Can Autism Be Diagnosed with Artificial Intelligence? A Narrative Review

Chaddad, Ahmad; Li, Jiali; Lu, Qizong; Li, Yujie; Okuwobi, Idowu Paul; Tanougast, Camel; Desrosiers, Christian; Niazi, Tamim

doi:10.3390/diagnostics11112032

Cited by 15 publications

(6 citation statements)

References 143 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ML is a subfield of artificial intelligence (AI) that enables systems to “learn” and build an analytical model to predict outcomes and improve from experience, with minimal human intervention. ML uses different supervised learning methods (e.g., support vector machines, neural networks, gradient-boosting machine, random forest) to classify ASDs [ 202 , 203 ]. These methods enable the machine to learn ASD-associated features and construct a relevant model that can be used for diagnostic purposes.…”

Section: Machine Learning To Detect Asd Biomarkersmentioning

confidence: 99%

Neuroimaging genetics approaches to identify new biomarkers for the early diagnosis of autism spectrum disorder

Nisar

Haris

2023

Mol Psychiatry

View full text Add to dashboard Cite

Autism-spectrum disorders (ASDs) are developmental disabilities that manifest in early childhood and are characterized by qualitative abnormalities in social behaviors, communication skills, and restrictive or repetitive behaviors. To explore the neurobiological mechanisms in ASD, extensive research has been done to identify potential diagnostic biomarkers through a neuroimaging genetics approach. Neuroimaging genetics helps to identify ASD-risk genes that contribute to structural and functional variations in brain circuitry and validate biological changes by elucidating the mechanisms and pathways that confer genetic risk. Integrating artificial intelligence models with neuroimaging data lays the groundwork for accurate diagnosis and facilitates the identification of early diagnostic biomarkers for ASD. This review discusses the significance of neuroimaging genetics approaches to gaining a better understanding of the perturbed neurochemical system and molecular pathways in ASD and how these approaches can detect structural, functional, and metabolic changes and lead to the discovery of novel biomarkers for the early diagnosis of ASD.

show abstract

Section: Machine Learning To Detect Asd Biomarkersmentioning

confidence: 99%

Neuroimaging genetics approaches to identify new biomarkers for the early diagnosis of autism spectrum disorder

Nisar

Haris

2023

Mol Psychiatry

View full text Add to dashboard Cite

show abstract

“…The primary objective is thoroughly synthesising existing conceptual and empirical articles and surveys, encompassing primary research while conducting a meta-narrative review [38]. A semi-systematic review has also proved sufficient to better understand complex areas like NLP and business research [39][40][41]. A critical literature analysis was performed to foresee Forex hourly price fluctuations, selecting pertinent sources from Yahoo Finance and Twitter Streaming APIs for the EUR/GBP currency pair.…”

Section: Incorporating Rational Choice Theory With Neuroscience and A...mentioning

confidence: 99%

Predicting Forex Currency Fluctuations Using a Novel Bio-Inspired Modular Neural Network

Bormpotsis,

Sedky,

Patel

2023

BDCC

View full text Add to dashboard Cite

In the realm of foreign exchange (Forex) market predictions, Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) have been commonly employed. However, these models often exhibit instability due to vulnerability to data perturbations attributed to their monolithic architecture. Hence, this study proposes a novel neuroscience-informed modular network that harnesses closing prices and sentiments from Yahoo Finance and Twitter APIs. Compared to monolithic methods, the objective is to advance the effectiveness of predicting price fluctuations in Euro to British Pound Sterling (EUR/GBP). The proposed model offers a unique methodology based on a reinvigorated modular CNN, replacing pooling layers with orthogonal kernel initialisation RNNs coupled with Monte Carlo Dropout (MCoRNNMCD). It integrates two pivotal modules: a convolutional simple RNN and a convolutional Gated Recurrent Unit (GRU). These modules incorporate orthogonal kernel initialisation and Monte Carlo Dropout techniques to mitigate overfitting, assessing each module’s uncertainty. The synthesis of these parallel feature extraction modules culminates in a three-layer Artificial Neural Network (ANN) decision-making module. Established on objective metrics like the Mean Square Error (MSE), rigorous evaluation underscores the proposed MCoRNNMCD–ANN’s exceptional performance. MCoRNNMCD–ANN surpasses single CNNs, LSTMs, GRUs, and the state-of-the-art hybrid BiCuDNNLSTM, CLSTM, CNN–LSTM, and LSTM–GRU in predicting hourly EUR/GBP closing price fluctuations.

show abstract

“…Artificial intelligence technology has obtained reliable results in genetic diagnosis and neuropsychological diagnoses of neurodevelopmental diseases, such as intellectual disability, autism, and depression ( 5 , 14 ), which makes it possible to break through the bottleneck of early prediction and intervention of AD.…”

Section: Application Scenarios Of the Metaverse In Medicine In Cognit...mentioning

confidence: 99%

The paradigm and future value of the metaverse for the intervention of cognitive decline

Zhou

Gao²,

Chen³

2022

Front. Public Health

View full text Add to dashboard Cite

Cognitive decline is a gradual neurodegenerative process that is affected by genetic and environmental factors. The doctor-patient relationship in the healthcare for cognitive decline is in a “shallow” medical world. With the development of data science, virtual reality, artificial intelligence, and digital twin, the introduction of the concept of the metaverse in medicine has brought alternative and complementary strategies in the intervention of cognitive decline. This article technically analyzes the application scenarios and paradigms of the metaverse in medicine in the field of mental health, such as hospital management, diagnosis, prediction, prevention, rehabilitation, progression delay, assisting life, companionship, and supervision. The metaverse in medicine has made primary progress in education, immersive consultation, dental disease, and Parkinson's disease, bringing revolutionary prospects for non-pharmacological complementary treatment of cognitive decline and other mental problems. In particular, with the demand for non-face-to-face communication generated by the global COVID-19 epidemic, the needs for uncontactable healthcare service for the elderly have increased. The paradigm of self-monitoring, self-healing, and healthcare experienced by the elderly through the metaverse in medicine, especially from meta-platform, meta-community, and meta-hospital, will be generated, which will reconstruct the service modes for the elderly people. The future map of the metaverse in medicine is huge, which depends on the co-construction of community partners.

show abstract

Can Autism Be Diagnosed with Artificial Intelligence? A Narrative Review

Cited by 15 publications

References 143 publications

Neuroimaging genetics approaches to identify new biomarkers for the early diagnosis of autism spectrum disorder

Neuroimaging genetics approaches to identify new biomarkers for the early diagnosis of autism spectrum disorder

Predicting Forex Currency Fluctuations Using a Novel Bio-Inspired Modular Neural Network

The paradigm and future value of the metaverse for the intervention of cognitive decline

Contact Info

Product

Resources

About