO is modelled by the incorporation of Fractional calculus (FC), Whale optimization algorithm (WOA) and Driving Training-based Optimization (DTBO) that trains the hyperparameters of CNN-TL. Moreover, the Convolutional Neural Networks (CNN) utilize the hyperparameters from trained models, like Alex Net and Shuffle Net in such a way that the CNN-TL is designed. To improve the detection efficiency, the nub region was extracted and carried out with the functional connectivity-based Whale Driving Training Optimization (WDTBO) algorithm. Moreover, the TL is tuned by the FWDTBO algorithm. The result reveals that the ASD detection technique, FWDTBO-CNN-TL acquired 90.7 % accuracy, 95.4 % sensitivity, 93.7 % specificity and 93 % f-measure with the ABIDE-II dataset.

Retinal Image Analysis for Simultaneous Classification and Severity Grading of Attention-Deficit Hyperactivity Disorder and Autism Spectrum Disorder using Deep Learning

Over the last 20 years, the number of children born with Autism Spectrum Disorder (ASD) and Attention-Deficit Hyperactivity Disorder (ADHD) has significantly increased. According to the U.S Centers for Disease Control and Prevention, the number of children with ASD in the United States had increased from 1 in 150 in 2000 to 1 in 36 in 2020, which is an increase of 316.7% and the number of children with ADHD has been around 10% of Population. As the number of children with ASD and ADHD is increasing rapidly, an early diagnosis of both mental disorders is essential, which can contribute to the improvement of the condition of children significantly. By employing retinal images, the early detection of ASD and ADHD in the developmental stages of childhood becomes feasible. Consequently, the development of a diagnostic system that identifies the presence of ASD and ADHD is essential for healthcare interventions and the enhancement of children's well-being when potential remediation is attainable. This research aims to develop a system for early diagnosis of ASD and ADHD utilizing retinal images and deep learning through convolutional neural networks. The proposed approach classifies the retinal images into disorder categories and severity levels. Experimental results demonstrate the viability of the proposed approach as a biometric for the early diagnosis of ASD and ADHD.

Comparison between the Clancy Behavior Scale and the Modified Checklist for Autism in Toddlers in Taiwan.

(1) Background: Precise diagnosis and early intervention are crucial for toddlers with autism spectrum disorder (ASD) to achieve a better prognosis. This study investigated the efficacy of the Clancy Behavior Scale (CBS) and Modified Checklist for Autism in Toddlers (M-CHAT) in detecting ASD among toddlers under 30 months of age. (2) Methods: A total of 215 toddlers (117 with ASD and 98 with development delays) aged between 18 and 29 months participated in this study. All the primary caregivers of these toddlers were recruited to complete the CBS and M-CHAT. (3) Results: The findings indicated that the accuracy of the CBS and M-CHAT was promising, and the short forms of these two instruments performed better than their full versions. The CBS:9 critical items presented a sensitivity of 0.75 and a specificity of 0.74, while the M-CHAT:14 brief items showed a sensitivity of 0.72 and a specificity of 0.85. (4) Conclusions: The diagnostic accuracy of high-risk ASD toddlers improved via the combination of CBS and M-CHAT, particularly when the information gathered from these two instruments were consistent. The findings may provide implications for enhancing the early detection of ASD.

Validar un cuestionario para evaluar el Conocimiento y la Estigmatización del TEA en la población peruana: una necesidad real

Autism Spectrum Disorder (ASD) is a neurodevelopmental disorder characterized by difficulties in social interaction, communication, and restricted and repetitive patterns of behavior. Over the past few decades, there has been an increase in awareness and early detection of ASD, significantly improving opportunities for intervention and support. However, individuals with ASD often face stigmatization and discrimination due to a lack of understanding about their condition, which can negatively affect their emotional and social well-being. Therefore, it is crucial to promote greater education and awareness about ASD to reduce stigma and foster a more inclusive society. (1)

Autism Spectrum Disorders: Etiology, Epidemiology, and Challenges for Public Health.

Autism spectrum disorder (ASD) is a growing public health problem. American psychiatrist Leo Kanner is considered the "father of autism." ASD encompasses a range of neurodevelopmental disorders that last throughout life. Symptoms of ASD include impairments in social skills, including specific repetitive behaviors, as well as abnormal sensory responses. The clinical symptoms of ASD vary among patients. Their severity also differs, both in the area of social communication and cognitive functioning. The etiology of ASD is still unclear, although a role is attributed to both genetic and environmental factors. According to the World Health Organization, 1/100 children have ASD, but these estimates vary depending on the methodology used. Nevertheless, early detection of ASD and initiation of appropriate therapy may be essential in the continued functioning of patients and their families. The purpose of this article is to provide an overview of current knowledge about autism spectrum disorders. We discuss factors associated with autism and the prevalence of ASD in various parts of the world, and identify the most common diseases comorbid with ASD, pointing to limitations in the quality of life of patients with ASD and their families.

Accuracy of behavioral responses in early detection of autism spectrum disorders in children aged 18 months to 4 years with speech delay

Background Early detection of autism spectrum disorders (ASD) in children with speech delay is important to improve outcomes. Behavioral responses to calling, teasing, poking, and blocking can be used to screen for ASD in daily practice.
 Objective To evaluate the accuracy of behavioral responses to stimuli in detecting ASD in children aged 18 months to 4 years with speech delay.
 Methods This cross-sectional study was conducted in children with speech delay aged 18 months to 4 years who visited the Outpatient Clinic of Cipto Mangunkusumo Hospital, Jakarta. Subjects were stimulated while playing by poking, teasing, calling, and blocking (stopping the child’s play using the examiner’s hand) and were assessed for their responses. Lack of seeking eye contact with the examiner following the stimulus was considered as a response suggestive of ASD. Independent diagnosis based on DSM-V criteria was considered the gold standard to diagnose ASD or non-ASD.
 Results A total of 109 children were included in this study, with an average age of 32 (SD 7.4) months. There were 52 subjects (47.7%) with ASD and 57 subjects (52.2%) with non-ASD. Behavioral response analysis revealed that calling, blocking and teasing had high sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) for identifying ASD. The poking response had the highest specificity to rule out ASD compared to other stimuli, with 75% sensitivity (95%CI 63.2% to 86.7%), 93% specificity (95%CI 86.3% to 99.6%), 90% PPV (95%CI 82% to 99.3%), and 80% NPV (95%CI 70.7% to 89.9%). When all behavioral responses were combined, with lack of a response to all four stimuli considered suggestive of ASD, we obtained 100% specificity, 42% sensitivity, 100% PPV and 65% NPV.
 Conclusion The combination of behavioral responses had high specificity, sensitivity, PPV, and NPV for early detection of ASD in children with speech delay.

Key personal factors and moderation effect of belief on shaping the willingness for early ASD detection in Jordan: A SEM Analysis

Background: Autism Spectrum Disorder (ASD) prevalence increases healthcare utilisation, underscoring healthcare providers' vital role in early detection. This growing prominence underscores the pivotal roles of healthcare providers in the early detection of ASD. Understanding the influence of their factors, Knowledge, Awareness, Experience, Preparedness, and Beliefs impact providers' Willingness for early ASD detection. This study explores these factors comprehensively, contributing to a nuanced understanding and assessing the effect of Beliefs on healthcare providers' Willingness for early ASD detection, examining their influence on Awareness, Knowledge, Experience, and perceived Preparedness. Methodology: In the Al-Mafraq region of Jordan, this study surveyed 202 participants from various healthcare facilities using structural equation modelling (SEM) to analyse the connection between Beliefs and healthcare providers' Awareness, Knowledge, Experience, perceived Preparedness, and Willingness for early ASD detection. Result: Belief moderated the path from Preparedness towards Willingness. This means that the higher the value of Belief, the greater the effect of healthcare providers' Preparedness for early ASD detection. Conclusion: The study uncovers significant associations between healthcare providers' Knowledge, Experience, and perceived Preparedness and their Willingness for early ASD detection. Belief emerges as a pivotal moderator, emphasising its influential role in shaping the connection between Preparedness and Willingness.

The role and impact of abnormal vitamin levels in autism spectrum disorders.

The prevalence of autism spectrum disorder (ASD), a neurodevelopmental disorder with a predominance of social behavioral disorders, has increased dramatically in various countries in recent decades. The interplay between genetic and environmental factors is believed to underlie ASD pathogenesis. Recent analyses have shown that abnormal vitamin levels in early life are associated with an increased risk of autism. As essential substances for growth and development, vitamins have been shown to have significant benefits for the nervous and immune systems. However, it is unknown whether certain vitamin types influence the emergence or manifestation of ASD symptoms. Several studies have focused on vitamin levels in children with autism, and neurotypical children have provided different insights into the types of vitamins and their intake. Here, we review the mechanisms and significance of several vitamins (A, B, C, D, E, and K) that are closely associated with the development of ASD in order to prevent, mitigate, and treat ASD. Efforts have been made to discover and develop new indicators for nutritional assessment of children with ASD to play a greater role in the early detection of ASD and therapeutic remission after diagnosis.

Examination of AI Algorithms for Image and MRI-based Autism Detection

Precise identification of autism spectrum disorder (ASD) is a challenging task due to the heterogeneity of ASD. Early diagnosis and interventions have positive effects on treatment and later skills development. Hence, it is necessary to provide families and communities with the resources, training, and tools required to diagnose and help patients. Recent work has shown that artificial intelligence-based methods are suitable for the identification of ASD. AI-based tools can be good resources for parents for early detection of ASD in their kids. Even AI-based advanced tools are helpful for health workers and physicians to detect ASD. Facial images and MRI are the best sources to understand ASD symptoms, hence are input required in AI-based model training. The trained models are used for the classification of ASD patients and normal kids. The deep learning models are found to be very accurate in ASD detection. In this paper, we present a comprehensive study of AI techniques like machine learning, image processing, and deep learning, and their accuracy when these techniques are used on facial and MRI images of ASD and normally developed kids.

Evaluating Autism diagnosis agreement between primary care physicians/practitioners and experts through ECHO Autism STAT

BackgroundEven though early intervention leads to improved outcomes for children with autism spectrum disorder (ASD), delays in diagnosis can have an impact on both children and families. ASD diagnostic practices have significantly evolved over time, in part, because of the lack of specialists to meet the demand. ECHO Autism STAT is one innovative model that increased the capacity of community primary care providers (PCPs) to reliably diagnose ASD within their own practices via hands-on training and virtual guidance and support from ASD specialists. The current study evaluated PCPs agreement with ECHO Autism experts in making independent clinical decisions related to ASD diagnosis in unambiguous cases. MethodAfter obtaining reliability on the STAT and attending 6 mo of ECHO Autism sessions, PCPs agreement with expert impressions was evaluated for (a) diagnosing unambiguous ASD and (b) identifying symptoms that met DSM-5 criteria. ResultsThe proportion of cases that achieved the highest PCP agreement score with ASD experts for overall ASD diagnostic impressions was 90% across all cases, 94% across unambiguous cases, and 84% across more complex cases. PCP agreement for DSM-5 symptom impressions was 79%, 87%, and 66% across all, unambiguous, and more complex cases, respectively. Results were significant for unambiguous cases when compared to more complex cases. ConclusionsPCPs can develop clinical expertise in the evaluation and diagnosis of young children with unambiguous ASD that is accurate and reliable. Development of this expertise can expand access for community-based diagnosis that is critical for early detection of ASD.

Factors Associated with Age at Diagnosis of Autism Spectrum Disorder in Pediatric Patients at Sawanpracharak Hospital, Thailand

Objective: This study aimed to determine the average age at diagnosis and the characteristics associated with the age of children at the diagnosis of autism spectrum disorder (ASD) at Sawanpracharak Hospital. Materials and Methods: A retrospective cross-sectional study was conducted from May 2023 to July 2023. Data were collected from the medical patient files of all children diagnosed with ASD between 2020 to 2022. Descriptive analysis was used to examine the characteristics of the children and their caregivers, and the children’s age at diagnosis. Factors associated with the age at diagnosis were assessed by chi-square test analysis. Results: In total, 100 patient records with complete information were collected. The average age at the diagnosis of ASD was 4.57± 1.61 years old, with 60% of the patients diagnosed after four years of age. Social communication deficit symptoms, including non-response to name and lack of pointing out objects of interest, were significantly associated with an early ASD diagnosis (p-value = 0.023 and 0.002, respectively). Being a firstborn child and the presence of delayed development were found to delay the diagnosis of ASD meaning it occurred at a later age (p-value = 0.002 and 0.019, respectively). However, sex, the caregiver’s education, and socioeconomic status were not related to the age at diagnosis. Conclusion: Most children with ASD who received treatment at Sawanpracharak Hospital were diagnosed late. Being a firstborn child, poor response to name being called, lack of pointing out objects of interest, and delayed development were related to the age of the children at ASD diagnosis. Differences in diagnostic age based on sociodemographic and clinical characteristics indicate the need for coordinated measures for the early detection of ASD.

Hybrid Techniques of Facial Feature Image Analysis for Early Detection of Autism Spectrum Disorder Based on Combined CNN Features.

Autism spectrum disorder (ASD) is a complex neurodevelopmental disorder characterized by difficulties in social communication and repetitive behaviors. The exact causes of ASD remain elusive and likely involve a combination of genetic, environmental, and neurobiological factors. Doctors often face challenges in accurately identifying ASD early due to its complex and diverse presentation. Early detection and intervention are crucial for improving outcomes for individuals with ASD. Early diagnosis allows for timely access to appropriate interventions, leading to better social and communication skills development. Artificial intelligence techniques, particularly facial feature extraction using machine learning algorithms, display promise in aiding the early detection of ASD. By analyzing facial expressions and subtle cues, AI models identify patterns associated with ASD features. This study developed various hybrid systems to diagnose facial feature images for an ASD dataset by combining convolutional neural network (CNN) features. The first approach utilized pre-trained VGG16, ResNet101, and MobileNet models. The second approach employed a hybrid technique that combined CNN models (VGG16, ResNet101, and MobileNet) with XGBoost and RF algorithms. The third strategy involved diagnosing ASD using XGBoost and an RF based on features of VGG-16-ResNet101, ResNet101-MobileNet, and VGG16-MobileNet models. Notably, the hybrid RF algorithm that utilized features from the VGG16-MobileNet models demonstrated superior performance, reached an AUC of 99.25%, an accuracy of 98.8%, a precision of 98.9%, a sensitivity of 99%, and a specificity of 99.1%.

Validating the Malaysian modified checklist for autism in toddlers, revised with follow-up (M-CHAT-R/F): a cross-cultural adaptation

IntroductionThe Modified Checklist for Autism in Toddlers, Revised with Follow-Up (M-CHAT-R/F) is a two-stage parent-reported tool for screening autism spectrum disorder (ASD). Early detection of ASD is highly associated with improved social communication and reduced restricted and repetitive behaviors associated with ASD. However, there is limited availability of ASD screening tools in Malaysia and there are no relevant validation studies published. The process of modifying a screening instrument to align with the cultural and linguistic characteristics of the target population is a crucial component in establishing the instrument's validity.MethodsTherefore, this study translates and culturally adapts the M-CHAT-R/F into Malay and verifies its psychometric properties among the Malaysian population. 500 Malaysian toddlers aged between 18 and 48 months were recruited from different settings. The parents of the toddlers were asked to complete the Malaysian M-CHAT-R/F. The reliability of the screening tool was verified using Cronbach's alpha.ResultsBy comparing the screening outcomes of the Malaysian M-CHAT-R/F and clinical evaluation results, the prevalence of ASD was determined as 6.6% in the sample. High values of sensitivity (96.6%) and specificity (93.2%) and a satisfactory positive predictive value (47.5%) supported the validity of the Malaysian M-CHAT-R/F. Furthermore, the receiver operating characteristic analysis yielded three as the optimal cut-off score of the Malaysian M-CHAT-R/F.DiscussionThese results suggest that the Malaysian M-CHAT-R/F is an effective screening tool reliable for use in clinical practice. Further investigation using a representative sample of the whole country is recommended given the high prevalence rate obtained in the current sample.

Autism Spectrum Disorder (ASD) Identification Using Feature-Based Machine Learning Classification Model

Autism Spectrum Disorder (ASD) is a developmental disorder that impairs the development of behaviors, communication, and learning abilities. Early detection of ASD helps patients to get beter training to communicate and interact with others. In this study, we identified ASD and non-ASD individuals using machine learning (ML) approaches. We used Gaussian naive Bayes (NB), k-nearest neighbors (KNN), random forest (RF), logistic regression (LR), Gaussian naive Bayes (NB), support vector machine (SVM) with linear basis function and decision tree (DT). We preprocessed the data using the imputation methods, namely linear regression, Mice forest, and Missforest. We selected the important features using the Simultaneous perturbation feature selection and ranking (SpFSR) technique from all 21 ASD features of three datasets combined (N=1,100 individuals) from University California Irvine (UCI) repository. We evaluated the performance of the method's discrimination, calibration, and clinical utility using a stratified 10-fold cross-validation method. We achieved the highest accuracy possible by using SVM with selected the most important 10 features. We observed the integration of imputation using linear regression, SpFSR and SVM as the most effective models, with an accuracy rate of 100% outperformed the previous studies in ASD prediciton

Control learning rate for autism facial detection via deep transfer learning.

Autism spectrum disorder (ASD) is a complex neurodevelopmental disorder that affects social interaction and communication. Early detection of ASD can significantly improve outcomes for individuals with the disorder, and there has been increasing interest in using machine learning techniques to aid in the diagnosis of ASD. One promising approach is the use of deep learning techniques, particularly convolutional neural networks (CNNs), to classify facial images as indicative of ASD or not. However, choosing a learning rate for optimizing the performance of these deep CNNs can be tedious and may not always result in optimal convergence. In this paper, we propose a novel approach called the control subgradient algorithm (CSA) for tackling ASD diagnosis based on facial images using deep CNNs. CSA is a variation of the subgradient method in which the learning rate is updated by a control step in each iteration of each epoch. We apply CSA to the popular DensNet-121 CNN model and evaluate its performance on a publicly available facial ASD dataset. Our results show that CSA is faster than the baseline method and improves the classification accuracy and loss compared to the baseline. We also demonstrate the effectiveness of using CSA with -regularization to further improve the performance of our deep CNN model.

'Caregivers' awareness matters': Call for a child-centred approach to early detection of autism spectrum disorder through well-child visits in Japan.

Early detection of autism spectrum disorder (ASD) is essential to provide children with timely treatment and support. Evidence-based screening measures make it possible to identify children with suspected ASD at an early stage. Although Japan has a universal healthcare system that covers well-child visits, detection rates of developmental disorders, including ASD, at 18 months vary widely between municipalities (0.2%-48.0%). The reasons for this high level of variation are poorly understood. The present study aims to describe the barriers and facilitators of incorporating ASD identification during well-child visits in Japan. This is a qualitative study that conducts semi-structured in-depth interviews in two municipalities of Yamanashi Prefecture. We recruited all public health nurses (n = 17) and paediatricians (n = 11) involved in the well-child visit in each municipality and caregivers of children who also participated in the visits during the study period (n = 21). We identified four themes characterizing the process of ASD identification in the target municipalities: (1) Identification of children with ASD is driven by caregivers' sense of concern, acceptance and awareness. (2) Multidisciplinary cooperation and shared decision-making is limited. (3) Skills and training for developmental disabilities screening are underdeveloped. (4) Caregivers' expectations shape the interaction in important ways. Non-standardization of screening methods, limited knowledge and skills on screening and child development among healthcare providers and poor coordination among healthcare providers and caregivers are the main barriers to effective early detection of ASD through well-child visits. The findings suggest the importance of promoting a child-centred care approach through the application of evidence-based screening measures and effective information sharing.

Early Detection of Autism in Children Using Transfer Learning

Autism spectrum disorder (ASD) is a challenging and complex neuro-development syndrome that affects the child’s language, speech, social skills, communication skills, and logical thinking ability. The early detection of ASD is essential for delivering effective, timely interventions. Various facial features such as a lack of eye contact, showing uncommon hand or body movements, babbling or talking in an unusual tone, and not using common gestures could be used to detect and classify ASD at an early stage. Our study aimed to develop a deep transfer learning model to facilitate the early detection of ASD based on facial features. A dataset of facial images of autistic and non-autistic children was collected from the Kaggle data repository and was used to develop the transfer learning AlexNet (ASDDTLA) model. Our model achieved a detection accuracy of 87.7% and performed better than other established ASD detection models. Therefore, this model could facilitate the early detection of ASD in clinical practice.

A Machine Learning Framework for Early-Stage Detection of Autism Spectrum Disorders

Autism Spectrum Disorder (ASD) is a type of neurodevelopmental disorder that affects the everyday life of affected patients. Though it is considered hard to completely eradicate this disease, disease severity can be mitigated by taking early interventions. In this paper, we propose an effective framework for the evaluation of various Machine Learning (ML) techniques for the early detection of ASD. The proposed framework employs four different Feature Scaling (FS) strategies i.e., Quantile Transformer (QT), Power Transformer (PT), Normalizer, and Max Abs Scaler (MAS). Then, the feature-scaled datasets are classified through eight simple but effective ML algorithms like Ada Boost (AB), Random Forest (RF), Decision Tree (DT), K-Nearest Neighbors (KNN), Gaussian Naïve Bayes (GNB), Logistic Regression (LR), Support Vector Machine (SVM) and Linear Discriminant Analysis (LDA). Our experiments are performed on four standard ASD datasets (Toddlers, Adolescents, Children, and Adults). Comparing the classification outcomes using various statistical evaluation measures (Accuracy, Receiver Operating Characteristic: ROC curve, F1-score, Precision, Recall, Mathews Correlation Coefficient: MCC, Kappa score, and Log loss), the best-performing classification methods, and the best FS techniques for each ASD dataset are identified. After analyzing the experimental outcomes of different classifiers on feature-scaled ASD datasets, it is found that AB predicted ASD with the highest accuracy of 99.25%, and 97.95% for Toddlers and Children, respectively and LDA predicted ASD with the highest accuracy of 97.12% and 99.03% for Adolescents and Adults datasets, respectively. These highest accuracies are achieved while scaling Toddlers and Children with normalizer FS and Adolescents and Adults with the QT FS method. Afterward, the ASD risk factors are calculated, and the most important attributes are ranked according to their importance values using four different Feature Selection Techniques (FSTs) i.e., Info Gain Attribute Evaluator (IGAE), Gain Ratio Attribute Evaluator (GRAE), Relief F Attribute Evaluator (RFAE), and Correlation Attribute Evaluator (CAE). These detailed experimental evaluations indicate that proper finetuning of the ML methods can play an essential role in predicting ASD in people of different ages. We argue that the detailed feature importance analysis in this paper will guide the decision-making of healthcare practitioners while screening ASD cases. The proposed framework has achieved promising results compared to existing approaches for the early detection of ASD.