scholarly journals Utility of MemTrax and Machine Learning Modeling in Classification of Mild Cognitive Impairment

2020 ◽  
Vol 77 (4) ◽  
pp. 1545-1558
Author(s):  
Michael F. Bergeron ◽  
Sara Landset ◽  
Xianbo Zhou ◽  
Tao Ding ◽  
Taghi M. Khoshgoftaar ◽  
...  
Keyword(s):  
Machine Learning ◽  
Cognitive Impairment ◽  
Mild Cognitive Impairment ◽  
Performance Metrics ◽  
Early Stage ◽  
Characteristic Curve ◽  
Classification Performance ◽  
Cognitive Screening ◽  
Cross Sectional ◽  
Machine Learning Classification

Background: The widespread incidence and prevalence of Alzheimer’s disease and mild cognitive impairment (MCI) has prompted an urgent call for research to validate early detection cognitive screening and assessment. Objective: Our primary research aim was to determine if selected MemTrax performance metrics and relevant demographics and health profile characteristics can be effectively utilized in predictive models developed with machine learning to classify cognitive health (normal versus MCI), as would be indicated by the Montreal Cognitive Assessment (MoCA). Methods: We conducted a cross-sectional study on 259 neurology, memory clinic, and internal medicine adult patients recruited from two hospitals in China. Each patient was given the Chinese-language MoCA and self-administered the continuous recognition MemTrax online episodic memory test on the same day. Predictive classification models were built using machine learning with 10-fold cross validation, and model performance was measured using Area Under the Receiver Operating Characteristic Curve (AUC). Models were built using two MemTrax performance metrics (percent correct, response time), along with the eight common demographic and personal history features. Results: Comparing the learners across selected combinations of MoCA scores and thresholds, Naïve Bayes was generally the top-performing learner with an overall classification performance of 0.9093. Further, among the top three learners, MemTrax-based classification performance overall was superior using just the top-ranked four features (0.9119) compared to using all 10 common features (0.8999). Conclusion: MemTrax performance can be effectively utilized in a machine learning classification predictive model screening application for detecting early stage cognitive impairment.

scholarly journals Mild Cognitive Impairment Detection Using Machine Learning Models Trained on Data Collected from Serious Games

2021 ◽  
Vol 11 (17) ◽  
pp. 8184
Author(s):  
Christos Karapapas ◽  
Christos Goumopoulos
Keyword(s):  
Machine Learning ◽  
Cognitive Impairment ◽  
Mild Cognitive Impairment ◽  
Serious Games ◽  
Evaluation Study ◽  
Classification Performance ◽  
Optimization Techniques ◽  
Machine Learning Algorithms ◽  
Cognitive Screening ◽  
Subjective Data

Mild cognitive impairment (MCI) is an indicative precursor of Alzheimer’s disease and its early detection is critical to restrain further cognitive deterioration through preventive measures. In this context, the capacity of serious games combined with machine learning for MCI detection is examined. In particular, a custom methodology is proposed, which consists of a series of steps to train and evaluate classification models that could discriminate healthy from cognitive impaired individuals on the basis of game performance and other subjective data. Such data were collected during a pilot evaluation study of a gaming platform, called COGNIPLAT, with 10 seniors. An exploratory analysis of the data is performed to assess feature selection, model overfitting, optimization techniques and classification performance using several machine learning algorithms and standard evaluation metrics. A production level model is also trained to deal with the issue of data leakage while delivering a high detection performance (92.14% accuracy, 93.4% sensitivity and 90% specificity) based on the Gaussian Naive Bayes classifier. This preliminary study provides initial evidence that serious games combined with machine learning methods could potentially serve as a complementary or an alternative tool to the traditional cognitive screening processes.

Performance of Validated MicroRNA Biomarkers for Alzheimer’s Disease in Mild Cognitive Impairment

2020 ◽  
Vol 78 (1) ◽  
pp. 245-263
Author(s):  
Ursula S. Sandau ◽  
Jack T. Wiedrick ◽  
Sierra J. Smith ◽  
Trevor J. McFarland ◽  
Theresa A. Lusardi ◽  
...  
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Cognitive Impairment ◽  
Mild Cognitive Impairment ◽  
Early Stage ◽  
Linear Trend ◽  
Area Under The Curve ◽  
Classification Performance ◽  
T Tau ◽  
Median Expression

Background: Cerebrospinal fluid (CSF) microRNA (miRNA) biomarkers of Alzheimer’s disease (AD) have been identified, but have not been evaluated in prodromal AD, including mild cognitive impairment (MCI). Objective: To assess whether a set of validated AD miRNA biomarkers in CSF are also sensitive to early-stage pathology as exemplified by MCI diagnosis. Methods: We measured the expression of 17 miRNA biomarkers for AD in CSF samples from AD, MCI, and cognitively normal controls (NC). We then examined classification performance of the miRNAs individually and in combination. For each miRNA, we assessed median expression in each diagnostic group and classified markers as trending linearly, nonlinearly, or lacking any trend across the three groups. For trending miRNAs, we assessed multimarker classification performance alone and in combination with apolipoprotein E ɛ4 allele (APOE ɛ4) genotype and amyloid-β42 to total tau ratio (Aβ42:T-Tau). We identified predicted targets of trending miRNAs using pathway analysis. Results: Five miRNAs showed a linear trend of decreasing median expression across the ordered diagnoses (control to MCI to AD). The trending miRNAs jointly predicted AD with area under the curve (AUC) of 0.770, and MCI with AUC of 0.705. Aβ42:T-Tau alone predicted MCI with AUC of 0.758 and the AUC improved to 0.813 (p = 0.051) after adding the trending miRNAs. Multivariate correlation of the five trending miRNAs with Aβ42:T-Tau was weak. Conclusion: Selected miRNAs combined with Aβ42:T-Tau improved classification performance (relative to protein biomarkers alone) for MCI, despite a weak correlation with Aβ42:T-Tau. Together these data suggest that that these miRNAs carry novel information relevant to AD, even at the MCI stage. Preliminary target prediction analysis suggests novel roles for these biomarkers.

scholarly journals The Use Of The Hungarian Test Your Memory (Tym-Hun), Mmse And Adas-Cog Tests For Patients With Mild Cognitive Impairment (Mci) In A Hungarian Population: A Cross-Sectional Study

2020 ◽  
Author(s):  
Szabolcs Garbóczy ◽  
Éva Magócs ◽  
Gergő Szőllősi ◽  
Szilvia Harsányi ◽  
Égerházi Anikó ◽  
...  
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Cognitive Impairment ◽  
Mild Cognitive Impairment ◽  
Early Recognition ◽  
Early Stage ◽  
Disease Process ◽  
Disease Assessment ◽  
Cross Sectional ◽  
Hungarian Population

Abstract BACKGROUND Alzheimer's Disease (AD) is a growing disease process with aging. If we could recognize the disease at an early stage and increase the number of years spent in a better condition through preventive and treatment measures, we could reduce the pressure both directly on families and indirectly on society. There is a need for testing methods that are easy to perform even in general practitioner’s office, inexpensive and non-invasive, which could help early recognition of mental decline. We have selected Test Your Memory (TYM), which has proven to be reliable for detecting AD and mild cognitive impairment (MCI) in several countries. Our study was designed to test the usability of the TYM-HUN comparing with the ADAS-Cog (Alzheimer's Disease Assessment Scale-Cognitive Subscale) in MCI recognition in the Hungarian population. METHODS TYM test was translated and validated into Hungarian (TYM-HUN). The TYM-HUN test was used in conjunction with and compared with the Mini-Mental State Examination (MMSE) and the ADAS-Cog. For our study, 50 subjects were selected, 25 MCI patients and 25 healthy controls. Spearman’s rank correlation was used to analyze the correlation between the scores of MMSE and ADAS-Cog with TYM-HUN. RESULTS MCI can be distinguished from AD and normal aging using ADAS-Cog and MMSE is a useful tool to detect dementia. We established a 'cut-off' point of TYM-HUN (44/45points) where optimal sensitivity and specificity values were obtained to screen MCI. The total TYM-HUN scores significantly correlated with the MMSE scores (ρ=0.626; p<0.001) and ADAS-Cog scores (ρ=-0.723; p<0.001). CONCLUSIONS Our results showed that the Hungarian version of TYM (TYM-HUN) is an easy, fast, self-administered questionnaire with the right low threshold regarding MCI and can be used for the early diagnosis of cognitive impairment.

scholarly journals Episodix: a serious game to detect cognitive impairment in senior adults. A psychometric study

PeerJ ◽  
2018 ◽  
Vol 6 ◽  
pp. e5478 ◽  
Author(s):  
Sonia Valladares-Rodriguez ◽  
Manuel J. Fernández-Iglesias ◽  
Luis Anido-Rifón ◽  
David Facal ◽  
Roberto Pérez-Rodríguez
Keyword(s):  
Machine Learning ◽  
Cognitive Impairment ◽  
Performance Metrics ◽  
Cognitive Impairments ◽  
Senior Adults ◽  
Cohen’S Kappa ◽  
Machine Learning Classification ◽  
Cohen's Kappa ◽  
Preliminary Study ◽  
Psychometric Validity

Introduction Assessment of episodic memory is traditionally used to evaluate potential cognitive impairments in senior adults. The present article discusses the capabilities of Episodix, a game to assess the aforementioned cognitive area, as a valid tool to discriminate among mild cognitive impairment (MCI), Alzheimer’s disease (AD) and healthy individuals (HC); that is, it studies the game’s psychometric validity study to assess cognitive impairment. Materials and Methods After a preliminary study, a new pilot study, statistically significant for the Galician population, was carried out from a cross-sectional sample of senior adults as target users. A total of 64 individuals (28 HC, 16 MCI, 20 AD) completed the experiment from an initial sample of 74. Participants were administered a collection of classical pen-and-paper tests and interacted with the games developed. A total of six machine learning classification techniques were applied and four relevant performance metrics were computed to assess the classification power of the tool according to participants’ cognitive status. Results According to the classification performance metrics computed, the best classification result is obtained using the Extra Trees Classifier (F1 = 0.97 and Cohen’s kappa coefficient = 0.97). Precision and recall values are also high, above 0.9 for all cognitive groups. Moreover, according to the standard interpretation of Cohen’s kappa index, classification is almost perfect (i.e., 0.81–1.00) for the complete dataset for all algorithms. Limitations Weaknesses (e.g., accessibility, sample size or speed of stimuli) detected during the preliminary study were addressed and solved. Nevertheless, additional research is needed to improve the resolution of the game for the identification of specific cognitive impairments, as well as to achieve a complete validation of the psychometric properties of the digital game. Conclusion Promising results obtained about psychometric validity of Episodix, represent a relevant step ahead towards the introduction of serious games and machine learning in regular clinical practice for detecting MCI or AD. However, more research is needed to explore the introduction of item response theory in this game and to obtain the required normative data for clinical validity.

Validation of the Addenbrooke’s Cognitive Examination-III in Mild Cognitive Impairment in Arabic Speakers in Egypt

2020 ◽  
pp. 1-5
Author(s):  
Tarik Qassem ◽  
Mohamed S. Khater ◽  
Tamer Emara ◽  
Doha Rasheedy ◽  
Heba M. Tawfik ◽  
...  
Keyword(s):  
Cognitive Impairment ◽  
Mild Cognitive Impairment ◽  
Characteristic Curve ◽  
Screening Tools ◽  
Arabic Version ◽  
Cognitive Screening ◽  
Egyptian Arabic ◽  
Arabic Speakers ◽  
Significant Difference ◽  
Addenbrooke’S Cognitive Examination

<b><i>Background and Aims:</i></b> Mild cognitive impairment (MCI) represents an important point on the pathway to developing dementia and a target for early detection and intervention. There is a shortage of validated cognitive screening tools in Arabic to diagnose MCI. The aim of this study was to validate Addenbrooke’s Cognitive Examination-III (ACE-III) (Egyptian-Arabic version) in a sample of patients with MCI, to provide cut-off scores in Egyptian-Arabic speakers. <b><i>Methods:</i></b> A total of 24 patients with MCI and 54 controls were included in the study and were administered the Egyptian-Arabic version of the ACE-III. <b><i>Results:</i></b> There was a statistically significant difference (<i>p</i> &#x3c; 0.001) in the total ACE-III score between MCI patients (mean 75.83, standard deviation (SD) 8.1) and controls (mean 86.26, SD 6.74). There was also a statistically significant difference between MCI patients and controls in the memory, fluency, and visuospatial sub-scores of the ACE-III (<i>p</i> &#x3c; 0.05) but not in attention and language sub-scores. Using a receiver operator characteristic curve, the optimal cut-off score for diagnosing MCI on the ACE-III total score was 81, with 75% sensitivity, 82% specificity, and 80% accuracy. <b><i>Conclusions:</i></b> The results of this study provide objective validation of the Egyptian-Arabic version of the ACE-III as a screening tool for MCI, with good sensitivity, specificity, and accuracy that are comparable to other translated versions of the ACE-III in MCI.

Contributions of the Computer-Administered Neuropsychological Screen for Mild Cognitive Impairment (CANS-MCI) for the diagnosis of MCI in Brazil

2014 ◽  
Vol 26 (9) ◽  
pp. 1483-1491 ◽  
Author(s):  
Cláudia M. Memória ◽  
Mônica S. Yassuda ◽  
Eduardo Y. Nakano ◽  
Orestes V. Forlenza
Keyword(s):  
Cognitive Impairment ◽  
Mild Cognitive Impairment ◽  
Goodness Of Fit ◽  
Formal Education ◽  
Factor Model ◽  
Characteristic Curve ◽  
Reliability And Validity ◽  
Cognitive Status ◽  
Cognitive Screening ◽  
Extensive Evaluation

ABSTRACTBackground:The Computer-Administered Neuropsychological Screen for Mild Cognitive Impairment (CANS-MCI) is a computer-based cognitive screening instrument that involves automated administration and scoring and immediate analyses of test sessions. The objective of this study was to translate and culturally adapt the Brazilian Portuguese version of the CANS-MCI (CANS-MCI-BR) and to evaluate its reliability and validity for the diagnostic screening of MCI and dementia due to Alzheimer's disease.Methods:The test was administered to 97 older adults (mean age 73.41 ± 5.27 years) with at least four years of formal education (mean education 12.23 ± 4.48 years). Participants were classified into three diagnostic groups according to global cognitive status (normal controls, n = 41; MCI, n = 35; AD, n = 21) based on clinical data and formal neuropsychological assessments.Results:The results indicated high internal consistency (Cronbach's α = 0.77) in the total sample. Three-month test-retest reliability correlations were significant and robust (0.875; p < 0.001). A moderate level of concurrent validity was attained relative to the screening test for MCI (MoCA test, r = 0.76, p < 0.001). Confirmatory factor analysis supported the three-factor model of the original test, i.e., memory, language/spatial fluency, and executive function/mental control. Goodness of fit indicators were strong (Bentler Comparative Fit Index = 0.96, Root Mean Square Error of Approximation = 0.09). Receiver operating characteristic curve analyses suggested high sensitivity and specificity (81% and 73% respectively) to screen for possible MCI cases.Conclusions:The CANS-MCI-BR maintains adequate psychometric characteristics that render it suitable to identify elderly adults with probable cognitive impairment to whom a more extensive evaluation by formal neuropsychological tests may be required.

scholarly journals Dual-task tests discriminate between dementia, mild cognitive impairment, subjective cognitive impairment, and healthy controls – a cross-sectional cohort study

2020 ◽  
Vol 20 (1) ◽  
Author(s):  
Hanna B. Åhman ◽  
Ylva Cedervall ◽  
Lena Kilander ◽  
Vilmantas Giedraitis ◽  
Lars Berglund ◽  
...  
Keyword(s):  
Cognitive Impairment ◽  
Mild Cognitive Impairment ◽  
Dual Task ◽  
Early Stage ◽  
Cognitive Test ◽  
Healthy Controls ◽  
Timed Up And Go ◽  
Cross Sectional ◽  
Single Task ◽  
Subjective Cognitive Impairment

Abstract Background Discrimination between early-stage dementia and other cognitive impairment diagnoses is central to enable appropriate interventions. Previous studies indicate that dual-task testing may be useful in such differentiation. The objective of this study was to investigate whether dual-task test outcomes discriminate between groups of individuals with dementia disorder, mild cognitive impairment, subjective cognitive impairment, and healthy controls. Methods A total of 464 individuals (mean age 71 years, 47% women) were included in the study, of which 298 were patients undergoing memory assessment and 166 were cognitively healthy controls. Patients were grouped according to the diagnosis received: dementia disorder, mild cognitive impairment, or subjective cognitive impairment. Data collection included participants’ demographic characteristics. The patients’ cognitive test results and diagnoses were collected from their medical records. Healthy controls underwent the same cognitive tests as the patients. The mobility test Timed Up-and-Go (TUG single-task) and two dual-task tests including TUG (TUGdt) were carried out: TUGdt naming animals and TUGdt months backwards. The outcomes registered were: time scores for TUG single-task and both TUGdt tests, TUGdt costs (relative time difference between TUG single-task and TUGdt), number of different animals named, number of months recited in correct order, number of animals per 10 s, and number of months per 10 s. Logistic regression models examined associations between TUG outcomes pairwise between groups. Results The TUGdt outcomes “animals/10 s” and “months/10 s” discriminated significantly (p < 0.001) between individuals with an early-stage dementia diagnosis, mild cognitive impairment, subjective cognitive impairment, and healthy controls. The TUGdt outcome “animals/10 s” showed an odds ratio of 3.3 (95% confidence interval 2.0–5.4) for the groups dementia disorders vs. mild cognitive impairment. TUGdt cost outcomes, however, did not discriminate between any of the groups. Conclusions The novel TUGdt outcomes “words per time unit”, i.e. “animals/10 s” and “months/10 s”, demonstrate high levels of discrimination between all investigated groups. Thus, the TUGdt tests in the current study could be useful as complementary tools in diagnostic assessments. Future studies will be focused on the predictive value of TUGdt outcomes concerning dementia risk for individuals with mild cognitive impairment or subjective cognitive impairment.

scholarly journals The Use Of The Hungarian Test Your Memory (Tym-hun), Mmse And Adas-cog Tests For Patients With Mild Cognitive Impairment (Mci) In A Hungarian Population: A Cross-sectional Study

2020 ◽  
Author(s):  
Szabolcs Garbóczy ◽  
Éva Magócs ◽  
Gergő Szőllősi ◽  
Szilvia Harsányi ◽  
Égerházi Anikó ◽  
...  
Keyword(s):  
Cognitive Impairment ◽  
Mild Cognitive Impairment ◽  
Early Recognition ◽  
Early Stage ◽  
Rank Correlation ◽  
Disease Process ◽  
Cross Sectional Study ◽  
Disease Assessment ◽  
Cross Sectional ◽  
Spearman’S Rank Correlation

Abstract BACKGROUNDAlzheimer's Disease (AD) is a growing disease process with aging. If we could recognize the disease at an early stage and increase the number of years spent in a better condition through preventive and treatment measures, we could reduce the pressure both directly on families and indirectly on society. There is a need for testing methods that are easy to perform even in general practitioner’s office, inexpensive and non-invasive, which could help early recognition of mental decline. We have selected Test Your Memory (TYM), which has proven to be reliable for detecting AD and mild cognitive impairment (MCI) in several countries. Our study was designed to test the usability of the TYM-HUN comparing with the ADAS-Cog (Alzheimer's Disease Assessment Scale-Cognitive Subscale) in MCI recognition in the Hungarian population.METHODSTYM test was translated and validated into Hungarian (TYM-HUN). The TYM-HUN test was used in conjunction with and compared with the Mini-Mental State Examination (MMSE) and the ADAS-Cog. For our study, 50 subjects were selected, 25 MCI patients and 25 healthy controls. Spearman’s rank correlation was used to analyze the correlation between the scores of MMSE and ADAS-Cog with TYM-HUN.RESULTSMCI can be distinguished from AD and normal aging using ADAS-Cog and MMSE is a useful tool to detect dementia. We established a 'cut-off' point of TYM-HUN (44/45points) where optimal sensitivity and specificity values were obtained to screen MCI. The total TYM-HUN scores significantly correlated with the MMSE scores (ρ=0.626; p<0.001) and ADAS-Cog scores (ρ=-0.723; p<0.001).CONCLUSIONSOur results showed that the Hungarian version of TYM (TYM-HUN) is an easy, fast, self-administered questionnaire with the right low threshold regarding MCI and can be used for the early diagnosis of cognitive impairment.

scholarly journals The use of the Hungarian Test Your Memory (TYM-HUN), MMSE and ADAS-Cog tests for patients with Mild Cognitive Impairment (MCI) in a Hungarian population: a cross-sectional study

2020 ◽  
Author(s):  
Szabolcs Garbóczy ◽  
Éva Magócs ◽  
Gergő Szőllősi ◽  
Szilvia Harsányi ◽  
Égerházi Anikó ◽  
...  
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Cognitive Impairment ◽  
Mild Cognitive Impairment ◽  
Early Recognition ◽  
Early Stage ◽  
Rank Correlation ◽  
Disease Process ◽  
Disease Assessment ◽  
Cross Sectional

Abstract BACKGROUND Alzheimer's Disease (AD) is a growing disease process with aging. If we could recognize the disease at an early stage and increase the number of years spent in a better condition through preventive and treatment measures, we could reduce the pressure both directly on families and indirectly on society. There is a need for testing methods that are easy to perform even in general practitioner’s office, inexpensive and non-invasive, which could help early recognition of mental decline. We have selected Test Your Memory (TYM), which has proven to be reliable for detecting AD and mild cognitive impairment (MCI) in several countries. Our study was designed to test the usability of the TYM-HUN comparing with the ADAS-Cog (Alzheimer's Disease Assessment Scale-Cognitive Subscale) in MCI recognition in the Hungarian population.METHODS TYM test was translated and validated into Hungarian (TYM-HUN). The TYM-HUN test was used in conjunction with and compared with the Mini-Mental State Examination (MMSE) and the ADAS-Cog. For our study, 50 subjects were selected, 25 MCI patients and 25 healthy controls. Spearman’s rank correlation was used to analyze the correlation between the scores of MMSE and ADAS-Cog with TYM-HUN.RESULTS MCI can be distinguished from AD and normal aging using ADAS-Cog and MMSE is a useful tool to detect dementia. We established a 'cut-off' point of TYM-HUN (44/45points) where optimal sensitivity and specificity values were obtained to screen MCI. The total TYM-HUN scores significantly correlated with the MMSE scores (ρ=0.626; p<0.001) and ADAS-Cog scores (ρ=-0.723; p<0.001).CONCLUSIONS Our results showed that the Hungarian version of TYM (TYM-HUN) is an easy, fast, self-administered questionnaire with the right low threshold regarding MCI and can be used for the early diagnosis of cognitive impairment.

Sign in / Sign up

Export Citation Format

Share Document