Back to Journals » Neuropsychiatric Disease and Treatment » Volume 14

Detection of cognitive impairment using a machine-learning algorithm

Authors Youn YC, Choi SH, Shin HW, Kim KW, Jang JW, Jung JJ, Hsiung GY, Kim SY

Received 17 May 2018

Accepted for publication 31 August 2018

Published 1 November 2018 Volume 2018:14 Pages 2939—2945


Checked for plagiarism Yes

Review by Single anonymous peer review

Peer reviewer comments 3

Editor who approved publication: Dr Taro Kishi

Young Chul Youn,1 Seong Hye Choi,2 Hae-Won Shin,1 Ko Woon Kim,3 Jae-Won Jang,4 Jason J Jung,5 Ging-Yuek Robin Hsiung,6 SangYun Kim7

1Department of Neurology, College of Medicine, Chung-Ang University, Seoul, South Korea; 2Department of Neurology, Inha University College of Medicine, Incheon, South Korea; 3Department of Neurology, Chonbuk National University Medical School and Hospital, Chonbuk, South Korea; 4Department of Neurology, Kangwon National University Hospital, Chuncheon, South Korea; 5Department of Computer Engineering, Chung-Ang University, Seoul, South Korea; 6Division of Neurology, Department of Medicine, University of British Columbia, Vancouver, BC, Canada; 7Department of Neurology, Seoul National University College of Medicine and Seoul National University Bundang Hospital, Seoul, South Korea

Purpose: The Mini-Mental State Examination (MMSE) is one of the most frequently used bedside screening measures of cognition. However, the Korean Dementia Screening Questionnaire (KDSQ) is an easier and more reliable screening method. Instead, other clinical variables and raw data were used for this study without the consideration of a cutoff value. The objective of this study was to develop a machine-learning algorithm for the detection of cognitive impairment (CI) based on the KDSQ and the MMSE.
Patients and methods: The original dataset from the Clinical Research Center for Dementia of South Korea study was obtained. In total, 9,885 and 300 patients were randomly allocated to the training and test datasets, respectively. We selected up to 24 variables including sex, age, education duration, diabetes mellitus, and hypertension. We trained a machine-learning algorithm using TensorFlow based on the training dataset and then calculated its accuracy using the test dataset. The cost was calculated by conducting a logistic regression.
Results: The accuracy of the model in predicting CI based on the KDSQ only, the MMSE only, and the combination of the KDSQ and MMSE was 84.3%, 88.3%, and 86.3%, respectively. For the KDSQ, the sensitivity for detecting CI was 91.50% and the specificity for detecting normal cognition (NL) was 59.60%. The sensitivity of the MMSE was 94.35%, and the specificity was 59.62%. When combining the KDSQ and the MMSE, the sensitivity for detecting CI was 91.5% and the specificity for detecting NL was 61.5%.
Conclusion: The algorithm predicting CI based on the MMSE is superior. However, the KDSQ can be administered more easily in clinical practice and the algorithm using KDSQ is a comparable screening tool.

Keywords: dementia, mild cognitive impairment, machine learning, TensorFlow, Mini-Mental State Examination, dementia questionnaire

Corrigendum for this paper has been published.

Creative Commons License This work is published and licensed by Dove Medical Press Limited. The full terms of this license are available at and incorporate the Creative Commons Attribution - Non Commercial (unported, v3.0) License. By accessing the work you hereby accept the Terms. Non-commercial uses of the work are permitted without any further permission from Dove Medical Press Limited, provided the work is properly attributed. For permission for commercial use of this work, please see paragraphs 4.2 and 5 of our Terms.

Download Article [PDF]  View Full Text [HTML][Machine readable]