Mild Cognitive Impairment Detection Using Association Rules Mining

Abstract

A single Mild cognitive impairment (MCI) is a transitional state between normal cognition and dementia. The typical diagnostic procedure relies on neuropsychological testing, which is insufficiently accurate and does not provide information on patients' clinical profiles. The objective of this paper is to improve the recognition of elderly primary care patients with MCI by using an approach typically applied in the market basket analysisassociation rules mining. In our case, the association rules represent various combinations of the clinical features or patterns associated with MCI. The analytical process was performed in line with the CRISP-DM, the methodology for data mining projects widely used in various research or industry domains. In the data preparation phase, we applied several approaches to improve the data quality like the k-Nearest Neighbour, correlation analysis, Chi Merge and K-Means algorithms. The analytical solution´s success was confirmed not only by the novelty and correctness of new knowledge, but also by the form of visualization that is easily understandable for domain experts. This iterative approach provides a set of rules (patterns) that meet minimum support and reliability. The extracted rules may help medical professionals recognize clinical patterns; however, the final decision depends on the expert. A medical expert has a crucial role in this process by enabling the link between the information contained in the rules and the evidence-based knowledge. It markedly contributes to the interpretability of the results.

Clusters of Physical Frailty and Cognitive Impairment and Their Associated Comorbidities in Older Primary Care Patients

“…The concept of MCI has been introduced to define a stage of cognitive decline between normal cognition and dementia that can be objectively measured but is still not severe enough to affect the activities of daily living [ 13 ]. Although MCI is associated with an increased risk for developing dementia, without additional complementary variables, this measure is not powerful enough to accurately predict dementia [ 14 , 15 ].…”

Multi-Class Text Classification on Khmer News Using Ensemble Method in Machine Learning Algorithms

“…While researchers have confirmed the better performance of the SVM, we still must implement a variety of machine learning classifiers to determine which model provides the best performance for the Khmer language dataset. In our research, there are 11 machine learning classifiers, including logistic regression (Hu et al, 2022), Complement Naive Bayes (Umar & Nur, 2022), Bernoulli Naive Bayes (Verma et al, 2020), k-nearest neighbours (Babič et al, 2020), perceptron (Sagheer et al, 2019) , support vector machines (Petridis et al, 2022), stochastic gradient descent (Bianchi et al, 2022), AdaBoost (Lee et al, 2022), decision tree (Arabameri et al, 2022) and random forest (Khan et al, 2022).…”

AI and Big Data in Healthcare: Towards a More Comprehensive Research Framework for Multimorbidity

“…The ideal platforms for exploratory studies represent all the properties of the investigated populations. In line with this approach, small studies require that participants be described with multiple features [ 71 , 72 ].…”