With the wide application of deep learning technology in disease diagnosis, especially the outstanding performance of convolutional neural network (CNN) in computer vision and image processing, more and more studies have proposed to use this algorithm to achieve the classification of Alzheimer’s disease (AD), mild cognitive impairment (MCI) and normal cognition (CN). This article systematically reviews the application progress of several classic convolutional neural network models in brain image analysis and diagnosis at different stages of Alzheimer’s disease, and discusses the existing problems and gives the possible development directions in order to provide some references.
ObjectiveTo systematically review the detection rate of cognitive impairment in Chinese patients with type 2 diabetes mellitus (T2DM).MethodsPubMed, EMbase, The Cochrane Library, CBM, CNKI, WanFang Data and VIP databases were searched to collect studies on the detection rate of cognitive impairment in Chinese patients with T2DM from inception to January 20th, 2021. Two reviewers independently screened literature, extracted data and evaluated the risk of bias of included studies. Meta-analysis was then performed using Stata 12.0 software.ResultsA total of 27 studies involving 7 920 cases were included. Meta-analysis results showed that the total detection rate of cognitive impairment in Chinese patients with T2DM was 43.2% (95%CI 36.9% to 49.6%). The results of subgroup analysis showed that in T2DM patients, the detection rate of cognitive impairment in males was 42.4% (95%CI 34.4% to 50.4%), and that in females was 48.2% (95%CI 40.9% to 55.6%). The detection rate of cognitive impairment was 25.4% (95%CI 14.7% to 36.0%) in patients under the age of 60 years, and 47.0% (95%CI 30.0% to 64.0%) in patients aged 60 years or above. The detection rate of cognitive impairment among those with primary school education level or below was 67.1% (95%CI 48.9% to 85.3%). The detection rate of cognitive impairment was 37.1% (95%CI 27.3% to 46.8%) among those with education level of junior high school or above. The detection rate of cognitive impairment in patients with disease duration less than 10 years was 28.4% (95%CI 16.0% to 40.9%) and that in patients with disease duration more than 10 years was 50.6% (95%CI 33.2% to 68.0%). The detection rate of cognitive impairment in married individuals was 45.6% (95%CI 35.8% to 55.4%) and that in singles was 68.1% (95%CI 57.5% to 78.7%). The detection rate of cognitive impairment in smokers was 38.9% (95%CI 30.7% to 47.2%) and in non-smokers was 40.9% (95%CI 32.1% to 49.6%). The detection rate of cognitive impairment in drinkers was 35.6% (95%CI 27.3% to 44.0%) and that in non-drinkers was 41.8% (95%CI 32.2% to 51.4%).ConclusionsThe detection rate of cognitive impairment in Chinese patients with T2DM is high. Due to the quantity and quality of included studies, more high-quality studies are needed to verify the above conclusions.
We in the present research proposed a classification method that applied infomax independent component analysis (ICA) to respectively extract single modality features of structural magnetic resonance imaging (sMRI) and positron emission tomography (PET). And then we combined these two features by using a method of weight combination. We found that the present method was able to improve the accurate diagnosis of Alzheimer's disease (AD) and mild cognitive impairment (MCI). Compared AD to healthy controls (HC): the study achieved a classification accuracy of 93.75%, with a sensitivity of 100% and a specificity of 87.64%. Compared MCI to HC: classification accuracy was 89.35%, with a sensitivity of 81.85% and a specificity of 99.36%. The experimental results showed that the bi-modality method performed better than the individual modality in comparison to classification accuracy.
ObjectiveTo systematically review the research status of risk prediction models for cognitive impairment in patients with T2DM. MethodsThe CNKI, WanFang Data, VIP, CBM, PubMed, Embase, Web of Science, Cochrane Library databases and clinical trial registration platform were electronically searched to collect relevant literature on risk prediction models for cognitive impairment in patients with T2DM from inception to February 13th, 2025. Two researchers independently screened the literature, extracted data, and assessed the risk of bias of the included studies, and then qualitative description and meta-analysis was performed. ResultsA total of 20 studies were included, involving 25 risk prediction models. In terms of the risk of bias, 20 studies were considered as high risk. With regards to applicability, 20 studies were high applicability. The pooled area under the curve (AUC) for modeling set was 0.83 (95%CI 0.79 to 0.88) and for the validation set was 0.83 (95%CI 0.79 to 0.87). It suggested that the model had good discrimination ability. The most common predictors included age, education level, duration of diabetes and depression. ConclusionThe overall performance of the risk prediction model for cognitive impairment in patients with T2DM is good, but the quality of the model needs to be improved.
Objective To analyze the efficacy of music therapy on the rehabilitation of post-stroke cognitive impairment (PSCI) and to provide a reference for rehabilitation intervention methods for PSCI. Methods Patients hospitalized in Beijing Bo’Ai Hospital, China Rehabilitation Research Center and diagnosed with PSCI between December 2020 and July 2022 were prospectively selected. According to the random number table method, patients were divided into a music therapy group and a control group. Both groups were given conventional neurology medication, nursing care, and conventional rehabilitation. The music therapy group received additional music therapy training, and both groups received treatment for one month. The Montreal Cognitive Assessment (MoCA), National Institute of Health Stroke Scale (NIHSS), Fugl-Meyer Assessment Scale (FMA), and modified Barthel Index (MBI) were used before and after treatment to assess patients’ cognitive function, degree of neurological deficits, motor function and activities of daily live. Results A total of 48 patients were included, with 24 patients in both groups. There was no statistically significant difference in gender, age, education level, stroke type, lesion location, comorbidities, history of myocardial infarction or peripheral vascular disease, and smoking status between the two groups of patients (P>0.05). Before and after treatment, most patients in the two groups did not score in terms of language and delayed recall scores, and the difference were not statistically significant (P>0.05). There was no statistically significant difference in MoCA scores, visual space and executive function, naming, attention, calculation, abstract thinking, and orientation scores between the two groups of patients before treatment (P>0.05). After treatment, the MoCA score, visual space and executive function, naming, attention, calculation, abstract thinking, and orientation scores of the music therapy group improved compared to before treatment (P<0.05), while the MoCA score, visual space and executive function, naming, attention, and orientation scores of the control group improved compared to before treatment (P<0.05). After treatment, the improvement in MoCA scores [5.0 (3.0, 6.0) vs. 2.5 (1.0, 4.0)], attention [1.0 (0.0, 1.0) vs. 0.0 (0.0, 1.0)], and abstract thinking scores [0.0 (0.0, 1.0) vs. 0.0 (0.0, 0.0)] in the music therapy group were better than that in the control group (P<0.05). There was no statistically significant difference in NIHSS, FMA, and MBI scores between the two groups of patients before treatment (P>0.05), and both groups improved after treatment compared to before treatment (P<0.05). After treatment, there was no statistically significant difference in the improvement of NIHSS, FMA, and MBI scores between the two groups of patients (P>0.05). Conclusions Compared with conventional rehabilitation therapy, training combined with music therapy is more beneficial for improving cognitive function in PSCI patients, especially in the cognitive domains of attention and abstract thinking. However, significant advantages have not been found in improving the degree of neurological impairment, limb motor function, and daily living activities.
ObjectivesTo systematically review the current status of cognitive impairment of the elderly in China.MethodsCNKI, VIP, CBM, WanFang Data, PubMed, EMbase and The Cochrane Library databases were electronically searched to collect studies on the current status of cognitive impairment of the elderly in China from January 1st, 2000 to March 12th, 2020. Two reviewers independently screened literature, extracted data and assessed risk of bias of included studies. Then, meta-analysis was performed by using Stata 14.1 software.ResultsA total of 126 studies involving 187 115 elderly were included. The results of meta-analysis showed that the cognitive impairment rate of the elderly in China was 22.0% (95%CI 20.4% to 23.6%). Subgroup analysis showed that the cognitive impairment rate was higher in females, seniors, low education level, residing in rural area, engaging in manual labor, no spouse, living alone, monthly income less than 1 000 yuan, and suffering from chronic diseases.ConclusionsCurrent evidence shows that the cognitive impairment rate of the elderly in China is 22%, which is relatively high in females, seniors, low education level, residing in rural area, engaging in manual labor, no spouse, living alone, low-income, and suffering from chronic diseases.
Epilepsy is defined as a disorder of brain neural function, characterized by the persistent possibility of seizures, which are usually sudden, brief, and recurrent. Cognition is a process of receiving information from the external world and analyzing and processing it, such as memory, language, visual-spatial, executive, calculation, comprehension, and judgement. With the increasing awareness of health, more and more scholars have begun to pay attention to the relationship between cognitive dysfunction and epilepsy. Data shows that over 80% of epilepsy patients have lower cognitive abilities than healthy people, and over 50% of patients have significant cognitive problems, which have a negative impact on their quality of life even greater than the seizures themselves. Cognitive impairment in epilepsy patients not only hinders their own treatment progress, but also has a negative impact on their daily life, academic and job performance, which brings huge care and economic pressure to their families and a heavy economic burden to the whole society. This review aimed to assess cognitive modules and provide key information for early diagnosis and treatment of patients.
Objective To systematically review the efficacy of six cognitive interventions on cognitive function of patients with mild cognitive impairment after stroke. Methods The PubMed, EMbase, Cochrane Library, SinoMed, WanFang Data and CNKI databases were electronically searched to collect randomized controlled trials on the effects of non-drug interventions on the cognitive function of patients with mild cognitive impairment after stroke from inception to March 2023. Two reviewers independently screened the literature, extracted data, and assessed the risk of bias of the included studies. Network meta-analysis was then performed using Openbugs 3.2.3 and Stata 16.0 software. Results A total of 72 studies involving 4 962 patients were included. The results of network meta-analysis showed that the following five cognitive interventions improved the cognitive function of stroke patients with mild cognitive impairment: cognitive control intervention (SMD=−1.28, 95%CI −1.686 to −0.90, P<0.05) had the most significant effect on the improvement of cognitive function, followed by computer cognitive training (SMD=−1.02, 95%CI −1.51 to −0.53, P<0.05), virtual reality cognitive training (SMD=−1.20, 95%CI −1.78 to −0.62, P<0.05), non-invasive neural regulation (SMD=−1.09, 95%CI −1.58 to −0.60, P<0.05), and cognitive stimulation (SMD=−0.94, 95%CI −1.82 to −0.07, P<0.05). Conclusion Five cognitive interventions are effective in improving cognitive function for stroke patients with mild cognitive impairment, among which cognitive control intervention is the most effective. Due to the limited quantity and quality of the included studies, more high-quality studies are needed to verify the above conclusion.