scispace - formally typeset
Search or ask a question
Proceedings ArticleDOI

A Machine Learning Approach to Predict Autism Spectrum Disorder

TL;DR: The evaluation results showed that the proposed prediction model provide better results in terms of accuracy, specificity, sensitivity, precision and false positive rate (FPR) for both kinds of datasets.
Abstract: In present day Autism Spectrum Disorder (ASD) is gaining its momentum faster than ever. Detecting autism traits through screening tests is very expensive and time consuming. With the advancement of artificial intelligence and machine learning (ML), autism can be predicted at quite early stage. Though number of studies have been carried out using different techniques, these studies didn't provide any definitive conclusion about predicting autism traits in terms of different age groups. Therefore this paper aims to propose an effective prediction model based on ML technique and to develop a mobile application for predicting ASD for people of any age. As outcomes of this research, an autism prediction model was developed by merging Random Forest-CART (Classification and Regression Trees) and Random Forest-Id3(Iterative Dichotomiser 3) and also a mobile application was developed based on the proposed prediction model. The proposed model was evaluated with AQ-10 dataset and 250 real dataset collected from people with and without autistic traits. The evaluation results showed that the proposed prediction model provide better results in terms of accuracy, specificity, sensitivity, precision and false positive rate (FPR) for both kinds of datasets.
Citations
More filters
Journal ArticleDOI
TL;DR: The results of these analytical approaches indicate that, when appropriately optimised, machine learning methods can provide good predictions of ASD status and suggests that it may possible to apply these models for the detection of ASD in its early stages.
Abstract: Autism Spectrum Disorder (ASD) is a group of neurodevelopmental disabilities that are not curable but may be ameliorated by early interventions. We gathered early-detected ASD datasets relating to toddlers, children, adolescents and adults, and applied several feature transformation methods, including log, Z-score and sine functions to these datasets. Various classification techniques were then implemented with these transformed ASD datasets and assessed for their performance. We found SVM showed the best performance for the toddler dataset, while Adaboost gave the best results for the children dataset, Glmboost for the adolescent and Adaboost for the adult datasets. The feature transformations resulting in the best classifications was sine function for toddler and Z-score for children and adolescent datasets. After these analyses, several feature selection techniques were used with these Z-score-transformed datasets to identify the significant ASD risk factors for the toddler, child, adolescent and adult subjects. The results of these analytical approaches indicate that, when appropriately optimised, machine learning methods can provide good predictions of ASD status. This suggests that it may possible to apply these models for the detection of ASD in its early stages.

90 citations


Cites methods from "A Machine Learning Approach to Pred..."

  • ...In addition, no study has evaluated in detail the early detection based on the ASD datasets, while we used a range of metrics (AUROC, kappa statistics and logloss) to assess this [2], [38], [39] (see Table 13)....

    [...]

  • ...[38] developed an autism prediction model by merging Random Forest-CART (RF-CART) and Random Forest-ID3 (RF-ID3) and their proposed models predicted ASD with 92....

    [...]

  • ...and adult datasets were explored and ranked which were not shown properly in the previous studies [2], [38], [39]...

    [...]

Journal ArticleDOI
TL;DR: In this paper, some of the research works in the field of application of AI, ML, and IoT in autism were reviewed and incorporation of the autism facilities in smart city environment is described.

47 citations

Journal ArticleDOI
TL;DR: This work used a machine learning algorithm (support vector machine) to examine whether ASD detection can be improved by identifying a subset of behavioral features from the ADOS Module 4 in a routine clinical sample of high-functioning adolescents and adults with ASD.
Abstract: Diagnosing autism spectrum disorders (ASD) is a complicated, time-consuming process which is particularly challenging in older individuals. One of the most widely used behavioral diagnostic tools is the Autism Diagnostic Observation Schedule (ADOS). Previous work using machine learning techniques suggested that ASD detection in children can be achieved with substantially fewer items than the original ADOS. Here, we expand on this work with a specific focus on adolescents and adults as assessed with the ADOS Module 4. We used a machine learning algorithm (support vector machine) to examine whether ASD detection can be improved by identifying a subset of behavioral features from the ADOS Module 4 in a routine clinical sample of N = 673 high-functioning adolescents and adults with ASD (n = 385) and individuals with suspected ASD but other best-estimate or no psychiatric diagnoses (n = 288). We identified reduced subsets of 5 behavioral features for the whole sample as well as age subgroups (adolescents vs. adults) that showed good specificity and sensitivity and reached performance close to that of the existing ADOS algorithm and the full ADOS, with no significant differences in overall performance. These results may help to improve the complicated diagnostic process of ASD by encouraging future efforts to develop novel diagnostic instruments for ASD detection based on the identified constructs as well as aiding clinicians in the difficult question of differential diagnosis.

42 citations

Journal ArticleDOI
TL;DR: An algorithm, namely Modified Grasshopper Optimization Algorithm (MGOA), capable of detecting Autism Spectrum Disorder at all stages of life is proposed, a nature-inspired algorithm that has the potential to explore and exploit the search space effectively.

25 citations

Book ChapterDOI
01 Jan 2022
TL;DR: In this article, three different ensemble ML models were proposed to classify the tweet data into three sentiment labels: positive, negative, and neutral, and the study found that stacking classifier (SC) showed the highest F1-score (83.5%), followed by the voting classifier(VC) (83 3%), and bagging classifier-BC (83 2%).
Abstract: Since the beginning of the global COVID-19 pandemic, measuring public opinion has been considered as one of the most critical issues for decision-makers to fight against the pandemic, such as implementing a national lockdown, introducing quarantine procedure, providing health services, and the like. During the COVID-19 pandemic, decision-makers in several countries around the world made a number of critical decisions focused on public opinion to combat coronavirus. In the field of natural language processing, sentiment analysis has emerged for mining public opinion, while machine learning (ML) algorithms are very common for analyzing sentiment. In this research, approximately 12 thousand tweets from United Kingdom (UK) were rigorously annotated by three independent reviewers, and based on the labeled tweets, three different ensemble ML models were proposed to classify the tweet data into three sentiment labels: positive, negative, and neutral. The study found that stacking classifier (SC) showed the highest F1-score (83.5%), followed by the voting classifier (VC) (83.3%) and bagging classifier (BC) (83.2%).

24 citations

References
More filters
01 Jan 2007

17,341 citations

01 Jan 2007
TL;DR: random forests are proposed, which add an additional layer of randomness to bagging and are robust against overfitting, and the randomForest package provides an R interface to the Fortran programs by Breiman and Cutler.
Abstract: Recently there has been a lot of interest in “ensemble learning” — methods that generate many classifiers and aggregate their results. Two well-known methods are boosting (see, e.g., Shapire et al., 1998) and bagging Breiman (1996) of classification trees. In boosting, successive trees give extra weight to points incorrectly predicted by earlier predictors. In the end, a weighted vote is taken for prediction. In bagging, successive trees do not depend on earlier trees — each is independently constructed using a bootstrap sample of the data set. In the end, a simple majority vote is taken for prediction. Breiman (2001) proposed random forests, which add an additional layer of randomness to bagging. In addition to constructing each tree using a different bootstrap sample of the data, random forests change how the classification or regression trees are constructed. In standard trees, each node is split using the best split among all variables. In a random forest, each node is split using the best among a subset of predictors randomly chosen at that node. This somewhat counterintuitive strategy turns out to perform very well compared to many other classifiers, including discriminant analysis, support vector machines and neural networks, and is robust against overfitting (Breiman, 2001). In addition, it is very user-friendly in the sense that it has only two parameters (the number of variables in the random subset at each node and the number of trees in the forest), and is usually not very sensitive to their values. The randomForest package provides an R interface to the Fortran programs by Breiman and Cutler (available at http://www.stat.berkeley.edu/ users/breiman/). This article provides a brief introduction to the usage and features of the R functions.

14,830 citations


"A Machine Learning Approach to Pred..." refers background in this paper

  • ...This somewhat counter intuitive strategy turns out to perform very well compared to many other classifiers, including discriminant analysis, support vector machines and neural networks, and is robust against over-fitting [18]....

    [...]

01 Jan 2007

2,447 citations


"A Machine Learning Approach to Pred..." refers methods in this paper

  • ...To develop an effective predictive model, AQ-10 dataset was used which consists of three different datasets based on AQ-10 screening tool questions [16]....

    [...]

Journal ArticleDOI
TL;DR: A broad survey of the different types of machine learning methods being used, the types of data being integrated and the performance of these methods in cancer prediction and prognosis is conducted, including a growing dependence on protein biomarkers and microarray data, a strong bias towards applications in prostate and breast cancer, and a heavy reliance on "older" technologies.
Abstract: Machine learning is a branch of artificial intelligence that employs a variety of statistical, probabilistic and optimization techniques that allows computers to “learn” from past examples and to detect hard-to-discern patterns from large, noisy or complex data sets. This capability is particularly well-suited to medical applications, especially those that depend on complex proteomic and genomic measurements. As a result, machine learning is frequently used in cancer diagnosis and detection. More recently machine learning has been applied to cancer prognosis and prediction. This latter approach is particularly interesting as it is part of a growing trend towards personalized, predictive medicine. In assembling this review we conducted a broad survey of the different types of machine learning methods being used, the types of data being integrated and the performance of these methods in cancer prediction and prognosis. A number of trends are noted, including a growing dependence on protein biomarkers and mi...

967 citations


"A Machine Learning Approach to Pred..." refers methods in this paper

  • ...For example, in [3] Cruz et al tried to diagnose cancer using ML while in [4] Khan et al used ML to predict if...

    [...]

Journal ArticleDOI
TL;DR: The results improved the state-of-the-art by achieving 70% accuracy in identification of ASD versus control patients in the dataset, and identified the areas of the brain that contributed most to differentiating ASD from typically developing controls as per the deep learning model.

583 citations


"A Machine Learning Approach to Pred..." refers methods in this paper

  • ...Heinsfeld [12] applied deep learning algorithm and neural network to...

    [...]