With the deepening of the reform of the medical and health system and the continuous optimization of the medical order,it is especially important to organize the development of admission and discharge standards and improve the service of preparing patients for discharge.In recent years,the research and application of machine learning technology in the medical field has been intensifying,and it has unique advantages in processing data and risk prediction research.Therefore,this paper reviews the development process,types of machine leaming,the content and effects of its application in patient discharge preparation services,and the current problems,in order to provide references for healthcare professionals to implement the best clinical decisions and further improve the patient discharge preparation service model.

Heart failure is one of the major cardiovascular diseases threatening human health, and its development to the end stage seriously affects the physical and mental health and quality of life of patients. Hospice care can improve the quality of life of patients at the end of the disease, relieve the burden of symptoms of patients, and reduce the readmission rate of patients. This paper reviews the assessment tools of hospice care for patients with end-stage heart failure, specifically introduces the content, reliability, validity, advantages and disadvantages of the assessment tools, and summarizes the existing hospice care measures, with a view to providing reference for clinical medical and nursing staff to select appropriate assessment tools and build a hospice care model suitable for patients with end-stage heart failure in China.

Objective:To conduct a systematic review of cardiovascular disease risk perception scale for community residents, so as to provide a basis for clinical medical personnel to choose high-quality assessment tools.Methods:PubMed, Embase, CINAHL, Web of Science, China Biology Medicine disc, CNKI, Wanfang Data and VIP were searched for studies on cardiovascular disease risk perception scales for community residents from the establishment of the databases to December 10, 2022. Based on the Consensus-based Standards for the Selection of Health Measurement Instruments (COSMIN) and the modified version of the Grading of Recommendations Assessment, Development and Evaluation (GRADE) , two researchers independently evaluated the methodological and measurement properties of the included scales, scoring evidence and forming recommendations.Results:A total of 9 literatures were included, involving 5 scales.None of the scales were assessed for measurement error, cross-cultural validity and responsiveness. The recommendation strength of four scales was class B, and one was class C.Conclusions:There is no recommended scale at present. It is suggested that future studies should take COSMIN guidelines as a guide to further strictly evaluate the measurement attributes of existing scales or construct new scales, so as to provide references for clinical research to provide higher quality assessment tools.

Objective To systematically evaluate the prognostic prediction model for chronic heart failure patients in China, and provide reference for the construction, application, and promotion of related prognostic prediction models. Methods A comprehensive search was conducted on the studies related to prognostic prediction model for Chinese patients with chronic heart failure published in The Cochrane Library, PubMed, EMbase, Web of Science, CNKI, VIP, Wanfang, and the China Biological Medicine databases from inception to March 31, 2023. Two researchers strictly followed the inclusion and exclusion criteria to independently screen literature and extract data, and used the prediction model risk of bias assessment tool (PROBAST) to evaluate the quality of the models. Results A total of 25 studies were enrolled, including 123 prognostic prediction models for chronic heart failure patients. The area under the receiver operating characteristic curve (AUC) of the models ranged from 0.690 to 0.959. Twenty-two studies mostly used random splitting and Bootstrap for internal model validation, with an AUC range of 0.620-0.932. Seven studies conducted external validation of the model, with an AUC range of 0.720-0.874. The overall bias risk of all models was high, and the overall applicability was low. The main predictive factors included in the models were the N-terminal pro-brain natriuretic peptide, age, left ventricular ejection fraction, New York Heart Association heart function grading, and body mass index. Conclusion The quality of modeling methodology for predicting the prognosis of chronic heart failure patients in China is poor, and the predictive performance of different models varies greatly. For developed models, external validation and clinical application research should be vigorously carried out. For model development research, it is necessary to comprehensively consider various predictive factors related to disease prognosis before modeling. During modeling, large sample and prospective studies should be conducted strictly in accordance with the PROBAST standard, and the research results should be comprehensively reported using multivariate prediction model reporting guidelines to develop high-quality predictive models with strong scalability.