Mild cognitive impairment, dementia, and cognitive dysfunction screening using machine learning

Identification of amnestic mild cognitive impairment by structural and functional MRI using a machine-learning approach

OBJECTIVE

The importance of early treatment for mild cognitive impairment (MCI) has been extensively shown. However, classifying patients presenting with memory complaints in clinical practice as having MCI vs normal results is difficult. Herein, we assessed the feasibility of applying a machine learning approach based on structural volumes and functional connectomic profiles to classify the cognitive levels of cognitively unimpaired (CU) and amnestic MCI (aMCI) groups. We further applied the same method to distinguish aMCI patients with a single memory impairment from those with multiple memory impairments.

METHODS

Fifty patients with aMCI were enrolled and classified as having either verbal or visual-aMCI (verbal or visual memory impairment), or both aMCI (verbal and visual memory impairments) based on memory test results. In addition, 26 CU patients were enrolled in the control group. All patients underwent structural T1-weighted magnetic resonance imaging (MRI) and resting-state functional MRI. We obtained structural volumes and functional connectomic profiles from structural and functional MRI, respectively, using graph theory. A support vector machine (SVM) algorithm was employed, and k-fold cross-validation was performed to discriminate between groups.

RESULTS

The SVM classifier based on structural volumes revealed an accuracy of 88.9% at classifying the cognitive levels of patients with CU and aMCI. However, when the structural volumes and functional connectomic profiles were combined, the accuracy increased to 92.9%. In the classification of verbal or visual-aMCI (n = 22) versus both aMCI (n = 28), the SVM classifier based on structural volumes revealed a low accuracy of 36.7%. However, when the structural volumes and functional connectomic profiles were combined, the accuracy increased to 53.1%.

CONCLUSION

Structural volumes and functional connectomic profiles obtained using a machine learning approach can be used to classify cognitive levels to distinguish between aMCI and CU patients. In addition, combining the functional connectomic profiles with structural volumes results in a better classification performance than the use of structural volumes alone for identifying both "aMCI versus CU" and "verbal- or visual-aMCI versus both aMCI" patients.

Study protocol for a prediction model for mild cognitive impairment in older adults with diabetes mellitus and construction of a nurse-led screening system: a prospective observational study

INTRODUCTION

With an increasing number of older adults in China, the number of people with cognitive impairment is also increasing. To decrease the risk of dementia, it is necessary to timely detect mild cognitive impairment (MCI), which is the preliminary stage of dementia. The prevalence of MCI is relatively high among older adults with diabetes mellitus (DM); however, no effective screening strategy has been designed for this population. This study will construct a nurse-led screening system to detect MCI in community-dwelling older adults with DM in a timely manner.

METHODS AND ANALYSIS

A total of 642 participants with DM will be recruited (n=449 for development, n=193 for validation). The participants will be divided into MCI and none-MCI groups. The candidate predictors will include demographic variables, lifestyle factors, history of diseases, physical examinations, laboratory tests and neuropsychological tests. Univariate analysis, least absolute shrinkage and selection operator regression screening, and multivariate logistic regression analysis will be conducted to identify the outcome indicators. Based on the multivariate logistic regression equation, we will develop a traditional model as a comparison criterion for the machine learning models. The Hosmer-Lemeshow goodness-of-fit test and calibration curve will be used to evaluate the calibration. Sensitivity, specificity, area under the curves and clinical decision curve analysis will be performed for all models. We will report the sensitivity, specificity, area under the curve and decision curve analysis of the validation dataset. A prediction model with better performance will be adopted to form the nurse-led screening system.

ETHICS AND DISSEMINATION

This prospective study has received institutional approval of the Medical Ethics Committee of Qidong Hospital of TCM (QDSZYY-LL-20220621). Study results will be disseminated through conference presentations, Chinese Clinical Trial Registry and publication.

TRIAL REGISTRATION NUMBER

ChiCTR2200062855.

Navigating the dementia landscape: Biomarkers and emerging therapies

The field of dementia research has witnessed significant developments in our understanding of neurodegenerative disorders, with a particular focus on Alzheimer's disease (AD) and Frontotemporal Dementia (FTD). Dementia, a collection of symptoms arising from the degeneration of brain cells, presents a significant healthcare challenge, especially as its prevalence escalates with age. This abstract delves into the complexities of these disorders, the role of biomarkers in their diagnosis and monitoring, as well as emerging neurophysiological insights. In the context of AD, anti-amyloid therapy has gained prominence, aiming to reduce the accumulation of amyloid-beta (Aβ) plaques in the brain, a hallmark of the disease. Notably, Leqembi recently received full FDA approval, marking a significant breakthrough in AD treatment. Additionally, ongoing phase 3 clinical trials are investigating novel therapies, including Masitinib and NE3107, focusing on cognitive and functional improvements in AD patients. In the realm of FTD, research has unveiled distinct neuropathological features, including the involvement of proteins like TDP-43 and progranulin, providing valuable insights into the diagnosis and management of this heterogeneous condition. Biomarkers, including neurofilaments and various tau fragments, have shown promise in enhancing diagnostic accuracy. Neurophysiological techniques, such as transcranial magnetic stimulation (TMS), have contributed to our understanding of AD and FTD. TMS has uncovered unique neurophysiological signatures, highlighting impaired plasticity, hyperexcitability, and altered connectivity in AD, while FTD displays differences in neurotransmitter systems, particularly GABAergic and glutamatergic circuits. Lastly, ongoing clinical trials in anti-amyloid therapy for AD, such as Simufilam, Solanezumab, Gantenerumab, and Remternetug, offer hope for individuals affected by this devastating disease, with the potential to alter the course of cognitive decline. These advancements collectively illuminate the evolving landscape of dementia research and the pursuit of effective treatments for these challenging conditions.

Applications of Artificial Intelligence in the Neuropsychological Assessment of Dementia: A Systematic Review

In the context of advancing healthcare, the diagnosis and treatment of cognitive disorders, particularly Mild Cognitive Impairment (MCI) and Alzheimer's Disease (AD), pose significant challenges. This review explores Artificial Intelligence (AI) and Machine Learning (ML) in neuropsychological assessment for the early detection and personalized treatment of MCI and AD. The review includes 37 articles that demonstrate that AI could be an useful instrument for optimizing diagnostic procedures, predicting cognitive decline, and outperforming traditional tests. Three main categories of applications are identified: (1) combining neuropsychological assessment with clinical data, (2) optimizing existing test batteries using ML techniques, and (3) employing virtual reality and games to overcome the limitations of traditional tests. Despite advancements, the review highlights a gap in developing tools that simplify the clinician's workflow and underscores the need for explainable AI in healthcare decision making. Future studies should bridge the gap between technical performance measures and practical clinical utility to yield accurate results and facilitate clinicians' roles. The successful integration of AI/ML in predicting dementia onset could reduce global healthcare costs and benefit aging societies.

CERAD-NAB and flexible battery based neuropsychological differentiation of Alzheimer's dementia and depression using machine learning approaches

Depression (DEP) and dementia of the Alzheimer's type (DAT) represent the most common neuropsychiatric disorders in elderly patients. Accurate differential diagnosis is indispensable to ensure appropriate treatment. However, DEP can yet mimic cognitive symptoms of DAT and patients with DAT often also present with depressive symptoms, impeding correct diagnosis. Machine learning (ML) approaches could eventually improve this discrimination using neuropsychological test data, but evidence is still missing. We therefore employed Support Vector Machine (SVM), Naïve Bayes (NB), Random Forest (RF) and conventional Logistic Regression (LR) to retrospectively predict the diagnoses of 189 elderly patients (68 DEP and 121 DAT) based on either the well-established Consortium to Establish a Registry for Alzheimer's Disease neuropsychological assessment battery (CERAD-NAB) or a flexible battery approach (FLEXBAT). The best performing combination consisted of FLEXBAT and NB, correctly classifying 87.0% of patients as either DAT or DEP. However, all accuracies were similar across algorithms and test batteries (83.0% - 87.0%). Accordingly, our study is the first to show that common ML algorithms with their default parameters can accurately differentiate between patients clinically diagnosed with DAT or DEP using neuropsychological test data, but do not necessarily outperform conventional LR.

Measurement of Prevalent Versus Incident Dementia Cases in Epidemiologic Studies

Because dementia is progressive, incident cases are on average milder than prevalent cases, affecting the performance of cognitive tests and questions on functional limitations (i.e., cognition/functional limitation items) used for dementia assessment. Longitudinal studies assess incident cases, while cross-sectional studies assess prevalent cases, but differences are not typically considered when researchers select items to include in studies. We used longitudinal data from the Religious Orders Study and Memory and Aging Project (ROSMAP) (n = 3,446) collected between 1994 and 2021 to characterize differences in associations between items (cognition: 35 items; functional limitations: 14 items) and incident or prevalent dementia using multinomial regression models with generalized estimating equations, controlling for ROSMAP cohort (Religious Orders Study or Memory and Aging Project), age, sex, race, and education. The association between a given item and incident dementia was significantly weaker than the association between the same item and prevalent dementia for 46 of 49 items. However, there was variability, with larger differences for some items, including naming a pencil (prevalence odds ratio = 0.02 (95% confidence interval: 0.02, 0.03); incidence odds ratio = 0.10 (95% confidence interval: 0.06, 0.17); P for difference < 0.001). Important differences exist in the performance of cognition/functional limitation items for measurement of incident versus prevalent dementia. Differences can inform the choice of items for cross-sectional studies of prevalent cases or longitudinal studies of incident cases, leading to reduced misclassification and increased statistical power.

The application of cross-sectionally derived dementia algorithms to longitudinal data in risk factor analyses

PURPOSE

Dementia algorithms are often developed in cross-sectional samples but implemented in longitudinal studies to ascertain incident dementia. However, algorithm performance may be higher in cross-sectional settings, and this may impact estimates of risk factor associations.

METHODS

We used data from the Religious Orders Study and the Memory and Aging Project (N = 3460) to assess the performance of example algorithms in classifying prevalent dementia in cross-sectional samples versus incident dementia in longitudinal samples. We used an applied example and simulation study to characterize the impact of varying sensitivity, specificity, and unequal sensitivity or specificity between exposure groups (differential performance) on estimated hazard ratios from Cox models.

RESULTS

Using all items, algorithm sensitivity was higher for prevalent (0.796) versus incident dementia (0.719); hazard ratios had slight bias. Sensitivity differences were larger using a subset of items (0.732 vs. 0.600) and hazard ratios were 13%-19% higher across adjustment sets compared to estimates using gold-standard dementia status. Simulations indicated specificity and differential algorithmic performance between exposure groups may have large effects on hazard ratios.

CONCLUSIONS

Algorithms developed using cross-sectional data may be adequate for longitudinal settings when performance is high and non-differential. Poor specificity or differential performance between exposure groups may lead to biases.

Development of a Machine Learning Model to Discriminate Mild Cognitive Impairment Subjects from Normal Controls in Community Screening

Background: Mild cognitive impairment (MCI) is a transitional stage between normal aging and probable Alzheimer's disease. It is of great value to screen for MCI in the community. A novel machine learning (ML) model is composed of electroencephalography (EEG), eye tracking (ET), and neuropsychological assessments. This study has been proposed to identify MCI subjects from normal controls (NC). Methods: Two cohorts were used in this study. Cohort 1 as the training and validation group, includes184 MCI patients and 152 NC subjects. Cohort 2 as an independent test group, includes 44 MCI and 48 NC individuals. EEG, ET, Neuropsychological Tests Battery (NTB), and clinical variables with age, gender, educational level, MoCA-B, and ACE-R were selected for all subjects. Receiver operating characteristic (ROC) curves were adopted to evaluate the capabilities of this tool to classify MCI from NC. The clinical model, the EEG and ET model, and the neuropsychological model were compared. Results: We found that the classification accuracy of the proposed model achieved 84.5 ± 4.43% and 88.8 ± 3.59% in Cohort 1 and Cohort 2, respectively. The area under curve (AUC) of the proposed tool achieved 0.941 (0.893-0.982) in Cohort 1 and 0.966 (0.921-0.988) in Cohort 2, respectively. Conclusions: The proposed model incorporation of EEG, ET, and neuropsychological assessments yielded excellent classification performances, suggesting its potential for future application in cognitive decline prediction.

Neuropsychological test using machine learning for cognitive impairment screening

OBJECTIVES

Neuropsychological tests (NPTs) are widely used tools to evaluate cognitive functioning. The interpretation of these tests can be time-consuming and requires a specialized clinician. For this reason, we trained machine learning models that detect normal controls (NC), cognitive impairment (CI), and dementia among subjects.

PATIENTS AND METHODS

A total number of 14,927 subject datasets were collected from the formal neuropsychological assessments Seoul Neuropsychological Screening Battery (SNSB) by well-qualified neuropsychologists. The dataset included 44 NPTs of SNSB, age, education level, and diagnosis of each participant. The dataset was preprocessed and classified according to three different classes NC, CI, and dementia. We trained machine-learning with a supervised machine learning classifier algorithm support vector machine (SVM) 30 times with classification from scikit-learn (https://scikit-learn.org/stable/) to distinguish the prediction accuracy, sensitivity, and specificity of the models; NC vs. CI, NC vs. dementia, and NC vs. CI vs. dementia. Confusion matrixes were plotted using the testing dataset for each model.

RESULTS

The trained model's 30 times mean accuracies for predicting cognitive states were as follows; NC vs. CI model was 88.61 ± 1.44%, NC vs. dementia model was 97.74 ± 5.78%, and NC vs. CI vs. dementia model was 83.85 ± 4.33%. NC vs. dementia showed the highest accuracy, sensitivity, and specificity of 97.74 ± 5.78, 97.99 ± 5.78, and 96.08 ± 4.33% in predicting dementia among subjects, respectively.

CONCLUSION

Based on the results, the SVM algorithm is more appropriate in training models on an imbalanced dataset for a good prediction accuracy compared to natural network and logistic regression algorithms. The NC vs. dementia machine-learning trained model with SVM based on NPTs SNSB dataset could assist neuropsychologists in classifying the cognitive function of subjects.

Discrimination of the Cognitive Function of Community Subjects Using the Arterial Pulse Spectrum and Machine-Learning Analysis

Early identification of cognitive impairment would allow affected patients to receive care at earlier stage. Changes in the arterial stiffness have been identified as a prominent pathological feature of dementia. This study aimed to verify if applying machine-learning analysis to spectral indices of the arterial pulse waveform can be used to discriminate different cognitive conditions of community subjects. 3-min Radial arterial blood pressure waveform (BPW) signals were measured noninvasively in 123 subjects. Eight machine-learning algorithms were used to evaluate the following 4 pulse indices for 10 harmonics (total 40 BPW spectral indices): amplitude proportion and its coefficient of variation; phase angle and its standard deviation. Significant differences were noted in the spectral pulse indices between Alzheimer’s-disease patients and control subjects. Using them as training data (AUC = 70.32% by threefold cross-validation), a significant correlation (R² = 0.36) was found between the prediction probability of the test data (comprising community subjects at two sites) and the Mini-Mental-State-Examination score. This finding illustrates possible physiological connection between arterial pulse transmission and cognitive function. The present findings from pulse-wave and machine-learning analyses may be useful for discriminating cognitive condition, and hence in the development of a user-friendly, noninvasive, and rapid method for the early screening of dementia.

Random Forest Model in the Diagnosis of Dementia Patients with Normal Mini-Mental State Examination Scores

Background: Mini-Mental State Examination (MMSE) is the most widely used tool in cognitive screening. Some individuals with normal MMSE scores have extensive cognitive impairment. Systematic neuropsychological assessment should be performed in these patients. This study aimed to optimize the systematic neuropsychological test battery (NTB) by machine learning and develop new classification models for distinguishing mild cognitive impairment (MCI) and dementia among individuals with MMSE ≥ 26. Methods: 375 participants with MMSE ≥ 26 were assigned a diagnosis of cognitively unimpaired (CU) (n = 67), MCI (n = 174), or dementia (n = 134). We compared the performance of five machine learning algorithms, including logistic regression, decision tree, SVM, XGBoost, and random forest (RF), in identifying MCI and dementia. Results: RF performed best in identifying MCI and dementia. Six neuropsychological subtests with high-importance features were selected to form a simplified NTB, and the test time was cut in half. The AUC of the RF model was 0.89 for distinguishing MCI from CU, and 0.84 for distinguishing dementia from nondementia. Conclusions: This simplified cognitive assessment model can be useful for the diagnosis of MCI and dementia in patients with normal MMSE. It not only optimizes the content of cognitive evaluation, but also improves diagnosis and reduces missed diagnosis.