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

IF 2 3区心理学 Q3 PSYCHOLOGY, CLINICAL

Behavior Modification Pub Date : 2022-09-01 Epub Date: 2021-08-12 DOI:10.1177/01454455211038208

Tessa Taylor, Marc J Lanovaz

{"title":"Machine Learning to Support Visual Inspection of Data: A Clinical Application.","authors":"Tessa Taylor, Marc J Lanovaz","doi":"10.1177/01454455211038208","DOIUrl":null,"url":null,"abstract":"<p><p>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.</p>","PeriodicalId":48037,"journal":{"name":"Behavior Modification","volume":null,"pages":null},"PeriodicalIF":2.0000,"publicationDate":"2022-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Behavior Modification","FirstCategoryId":"102","ListUrlMain":"https://doi.org/10.1177/01454455211038208","RegionNum":3,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2021/8/12 0:00:00","PubModel":"Epub","JCR":"Q3","JCRName":"PSYCHOLOGY, CLINICAL","Score":null,"Total":0}

引用次数: 2

Abstract

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.

查看原文本刊更多论文

支持数据视觉检测的机器学习:临床应用。

儿科喂养项目的从业人员通常依靠单例实验设计和目视检查来做出治疗决定(例如，是否改变或保持治疗)。然而，研究人员已经表明，这种做法仍然是主观的，目前还没有就支持视觉检查结果的最佳方法达成共识。为了解决这个问题，我们提出了第一个使用机器学习来分析治疗效果的儿科喂养治疗评估应用。一名患有自闭症谱系障碍的5岁男孩参加了为期两周的家庭行为分析治疗计划。我们比较了机器学习和专家视觉分析在改进逆转设计中对儿科喂养治疗效果的相互一致性。视觉分析和机器学习模型对治疗的有效性总体上是一致的，而总体上的一致性仍然很高。总的来说，结果表明机器学习可以为儿科喂养治疗评估中实施的单例实验设计的分析提供额外的支持。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Behavior Modification PSYCHOLOGY, CLINICAL-

CiteScore

5.30

自引率

0.00%

发文量

期刊介绍： For two decades, researchers and practitioners have turned to Behavior Modification for current scholarship on applied behavior modification. Starting in 1995, in addition to keeping you informed on assessment and modification techniques relevant to psychiatric, clinical, education, and rehabilitation settings, Behavior Modification revised and expanded its focus to include treatment manuals and program descriptions. With these features you can follow the process of clinical research and see how it can be applied to your own work. And, with Behavior Modification, successful clinical and administrative experts have an outlet for sharing their solutions in the field.