View : 359 Download: 85

Prediction of cognitive impairment via deep learning trained with multi-center neuropsychological test data

Title
Prediction of cognitive impairment via deep learning trained with multi-center neuropsychological test data
Authors
Kang, Min JuKim, Sang YunNa, Duk L.Kim, Byeong C.Yang, Dong WonKim, Eun-JooNa, Hae RiHan, Hyun JeongLee, Jae-HongKim, Jong HunPark, Kee HyungPark, Kyung WonHan, Seol-HeuiKim, Seong YoonYoon, Soo JinYoon, BoraSeo, Sang WonMoon, So YoungYang, YoungSoonShim, Yong S.Baek, Min JaeJeong, Jee HyangChoi, Seong HyeYoun, Young Chul
Ewha Authors
정지향
SCOPUS Author ID
정지향scopus
Issue Date
2019
Journal Title
BMC MEDICAL INFORMATICS AND DECISION MAKING
ISSN
1472-6947JCR Link
Citation
BMC MEDICAL INFORMATICS AND DECISION MAKING vol. 19, no. 1
Keywords
Machine learningNeuropsychological testDementiaMild cognitive impairmentAlzheimer's disease
Publisher
BMC
Indexed
SCIE; SCOPUS WOS scopus
Document Type
Article
Abstract
Background Neuropsychological tests (NPTs) are important tools for informing diagnoses of cognitive impairment (CI). However, interpreting NPTs requires specialists and is thus time-consuming. To streamline the application of NPTs in clinical settings, we developed and evaluated the accuracy of a machine learning algorithm using multi-center NPT data. Methods Multi-center data were obtained from 14,926 formal neuropsychological assessments (Seoul Neuropsychological Screening Battery), which were classified into normal cognition (NC), mild cognitive impairment (MCI) and Alzheimer's disease dementia (ADD). We trained a machine learning model with artificial neural network algorithm using TensorFlow () to distinguish cognitive state with the 46-variable data and measured prediction accuracies from 10 randomly selected datasets. The features of the NPT were listed in order of their contribution to the outcome using Recursive Feature Elimination. Results The ten times mean accuracies of identifying CI (MCI and ADD) achieved by 96.66 +/- 0.52% of the balanced dataset and 97.23 +/- 0.32% of the clinic-based dataset, and the accuracies for predicting cognitive states (NC, MCI or ADD) were 95.49 +/- 0.53 and 96.34 +/- 1.03%. The sensitivity to the detection CI and MCI in the balanced dataset were 96.0 and 96.0%, and the specificity were 96.8 and 97.4%, respectively. The 'time orientation' and '3-word recall' score of MMSE were highly ranked features in predicting CI and cognitive state. The twelve features reduced from 46 variable of NPTs with age and education had contributed to more than 90% accuracy in predicting cognitive impairment. Conclusions The machine learning algorithm for NPTs has suggested potential use as a reference in differentiating cognitive impairment in the clinical setting.
Show the fulltext
DOI
10.1186/s12911-019-0974-x
Appears in Collections:
의과대학 > 의학과 > Journal papers
Files in This Item:
Prediction of cognitive impairment.pdf(2.07 MB) Download
Export
RIS (EndNote)
XLS (Excel)
XML


qrcode

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

BROWSE