scholarly journals A machine learning approach to inform developmental milestone achievement for children with autism (Preprint)

2021 ◽  
Author(s):  
Munirul M. Haque ◽  
Masud Rabbani ◽  
Dipranjan Das Dipal ◽  
Md Ishrak Islam Zarif ◽  
Anik Iqbal ◽  
...  
Keyword(s):  
Machine Learning ◽  
Autism Spectrum Disorder ◽  
Children With Autism ◽  
Autism Spectrum ◽  
The Other ◽  
Supervised Machine Learning ◽  
Learning Models ◽  
Children With Asd ◽  
Socio Demographic Factors ◽  
Machine Learning Models

BACKGROUND Care for children with autism spectrum disorder (ASD) can be challenging for families and medical care systems. This is especially true in Low-and-Middle-Income-countries (LMIC) like Bangladesh. To improve family-practitioner communication and developmental monitoring of children with ASD, [spell out] (mCARE) was developed. Within this study, mCARE was used to track child milestone achievement and family socio-demographic assets to inform mCARE feasibility/scalability and family-asset informed practitioner recommendations. OBJECTIVE The objectives of this paper are three-fold. First, document how mCARE can be used to monitor child milestone achievement. Second, demonstrate how advanced machine learning models can inform our understanding of milestone achievement in children with ASD. Third, describe family/child socio-demographic factors that are associated with earlier milestone achievement in children with ASD (across five machine learning models). METHODS Using mCARE collected data, this study assessed milestone achievement in 300 children with ASD from Bangladesh. In this study, we used four supervised machine learning (ML) algorithms (Decision Tree, Logistic Regression, k-Nearest Neighbors, Artificial Neural Network) and one unsupervised machine learning (K-means Clustering) to build models of milestone achievement based on family/child socio-demographic details. For analyses, the sample was randomly divided in half to train the ML models and then their accuracy was estimated based on the other half of the sample. Each model was specified for the following milestones: Brushes teeth, Asks to use the toilet, Urinates in the toilet or potty, and Buttons large buttons. RESULTS This study aimed to find a suitable machine learning algorithm for milestone prediction/achievement for children with ASD using family/child socio-demographic characteristics. For, Brushes teeth, the three supervised machine learning models met or exceeded an accuracy of 95% with Logistic Regression, KNN, and ANN as the most robust socio-demographic predictors. For Asks to use toilet, 84.00% accuracy was achieved with the KNN and ANN models. For these models, the family socio-demographic predictors of “family expenditure” and “parents’ age” accounted for most of the model variability. The last two parameters, Urinates in toilet or potty and Buttons large buttons had an accuracy of 91.00% and 76.00%, respectively, in ANN. Overall, the ANN had a higher accuracy (Above ~80% on average) among the other algorithms for all the parameters. Across the models and milestones, “family expenditure”, “family size/ type”, “living places” and “parent’s age and occupation” were the most influential family/child socio-demographic factors. CONCLUSIONS mCARE was successfully deployed in an LMIC (i.e., Bangladesh), allowing parents and care-practitioners a mechanism to share detailed information on child milestones achievement. Using advanced modeling techniques this study demonstrates how family/child socio-demographic elements can inform child milestone achievement. Specifically, families with fewer socio-demographic resources reported later milestone attainment. Developmental science theories highlight how family/systems can directly influence child development and this study provides a clear link between family resources and child developmental progress. Clinical implications for this work could include supporting the larger family system to improve child milestone achievement. CLINICALTRIAL We took the IRB from Marquette University Institutional Review Board on July 9, 2020, with the protocol number HR-1803022959, and titled “MOBILE-BASED CARE FOR CHILDREN WITH AUTISM SPECTRUM DISORDER USING REMOTE EXPERIENCE SAMPLING METHOD (MCARE)” for recruiting a total of 316 subjects, of which we recruited 300. (Details description of participants in Methods section)

Application of Machine Learning Techniques to Predict Binding Affinity for Drug Targets: A Study of Cyclin-Dependent Kinase 2

2020 ◽  
Vol 28 (2) ◽  
pp. 253-265 ◽  
Author(s):  
Gabriela Bitencourt-Ferreira ◽  
Amauri Duarte da Silva ◽  
Walter Filgueira de Azevedo
Keyword(s):  
Machine Learning ◽  
Binding Affinity ◽  
Predictive Performance ◽  
Supervised Machine Learning ◽  
Machine Learning Techniques ◽  
Scoring Functions ◽  
Cyclin Dependent Kinase ◽  
Learning Models ◽  
Learning Techniques ◽  
Machine Learning Models

Background: The elucidation of the structure of cyclin-dependent kinase 2 (CDK2) made it possible to develop targeted scoring functions for virtual screening aimed to identify new inhibitors for this enzyme. CDK2 is a protein target for the development of drugs intended to modulate cellcycle progression and control. Such drugs have potential anticancer activities. Objective: Our goal here is to review recent applications of machine learning methods to predict ligand- binding affinity for protein targets. To assess the predictive performance of classical scoring functions and targeted scoring functions, we focused our analysis on CDK2 structures. Methods: We have experimental structural data for hundreds of binary complexes of CDK2 with different ligands, many of them with inhibition constant information. We investigate here computational methods to calculate the binding affinity of CDK2 through classical scoring functions and machine- learning models. Results: Analysis of the predictive performance of classical scoring functions available in docking programs such as Molegro Virtual Docker, AutoDock4, and Autodock Vina indicated that these methods failed to predict binding affinity with significant correlation with experimental data. Targeted scoring functions developed through supervised machine learning techniques showed a significant correlation with experimental data. Conclusion: Here, we described the application of supervised machine learning techniques to generate a scoring function to predict binding affinity. Machine learning models showed superior predictive performance when compared with classical scoring functions. Analysis of the computational models obtained through machine learning could capture essential structural features responsible for binding affinity against CDK2.

scholarly journals Parents’ Perceptions of Early Interventions and Related Services for Children with Autism Spectrum Disorder in Saudi Arabia

2016 ◽  
Vol 9 (10) ◽  
pp. 128 ◽  
Author(s):  
Faihan Alotaibi ◽  
Nabil Almalki
Keyword(s):  
Autism Spectrum Disorder ◽  
Saudi Arabia ◽  
Early Intervention ◽  
Children With Autism ◽  
Autism Spectrum ◽  
Spectrum Disorder ◽  
Early Interventions ◽  
Related Services ◽  
Children With Asd ◽  
The Government

<p class="apa">The present study sought to examine parents’ perceptions of early interventions and related services for children with autism spectrum disorder (ASD) in Saudi Arabia. In this study a survey was distributed to a sample of 80 parents with children who have ASD. Parents also were asked open-ended questions to enable them to provide suggestions. The findings indicate that parents have varying perceptions of early interventions and related services. However, they seem to agree that these services are important in assisting their children. Accordingly, parents have suggested that the government needs to increase these services by providing more centers for children with ASD in Saudi Arabia, providing more specialists to deal with children with ASD, promoting inclusion in regular schools and providing more information on early intervention.</p>

scholarly journals Implication of the Sensory Environment in Children with Autism Spectrum Disorder: Perspectives from School

2021 ◽  
Vol 18 (14) ◽  
pp. 7670
Author(s):  
Ana Gentil-Gutiérrez ◽  
José Luis Cuesta-Gómez ◽  
Paula Rodríguez-Fernández ◽  
Jerónimo Javier González-Bernal
Keyword(s):  
Autism Spectrum Disorder ◽  
Sensory Processing ◽  
Children With Autism ◽  
Autism Spectrum ◽  
Spectrum Disorder ◽  
Sensory Profile ◽  
School Factors ◽  
Cross Sectional ◽  
Sensory Stimuli ◽  
Children With Asd

(1) Background: Children with Autism Spectrum Disorder (ASD) frequently have difficulties in processing sensory information, which is a limitation when participating in different contexts, such as school. The objective of the present study was to compare the sensory processing characteristics of children with ASD in the natural context of school through the perception of professionals in the field of education, in comparison with neurodevelopmental children (2) Methods: A cross-sectional descriptive study as conducted with study population consisting of children between three and ten years old, 36 of whom were diagnosed with ASD and attended the Autismo Burgos association; the remaining 24 had neurotypical development. The degree of response of the children to sensory stimuli at school was evaluated using the Sensory Profile-2 (SP-2) questionnaire in its school version, answered by the teachers. (3) Results: Statistically significant differences were found in sensory processing patterns (p = 0.001), in sensory systems (p = 0.001) and in school factors (p = 0.001). Children with ASD who obtained worse results. (4) Conclusions: Children with ASD are prone to present sensory alterations in different contexts, giving nonadapted behavioral and learning responses.

scholarly journals Autism Detection in Children by Combined Use of Gaze Preference and the M-CHAT-R in a Resource-Scarce Setting

2021 ◽  
Vol 51 (3) ◽  
pp. 994-1006
Author(s):  
Kelly Jensen ◽  
◽  
Sassan Noazin ◽  
Leandra Bitterfeld ◽  
Andrea Carcelen ◽  
...  
Keyword(s):  
Autism Spectrum Disorder ◽  
Children With Autism ◽  
Autism Spectrum ◽  
Typically Developing ◽  
Early Screening ◽  
Resource Limited Settings ◽  
Children With Asd ◽  
Resource Limited ◽  
Combined Use ◽  
Better Than

AbstractMost children with autism spectrum disorder (ASD), in resource-limited settings (RLS), are diagnosed after the age of four. Our work confirmed and extended results of Pierce that eye tracking could discriminate between typically developing (TD) children and those with ASD. We demonstrated the initial 15 s was at least as discriminating as the entire video. We evaluated the GP-MCHAT-R, which combines the first 15 s of manually-coded gaze preference (GP) video with M-CHAT-R results on 73 TD children and 28 children with ASD, 36–99 months of age. The GP-MCHAT-R (AUC = 0.89 (95%CI: 0.82–0.95)), performed significantly better than the MCHAT-R (AUC = 0.78 (95%CI: 0.71–0.85)) and gaze preference (AUC = 0.76 (95%CI: 0.64–0.88)) alone. This tool may enable early screening for ASD in RLS.

Wechsler Intelligence Scale for Children, Fifth Edition Profiles of Children With Autism Spectrum Disorder Using a Classification and Regression Trees Analysis

2021 ◽  
pp. 073428292110259
Author(s):  
Brittany A. Dale ◽  
W. Holmes Finch ◽  
Kassie A. R. Shellabarger ◽  
Andrew Davis
Keyword(s):  
Autism Spectrum Disorder ◽  
Language Impairment ◽  
Children With Autism ◽  
Autism Spectrum ◽  
Spectrum Disorder ◽  
Intelligence Scale ◽  
Cart Analysis ◽  
Children With Asd ◽  
Classification And Regression ◽  
Pattern Of Performance

The Wechsler Intelligence Scales for Children (WISC) are the most widely used instrument in assessing cognitive ability, especially with children with autism spectrum disorder (ASD). Previous literature on the WISC has demonstrated a divergent pattern of performance on the WISC for children ASD compared to their typically developing peers; however, there is a lack of research concerning the most recent iteration, the Wechsler Intelligence Scale for Children, Fifth Edition (WISC-V). Due to the distinctive changes made to the WISC-V, we sought to identify the pattern of performance of children with ASD on the WISC-V using a classification and regression (CART) analysis. The current study used the standardization sample data of the WISC-V obtained from NCS Pearson, Inc. Sixty-two children diagnosed with ASD, along with their demographically matched controls, comprised the sample. Results revealed the Comprehension and Letter-Number Sequencing subtests were the most important factors in predicting group membership for children with ASD with an accompanying language impairment. Children with ASD without an accompanying language impairment, however, were difficult to distinguish from matched controls through the CART analysis. Results suggest school psychologists and other clinicians should administer all primary and supplemental subtests of the WISC-V as part of a comprehensive assessment of ASD.

scholarly journals Prediction of Head Movement in 360-Degree Videos Using Attention Model

Sensors ◽  
2021 ◽  
Vol 21 (11) ◽  
pp. 3678
Author(s):  
Dongwon Lee ◽  
Minji Choi ◽  
Joohyun Lee
Keyword(s):  
Machine Learning ◽  
Short Term Memory ◽  
Moving Average ◽  
The Other ◽  
Learning Models ◽  
Short Term ◽  
Term Memory ◽  
Attention Model ◽  
Long Short Term Memory ◽  
Machine Learning Models

In this paper, we propose a prediction algorithm, the combination of Long Short-Term Memory (LSTM) and attention model, based on machine learning models to predict the vision coordinates when watching 360-degree videos in a Virtual Reality (VR) or Augmented Reality (AR) system. Predicting the vision coordinates while video streaming is important when the network condition is degraded. However, the traditional prediction models such as Moving Average (MA) and Autoregression Moving Average (ARMA) are linear so they cannot consider the nonlinear relationship. Therefore, machine learning models based on deep learning are recently used for nonlinear predictions. We use the Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) neural network methods, originated in Recurrent Neural Networks (RNN), and predict the head position in the 360-degree videos. Therefore, we adopt the attention model to LSTM to make more accurate results. We also compare the performance of the proposed model with the other machine learning models such as Multi-Layer Perceptron (MLP) and RNN using the root mean squared error (RMSE) of predicted and real coordinates. We demonstrate that our model can predict the vision coordinates more accurately than the other models in various videos.

scholarly journals A study of micromanufacturing process fingerprints in micro-injection moulding for machine learning and Industry 4.0 applications

2021 ◽  
Author(s):  
Mert Gülçür ◽  
Ben Whiteside
Keyword(s):  
Machine Learning ◽  
Linear Regression ◽  
Multiple Linear Regression ◽  
Injection Moulding ◽  
Industry 4.0 ◽  
Supervised Machine Learning ◽  
Process Conditions ◽  
Learning Models ◽  
Micro Injection Moulding ◽  
Machine Learning Models

AbstractThis paper discusses micromanufacturing process quality proxies called “process fingerprints” in micro-injection moulding for establishing in-line quality assurance and machine learning models for Industry 4.0 applications. Process fingerprints that we present in this study are purely physical proxies of the product quality and need tangible rationale regarding their selection criteria such as sensitivity, cost-effectiveness, and robustness. Proposed methods and selection reasons for process fingerprints are also justified by analysing the temporally collected data with respect to the microreplication efficiency. Extracted process fingerprints were also used in a multiple linear regression scenario where they bring actionable insights for creating traceable and cost-effective supervised machine learning models in challenging micro-injection moulding environments. Multiple linear regression model demonstrated %84 accuracy in predicting the quality of the process, which is significant as far as the extreme process conditions and product features are concerned.

Sign in / Sign up

Export Citation Format

Share Document