INTRODUCTION: This study aimed to examine patterns of diagnosis, cognitive and adaptive functioning, and school placement outcomes in autistic children in Singapore, and to assess earlier predictive factors of cognitive outcomes. METHOD: Retrospective data were extracted from medical records of a specialist developmental paediatrics service for children born in 2008-2011 and referred to the autism clinic or were given a diagnosis of autism. Data items included demographic data, diagnostic methods, psychological assessment results, early intervention attendance and school placement outcomes. RESULTS: A total of 2124 children (82.6% male; 66.4% Chinese, 13.4% Malay, 9.8% Indian and 10.5% Others) were diagnosed with autism from the 4 birth-year cohorts. The mean (SD) age of the first clinical diagnosis of autism was 3.56 (1.14) years, with 81.0% of children receiving a concordant initial clinical diagnosis. A total of 1811 (85.2%) had a formal diagnostic assessment using the Autism Diagnostic Observation Schedule (ADOS) at a mean (SD) age of 4.16 (1.11) years. Of 1326 with cognitive and adaptive assessment results, 16.6% had mild and 19.8% had moderate-severe cognitive impairment. Of 1483 with school placement outcomes, 45.9% went to mainstream schools, 21.8% entered SPED schools offering the national curriculum and 32.3% required customised curriculum SPED schools. Logistic regression showed that factors predicting intellectual impairment included higher ADOS scores (aOR 95% CI 1.13 [1.08-1.19] for Comm+SI total and 1.53 [1.33-1.75] for SBRI total), higher social communication level of support (based on the DSM-5 criteria) (aOR [95% CI] 2.14 [1.10-4.16] for level 2 and 14.94 [5.77-38.64] for level 3), and minority race (aOR [95% CI] 2.82 [1.52-5.20] for Malay, 5.19 [2.36-11.44] for Indian, and 4.54 [1.91-10.79] for Others). CONCLUSION These findings could guide policymakers and practitioners worldwide to strategically allocate diagnostic, intervention and educational resources, maximising developmental outcomes for autistic children across diverse settings.
Humans ; Singapore/epidemiology* ; Male ; Female ; Retrospective Studies ; Child, Preschool ; Autistic Disorder/complications* ; Child ; Early Intervention, Educational ; Cognitive Dysfunction/diagnosis* ; Cognition

This study was to examine the validity of the Japanese version of MemScreen (MemScreen-J), a touchscreen MCI screening test. 20 patients with MCI aged 65-90 years at the Juntendo Tokyo Koto Geriatric Medical Center were recruited as cases in December 2023. Non-cases were recruited from local residents in Toon City, Ehime Prefecture in February 2024 and 40 residents, without a medical history of MCI, aged 58-84 years were included in the present study. MemScreen-J test, a self-administered screening test in the form of a digital application, downloadable on a tablet, was administered to participants to assess their cognitive function. Defining the group at high risk of MCI based on a MemScreen-J test score of 28 or lower achieved the best Youden index in the study sample, with a sensitivity of 0.75 and a specificity of 0.98. MemScreen-J appeared to be a valid screening tool among persons at the prodromal stage of dementia, given reasonably high accuracy in detection of MCI. This innovative neuropsychological test could be the first step in a diagnostic approach to cognitive complaints in a community, identifying persons at the preclinical stage of dementia.
Humans ; Cognitive Dysfunction/diagnosis* ; Aged ; Aged, 80 and over ; Male ; Female ; Japan ; Neuropsychological Tests ; Middle Aged ; Mass Screening/methods* ; Sensitivity and Specificity ; Reproducibility of Results ; East Asian People

OBJECTIVE: As an age-related neurodegenerative disease, the prevalence of mild cognitive impairment (MCI) increases with age. Within the framework of traditional Chinese medicine, spleen-kidney deficiency syndrome (SKDS) is recognized as the most frequent MCI subtype. Due to the covert and gradual onset of MCI, in community settings it poses a significant challenge for patients and their families to discern between typical aging and pathological changes. There exists an urgent need to devise a preliminary diagnostic tool designed for community-residing older adults with MCI attributed to SKDS (MCI-SKDS). METHODS: This investigation enrolled 312 elderly individuals diagnosed with MCI, who were randomly distributed into training and test datasets at a 3:1 ratio. Five machine learning methods, including logistic regression (LR), decision tree (DT), naive Bayes (NB), support vector machine (SVM), and gradient boosting (GB), were used to build a diagnostic prediction model for MCI-SKDS. Accuracy, sensitivity, specificity, precision, F1 score, and area under the curve were used to evaluate model performance. Furthermore, the clinical applicability of the model was evaluated through decision curve analysis (DCA). RESULTS: The accuracy, precision, specificity and F1 score of the DT model performed best in the training set (test set), with scores of 0.904 (0.845), 0.875 (0.795), 0.973 (0.875) and 0.973 (0.875). The sensitivity of the training set (test set) of the SVM model performed best among the five models with a score of 0.865 (0.821). The area under the curve of all five models was greater than 0.9 for the training dataset and greater than 0.8 for the test dataset. The DCA of all models showed good clinical application value. The study identified ten indicators that were significant predictors of MCI-SKDS. CONCLUSION The risk prediction index derived from machine learning for the MCI-SKDS prediction model is simple and practical; the model demonstrates good predictive value and clinical applicability, and the DT model had the best performance. Please cite this article as: Ai YT, Zhou S, Wang M, Zheng TY, Hu H, Wang YC, Li YC, Wang XT, Zhou PJ. Development of a machine learning-based risk prediction model for mild cognitive impairment with spleen-kidney deficiency syndrome in the elderly. J Integr Med. 2025; 23(4): 390-397.
Humans ; Cognitive Dysfunction/diagnosis* ; Aged ; Male ; Female ; Machine Learning ; Spleen ; Aged, 80 and over ; Kidney ; Medicine, Chinese Traditional

Objective To evaluate the reliability and validity and perform cost-consequence analysis of the brief version of the Montreal cognitive assessment(MoCA)for identifying cognitive impairment in a community-based population ≥50 years of age.Methods The internal consistency and retest reliability of the brief version of the MoCA were analyzed,and the area under the curve(AUC),sensitivity,and specificity were determined to discriminate mild cognitive impairment(MCI)and dementia with the clinical dementia rating(CDR)as the diagnostic criterion.The consistency between the brief version and the full version was analyzed by the Kappa test and the Bland-Altman method,and the number of individuals entering the diagnostic assessment and the overall assessment time were estimated and compared between the two versions.Results A total of 303 individuals were included in this study,of whom 192,94,and 17 had normal cognitive function,MCI,and dementia,respectively.The Cronbach's α and re-test coefficients of the brief version of MoCA were 0.754 and 0.711(P<0.001),respectively.The brief version showed the AUC,sensitivity,and specificity of 0.889,74.5%,and 93.8% for identifying MCI,and 0.994,100%,and 93.8% for identifying dementia,respectively.When the brief version of MoCA was used to identify 94 patients with MCI in 303 individuals,107 individuals required additional diagnostic assessment,with an overall assessment time of 142.4 h,which represented decreases of 21.3% and 32.7%,respectively,compared with those of the full version.When the brief version of MoCA was used to identify 17 patients with dementia in 303 individuals,35 individuals required additional diagnostic assessment,with an overall assessment time of 70.4 h,a decrease of 29.5% in the time cost compared with the full version.Conclusions The brief version of MoCA can identify cognitively impaired individuals in a community-based middle-aged and elderly population,with diagnostic validity comparable to that of the full version but less time cost and fewer individuals needing additional diagnostic assessment to detect true-positive cases.It could be expanded for use in the community-based primary screening setting.
Humans ; Aged ; Middle Aged ; Cognitive Dysfunction/diagnosis* ; Male ; Female ; Mental Status and Dementia Tests ; Reproducibility of Results ; Dementia/diagnosis* ; Sensitivity and Specificity ; Aged, 80 and over ; Cost-Benefit Analysis

Vascular cognitive impairment (VCI) encompasses a wide spectrum of cognitive disorders, ranging from mild cognitive impairment to vascular dementia. Its diagnosis relies on thorough clinical evaluations and neuroimaging. VCI predominately arises from vascular risk factors (VRFs) and cerebrovascular disease, either independently or in conjunction with neurodegeneration. Growing evidence underscores the prevalence of VRFs, highlighting their potential for early prediction of cognitive impairment and dementia in later life. The precise mechanisms linking vascular pathologies to cognitive deficits remain elusive. Chronic cerebrovascular pathology is the most common neuropathological feature of VCI, often interacting synergistically with neurodegenerative processes. Current research efforts are focused on developing and validating reliable biomarkers to unravel the etiology of vascular brain changes in VCI. The collaborative integration of these biomarkers into clinical practice, alongside routine incorporation into neuropathological assessments, presents a promising strategy for predicting and stratifying VCI. The cornerstone of VCI prevention remains the control of VRFs, which includes multi-domain lifestyle modifications. Identifying appropriate pharmacological approaches is also of paramount importance. In this review, we synthesize recent advancements in the field of VCI, including its definition, determinants of vascular risk, pathophysiology, neuroimaging and fluid-correlated biomarkers, predictive methodologies, and current intervention strategies. Increasingly evident is the notion that more rigorous research for VCI, which arises from a complex interplay of physiological events, is still needed to pave the way for better clinical outcomes and enhanced quality of life for affected individuals.
Humans ; Cognitive Dysfunction/diagnosis* ; Dementia, Vascular/therapy* ; Risk Factors ; Biomarkers ; Cerebrovascular Disorders/diagnosis*

INTRODUCTION: This study aimed to elucidate the cognitive profile of patients with mild cognitive impairment with Lewy bodies (MCI-LB) and to compare it to that of patients with mild cognitive impairment due to Alzheimer's disease (MCI-AD). METHODS: Subjects older than 60 years with probable MCI-LB (n = 60) or MCI-AD (n = 60) were recruited. All patients were tested with Mini-Mental State Examination (MMSE) and Montreal Cognitive Assessment (MoCA) to assess their global cognitive profile. RESULTS: The MCI-AD and MCI-LB patients did not differ in total MMSE and MoCA scores. However, some sub-items in MMSE and MoCA were shown to be screening markers for differentiating MCI-LB from MCI-AD. In the visuoconstructive test, the total score and hands subitem score in the clock-drawing test were significantly lower in MCI-LB than in MCI-AD. As for the executive function, the 'animal fluency test', 'repeat digits backward test' and 'take paper by your right hand' in MMSE all showed lower scores in MCI-LB compared with MCI-AD. As for memory, 'velvet' and 'church' in MoCA and 'ball' and 'national flag' in MMSE had lower scores in MCI-AD than in MCI-LB. CONCLUSION This study presents the cognitive profile of patients with MCI-LB. In line with the literature on Dementia with Lewy bodies, our results showed lower performance on tests for visuoconstructive and executive function, whereas memory remained relatively spared in the early period.
Humans ; Cognitive Dysfunction ; Alzheimer Disease/diagnosis* ; Neuropsychological Tests ; Cognition

In order to fully explore the neural oscillatory coupling characteristics of patients with mild cognitive impairment (MCI), this paper analyzed and compared the strength of the coupling characteristics for 28 MCI patients and 21 normal subjects under six different-frequency combinations. The results showed that the difference in the global phase synchronization index of cross-frequency coupling under δ-θ rhythm combination was statistically significant in the MCI group compared with the normal control group ( P = 0.025, d = 0.398). To further validate this coupling feature, this paper proposed an optimized convolutional neural network model that incorporated a time-frequency data enhancement module and batch normalization layers to prevent overfitting while enhancing the robustness of the model. Based on this optimized model, with the phase locking value matrix of δ-θ rhythm combination as the single input feature, the diagnostic accuracy of MCI patients was (95.49 ± 4.15)%, sensitivity and specificity were (93.71 ± 7.21)% and (97.50 ± 5.34)%, respectively. The results showed that the characteristics of the phase locking value matrix under the combination of δ-θ rhythms can adequately reflect the cognitive status of MCI patients, which is helpful to assist the diagnosis of MCI.
Humans ; Electroencephalography/methods* ; Cognitive Dysfunction/diagnosis* ; Neural Networks, Computer ; Sensitivity and Specificity

Alzheimer's disease (AD) is an irreversible neurodegenerative disorder that damages patients' memory and cognitive abilities. Therefore, the diagnosis of AD holds significant importance. The interactions between regions of interest (ROIs) in the brain often involve multiple areas collaborating in a nonlinear manner. Leveraging these nonlinear higher-order interaction features to their fullest potential contributes to enhancing the accuracy of AD diagnosis. To address this, a framework combining nonlinear higher-order feature extraction and three-dimensional (3D) hypergraph neural networks is proposed for computer-assisted diagnosis of AD. First, a support vector machine regression model based on the radial basis function kernel was trained on ROI data to obtain a base estimator. Then, a recursive feature elimination algorithm based on the base estimator was applied to extract nonlinear higher-order features from functional magnetic resonance imaging (fMRI) data. These features were subsequently constructed into a hypergraph, leveraging the complex interactions captured in the data. Finally, a four-dimensional (4D) spatiotemporal hypergraph convolutional neural network model was constructed based on the fMRI data for classification. Experimental results on the Alzheimer's Disease Neuroimaging Initiative (ADNI) database demonstrated that the proposed framework outperformed the Hyper Graph Convolutional Network (HyperGCN) framework by 8% and traditional two-dimensional (2D) linear feature extraction methods by 12% in the AD/normal control (NC) classification task. In conclusion, this framework demonstrates an improvement in AD classification compared to mainstream deep learning methods, providing valuable evidence for computer-assisted diagnosis of AD.
Humans ; Alzheimer Disease/diagnostic imaging* ; Neural Networks, Computer ; Magnetic Resonance Imaging/methods* ; Neuroimaging/methods* ; Diagnosis, Computer-Assisted ; Brain ; Cognitive Dysfunction

Alzheimer's disease (AD) is a progressive and irreversible neurodegenerative disease. Neuroimaging based on magnetic resonance imaging (MRI) is one of the most intuitive and reliable methods to perform AD screening and diagnosis. Clinical head MRI detection generates multimodal image data, and to solve the problem of multimodal MRI processing and information fusion, this paper proposes a structural and functional MRI feature extraction and fusion method based on generalized convolutional neural networks (gCNN). The method includes a three-dimensional residual U-shaped network based on hybrid attention mechanism (3D HA-ResUNet) for feature representation and classification for structural MRI, and a U-shaped graph convolutional neural network (U-GCN) for node feature representation and classification of brain functional networks for functional MRI. Based on the fusion of the two types of image features, the optimal feature subset is selected based on discrete binary particle swarm optimization, and the prediction results are output by a machine learning classifier. The validation results of multimodal dataset from the AD Neuroimaging Initiative (ADNI) open-source database show that the proposed models have superior performance in their respective data domains. The gCNN framework combines the advantages of these two models and further improves the performance of the methods using single-modal MRI, improving the classification accuracy and sensitivity by 5.56% and 11.11%, respectively. In conclusion, the gCNN-based multimodal MRI classification method proposed in this paper can provide a technical basis for the auxiliary diagnosis of Alzheimer's disease.
Humans ; Alzheimer Disease/diagnostic imaging* ; Neurodegenerative Diseases ; Magnetic Resonance Imaging/methods* ; Neural Networks, Computer ; Neuroimaging/methods* ; Cognitive Dysfunction/diagnosis*

The recurrent neural network architecture improves the processing ability of time-series data. However, issues such as exploding gradients and poor feature extraction limit its application in the automatic diagnosis of mild cognitive impairment (MCI). This paper proposed a research approach for building an MCI diagnostic model using a Bayesian-optimized bidirectional long short-term memory network (BO-BiLSTM) to address this problem. The diagnostic model was based on a Bayesian algorithm and combined prior distribution and posterior probability results to optimize the BO-BiLSTM network hyperparameters. It also used multiple feature quantities that fully reflected the cognitive state of the MCI brain, such as power spectral density, fuzzy entropy, and multifractal spectrum, as the input of the diagnostic model to achieve automatic MCI diagnosis. The results showed that the feature-fused Bayesian-optimized BiLSTM network model achieved an MCI diagnostic accuracy of 98.64% and effectively completed the diagnostic assessment of MCI. In conclusion, based on this optimization, the long short-term neural network model has achieved automatic diagnostic assessment of MCI, providing a new diagnostic model for intelligent diagnosis of MCI.
Humans ; Bayes Theorem ; Neural Networks, Computer ; Algorithms ; Brain ; Cognitive Dysfunction/diagnosis*