The prevalence of age-related cognitive impairment, including dementia, has significantly increased with population aging. It has been shown that cognitive function is associated with gait status. Previously, researchers used statistical analysis methods instead of machine learning methods to study the gait of amnestic mild cognitive impairment (aMCI) and Alzheimer's disease (AD) .
To develop a model to identify aMCI and AD based on gait status using machine learning methods, explore gait markers differentiating between aMCI and AD, and to assess their possible values as aided tools in diagnosing aMCI and AD.
We recruited 102 cases from the Rehabilitation Hospital Affiliated to National Research Center for Rehabilitation Technical Aids, the First People's Hospital of Foshan, and Affiliated Zhongshan Hospital of Dalian University from December 2018 to December 2020, and included 98 of them according to the screening criteria, including 55 patients with aMCI, 10 patients with AD, and 33 healthy controls (HC) . The gait parameters of the participants were collected during performing single-task (free walking) , dual-task (counting backwards in sevens) and another dual-task (counting backwards from 100) using a wearable device. Random forest (RF) algorithm and gradient boosting decision tree (GBDT) algorithm were separately used to establish a model to compare the effect of two algorithms in recognizing three groups, with 10 gait parameters as predictive variables and the physical status (healthy, aMCI, AD) as response variables. Then important features were chosen using a machine learning algorithm combined with recursive feature elimination (RFE) .
No statistically significant differences were found among the three groups in terms of sex ratio, average age, height, body weight or shoe size (P>0.05) , while the differences in terms of average MMSE score and MoCA score were statistically significant (P<0.05) . In the free walking test, aMCI group and AD group had shorter average stride length and smaller average heel-to-ground angle (HtA) than HC group (P<0.05) . AD group had slower average gait speed and smaller average toe-off angle (ToA) than both HC group and aMCI group (P<0.05) . In performing the dual-task of counting backwards in sevens, compared with HC group, aMCI group and AD group had slower average gait speed and smaller average ToA and HtA (P<0.05) . AD group had longer average stance phase than HC group (P<0.05) . AD group had average smaller ToA than aMCI group (P<0.05) .In performing the dual-task of counting backwards from 100, AD group had slower average gait speed and smaller average HtA and ToA than both HC group and aMCI group (P<0.05) . Moreover, AD group had shorter average stride length than HC group (P<0.05) . The average HtA in aMCI group was smaller than that in HC group (P<0.05) . Using the GBDT-RFE method, we found important gait features in distinguishing between aMCI and AD to be the stride length, ToA and HtA, and the model using the RF algorithm performed better in identifying aMCI and AD, with an accuracy as high as 87.69%.
Stride length, ToA and HtA are important gait markers to identify aMCI and AD. These findings could help clinicians diagnose aMCI and AD in the future.
The number of dementia patients is increasing along with the aging of the population. Dementia greatly impairs health and quality of life of patients, so early prevention and identification are particularly important.
To compare the results of the brief Community Screening Interview for Dementia (CSI-D) and the Mini-Mental State Examination (MMSE) in dementia screening, and to assess the examination consistency of the two scales.
In November 2021, we collected data of a sample of 2 668 middle-aged and elderly people with complete data (including assessment results of CSI-D and MMSE, sex, age, place of residence, education level and marital status) of the CHARLS 2018. The brief CSI-D and MMSE were used to screen the risk of dementia. Pearson correlation analysis was used to analyze the correlation of the scores of the brief CSI-D with those of MMSE. The consistencies of the two scales in the screening of dementia in all cases and subgroups divided by personal characteristics were calculated, the overall consistency was assessed using Kappa statistic.
The average CSI-D score and average MMSE score for all participants were (5.84±2.26) and (24.93±3.24) , respectively. Pearson correlation analysis showed that the brief CSI-D score was positively correlated with the MMSE score (r=0.394, P<0.001) . The overall prevalence of dementia was 27.36% (730/2 668) screened by the brief CSI-D, and was 22.11% (590/2 668) by the MMSE, showing statistically significant difference (χ2=40.167, P<0.001) . The consistency of the two scales in screening dementia in all cases was 20.22%, and ranged from 12.50% to 30.43% in screening dementia in subgroups divided by personal characteristics. Kappa statistic showed that the kappa value between the two scales was 0.121 (P<0.001) , suggesting a weak level of consistency.
In general, there are differences and weak consistency in the screening results of dementia between CSI-D and MMSE in general household population. Therefore, the use of the scales should be analyzed according to the actual situation. The in-depth comparison and discussion on the screening accuracy of the two scales could be further performed in combination with the gold standard for diagnosing dementia.
Cognitive impairment prevalence is increasing as aging population grows in China, which greatly affects the quality of life of the sufferers. Currently, the screening forcognitive-linguistic impairment still relies on traditional neuropsychological scales, which are technically demanding, time-consuming, and poorly tolerant.
To explore the feasibility of the Computer-aided Language Assessment System (CLAS) in the measurement of cognitive-linguistic impairment.
Random sampling method was used to recruit 73 participants, among them 55 (75.3%) were stroke/brain injury patients〔with a baseline score of 10-20 on the Mini-Mental State Examination (MMSE) 〕hospitalized in Department of Rehabilitation Medicine, the First Hospital of Jinan University from March 2018 to March 2020, and the other 18 (24.7%) were healthy volunteers (consisting of undergraduate medicalinterns from Jinan University, family members and accompanying caregivers of the patients) . The CLAS, Montreal Cognitive Assessment Scale (MoCA) , MMSE and Aphasia Battery of Chinese (ABC) were used to evaluate the linguistic and cognition functions of the participants. The Spearman correlation was used to assess the correlation of the score of CLAS with that of MoCA and MMSE. A receiver operating characteristic curve (ROC) of CLAS was plotted to estimate its diagnostic value for cognitive-linguistic impairment, with sensitivity, specificity and accuracy being calculated as well. A satisfaction survey was conducted in 18 healthy volunteers to understand their satisfaction with the use of the CLAS.
The total CLAS score was positively correlated with that of MMSE, and MoCA (rs=0.910, 0.884, P<0.05) .Compared with MoCA (total MoCA score <26) in combination with ABC in diagnosing cognitive impairment, the CLAS had an AUC of 0.733〔95%CI (0.632, 0.834) , P<0.001〕in identifying cognitive-linguistic impairment when the optimal cut-off value was set as 85 points, and the maximum Youden index was obtained, with 1.000 sensitivity, 0.703 specificity, and 0.931 (68/73) accuracy. The average satisfaction score of 18 healthy volunteers was (4.07±0.48) , indicating an overall satisfaction level of "satisfactory".
High participant satisfaction with the CLAS was obtained in this study. And as the CLAS has proven to have good validity and diagnostic accuracy, as well as good performance in identifying cognitive-linguistic impairment, it could be applied to the screening and identification of cognitive-linguistic impairment.
Cognitive frailty is a cognitive impairment state between normal aging and dementia. Cognitive frailty is associated with higher possibility of negative clinical events than simple frailty or cognitive impairment in older people. As cognitive frailty could be reversible toa certain degree, early identification of high-risk groups and timely intervention are particularly important in reducing adverse prognoses and improving the quality of life of elderly patients in their later years.
To investigate the prevalence and influencing factors of cognitive frailty, and its relationship with two-year post-discharge mortality in hospitalized elderly patients with comorbidities.
The data were collected from part of the project "Research and Demonstration of Clinical Management and Community-based Continuing Care Models for Older People with Comorbidities", involving a cluster sample of older inpatients with comorbidity aged≥60 years recruited from Department of Gerontology, Chengdu Fifth People's Hospital from November 2015 to January 2018. Demographics, chronic disease prevalence, and comprehensive geriatric assessment results were collected. Cognitive frailty was assessed by the FRAIL scale and Mini-Mental State Examination. Binary Logistic regression was used to analyze the influencing factors of cognitive frailty. The survival status was investigated at the end of a two-year follow-up after discharge. Cox regression was used to analyze the relationship of cognitive frailty with two-year post-discharge mortality.
A total of 554 cases were included, and 15.9% (88/554) of them had cognitive frailty. Compared with non-cognitive frailty group, cognitive frailty group had older average age, lower prevalence of high school education or above, lower average family care score, higher prevalence of malnutrition, depression, dependence in activities of daily living and balance dysfunction (P<0.05) . Binary Logistic regression analysis showed that malnutrition, balance dysfunction, and family care disorder were independent factors of cognitive frailty. During the follow-up period, 456 patients (82.3%) survived, 81 (14.6%) died, and 17 (3.1%) were lost to follow-up. After controlling for confounding factors, Cox regression analysis indicated that, the risk of two-year post-discharge mortality in cognitive frailty group was 2.039〔95%CI (1.060, 3.922) 〕times higher than that of those with normal cognitive function and non-frailty, and was 5.266〔95%CI (3.159, 8.778) 〕times higher than that of those with simple cognitive frailty (P<0.05) .
Cognitive frailty is common among elderly inpatients with comorbid conditions, and it can increase the relative risk of two-year post-discharge mortality. Clinical medical workers should pay more attention to this group to identify high-risk individuals of cognitive frailty as soon as possible and give them preventive interventionsin time.
