Dataset Information

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

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.

SUBMITTER: Park JH

PROVIDER: S-EPMC10623967 | biostudies-literature | 2020 Jan-Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

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

Park Jin-Hyuck JH

American journal of Alzheimer's disease and other dementias 20200101

<h4>Background</h4>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.<h4>Objective</h4>This study was to evaluate the efficacy machine learning algorithms based on the mSTS-MCI and Korean version of MoCA.<h4>Method</h4>In total, 103 healthy individuals and 74 patients with MCI were randomly divided into training and test data sets, ...[more]

PMID: 32602347

Similar Datasets

Project description:BackgroundClinical markers of cognitive decline in Parkinson's disease (PD) encompass several mental non-motor symptoms such as hallucinations, apathy, anxiety, and depression. Furthermore, freezing of gait (FOG) and specific gait alterations have been associated with cognitive dysfunction in PD. Finally, although low cerebrospinal fluid levels of amyloid-β42 have been found to predict cognitive decline in PD, hitherto PET imaging of amyloid-β (Aβ) failed to consistently demonstrate the association between Aβ plaques deposition and mild cognitive impairment in PD (PD-MCI).AimFinding significant features associated with PD-MCI through a machine learning approach.Patients and methodsPatients were assessed with an extensive clinical and neuropsychological examination. Clinical evaluation included the assessment of mental non-motor symptoms and FOG using the specific items of the MDS-UPDRS I and II. Based on the neuropsychological examination, patients were classified as subjects without and with MCI (noPD-MCI, PD-MCI). All patients were evaluated using a motion analysis system. A subgroup of PD patients also underwent amyloid PET imaging. PD-MCI and noPD-MCI subjects were compared with a univariate statistical analysis on demographic data, clinical features, gait analysis variables, and amyloid PET data. Then, machine learning analysis was performed two times: Model 1 was implemented with age, clinical variables (hallucinations/psychosis, depression, anxiety, apathy, sleep problems, FOG), and gait features, while Model 2, including only the subgroup performing PET, was implemented with PET variables combined with the top five features of the former model.ResultsSeventy-five PD patients were enrolled (33 PD-MCI and 42 noPD-MCI). PD-MCI vs. noPD-MCI resulted in older and showed worse gait patterns, mainly characterized by increased dynamic instability and reduced step length; when comparing amyloid PET data, the two groups did not differ. Regarding the machine learning analyses, evaluation metrics were satisfactory for Model 1 overcoming 80% for accuracy and specificity, whereas they were disappointing for Model 2.ConclusionsThis study demonstrates that machine learning implemented with specific clinical features and gait variables exhibits high accuracy in predicting PD-MCI, whereas amyloid PET imaging is not able to increase prediction. Additionally, our results prompt that a data mining approach on certain gait parameters might represent a reliable surrogate biomarker of PD-MCI.

Project description:IntroductionAdvances in mobile computing platforms and the rapid development of wearable devices have made possible the continuous monitoring of patients with mild cognitive impairment (MCI) and their daily activities. Such rich data can reveal more subtle changes in patients' behavioral and physiological characteristics, providing new ways to detect MCI anytime, anywhere. Therefore, we aimed to investigate the feasibility and validity of digital cognitive tests and physiological sensors applied to MCI assessment.MethodsWe collected photoplethysmography (PPG), electrodermal activity (EDA) and electroencephalogram (EEG) signals from 120 participants (61 MCI patients, 59 healthy controls) during rest and cognitive testing. The features extracted from these physiological signals involved the time domain, frequency domain, time-frequency domain and statistics. Time and score features during the cognitive test are automatically recorded by the system. In addition, selected features of all modalities were classified by tenfold cross-validation using five different classifiers.ResultsThe experimental results showed that the weighted soft voting strategy combining five classifiers achieved the highest classification accuracy (88.9%), precision (89.9%), recall (88.2%), and F1 score (89.0%). Compared to healthy controls, the MCI group typically took longer to recall, draw, and drag. Moreover, during cognitive testing, MCI patients showed lower heart rate variability, higher electrodermal activity values, and stronger brain activity in the alpha and beta bands.DiscussionIt was found that patients' classification performance improved when combining features from multiple modalities compared to using only tablet parameters or physiological features, indicating that our scheme could reveal MCI-related discriminative information. Furthermore, the best classification results on the digital span test across all tasks suggest that MCI patients may have deficits in attention and short-term memory that came to the fore earlier. Finally, integrating tablet cognitive tests and wearable sensors would provide a new direction for creating an easy-to-use and at-home self-check MCI screening tool.

Dataset Information

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

Background

Objective

Method

Result

Conclusion

Publications

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

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets