Machine-Learning Algorithms Based on Screening Tests for Mild Cognitive Impairment.

IF 2.7 4区医学 Q2 CLINICAL NEUROLOGY

American Journal of Alzheimers Disease and Other Dementias Pub Date : 2020-01-01 DOI:10.1177/1533317520927163

Jin-Hyuck Park

{"title":"Machine-Learning Algorithms Based on Screening Tests for Mild Cognitive Impairment.","authors":"Jin-Hyuck Park","doi":"10.1177/1533317520927163","DOIUrl":null,"url":null,"abstract":"Background: The mobile screening test system for mild cognitive impairment (mSTS-MCI) was developed and validated to address the low sensitivity and specificity of the Montreal Cognitive Assessment (MoCA) widely used clinically.Objective: This study was to evaluate the efficacy machine learning algorithms based on the mSTS-MCI and Korean version of MoCA.Method: In total, 103 healthy individuals and 74 patients with MCI were randomly divided into training and test data sets, respectively. The algorithm using TensorFlow was trained based on the training data set, and then its accuracy was calculated based on the test data set. The cost was calculated via logistic regression in this case.Result: Predictive power of the algorithms was higher than those of the original tests. In particular, the algorithm based on the mSTS-MCI showed the highest positive-predictive value.Conclusion: The machine learning algorithms predicting MCI showed the comparable findings with the conventional screening tools.","PeriodicalId":50816,"journal":{"name":"American Journal of Alzheimers Disease and Other Dementias","volume":null,"pages":null},"PeriodicalIF":2.7000,"publicationDate":"2020-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10623967/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"American Journal of Alzheimers Disease and Other Dementias","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1177/1533317520927163","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"CLINICAL NEUROLOGY","Score":null,"Total":0}

引用次数: 0

Abstract

Background: The mobile screening test system for mild cognitive impairment (mSTS-MCI) was developed and validated to address the low sensitivity and specificity of the Montreal Cognitive Assessment (MoCA) widely used clinically.

Objective: This study was to evaluate the efficacy machine learning algorithms based on the mSTS-MCI and Korean version of MoCA.

Method: In total, 103 healthy individuals and 74 patients with MCI were randomly divided into training and test data sets, respectively. The algorithm using TensorFlow was trained based on the training data set, and then its accuracy was calculated based on the test data set. The cost was calculated via logistic regression in this case.

Result: Predictive power of the algorithms was higher than those of the original tests. In particular, the algorithm based on the mSTS-MCI showed the highest positive-predictive value.

Conclusion: The machine learning algorithms predicting MCI showed the comparable findings with the conventional screening tools.

查看原文本刊更多论文

基于轻度认知障碍筛查测试的机器学习算法。

背景：开发并验证轻度认知障碍移动筛查测试系统（mSTS-MCI）是为了解决临床上广泛使用的蒙特利尔认知评估（MoCA）灵敏度和特异性较低的问题：本研究旨在评估基于 mSTS-MCI 和韩国版 MoCA 的机器学习算法的有效性：方法：将 103 名健康人和 74 名 MCI 患者分别随机分为训练数据集和测试数据集。根据训练数据集对使用 TensorFlow 的算法进行训练，然后根据测试数据集计算其准确率。在这种情况下，成本是通过逻辑回归来计算的：结果：算法的预测能力高于原始测试。尤其是基于 mSTS-MCI 的算法显示出最高的正预测值：结论：预测 MCI 的机器学习算法显示出与传统筛查工具相当的结果。

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

American Journal of Alzheimers Disease and Other Dementias GERIATRICS & GERONTOLOGY-CLINICAL NEUROLOGY

CiteScore

5.40

自引率

0.00%

发文量

审稿时长

6-12 weeks

期刊介绍： American Journal of Alzheimer''s Disease and other Dementias® (AJADD) is for professionals on the frontlines of Alzheimer''s care, dementia, and clinical depression--especially physicians, nurses, psychiatrists, administrators, and other healthcare specialists who manage patients with dementias and their families. This journal is a member of the Committee on Publication Ethics (COPE).