Machine learning based identification of elderly persons with cognitive impairment using dynamic time warping

BackgroundClinical Dementia Rating (CDR) and its evaluation have been important nowadays as its prevalence in older ages after 60 years. Early identification of dementia can help the world to take preventive measures as most of them are treatable. The cellular Automata (CA) framework is a powerful tool in analyzing brain dynamics and modeling the prognosis of Alzheimer’s disease.MethodThe proposed algorithm uses the CA framework to construct features for the classifier for the classification of classes in the dataset. A subject is assigned to a CA cell grid based on its feature values as rows and the specified number of cells in each row. When a CA grid receives a feature from a subject, the feature values are distributed among the cells using a transfer function. The distribution of featured values in the CA grid from the initialized cell to the neighboring cells in the row with a diffusion rate of 20%. Hence, redistributed CA images have been obtained for all the subjects. Deep learning architecture constituted with 4 layered Conv2d has been modeled for the classification of the CA images to classify low, moderate, and severe cognitive impairment.ResultCDR from the ADNI dataset comprising 1948 subjects has been preprocessed for the six features and three classes (i.e., Low, moderate, and severe cognitive impairment) with 70% train sets and 30% test sets. A balanced dataset of 89 subjects for moderate and severe cognitive impairment has given the classification accuracy of 96%. A balanced dataset of 363 subjects for low and moderate cognitive impairment has given the classification accuracy of 95%.ConclusionA CA framework for the classification of cognitive impairment has been achieved with good accuracy. The implementation of the CA approach and its runtime performance has an advantage over the well‐known algorithms by giving a good pathway in contributing to the classification problems.

Detecting early-stage Parkinson's disease from gait data.

Objective: Research has reported associations among selected genetic susceptibility biomarkers and risk of (a) normal cognitive aging decrements, (b) established mild cognitive impairment (MCI), and (c) sporadic Alzheimer's disease (AD). In focusing on the transitional normal-to-early MCI phase, we examine associations among three theoretically relevant polymorphisms (APOE [rs429358, rs7412], BDNF [rs6265], COMT [rs4680]) and both baseline cognitive status (MCI vs. normal aging) and two-wave (four-year) longitudinal stability or change profiles. The latter included three profiles: (a) stable as normal aging, (b) stable or chronic impairment (MCI-to-MCI), and (c) emergence of impairment (normal-to-MCI).Method: Genotyped older adults (n = 237 at baseline; age range = 64–91; 62% women) from the Victoria Longitudinal Study were examined for (a) independent and interactive associations of three genetic polymorphisms with (b) two objectively classified cognitive status groups (not-impaired controls (NIC) and MCI) at (c) both baseline and across a two-wave (four-year) longitudinal interval.Results: First, logistic regression revealed that the presence of at least one APOE ε4 allele (the risk factor for AD) was linked to greater baseline risk of objective MCI. Second, multinomial logistic regression revealed that (a) the presence of an APOE ε4 allele was associated with an increased risk of 4-year MCI status stability (chronicity), and (b) the COMT homozygous risk genotype (G/G or Val/Val) was associated with an increased risk of both MCI-to-MCI stability (chronicity) and emerging NIC-to-MCI conversion.Discussion: Both chronicity and emergence of objectively classified early cognitive impairment may be genetically heterogeneous phenomena, with influences from a panel of both normal cognitive aging (COMT) and AD-related (APOE) polymorphisms.

Ecological patterns are often fundamentally chronological. However, generalization of data is necessarily accompanied by a loss of detail or resolution. Temporal data in particular contain information not only in data values but in the temporal structure, which is lost when these values are aggregated to provide point estimates. Dynamic time warping (DTW) is a time series comparison method that is capable of efficiently comparing series despite temporal offsets that confound other methods. The DTW method is both efficient and remarkably flexible, capable of efficiently matching not only time series but also any sequentially structured data set, which has made it a popular technique in machine learning, artificial intelligence, and big data analytical tasks. DTW is rarely used in ecology despite the ubiquity of temporally structured data. As technological advances have increased the richness of small‐scale ecological data, DTW may be an attractive analysis technique because it is able to utilize the additional information contained in the temporal structure of many ecological data sets. In this study, we use an example data set of high‐resolution fish movement records obtained from otolith microchemistry to compare traditional analysis techniques with DTW clustering. Our results suggest that DTW is capable of detecting subtle behavioral patterns within otolith data sets which traditional data aggregation techniques cannot. These results provide evidence that the DTW method may be useful across many of the temporal data types commonly collected in ecology, as well other sequentially ordered “pseudo time series” data such as classification of species by shape.

Mild cognitive impairment (MCI) is a transitional stage between normal aging and early Alzheimer’s disease (AD). The presence of extracellular amyloid-beta (Aβ) in Braak regions suggests a connection with cognitive dysfunction in MCI/AD. Investigating the multivariate predictive relationships between regional Aβ biomarkers and cognitive function can aid in the early detection and prevention of AD. We introduced machine learning approaches to estimate cognitive dysfunction from regional Aβ biomarkers and identify the Aβ-related dominant brain regions involved with cognitive impairment. We employed Aβ biomarkers and cognitive measurements from the same individuals to train support vector regression (SVR) and artificial neural network (ANN) models and predict cognitive performance solely based on Aβ biomarkers on the test set. To identify Aβ-related dominant brain regions involved in cognitive prediction, we built the local interpretable model-agnostic explanations (LIME) model. We found elevated Aβ in MCI compared to controls and a stronger correlation between Aβ and cognition, particularly in Braak stages III–IV and V–VII (p < 0.05) biomarkers. Both SVR and ANN, especially ANN, showed strong predictive relationships between regional Aβ biomarkers and cognitive impairment (p < 0.05). LIME integrated with ANN showed that the parahippocampal gyrus, inferior temporal gyrus, and hippocampus were the most decisive Braak regions for predicting cognitive decline. Consistent with previous findings, this new approach suggests relationships between Aβ biomarkers and cognitive impairment. The proposed analytical framework can estimate cognitive impairment from Braak staging Aβ biomarkers and delineate the dominant brain regions collectively involved in AD pathophysiology.

Indonesia's rapidly aging demographic presents significant challenges, particularly in dementia among older people in resource-limited settings, such as nursing homes. However, there are limited reports on the deterioration of cognitive function and risk factors of dementia among older people in nursing homes. Early identification of dementia is essential for timely intervention and management. This study aimed to investigate and follow up on the cognitive function and risk factors of dementia among older people living in nursing homes. An observational cohort study was conducted over 6 months (April to October 2024) involving 162 participants from government (n = 83) and private nursing homes (n = 79). Implementation of early dementia screening was carried out using the Montreal Cognitive Assessment in the Indonesian version (MoCA INA) instrument to indicate cognitive function impairment. In addition, the Self-reporting of Physical Activity Questionnaire Indonesia (SPAQ-I) was used to identify physical activity. Descriptive statistics, McNemar, Chi-square, Fisher's Exact, Independent t-test, and multivariate regression were then used to analyze data. Older individuals did not differ in terms of gender, age, education, or length of stay. However, residents of the private nursing home had significantly higher physical activity levels (t = -2.04, p = 0.040), and a greater proportion engaged in adequate activity (65.8% vs. 50.6%, χ2 = 4.23, p = 0.040). Over a six-month period, cognitive function significantly declined among residents in the government nursing home (normal: p = 0.021; mild: p = 0.012; moderate: p = 0.003), whereas no significant change was observed among residents in the private nursing home. At the endpoint, mean cognitive function scores were slightly higher in the private nursing home (20.23 ± 3.45) than in the government nursing home (19.70 ± 4.39), with a very small effect size (Cohen's d = 0.13). Multiple regression analysis revealed that older age (β = -0.396, p <0.001) and lower levels of physical activity (β = 0.163, p = 0.030) were significantly associated with lower cognitive scores. Dementia screening can enhance care planning for age-related cognitive impairment by enabling early identification and management. Early detection allows nurses to implement more effective care strategies. Additionally, higher physical activity levels were associated with better cognitive function, highlighting a modifiable factor that may help maintain cognitive health among older adults in nursing homes.

BackgroundApproximately 30% of individuals with stroke experience impending cognitive decline, often leading to dementia over the subsequent years. Despite an increased risk of dementia among individuals with stroke, there is no predictive tool to identify stroke individuals who are at higher risk of future cognitive decline. The purpose of the Come‐Drive study is to identify whether dual impairments in cognitive and motor function may provide behavioral biomarkers to predict future cognitive decline in stroke.MethodThirty‐two stroke survivors (cognitively impaired; N = 16 and cognitively normal; N = 16) participated. All participants performed (1) Cognitive tasks: A divided attention task provided mean processing time. A simple reaction time task with the unaffected upper extremity provided an index of variability in processing time. (2) Motor tasks: Overground walking to provide gait speed and gait (stride time) variability measurements. Hierarchical logistic regression analyses were performed to determine whether processing speed and/or gait performance predicted participants’ cognitive status.ResultThe cognitively impaired stroke group showed significantly increased mean processing time (p = 0.001), and increased variability in processing time (p = 0.005), compared to the cognitively normal stroke group. The cognitively impaired stroke group showed slower gait speed and amplified gait variability, but these differences failed to reach statistical significance (p &gt; 0.05). The logistic regression showed that the mean and variability of processing time significantly predicted the cognitive status in the individuals with stroke (X2 (4) = 17.29, p = 0.002). Gait speed and gait variability did not emerge as significant predictors of cognitive status in individuals with stroke. The regression model accounted for 58% of the variance in determining the cognitive status post‐stroke with 83% accuracy.ConclusionDual decline in processing speed and gait did not emerge to be better predictors of cognitive status in individuals with stroke than the decline in processing speed alone. Perhaps a more complex motor task may serve as a better predictor of cognitive decline than a simple overground walking task. Overall, unique impairments in cognitive processing speed may serve as indicators of poor cognitive status in individuals with stroke.

Artificial Intelligence (AI) is emerging fast in the care of the elderly and demented patients; valuable technologies are being developed to track cognitive health decline in the elderly. With the increased average life span of the global citizen, the demand for early detection and differential management of cognitive impairment has risen. Applications like machine learning and NLP, as well as computer vision, are being used to track cognitive ability and diagnose conditions like dementia – early-stage Alzheimer’s included. These AI-based systems use large amount of data like medical records and neuroimages or behavior of a patient, to understand things like changes in cognition that might not be otherwise detected. Also, AI can provide the development of individual programs of assistance for those patients who need it, which can increase the quality of patient’s life and decrease the load on carers. This paper seeks to understand how artificial intelligence may assist in the management of cognitive health and early identification of dementia in elderly people as well as possible care plans applicable to such persons.

Cloud computing has become indispensable for meeting the rising demand for compute-intensive applications by providing cost-effective computational and storage resources. As reliance on cloud services increases, optimizing resource allocation is more critical than ever. This study introduces CloudProphet, an innovative machine learning-based framework designed to predict virtual machine (VM) performance in cloud environments. The approach begins with Dynamic Time Warping (DTW) to classify different types of applications based on their behavioral patterns. It further employs Pearson correlation to identify runtime metrics that are highly correlated with performance, ensuring that only the most relevant features are used in prediction models. These selected metrics are incorporated into three variations of deep learning models for evaluation: (1) an LSTM model without the use of DTW or feature selection, (2) an LSTM model with both DTW classification and selected features, and (3) a GRU model leveraging both DTW and highly correlated runtime indicators. Among these, the GRU-based approach demonstrates superior performance, achieving a remarkable 99.3% accuracy in predicting VM performance. The methodology is validated using a publicly available cloud workload dataset from GitHub and is further enhanced through real-time experimentation on live datasets to ensure practical applicability. The results highlight the robustness and accuracy of the proposed GRU model in forecasting both application types and VM behavior, making it a powerful tool for improving cloud resource management. By effectively anticipating workload demands and system performance, CloudProphet aids in reducing latency, minimizing resource wastage, and enhancing overall cloud service efficiency. This study underscores the value of combining time-series alignment techniques like DTW with correlation-based metric selection and advanced deep learning models such as GRU, ultimately offering a scalable and accurate solution for proactive and intelligent cloud performance prediction.

Although mild cognitive impairment (MCI) faces significant challenges in terms of early diagnosis and intervention, machine learning (ML) shows promise in managing complex data for MCI and dementia prediction. This study assessed and compared the predictive accuracy of ML models with traditional logistic regression in identifying MCI and dementia onset using the Korean Longitudinal Study of Aging (KLoSA) dataset. The sample comprised 4,975 older adults aged 60 years or older. Identification of MCI and dementia relied on self-reported diagnoses with sociodemographic, lifestyle, and health-related variables as key covariates. The dataset was categorized into training and test sets to predict MCI and dementia, employing models such as logistic regression, light gradient-boosting machine, XGBoost, CatBoost, and Random Forest. Shapley additive explanation values were used to determine the contribution of each feature to the prediction rate. Logistic regression excelled in predicting dementia onset, whereas XGBoost performed better in predicting MCI (XGBoost AUC: 0.7271; Random Forest AUC: 0.6741). Increased assets reduced MCI risk, however, lower education, reduced activities of daily living functional ability, and pain in daily life increased MCI risk. Predictors of developing dementia were being female, older age, reduced activities of daily living functional ability, and lower education. The ML algorithms, particularly XGBoost, demonstrated potential for predicting MCI onset using KLoSA data. This study underscores the crucial role of sociodemographic factors in the early prediction and prevention of cognitive impairment. By leveraging readily available sociodemographic and health-related characteristics, more cost-effective and targeted interventions can be provided to at-risk community-dwelling older adults.

Mild cognitive impairment (MCI) has a high prevalence and is a risk factor for dementia. Furthering understanding of MCI has been identified as a public health priority. This research aimed to explore views about the causes of cognitive impairment and identify associations between cognitive impairment, dementia, and normative ageing. Semi-structured qualitative interviews were conducted with 22 participants with different stakeholder perspectives on the area of MCI in England, and analysed thematically. Our analysis focuses on two main themes: 1) causes of cognitive impairment, and 2) ageing, dementia, and dying. Most participants viewed cognitive impairment as a transitional state between normative ageing and dementia. Participants expressed their fear of cognitive impairment and dementia, and made clear links between cognitive impairment and dying. Participants also showed an awareness of the links between lifestyle factors and cognitive health. However, linkage between lifestyle and cognition was discussed only when explicitly asked, suggesting that this was not especially salient for participants when considering the causes and risk factors for cognitive impairment. The results of this study highlight key areas for future public health initiatives, such as a focus on the multitude of benefits offered by adopting a healthy diet and physical exercise in reducing risk of cognitive impairment.

Age-associated cognitive decline has become a major threat to both personal welfare and public health and can further develop into Dementia/Alzheimer's disease. Sleep is significantly correlated with cognitive function, but both cognitive impairment and sleep problems increase with normal aging. This study explored how sleep duration affects cognitive performance among older adults in China. Using data from the Chinese Longitudinal Healthy Longevity Survey (CLHLS) in 2014 and 2018, cognitive function was assessed via the Mini-Mental State Examination (MMSE), which included five domains: orientation, registration, attention or calculation, recall, and language. Logistic regression was used to examine whether the change in sleep duration was a risk factor for cognitive impairment. We also used multinomial logistic regression to study the impact of sleep duration and the changes in sleep duration on cognitive changes during the follow-up period. The empirical study showed a U-shaped relationship between sleep duration and increased risk of cognitive impairment. Short (< 6 hours) and long (> 8 hours) sleep durations were positively associated with cognitive impairment. Tests of interactions between sleep duration and sleep quality showed that short sleep durations with fair sleep quality had an increased risk of cognitive impairment. Further, the participants were divided into three groups: normal cognition (MMSE > 24), mild cognitive impairment (MCI, 18 ≤ MMSE score ≤ 24), and severe cognitive impairment (MMSE < 18). First, of the participants with normal cognition at baseline, those who sleeping > 7 h at follow-up and > 7 h at both baseline and 4-year follow-up assessments could increase the risk of cognitive impairment. Second, for individuals with MCI at baseline, those who transitioned to sleeping > 7 h at follow-up period and > 7 h at both baseline and 4-year follow-up assessments had a lower chance of reverting to normal cognition. Excessive sleep may be a major risk for cognitive impairment among older adults. Furthermore, a moderate amount of sleep could be a possible strategy to prevent cognitive impairment.

Mild cognitive impairment (MCI) is a clinical condition characterized by a decline in cognitive ability and progression of cognitive impairment. It is often considered a transitional stage between normal aging and Alzheimer's disease (AD). This study aimed to compare deep learning (DL) and traditional machine learning (ML) methods in predicting MCI using plasma proteomic biomarkers. A total of 239 adults were selected from the Alzheimer's Disease Neuroimaging Initiative (ADNI) cohort along with a pool of 146 plasma proteomic biomarkers. We evaluated seven traditional ML models (support vector machines (SVMs), logistic regression (LR), naïve Bayes (NB), random forest (RF), k-nearest neighbor (KNN), gradient boosting machine (GBM), and extreme gradient boosting (XGBoost)) and six variations of a deep neural network (DNN) model-the DL model in the H2O package. Least Absolute Shrinkage and Selection Operator (LASSO) selected 35 proteomic biomarkers from the pool. Based on grid search, the DNN model with an activation function of "Rectifier With Dropout" with 2 layers and 32 of 35 selected proteomic biomarkers revealed the best model with the highest accuracy of 0.995 and an F1 Score of 0.996, while among seven traditional ML methods, XGBoost was the best with an accuracy of 0.986 and an F1 Score of 0.985. Several biomarkers were correlated with the APOE-ε4 genotype, polygenic hazard score (PHS), and three clinical cerebrospinal fluid biomarkers (Aβ42, tTau, and pTau). Bioinformatics analysis using Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) revealed several molecular functions and pathways associated with the selected biomarkers, including cytokine-cytokine receptor interaction, cholesterol metabolism, and regulation of lipid localization. The results showed that the DL model may represent a promising tool in the prediction of MCI. These plasma proteomic biomarkers may help with early diagnosis, prognostic risk stratification, and early treatment interventions for individuals at risk for MCI.

Feasibility of assessing cognitive impairment via distributed camera network and privacy-preserving edge computing.

ObjectiveAlzheimer’s disease (AD) is a neurodegenerative disease characterized by progressive deterioration of memory and cognition. Mild cognitive impairment (MCI) has been implicated as a prodromal phase of AD. Although abnormal functional connectivity (FC) has been demonstrated in AD and MCI, the clinical differentiation of AD, MCI, and normal aging remains difficult, and the distinction between MCI and normal aging is especially problematic. We hypothesized that FC between the hippocampus and other brain structures is altered in AD and MCI, and that measurement of abnormal FC could have diagnostic utility for the classification of different AD stages.MethodsElderly adults aged 60–85 years were assigned to AD, MCI, or normal control (NC) groups based on clinical criteria. Functional magnetic resonance scanning was completed by 119 subjects. Five dimension reduction/classification methods were applied, using hippocampus-derived FC strengths as input features. Classification performance of the five dimensionality reduction methods was compared between AD, MCI, and NC groups.ResultsFCs between the hippocampus and left insula, left thalamus, cerebellum, right lingual gyrus, posterior cingulate cortex, and precuneus were significantly reduced in AD and MCI. Support vector machine learning coupled with sparse principal component analysis demonstrated the best discriminative performance, yielding classification accuracies of 82.02% (AD vs. NC), 81.33% (MCI vs. NC), and 81.08% (AD vs. MCI).ConclusionHippocampus-seed-based FCs were significantly different between AD, MCI, and NC groups. FC assessment combined with widely used machine learning methods can improve AD differential diagnosis, and may be especially useful to distinguish MCI from normal aging.