Objective To analyze the risk factors of cerebral arterial vessel wall calcification in ca-rotid atherosclerosis(CAS)patients by applying random forest model and logistic regression model.Methods A total of 180 CAS patients admitted to Department of Neurosurgery of Heng-shui People's Hospital from August 2021 to February 2024 were enrolled,and divided into a train-ing set(126 patients)and a testing set(54 patients)in a ratio of 7∶3.The patients in the training set were divided into the calcification group(42 cases)and the non-calcification group(84 cases)according to the results of CTA for calcification in the cerebral arterial vessel wall.General clinical data were compared between the two groups to screen the variables with statistical differences,and these variable were taken into the random forest model and logistic regression model.Risk factors for CAS patients with cerebral arterial wall calcification were analyzed,and the predictive performance of the 2 models was compared with ROC curve analysis.Results The results of ran-dom forest algorithm indicated that the top 5 risk factors affecting cerebral arterial wall calcifica-tion in CAS patients were hypertension,diabetes,LDL-C,age,and homocysteine.Multivariate lo-gistic regression analysis model revealed that age,hypertension,diabetes,LDL-C and homocys-teine were risk factors for cerebral arterial wall calcification in CAS patients(OR=1.039,95％CI:1.009-1.075;OR=1.006,95％CI:1.001-1.023;OR=2.053,95％CI:1.341-3.172;OR=1.687,95％CI:1.116-3.304;OR=1.149,95％CI:1.007-1.291).The prediction indicators of random forest model were better than those of logistic regression analysis model,but the differ-ence between training set and testing set was greater than that of logistic regression analysis mod-el.The stability of logistic regression analysis model was better,and the prediction efficiency of combined model was better than that of single model.Conclusion The random forest model has a higher predictive efficacy,and the logistic regression model is more stable,so that the combination of the two models has a higher predictive value.

Objective To investigate the iodine intake level and the prevalence of thyroid nodules in Harbin City,and to study the correlation between the concentration of urinary iodine and the prevalence of thyroid nodules.Methods In Harbin,18 communities were randomly selected and specimens were collected from fasting morning urine from 2015 to 2017.The urine iodine concentration (UIC) was detected by arsenic cerium catalytic spectrophotometry,and the thyroid nodule was examined by B ultrasound.Results A total of 2 552 residents aged (45.79 ± 12.06) years old agreed to participate in the study,including 371 males and 2 181 females.The median UIC in all participants was 159.8 μg/L,there was a significant difference in urine iodine frequency distribution among age groups (x2 =40.097,P ＜ 0.01).Furthermore,the median UIC in male was 166.6 μg/L,and in female was 156.2 μg/L.There was a significant difference in UICs between male and female (U =2.122,P ＜ 0.05).The prevalence of total thyroid nodules in all participants was 48.75％ (1 244/2 552),and the standardized rate was 40.55％.Significant difference in the detection rate of thyroid nodules was observed among age groups (x2 =114.922,P ＜ 0.01),and there was a positive and significant correlation between the detection rate of thyroid nodules and increasing age (xtrand =111.746,P ＜ 0.01).Furthermore,in male,41.24％ (153/371) had thyroid nodules,with standardized prevalence rate of 41.13％,and in female,50.02％ (1 091/2 181) had thyroid nodules,with standardized prevalence rate of 49.20％.Likewise,there was a significant difference in the detection rate of thyroid nodules between male and female(x2 =9.790,P ＜ 0.01).The detection rate of thyroid nodules in the iodine deficient population (urinary iodine was 0-＜ 100 μg/L) was 55.58％ (244/439),and the incidence of thyroid nodules in the iodine adequate or optimal population (urinary iodine was 100-＜ 200 μg/L) was 46.68％ (591/1 266).Conclusions The total iodine level of the population in Harbin City of Heilongjiang Province is at adequate level.The detection rate of thyroid nodules is high and it is increased with age.The detection rate of thyroid nodules is higher in female than male.Regular detection of urine iodine and adjusting iodine nutrition will help prevent thyroid nodules.

Cerebral small vessel disease (CSVD) is a group of cerebrovascular system disease syndromes that involve perforating arteries, capillaries, and small veins. Because of the high incidence of CSVD in the elderly and its great harm, it is particularly important to identify and diagnose the diseases as early as possible. With the development of artificial intelligence technology, intelligent algorithms such as machine learning, deep learning, and computer neural networks are increasingly being applied in the medical field. This article reviews the application of artificial intelligence technology in the evaluation of CSVD imaging markers and blood biomarkers in recent years.

Vascular cognitive impairment (VCI) refers to a cognitive impairment syndrome caused by cerebrovascular disease and its risk factors, and encompasses a spectrum from mild cognitive impairment to vascular dementia. It is the second leading cause of dementia after Alzheimer's disease (AD). The clinical manifestations of VCI often overlap with neurological diseases such as AD, and its neuropathological changes are heterogeneous, lacking specificity in clinical diagnosis and treatment, thus delaying the optimal timing of treatment. In recent years, with the continuous development of brain structure-function coupling analysis methods based on multimodal MRI, the correlation between brain structure and function has been comprehensively revealed, which is helpful for exploring the pathological and physiological mechanisms of VCI. This article reviews the research progress on the application of multimodal MRI in VCI in recent years, including the study of brain structure function-coupling based on multimodal MRI.