International Journal of
Environmental Research
and Public Health
Article
Medical Health Records-Based Mild Cognitive Impairment
(MCI) Prediction for Effective Dementia Care
Soo-Jin Lim
1,2,3
, Zoonky Lee
3
, Lee-Nam Kwon
1,2
and Hong-Woo Chun
1,2,
*
Citation: Lim, S.-J.; Lee, Z.; Kwon,
L.-N.; Chun, H.-W. Medical Health
Records-Based Mild Cognitive
Impairment (MCI) Prediction for
Effective Dementia Care. Int. J.
Environ. Res. Public Health 2021, 18,
9223. https://doi.org/10.3390/
ijerph18179223
Academic Editors: Keun-Ho Ryu and
Nipon Theera-Umpon
Received: 22 July 2021
Accepted: 30 August 2021
Published: 1 September 2021
Publisher’s Note: MDPI stays neutral
with regard to jurisdictional claims in
published maps and institutional affil-
iations.
Copyright: © 2021 by the authors.
Licensee MDPI, Basel, Switzerland.
This article is an open access article
distributed under the terms and
conditions of the Creative Commons
Attribution (CC BY) license (https://
creativecommons.org/licenses/by/
4.0/).
1
Convergence Research Center for Diagnosis, Treatment and Care System of Dementia, Korea Institute of
Science and Technology, Seoul 02792, Korea; sjlim@kist.re.kr (S.-J.L.); ynkwon@kist.re.kr (L.-N.K.)
2
Future Technology Analysis Center, Korea Institute of Science and Technology Information,
Seoul 02456, Korea
3
Graduate School of Information, Yonsei University, Seoul 03722, Korea; zlee@yonsei.ac.kr
* Correspondence: hw.chun@kist.re.kr; Tel.: +82-2-958-7252
Abstract:
Dementia is a cognitive impairment that poses a global threat. Current dementia treatments
slow the progression of the disease. The timing of starting such treatment markedly affects the effec-
tiveness of the treatment. Some experts mentioned that the optimal timing for starting the currently
available treatment in order to delay progression to dementia is the mild cognitive impairment stage,
which is the prior stage of dementia. However, medical records are typically only available at a later
stage, i.e., from the early or middle stage of dementia. In order to address this limitation, this study
developed a model using national health information data from 5 years prior, to predict dementia
development 5 years in the future. The Senior Cohort Database, comprising 550,000 samples, were
used for model development. The F-measure of the model predicting dementia development after
a 5-year incubation period was 77.38%. Models for a 1- and 3-year incubation period were also
developed for comparative analysis of dementia risk factors. The three models had some risk factors
in common, but also had unique risk factors, depending on the stage. For the common risk factors,
a difference in disease severity was confirmed. These findings indicate that the diagnostic criteria
and treatment strategy for dementia should differ depending on the timing. Furthermore, since the
results of this study present new dementia risk factors that have not been reported previously, this
study may also contribute to identification of new dementia risk factors.
Keywords:
dementia early prediction; machine learning; medical records; mild cognitive impairment
prediction; senior cohort
1. Introduction
With the aging of the population, early diagnosis and timely treatment of dementia are
among the key focus areas in medicine. Early treatment of dementia can slow the disease
progression, whereas a delay in treatment leads to reduced efficacy of medication and
shortens the period during which the patient can benefit from the effect of treatment [
1
].
It has been concluded that the earliest point of diagnosis at which treatment is effective
is mild cognitive impairment (MCI), which is considered to represent the early stage of
dementia [
2
]. MCI refers to a state in which the patient experiences a decline in short-term
memory, with forgetfulness regarding recent events, but with no significant impairment
in everyday functioning [
3
]. Given that taking early preventive measures at the stage of
MCI delays the progression to dementia, researchers have increasingly emphasized the
importance of early prediction of MCI [4].
Several studies have developed techniques for the early diagnosis of dementia based
on brain magnetic resonance imaging (MRI), which has presented excellent performance,
with area under the ROC curve (AUC) values of 98% for Alzheimer’s disease and 87% for
MCI in a previous study [
5
]. Positron emission tomography (PET), the most commonly
employed neuroimaging tool for dementia diagnosis, can demonstrate neurometabolic
Int. J. Environ. Res. Public Health 2021, 18, 9223. https://doi.org/10.3390/ijerph18179223 https://www.mdpi.com/journal/ijerph
