Identification and analysis of behavioral phenotypes in autism spectrum disorder via unsupervised machine learning

Stevens, Elizabeth; Dixon, Dennis R.; Novack, Marlena N.; Granpeesheh, Doreen; Smith, Tristram; Linstead, Erik

doi:10.1016/j.ijmedinf.2019.05.006

Cited by 76 publications

(50 citation statements)

References 62 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Previous studies mostly focused on a specific disease using ad hoc cohorts of patients and features [8][9][10][11]43,44 . While these studies obtained relevant clinically meaningful results, the computational framework is hard to replicate for different diseases and it is tied to the specific study and to the specific data.…”

Section: Discussionmentioning

confidence: 99%

Deep representation learning of electronic health records to unlock patient stratification at scale

et al. 2020

View full text Add to dashboard Cite

Deriving disease subtypes from electronic health records (EHRs) can guide next-generation personalized medicine. However, challenges in summarizing and representing patient data prevent widespread practice of scalable EHR-based stratification analysis. Here we present an unsupervised framework based on deep learning to process heterogeneous EHRs and derive patient representations that can efficiently and effectively enable patient stratification at scale. We considered EHRs of 1,608,741 patients from a diverse hospital cohort comprising a total of 57,464 clinical concepts. We introduce a representation learning model based on word embeddings, convolutional neural networks, and autoencoders (i.e., ConvAE) to transform patient trajectories into lowdimensional latent vectors. We evaluated these representations as broadly enabling patient stratification by applying hierarchical clustering to different multi-disease and disease-specific patient cohorts. ConvAE significantly outperformed several baselines in a clustering task to identify patients with different complex conditions, with 2.61 entropy and 0.31 purity average scores. When applied to stratify patients within a certain condition, ConvAE led to various clinically relevant subtypes for different disorders, including type 2 diabetes, Parkinson's disease, and Alzheimer's disease, largely related to comorbidities, disease progression, and symptom severity. With these results, we demonstrate that ConvAE can generate patient representations that lead to clinically meaningful insights. This scalable framework can help better understand varying etiologies in heterogeneous sub-populations and unlock patterns for EHR-based research in the realm of personalized medicine.

show abstract

Section: Discussionmentioning

confidence: 99%

Deep representation learning of electronic health records to unlock patient stratification at scale

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Stevens et al [29] identified and analyzed behavioral phenotypes in ASD using unsupervised machine learning as well. The authors mainly applied Gaussian mixture models and hierarchical clustering.…”

Section: Classifying Asd By Enhanced New Machine Learning Techniquesmentioning

confidence: 99%

A Review of Machine Learning Methods of Feature Selection and Classification for Autism Spectrum Disorder

et al. 2020

View full text Add to dashboard Cite

Autism Spectrum Disorder (ASD), according to DSM-5 in the American Psychiatric Association, is a neurodevelopmental disorder that includes deficits of social communication and social interaction with the presence of restricted and repetitive behaviors. Children with ASD have difficulties in joint attention and social reciprocity, using non-verbal and verbal behavior for communication. Due to these deficits, children with autism are often socially isolated. Researchers have emphasized the importance of early identification and early intervention to improve the level of functioning in language, communication, and well-being of children with autism. However, due to limited local assessment tools to diagnose these children, limited speech-language therapy services in rural areas, etc., these children do not get the rehabilitation they need until they get into compulsory schooling at the age of seven years old. Hence, efficient approaches towards early identification and intervention through speedy diagnostic procedures for ASD are required. In recent years, advanced technologies like machine learning have been used to analyze and investigate ASD to improve diagnostic accuracy, time, and quality without complexity. These machine learning methods include artificial neural networks, support vector machines, a priori algorithms, and decision trees, most of which have been applied to datasets connected with autism to construct predictive models. Meanwhile, the selection of features remains an essential task before developing a predictive model for ASD classification. This review mainly investigates and analyzes up-to-date studies on machine learning methods for feature selection and classification of ASD. We recommend methods to enhance machine learning’s speedy execution for processing complex data for conceptualization and implementation in ASD diagnostic research. This study can significantly benefit future research in autism using a machine learning approach for feature selection, classification, and processing imbalanced data.

show abstract

“…[12,26] The objective of the support vector machine algorithm, SVM, is to find a hyperplane in N-dimensional space (N: the number of features) that distinctly classify the data points. [2,5,27] data, data mining, uses complex mathematical machine learning algorithms [28].…”

Section: H Recent Machine Learning Research On Asd Screening and Diamentioning

confidence: 99%

Autism Spectrum Disorder Diagnosis using Optimal Machine Learning Methods

Alteneiji¹,

Mohammed²,

Usman³

2020

IJACSA

View full text Add to dashboard Cite

Autism spectrum disorder (ASD) is the disorder of communication and behavior that affects children and adults. It can be diagnosed at any stage of life. Most importantly, the first two years of life, regardless of ethnicity, race, or economic groups. There are different variations of ASD according to the severity and type of symptoms experienced by people. It is a lifelong disorder, but treatment and services can improve the symptoms. The literature focuses on one of the main methods used by physicians to diagnose ASD. Many types of research and medical reports have been reviewed; however, a few of them only give good medical results for the strong differentiation of ASD from healthy people. This paper focuses on using machine learning algorithms to predict an individual with specific ASD symptoms. The target is to predict an individual with specific ASD symptoms and finding the best machine learning model for diagnosis. Further, the paper aims to make the autism diagnosis faster to deliver the required treatment at an early stage of child development.

show abstract

Identification and analysis of behavioral phenotypes in autism spectrum disorder via unsupervised machine learning

Cited by 76 publications

References 62 publications

Deep representation learning of electronic health records to unlock patient stratification at scale

Deep representation learning of electronic health records to unlock patient stratification at scale

A Review of Machine Learning Methods of Feature Selection and Classification for Autism Spectrum Disorder

Autism Spectrum Disorder Diagnosis using Optimal Machine Learning Methods

Contact Info

Product

Resources

About