Comparison of Classification Algorithms of the Autism Spectrum Disorder Diagnosis

Lawi, Armin; Aziz, Firman

doi:10.1109/eiconcit.2018.8878593

Cited by 10 publications

(5 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ASD features have received little attention in the minimal research that had been done on recognising and assessing them in the clinical setting under the DSM-5, despite the introduction of sophisticated diagnostic tools based on ML. Armin Lawi [2] Using sample datasets of adult adults aged 17 and older, the best estimate results and k-fold values for each classification approach are investigated. However, Logistic Regression had a high rate of classification errors during testing, and K-Nearest Neighbours required more iterations to achieve the best performance.…”

Section: IImentioning

confidence: 99%

Prediction of Autism Spectrum Disorder based on Machine Learning Approach

Chandrappa,

BR,

Pahuja

2023

IJRASET

View full text Add to dashboard Cite

In recent years, awareness of autism spectrum disorder (ASD) has grown faster than before. As everyone is aware, ASD is a disorder of neurodevelopment that also encompasses problems with conduct and social interaction. The degree of symptom severity and each individual's experience with ASD vary. Any age can be used to diagnose autism. According to research, violence, self-harm, elopement. tantrums, preoccupation, and lack of obedience are behaviour patterns most frequently observed in people with autism. Therefore, it is imperative to spot any sign of severe ASD as soon as possible. ML methods like Random Forest, Naive Bayes, Decision Tree, K- Nearest Neighbour, Logistic Regression, and Support Vector Machine (SVM) are employed in this work. With the use of algorithms that have been used to decide which gives accurate results in terms of speed and accuracy, performance metrics assist in examining the degree of correctness of each piece of data across all users. ML methods like Random Forest, Naive Bayes, Decision Tree, K-Nearest Neighbour, Logistic Regression, and Support Vector Machine (SVM) are employed in this work. With the use of algorithms that have been used to decide which gives accurate results in terms of speed and accuracy, performance metrics assist in examining the degree of correctness of each piece of data across all users.

show abstract

Section: IImentioning

confidence: 99%

Prediction of Autism Spectrum Disorder based on Machine Learning Approach

Chandrappa,

BR,

Pahuja

2023

IJRASET

View full text Add to dashboard Cite

show abstract

“…The main contribution of studies [6,47,48] is that the exploration of ASD using classification algorithms trained with a set of attributes produces outstanding prediction results based on sociodemographic features. The studies [18,[49][50][51][52] were aimed at utilizing feature selection to determine common influential attributes that are usually selected by feature selection methods and have a direct impact on the classification performance of predicting/screening tools, which shows a comparison of the performance of different prediction algorithms to diagnose ASD, which uses more than one algorithm and determines the best model based on the accuracy [53][54][55][56].…”

Section: Diagnosis Of Asd Towardmentioning

confidence: 99%

“…Furthermore, there is a requirement to develop fast medical diagnostic systems using the integration of ML methods [44]. AI algorithms have been used to save costs for human diagnosis and improve the quality of prediction [54,55,66]. ASD prediction can facilitate the time and effort of the medical staff based on the efficiency of the prediction model.…”

Section: Improving Early Diagnosis and Treatmentmentioning

confidence: 99%

See 1 more Smart Citation

Diagnosis-Based Hybridization of Multimedical Tests and Sociodemographic Characteristics of Autism Spectrum Disorder Using Artificial Intelligence and Machine Learning Techniques: A Systematic Review

Alqaysi

Albahri

Hamid

2022

International Journal of Telemedicine and Applications

View full text Add to dashboard Cite

Autism spectrum disorder (ASD) is a complex neurobehavioral condition that begins in childhood and continues throughout life, affecting communication and verbal and behavioral skills. It is challenging to discover autism in the early stages of life, which prompted researchers to intensify efforts to reach the best solutions to treat this challenge by introducing artificial intelligence (AI) techniques and machine learning (ML) algorithms, which played an essential role in greatly assisting the medical and healthcare staff and trying to obtain the highest predictive results for autism spectrum disorder. This study is aimed at systematically reviewing the literature related to the criteria, including multimedical tests and sociodemographic characteristics in AI techniques and ML contributions. Accordingly, this study checked the Web of Science (WoS), Science Direct (SD), IEEE Xplore digital library, and Scopus databases. A set of 944 articles from 2017 to 2021 is collected to reveal a clear picture and better understand all the academic literature through a definitive collection of 40 articles based on our inclusion and exclusion criteria. The selected articles were divided based on similarity, objective, and aim evidence across studies. They are divided into two main categories: the first category is “diagnosis of ASD based on questionnaires and sociodemographic features” ( n = 39 ). This category contains a subsection that consists of three categories: (a) early diagnosis of ASD towards analysis, (b) diagnosis of ASD towards prediction, and (c) diagnosis of ASD based on resampling techniques. The second category consists of “diagnosis ASD based on medical and family characteristic features” ( n = 1 ). This multidisciplinary systematic review revealed the taxonomy, motivations, recommendations, and challenges of diagnosis ASD research in utilizing AI techniques and ML algorithms that need synergistic attention. Thus, this systematic review performs a comprehensive science mapping analysis and identifies the open issues that help accomplish the recommended solution of diagnosis ASD research. Finally, this study critically reviews the literature and attempts to address the diagnosis ASD research gaps in knowledge and highlights the available ASD datasets, AI techniques and ML algorithms, and the feature selection methods that have been collected from the final set of articles.

show abstract

“…По третьему вопросу для эффективной ИИ важно определение различных видов факторов риска РАС [27]. Авторы отмечают, что проведение исследований в раннем возрасте на определение РАС свидетельствует о том, что алгоритмы ИИ позволяют снизить затраты на здравоохранение [28,29]. Сложности с прогнозированием РАС связаны со сложностью дифференцирования множества других психических расстройств, некоторые проявления которых очень похожи на проявления с симптомами РАС [23,30].…”

unclassified

Роль Искусственного Интеллекта Для Лечения Детей С Расстройством Аутистического Спектра: Международный Опыт

Кошербаева,

Самамбаева,

Сабырдилда

et al. 2023

Farmaciâ Kazahstana

View full text Add to dashboard Cite

Введение. Расстройства аутистического спектра (РАС) — это расстройство развития нервной системы, для которых характерны поведенческие и психологические проблемы у детей. Наблюдается рост распространённости РАС во всем мире. В последние десятилетия наблюдается рост исследований по применению искусственного интеллекта (ИИ), позволяющий ускорить процесс диагностики, и впоследствии раннего доступа к лечению детей с РАС. Целью нашего обзора является изучить применение искусственного интеллекта для детей с РАС. Методы. Был проведен обзор литературы существующих систематических обзоров и мета-анализов с 2013 по 2023 г. Поиск литературы проводился в базах данных PubMed, Кокрановская база систематических обзоров и Scopus. Поиск был ограничен человеческой популяцией, исследованиями на английском и русском языке. Каждое включенное исследование оценивалось по чек-листу AMSTAR-2. Результаты. Мы проанализировали результаты пяти систематических обзоров, двух мета-анализов, трех систематических обзоров-мета-анализов. В настоящее время нет единых подходов применения ИИ для диагностики и лечения детей с РАС. Существующие алгоритмы машинного обучения подразделяется на контролируемое, полу-контролируемое, неконтролируемое. Большинство работ включали в себя оценку производительности машины опорных векторов, нейронные сети и деревья решений, из которых наибольшую эффективность продемонстрировал анализ нейронной сети. ИИ применяется различными способами для диагностики и лечения РАС. Важно отметить, что системы на основе ИИ все еще разрабатываются и проверяются, и не все они еще широко применяются в клинической практике. Кроме того, модели ИИ следует использовать как дополнительный инструмент, а не как единственный метод диагностики, и всегда под наблюдением квалифицированного специалиста. Выводы. Проведенный анализ показал рост исследований в области ИИ для диагностики и лечения РАС, который имеет большой потенциал в будущих разработках и производительности.

show abstract

Comparison of Classification Algorithms of the Autism Spectrum Disorder Diagnosis

Cited by 10 publications

References 22 publications

Prediction of Autism Spectrum Disorder based on Machine Learning Approach

Prediction of Autism Spectrum Disorder based on Machine Learning Approach

Diagnosis-Based Hybridization of Multimedical Tests and Sociodemographic Characteristics of Autism Spectrum Disorder Using Artificial Intelligence and Machine Learning Techniques: A Systematic Review

Роль Искусственного Интеллекта Для Лечения Детей С Расстройством Аутистического Спектра: Международный Опыт

Contact Info

Product

Resources

About