Text classification, as an important research area of text mining, can quickly and effectively extract valuable information to address the challenges of organizing and managing large-scale text data in the era of big data. Currently, the related research on text classification tends to focus on the application in fields such as information filtering, information retrieval, public opinion monitoring, and library and information, with few studies applying text classification methods to the field of tourist attractions. In light of this, a corpus of tourist attraction description texts is constructed using web crawler technology in this paper. We propose a novel text representation method that combines Word2Vec word embeddings with TF-IDF-CRF-POS weighting, optimizing traditional TF-IDF by incorporating total relative term frequency, category discriminability, and part-of-speech information. Subsequently, the proposed algorithm respectively combines seven commonly used classifiers (DT, SVM, LR, NB, MLP, RF, and KNN), known for their good performance, to achieve multi-class text classification for six subcategories of national A-level tourist attractions. The effectiveness and superiority of this algorithm are validated by comparing the overall performance, specific category performance, and model stability against several commonly used text representation methods. The results demonstrate that the newly proposed algorithm achieves higher accuracy and F1-measure on this type of professional dataset, and even outperforms the high-performance BERT classification model currently favored by the industry. Acc, marco-F1, and mirco-F1 values are respectively 2.29%, 5.55%, and 2.90% higher. Moreover, the algorithm can identify rare categories in the imbalanced dataset and exhibit better stability across datasets of different sizes. Overall, the algorithm presented in this paper exhibits superior classification performance and robustness. In addition, the conclusions obtained by the predicted value and the true value are consistent, indicating that this algorithm is practical. The professional domain text dataset used in this paper poses higher challenges due to its complexity (uneven text length, relatively imbalanced categories), and a high degree of similarity between categories. However, this proposed algorithm can efficiently implement the classification of multiple subcategories of this type of text set, which is a beneficial exploration of the application research of complex Chinese text datasets in specific fields, and provides a useful reference for the vector expression and classification of text datasets with similar content.

In recent years, telemedicine services have significantly improved healthcare quality and access for residents. However, challenges remain, including limited awareness and reluctance to adopt such services, especially among middle-aged and older patients with chronic conditions in remote areas. This study aimed to investigate the key factors influencing the adoption of telemedicine services among middle-aged and older patients with chronic conditions in rural China. A multicentre cross-sectional study was conducted between November 2023 and February 2024 at five hospitals in western China, targeting middle-aged and older patients (aged ≥ 45 years) with chronic conditions in rural areas. Participants completed the survey in person via QuestionnaireStar, with assistance provided as needed. The questionnaire was structured based on the Health Information Technology Adoption Model (HITAM) and included constructs such as Social Influence (SI), Perceived Usefulness (PU), Perceived Ease of Use (PEU), Perceived Reliability (PR), Perceived Health Threat (PHT), Self-efficacy (SE), Attitude Toward Using (ATU), Adoption Intention (AI) and Usage Behavior (UB). Data analysis was performed using structural equation modeling (SEM) to examine the relationships between these variables and to assess their impact on patients’ intention to adopt telemedicine services. Additionally, to further explore the factors influencing telemedicine services adoption, a generalized linear model (GLM) analysis was performed, incorporating variables such as age, gender, education level, monthly income, and health status. A total of 880 middle-aged and older patients with chronic conditions in rural areas were included in this study, with an average adoption intention score for telemedicine services of 3.94 (standard deviation 1.02). SEM analysis revealed that SI, SE, PR, and PHT were peripheral variables, while PEU, PU and ATU acted as core mediating variables that positively influenced patients’ intention to adopt telemedicine services, which in turn impacted their subsequent usage behavior. SI (z = 4.767, P<0.001), PU (z = 2.894, P = 0.004), and ATU (z = 4.545, P<0.001) showed significant direct positive effects on patients’ intention to adopt telemedicine services. GLM analysis revealed that education level (β = 0.032, P < 0.001), monthly income (β = 0.009, P = 0.049), required care (β = 0.034, P = 0.007), and cancer diagnosis (β = − 0.147, P < 0.001) were significant predictors of telemedicine adoption intention. This study identified key determinants influencing telemedicine services adoption among rural middle-aged and older patients with chronic conditions. The findings offer valuable insights for telemedicine services providers to enhance service design and implementation strategies, thereby promoting greater adoption and sustained use among this target population.

The academic research on the spatial distribution of pension institutions is mostly from the perspective of constructing or improving spatial analysis methods. It is not considered that with the development of social science and technology, the facilities and services of elderly care institutions will develop in the direction of intelligence. Exploring the intelligence level and spatial distribution of Shanghai’s elderly care institutions has important practical significance for improving and optimizing the service facilities and resource allocation of Shanghai’s pension institutions. The spatial scale and cluster distribution of pension institutions in Shanghai are described by means of standard deviation ellipse, kernel density analysis, spatial autocorrelation analysis, and spatial hotspot analysis. The Gini coefficient of intelligent bed is proposed to describe the comprehensive allocation of resources of pension institutions. Additionally, correlation analysis is used to explore the spatial fairness distribution of pension institutions in Shanghai. The results show that the development of pension institutions in various districts of Shanghai is uneven; the distribution of pension institutions is concentrated in the central urban area; the intelligent facilities, service resources, and the number of beds of pension institutions in the suburbs are better than those in the central urban area. Based on the analysis results, policy suggestions are put forward, such as optimizing the allocation of bed resources in pension institutions and focusing on building a more equitable and rationally structured smart pension institution.

Multimorbidity has emerged as a significant public health issue in the context of global population aging. Predicting and managing the progression of multimorbidity in the elderly population is crucial. This study aims to develop predictive models for multimorbidity trajectories in middle-aged and elderly populations and to identify the key factors influencing the progression of multimorbidity. First, a time-series clustering method was used to construct the multimorbidity trajectories. Then, predictive models based on machine learning techniques were developed to forecast the progression of different trajectories and identify key risk factors. This study utilized data from the China Health and Retirement Longitudinal Study (CHARLS) database, including 12,198 middle-aged and elderly individuals (aged 45 and above). Four distinct multimorbidity progression patterns were identified: Stable Low-Risk Group (45.26%), Progressively Worsening Group (14.35%), Moderate Stability Group (31.90%) and Consistently Deteriorating Group (8.49%). Among the predictive models, the XGBoost model achieved the best performance, with an accuracy of 0.664 (95%CI: 0.648-0.681), a macro ROC–AUC of 0.825 (95%CI: 0.816-0.834), a micro ROC–AUC of 0.884 (95%CI: 0.876-0.892), and a log loss of 0.806 (95%CI: 0.781-0.831). Other models, including Random Forest, Support Vector Machine, Logistic Regression, and Artificial Neural Networks, showed similar accuracy and ROC–AUC values. The study identified three key factors—baseline disease counts, self-rated Activities of Daily Living (ADL), and self-rated health status—as critical predictors of multimorbidity trajectories.

Objective: To comprehensively and systematically collect the methods used in the evaluation of patients with multiple chronic diseases both domestically and internationally, summarize and analyze the purpose, characteristics and validity of their initial development, and provide reference for health managers to choose appropriate evaluation methods for multiple chronic diseases.Methods: Analysis of the literature was based on searches conducted across eight electronic databases, including PubMed, EMBASE, Web of Science Core Collection, Scopus, Cochrane Library, CNKI, Wan Fang Database, and the Chinese Biomedical Literature Database (CBM). The initial search was completed on January 8, 2024, and the most recent update was conducted on December 10, 2024, with no restriction on the date of publication. The search process adhered to the 2020 PRISMA guidelines for systematic review.Results: 54 literatures meeting the criteria were included, involving 54 evaluation methods of multiple chronic diseases. It can be divided into four categories: (1) assessment based on equal weight of disease count and disease severity; (2) based on physiological and psychological health status assessment; (3) evaluation based on drug use; (4) natural language processing evaluation system.Conclusion: Attention should be paid to the assessment of patients with multiple chronic diseases, and standardized and unified assessment methods should be developed in the future to expand the coverage of diseases and deepen the depth of assessment, so as to provide more comprehensive and accurate health management for the growing number of patients with multiple chronic diseases.Without patient or public contribution: This systematic review is primarily based on the comprehensive analysis of published literature and did not involve new data collection or direct participation of patients, hence there was no direct contribution from patients or the public.Systematic review registration: https://www.crd.york.ac.uk/prospero/, CRD42024530474.