scholarly journals Machine Learning to Support Visual Inspection of Data: A Clinical Application

2021 ◽  
pp. 014544552110382
Author(s):  
Tessa Taylor ◽  
Marc J. Lanovaz
Keyword(s):  
Machine Learning ◽  
Visual Inspection ◽  
Single Case ◽  
Autism Spectrum ◽  
Experimental Designs ◽  
Feeding Programs ◽  
Home Based ◽  
Pediatric Feeding ◽  
Reversal Design ◽  
Additional Support

Practitioners in pediatric feeding programs often rely on single-case experimental designs and visual inspection to make treatment decisions (e.g., whether to change or keep a treatment in place). However, researchers have shown that this practice remains subjective, and there is no consensus yet on the best approach to support visual inspection results. To address this issue, we present the first application of a pediatric feeding treatment evaluation using machine learning to analyze treatment effects. A 5-year-old male with autism spectrum disorder participated in a 2-week home-based, behavior-analytic treatment program. We compared interrater agreement between machine learning and expert visual analysts on the effects of a pediatric feeding treatment within a modified reversal design. Both the visual analyst and the machine learning model generally agreed about the effectiveness of the treatment while overall agreement remained high. Overall, the results suggest that machine learning may provide additional support for the analysis of single-case experimental designs implemented in pediatric feeding treatment evaluations.

scholarly journals Machine Learning to Analyze Single-Case Graphs: A Comparison to Visual Inspection

2021 ◽  
Author(s):  
Marc J Lanovaz ◽  
Kieva Hranchuk
Keyword(s):  
Machine Learning ◽  
Error Rate ◽  
Effect Size ◽  
Visual Inspection ◽  
Type I Error ◽  
Single Case ◽  
Type I ◽  
Type I Error Rate ◽  
Novel Approach ◽  
Behavior Analysts

Behavior analysts commonly use visual inspection to analyze single-case graphs, but studies on its reliability have produced mixed results. To examine this issue, we compared the Type I error rate and power of visual inspection with a novel approach, machine learning. Five expert visual raters analyzed 1,024 simulated AB graphs, which differed on number of points per phase, autocorrelation, trend, variability, and effect size. The ratings were compared to those obtained by the conservative dual-criteria method and two models derived from machine learning. On average, visual raters agreed with each other on only 73% of graphs. In contrast, both models derived from machine learning showed the best balance between Type I error rate and power while producing more consistent results across different graph characteristics. The results suggest that machine learning may support researchers and practitioners in making less error when analyzing single-case graphs, but further replications remain necessary.

Embracing Our Visual Inspection and Analysis Tradition

2010 ◽  
Vol 33 (2) ◽  
pp. 71-77 ◽  
Author(s):  
Kathleen Artman ◽  
Mark Wolery ◽  
Paul Yoder
Keyword(s):  
Visual Inspection ◽  
Interobserver Agreement ◽  
Single Case ◽  
Internal Validity ◽  
Experimental Designs ◽  
Primary Study ◽  
Observer Drift

Most investigators using single-case experimental designs use interobserver agreement (IOA) checks to enhance the credibility of the collected data, and they report the results of those assessments using percentage of agreement estimates. An alternative is to graph both observers’ records of the measured behavior on the primary study graphs. Such graphing leads to greater transparency and is advocated for five reasons: (a) to make explicit how IOA assessments were distributed across the study, (b) to ensure agreement estimates are reported at the level of the measured behavior of interest rather than a broader observational code, (c) to detect observer drift, (d) to detect the effect of observer expectations, and (e) to put the IOA data in a more suitable context for assessing the internal validity of the study by eliminating the need for an arbitrary agreement criterion.

Using a Concept Map With RECALL to Increase the Comprehension of Science Texts for Children With Autism

2019 ◽  
Vol 35 (2) ◽  
pp. 90-100 ◽  
Author(s):  
Elizabeth M. Jackson ◽  
Mary Frances Hanline
Keyword(s):  
Single Case ◽  
Concept Map ◽  
Children With Autism ◽  
Natural World ◽  
Autism Spectrum ◽  
Language And Literacy ◽  
Science Text ◽  
Study Results ◽  
Reversal Design ◽  
And Mathematics

Learning science is important for students with autism spectrum disorder (ASD), as knowledge of science allows students to understand their natural world, and science, technology, engineering, and mathematics (STEM) education is increasingly emphasized in schools. Reading to learn science is, therefore, a vital skill in today’s schools for all students. Using a single-case reversal design, this study evaluated the effectiveness of Reading to Engage Children with Autism in Language and Literacy (RECALL; a shared reading intervention) combined with a concept map on the ability of young children with ASD to answer comprehension questions from science text. Two 5-year-old boys with ASD participated in this study. Results indicated that RECALL combined with a concept map was effective in increasing participants’ correct responding to comprehension questions from science text. Implications for intervention and research are discussed.

scholarly journals Side Deposit with Regular Texture Food for Clinical Cases In-Home

2020 ◽  
Vol 45 (4) ◽  
pp. 399-410 ◽  
Author(s):  
Tessa Taylor
Keyword(s):  
Hospital Setting ◽  
Autism Spectrum ◽  
Caregiver Training ◽  
Home Setting ◽  
Empirically Supported ◽  
Home Based ◽  
Mealtime Behavior ◽  
Reversal Design ◽  
Inappropriate Mealtime Behavior ◽  
Regular Texture

Abstract Objective Research has shown effectiveness of nonremoval of the spoon and physical guidance in increasing consumption and decreasing inappropriate mealtime behavior. The side deposit has been used to treat passive refusal in 2 studies (1 in a highly specialized hospital setting) using lower manipulated-texture foods on an infant gum brush. Methods We extended the literature by using regular texture bites of food with a finger prompt and side deposit (placing bites inside the side of the child’s mouth via the cheek) in an intensive home-based program setting in Australia, demonstrating that attention and tangible treatments alone were ineffective prior, fading the tangible treatment, showing caregiver training, and following up. 2 male children with autism spectrum disorder (with texture/variety selectivity; one with liquid dependence) participated in their homes. We used a reversal design to replicate effectiveness of the side deposit added to a treatment package. Results For both participants, we observed a >98% decrease in latency to acceptance, a 100% decrease in inappropriate mealtime behavior, and a 100% increase in consumption with the side deposit added. Variety was increased to over 85 regular texture foods. 100% of admission goals were met. Caregivers were trained to high procedural integrity and the protocol was generalized to school and the community. Gains maintained to 3 and 1.5 years. Conclusion This is important work in adding to the literature and support for the side deposit and expanding to regular texture, as well as replicating and extending empirically supported treatments for feeding internationally to the home setting.

scholarly journals Redistribution with Regular Texture Food for Clinical Cases In-Home

2020 ◽  
Author(s):  
Tessa Taylor
Keyword(s):  
United States ◽  
Autism Spectrum Disorder ◽  
Children With Autism ◽  
Autism Spectrum ◽  
Food Groups ◽  
Short Term ◽  
Home Based ◽  
Reversal Design ◽  
Regular Texture ◽  
Withdrawal Reversal

Research has shown effectiveness of a redistribution procedure for decreasing packing and increasing swallowing. Redistribution has been done using lower manipulated-texture foods on an infant gum brush in specialised United States hospitals. We extended this by using regular texture bites of food in a short-term (1-2 weeks) home-based programme in Australia, showing decreased then absent use of the procedure, and following up. Two children with autism spectrum disorder participated. We used a withdrawal/reversal design. Latency to swallow decreased. Participants increased variety to 90 and 122 regular texture foods across food groups. All goals were met including increasing independence in self-feeding. Both parents were trained. Gains maintained to 6 months and redistribution was no longer needed.

Diagnostic test accuracy for use of machine learning in diagnosis of autism spectrum disorder: A Systematic Review and Meta-Analysis (Preprint)

2019 ◽  
Author(s):  
Sun Jae Moon ◽  
Jin Seub Hwang ◽  
Rajesh Kana ◽  
John Torous ◽  
Jung Won Kim
Keyword(s):  
Machine Learning ◽  
Systematic Review ◽  
Autism Spectrum Disorder ◽  
Meta Analysis ◽  
Learning Algorithms ◽  
Structural Mri ◽  
Autism Spectrum ◽  
Machine Learning Algorithms ◽  
Spectrum Disorder ◽  
Test Accuracy

BACKGROUND Over the recent years, machine learning algorithms have been more widely and increasingly applied in biomedical fields. In particular, its application has been drawing more attention in the field of psychiatry, for instance, as diagnostic tests/tools for autism spectrum disorder. However, given its complexity and potential clinical implications, there is ongoing need for further research on its accuracy. OBJECTIVE The current study aims to summarize the evidence for the accuracy of use of machine learning algorithms in diagnosing autism spectrum disorder (ASD) through systematic review and meta-analysis. METHODS MEDLINE, Embase, CINAHL Complete (with OpenDissertations), PsyINFO and IEEE Xplore Digital Library databases were searched on November 28th, 2018. Studies, which used a machine learning algorithm partially or fully in classifying ASD from controls and provided accuracy measures, were included in our analysis. Bivariate random effects model was applied to the pooled data in meta-analysis. Subgroup analysis was used to investigate and resolve the source of heterogeneity between studies. True-positive, false-positive, false negative and true-negative values from individual studies were used to calculate the pooled sensitivity and specificity values, draw SROC curves, and obtain area under the curve (AUC) and partial AUC. RESULTS A total of 43 studies were included for the final analysis, of which meta-analysis was performed on 40 studies (53 samples with 12,128 participants). A structural MRI subgroup meta-analysis (12 samples with 1,776 participants) showed the sensitivity at 0.83 (95% CI-0.76 to 0.89), specificity at 0.84 (95% CI -0.74 to 0.91), and AUC/pAUC at 0.90/0.83. An fMRI/deep neural network (DNN) subgroup meta-analysis (five samples with 1,345 participants) showed the sensitivity at 0.69 (95% CI- 0.62 to 0.75), the specificity at 0.66 (95% CI -0.61 to 0.70), and AUC/pAUC at 0.71/0.67. CONCLUSIONS Machine learning algorithms that used structural MRI features in diagnosis of ASD were shown to have accuracy that is similar to currently used diagnostic tools.

scholarly journals “Guilt by association” is not competitive with genetic association for identifying autism risk genes

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Margot Gunning ◽  
Paul Pavlidis
Keyword(s):  
Machine Learning ◽  
Genetic Association ◽  
Gene Networks ◽  
Rare Variants ◽  
Association Studies ◽  
Genetic Disorders ◽  
Autism Spectrum ◽  
Biological Data ◽  
Disease Genes ◽  
Risk Genes

AbstractDiscovering genes involved in complex human genetic disorders is a major challenge. Many have suggested that machine learning (ML) algorithms using gene networks can be used to supplement traditional genetic association-based approaches to predict or prioritize disease genes. However, questions have been raised about the utility of ML methods for this type of task due to biases within the data, and poor real-world performance. Using autism spectrum disorder (ASD) as a test case, we sought to investigate the question: can machine learning aid in the discovery of disease genes? We collected 13 published ASD gene prioritization studies and evaluated their performance using known and novel high-confidence ASD genes. We also investigated their biases towards generic gene annotations, like number of association publications. We found that ML methods which do not incorporate genetics information have limited utility for prioritization of ASD risk genes. These studies perform at a comparable level to generic measures of likelihood for the involvement of genes in any condition, and do not out-perform genetic association studies. Future efforts to discover disease genes should be focused on developing and validating statistical models for genetic association, specifically for association between rare variants and disease, rather than developing complex machine learning methods using complex heterogeneous biological data with unknown reliability.

Sign in / Sign up

Export Citation Format

Share Document