Abbreviation (ISO4): Chinese Journal of Alzheimer's Disease and Related Disorders
Editor in chief: Jun WANG
Objective: To explore the applicability and efficacy of different machine learning algorithms in predicting protein biomarkers for Alzheimer's disease (AD), thereby overcoming the analytical bottlenecks of high-dimensional proteomics data and facilitating early and accurate diagnosis of AD. Methods: This paper systematically reviews the basic principles of seven common machine learning algorithms—Random Forest, Lasso Regression, Support Vector Machine, XGBoost, Decision Tree, Neural Network and Logistic Regression—and their specific applications in the prediction of AD protein biomarkers. In addition, based on the cerebrospinal fluid proteomic data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI), we systematically compared the predictive performance of these seven algorithms across different feature dimensions through multiple cross-validation. Results: The results showed that Lasso Regression exhibited the best performance in the high-dimensional feature space (with a peak area under the curve of 0.970), making it suitable for biomarker screening across the entire proteome; Support Vector Machine demonstrated the optimal stability (with the area under the curve stably ranging from 0.920 to 0.950); Neural Network performed excellently in high-dimensional data and could capture complex nonlinear relationships; XGBoost showed the fastest growth in low-dimensional features; Random Forest and Decision Tree could generate interpretable outputs; and Logistic Regression was only applicable to low-dimensional scenarios. Finally, the advantages, disadvantages and applicability of the seven methods are summarized, and current challenges and future directions are discussed. Conclusions: Lasso regression, support vector machine, and neural networks have significant advantages in screening capability, stability, and nonlinear modeling, respectively. In practice, the most appropriate algorithm should be selected based on data dimensionality and specific needs to improve the accuracy of early AD diagnosis and its potential for clinical translation.
Objective: To evaluate the correlation between autonomic dysfunction and cognitive function in patients with Parkinson's disease (PD). Methods: This study included 221 PD patients who visited the Movement Disorders Outpatient Department of Tianjin Huanhu Hospital from January 2023 to December 2024. All patients were evaluated using the Autonomic Neurological Assessment Scale (SCOPA-AUT) and were divided into two groups based on their SCOPA-AUT scores: group with high autonomic nervous symptom burden(H-ANS)(n=120) and low autonomic nervous symptom burden(L-ANS)(n=101). The differences between the H-ANS group and the L-ANS group using Pearson chi square test or non-parametric Mann Whitney U test were compared. Statistical analysis was conducted using Spearman correlation analysis and multiple linear regression. Results: Compared with patients with PD in the L-ANS group, those in the H-ANS group had a higher age (68.62±7.04 vs. 64.67±7.74, P<0.01), a longer duration of illness (5.13±5.10 vs. 3.94±3.10, P=0.043), and a later onset age (63.37±8.70 vs. 60.57±7.82, P=0.013). In the high-age group (age > 68 years) of Parkinson's disease (PD) patients, the H-ANS group had higher H&Y scores (3 vs. 2.5, P < 0.05), higher Unified Parkinson's Disease Rating Scale-III (UPDRS-III) scores (36.5 vs. 27.5, P < 0.05), and lower Montreal Cognitive Assessment (MoCA) scores (19 vs. 20, P = 0.047) compared to the L-ANS group. In the younger age group (aged ≤68 years), patients with PD in the H-ANS group had higher H&Y scores (2.5 vs. 2, P<0.05) and UPDRS-III scores (36.5 vs. 25, P<0.05) compared to those in the L-ANS group. However, there was no significant difference in cognitive scores between the two groups (P>0.05). In patients with PD in the older age group, there was a significant negative correlation between the total score of MoCA and digestive system disorders (r=-0.252, P=0.012). After controlling for confounding factors, the number of years of education showed an independent positive correlation with the total MoCA score (β=0.379, P<0.001), while the UPDRS-III score demonstrated an independent negative correlation with the total MoCA score (β=-0.319, P=0.005). However, various dimensions of autonomic nervous system function, including the digestive, urinary, cardiovascular, thermoregulatory, and pupillary regulatory systems, did not show any independent significant association with the total MoCA score (all P>0.05). Conclusion: In elderly patients with PD, autonomic dysfunction was significantly correlated with motor and cognitive functions. Further univariate analysis demonstrated that gastrointestinal dysfunction was significantly associated with cognitive decline. In younger patients with PD, the correlation between autonomic dysfunction and cognitive function is not obvious.
Objective: To investigate the efficacy of personalized interventions based on personality color theory in elderly patients with Alzheimer's disease. Methods: From June 2022 to June 2025, 60 elderly patients with Alzheimer's disease admitted to in hospital were selected and randomly assigned to a control group and an observation group, with 30 patients in each group. The control group received conventional nursing interventions, while the observation group received personalized interventions based on the theory of personality color. The cognitive function, negative emotions, sleep quality, and daily living abilities of the two groups were compared. Results: After the intervention, the MMSE score of the observation group was significantly higher than that of the control group (P<0.05); the SDS and SAS scores of the observation group were lower than those of the control group (P<0.05); the PSQI score of the observation group was lower than that of the control group (P<0.05); and the BI score of the observation group was higher than that of the control group (P<0.05). Conclusion: Personalized interventions based on the theory of personality color for elderly Alzheimer's patients can reduce negative psychological symptoms, improve sleep quality, enhance cognitive function, and improve their ability to perform daily activities.
Objective: To observe the effects of remimazolam and propofol on perioperative circulatory parameters, inflammatory markers, and short-term postoperative cognitive function in elderly patients undergoing lumbar spine surgery. Methods: A total of 84 elderly patients who underwent lumbar surgery in the Department of Orthopedics and Department of Traumatic Surgery of our hospital from April 2025 to April 2026 were enrolled as research subjects. They were divided into the propofol group and the remimazolam group by the randomnumber table method, with 42 cases in each group. Heart rate (HR) and mean arterial pressure (MAP) were monitored before anesthesia induction (T0), after anesthesia induction when BIS was <60 (T1), immediately after successful tracheal intubation (T2), and 30 min after anesthesia induction (T3). Serum levels of inflammatory factors, including interleukin-6 (IL-6), interleukin-10 (IL-10), and tumor necrosis factor-α (TNF-α), were measured before anesthesia induction and after extubation at the end of surgery. Delirium and cognitive function were compared between the two groups before surgery and 72 h after surgery. Recovery quality and adverse events were also compared between the two groups. Results: Repeated-measures analysis of variance showed that the time effect of HR was statistically significant (P<0.001), and both the between-group effect and time effect of MAP were statistically significant (P<0.05). HR at T1 was higher in the remimazolam group than in the propofol group, and MAP at T1 and T3 was higher in the remimazolam group than in the propofol group (P<0.05). Postoperative levels of IL-6, IL-10, and TNF-α were significantly higher than preoperative levels in both groups (P<0.001). Postoperative IL-6 and TNF-α levels were lower in the remimazolam group than in the propofol group (P<0.05). At 72 h after surgery, MMSE scores decreased in both groups compared with preoperative scores, while the MMSE score in the remimazolam group was higher than that in the propofol group (P<0.05). There were no significant differences in the incidence of postoperative delirium or recovery quality between the two groups (P>0.05). The total incidence of perioperative adverse events was lower in the remimazolam group than in the propofol group (21.43% vs. 45.24%, P<0.05). Conclusions: Compared with propofol, remimazolam for general anesthesia in elderly patients undergoing lumbar surgery can better maintain the stability of perioperative HR and MAP, alleviate postoperative inflammatory response, exert less impact on postoperative cognitive function, reduce the incidence of perioperative adverse events, and exhibit favorable clinical safety.
Objective: To analyze the clinical value of spindle wave parameters in sleep electroencephalography (EEG) for disease assessment in Alzheimer's disease (AD) patients and to investigate their correlation with memory levels and cognitive function. Methods: A total of 64 AD patients admitted to our hospital from April 2024 to October 2025 were enrolled as the study group, while 60 healthy individuals with normal cognitive function during the same period served as the control group. Both groups underwent sleep EEG examination along with assessments of memory levels and cognitive function. Results: The sleep spindle wave density in the study group was (0.81 ± 0.23) cycles/min, the Wechsler Memory Scale Fourth Edition (WMS-IV) score was (71.10 ± 5.89) points, and the Montreal Cognitive Assessment Scale (MoCA) score was (17.43 ± 3.20) points, all significantly lower than those in the control group (3.50 ± 0.76) cycles/min, (104.21 ± 8.73) points, and (28.36 ± 0.95) points, respectively; P <0.05). The sleep spindle wave duration in the study group was (0.65 ± 0.18) s, shorter than that in the control group (1.21 ± 0.27) s (P < 0.05). In patients with severe AD, the sleep spindle wave density, WMS-IV score, and MoCA score were all lower than those in patients with moderate or mild AD (P <0.05); similarly, patients with moderate AD exhibited lower values than those with mild AD (P <0.05). The sleep spindle wave duration in patients with severe AD was shorter than that in patients with moderate or mild AD (P <0.05), and the duration in patients with moderate AD was shorter than that in patients with mild AD (P <0.05). The sleep spindle wave density and duration in AD patients were positively correlated with WMS-IV scores and MoCA scores (P <0.05). Conclusion: The density and duration of spindle waves on sleep electroencephalography exhibit a clear positive correlation with memory levels and overall cognitive function in Alzheimer's disease (AD) patients. providing a reference basis for the objective assessment of AD severity.
Objective: To investigate the occurrence of delirium in patients with acute cerebral infarction (ACI) after endovascular intervention therapy and analyze its influencing factors. Methods: A total of 78 patients with acute cerebral infarction (ACI) who underwent endovascular intervention treatment in our hospital from January 2023 to January 2026 were selected, and their clinical data were collected to calculate the incidence of delirium. At the same time, patients were divided into delirium group and non delirium group based on whether they experienced delirium. By comparing the data of the two groups, the influencing factors that led to delirium in ACI patients after intravascular intervention therapy were analyzed. Results: Among the 78 ACI patients who underwent endovascular interventional therapy, 20 cases developed delirium after treatment, with an incidence rate of 25.64%. There were significant differences in age, hypertension, time from onset to vascular opening, cerebral infarction area, preoperative collateral circulation classification, occurrence of postoperative complications and nutritional support between the delirium group and the non-delirium group (P < 0.05). The results of the multivariate Logistic regression model analysis indicated that advanced age, history of hypertension, long interval from onset to vascular opening, large-area cerebral infarction, poor preoperative collateral circulation, postoperative complications, and inadequate nutritional support were all independent risk factors for delirium symptoms in ACI patients after endovascular interventional therapy (P < 0.05). Conclusions: ACI patients have a higher risk of delirium after intravascular intervention therapy, and there are many influencing factors that can cause delirium. Clinical interventions should be taken based on controllable factors to actively prevent delirium.
Objective: To investigate the efficacy of donepezil tablets combined with idebenone tablets in the treatment of amnestic mild cognitive impairment (aMCI) and its impact on neurotransmitter function. Methods: 60 patients with aMCI admitted to our hospital from January 2025 to December 2025 were selected and divided into two groups by random number table method. The control group (30 patients) was treated with donepezil tablets, and the observation group (30 patients) was treated with donepezil tablets combined with idebenone tablets. The efficacy, cognitive function, neurotransmitter function, oxidative stress response and adverse reactions were compared between the two groups after 12 weeks of treatment. Results: The observation group exhibited a higher overall efficacy rate compared to the control group (P<0.05). Following treatment, the levels of serotonin (5-HT), acetylcholine (Ach), and dopamine (DA) in the observation group were significantly higher than those in the control group (P<0.05). Additionally, post-treatment, the observation group scored higher on the Mini-Mental State Examination (MMSE) and Montreal Cognitive Assessment (MoCA) compared to the control group (P<0.05). Furthermore, after treatment, the observation group had lower levels of homocysteine (Hcy) and malondialdehyde (MDA) and a higher level of superoxide dismutase (SOD) compared to the control group (P<0.05). No significant differences were observed in adverse reactions between the two groups (P>0.05). Conclusions: The combined use of donepezil and idebenone in the treatment of aMCI can enhance efficacy, promote improvements in neurotransmitter function and cognitive function, reduce systemic inflammation and oxidative stress response, and offers high safety.
Objective: To improve clinical reasoning for early and accurate diagnosis in patients presenting with memory difficulties. Methods: The clinical course of a 62-year-old woman with memory concerns were reported. A structured diagnostic work-up for cognitive impairment was reviewed, and the relationship between depressive symptoms and cognitive performance was discussed in light of current literature. Results: A comprehensive history should cover multiple cognitive domains, neuropsychiatric symptoms, sleep, motor features, functional impact, medications, and family history. Neuropsychological testing suggested amnestic mild cognitive impairment (aMCI) rather than subjective cognitive decline (SCD). Brain MRI revealed no structural abnormalities. Molecular imaging findings were negative for Alzheimer’s disease (AD). Based on a comprehensive clinical history and neuropsychological assessments, the patient was considered to have depressive symptoms. Cognitive impairment is common in patients with depression, and the relationship between depression and cognitive decline is complex and bidirectional. Conclusions: Molecular imaging provides high specificity for neurodegenerative disorders such as AD. The interaction between depressive symptoms and cognitive impairment should be carefully considered during diagnostic evaluation, and longitudinal follow-up is essential.
Blood biomarkers are increasingly used in Alzheimer’s disease (AD). Their clinical use depends on appropriate cutoff definitions and consistent interpretation of results. Current cutoff strategies are mainly based on external reference standards, receiver operating characteristic (ROC) analysis, reference intervals, and population distributions. More recent approaches include ratio-based measures, multi-marker combinations, gray-zone classification, and longitudinal monitoring, particularly when biomarker values fall near the cutoff or when results are interpreted in clinically diverse populations. Biomarker levels may also be influenced by age, apolipoprotein E ε4 genotype, comorbidities, and analytical platform differences, which limit the use of a universal cutoff across different settings. Future studies should move beyond one-time classification toward task-specific interpretation and repeated measurement over time to improve clinical use in screening, diagnosis, and follow-up.
Alzheimer’s disease (AD) is a neurodegenerative disorder characterized by abnormal amyloid-β (Aβ) deposition, tau hyperphosphorylation, synaptic injury, neuroinflammation, and cognitive decline. Chronic stress may shift the stress response from short-term adaptation to long-term allostatic load and thereby promote AD pathological progression through sustained activation of the hypothalamic-pituitary-adrenal (HPA) axis, impairment of glucocorticoid (GC)-glucocorticoid receptor (GR)-mediated negative feedback, pro-inflammatory microglial activation, and activation of the NLRP3 inflammasome. In recent years, studies have shown that acupuncture may alleviate Aβ/Tau-related pathology and cognitive impairment in animal models of AD by regulating HPA-axis activity, improving GC/GR feedback function, restoring microglial polarization homeostasis, and suppressing the TLR4/NF-κB/NLRP3 inflammatory cascade. From the perspective of the chronic stress axis, this review systematically summarizes the mechanisms by which chronic stress promotes AD progression and discusses the potential pathways through which acupuncture intervenes in chronic stress-related AD, with the aim of providing a theoretical basis for mechanistic animal studies, model development, and subsequent clinical validation of acupuncture interventions for AD.
Synaptic dysfunction and loss are early core pathological events in neurodegenerative diseases. This article systematically reviews the cellular and molecular mechanisms underlying synaptic dysfunction, identifying the dysregulation of neurons, astrocytes, and microglia as the core cellular mechanism. Furthermore, it highlights the intertwined pathological networks of neuroinflammation, metabolic disorder, and protein homeostasis imbalance, which collectively drive the vicious cycle of synaptic dysfunction. Additionally, the article introduces the synaptic regeneration regulatory system centered around brain-derived neurotrophic factor and summarizes emerging therapeutic strategies such as small molecule drugs targeting multiple pathways, cell and gene therapies, non-coding RNA regulation, and non-pharmacological interventions. Furthermore, it discusses the application of cutting-edge technologies such as synaptic density PET imaging, induced pluripotent stem cells (iPSC), and brain organoids in synaptic regeneration research. In the future, the treatment of neurodegenerative diseases may shift from single-target approaches to multidimensional interventions, integrating various therapies and lifestyle adjustments to achieve a leap from delaying disease progression to functional restoration.
Alzheimer's disease (AD) is a common neurodegenerative disorder characterized pathologically by the deposition of senile plaques and neurofibrillary tangles, with biochemical alterations involving abnormal accumulation of β-amyloid (Aβ) and hyperphosphorylation of TAU protein in the brain. As an advanced molecular imaging technique, positron emission tomography-computed tomography (PET-CT) enables non-invasive, high-resolution visualization of the spatiotemporal distribution patterns of Aβ deposition. This review summarizes the current applications of amyloid PET-CT in the diagnosis and treatment of AD, including its capability for early detection of Aβ deposition, dynamic tracking of spatiotemporal Aβ changes, comparison with other diagnostic methods, correlation with Tau PET-CT findings, role in therapeutic evaluation, as well as its limitations and future prospects, aiming to provide direction for clinical management and research in AD.
ISSN 2096-5516 (Print)
Started from 2018
Published by: China Association for Alzheimer’s Disease