Search

Objective To explore the feasibility of constructing prediction models of postoperative sepsis mortality risk based on machine learning in patients undergoing abdominal surgery. Methods A case-control trial was designed and conducted on the patients diagnosed with sepsis after abdominal surgery from Medical Information Mart for Intensive Care Ⅳ (MIMIC-Ⅳ) database, and 90-day mortality was defined as the primary endpoint event after hospitalization. The dataset was ramdomly split into training (70%) and test (30%) datasets according to wether diagnosed with postopertive sepsis or not. On the training dataset, logistic regression (LR), gradient boosting decision tree (GBDT), random forest (RF), support vector machine (SVM) and adaptive boosting (AdaBoost) were used to develop the prediction model for death. The area under the receiver operating characteristic curve (AUC), sensitivity, specificity, positive predictive value, negative predictive value, accuracy and F1 score were used for model evaluation on the test dataset. Results A total of 986 patients were finally analyzed, of whom 251 patients (25.5%) died within 90 d after hospitalization. The AUC values of LR, GBDT, RF, SVM and AdaBoost prediction models were 0.852, 0.903, 0.921, 0.940 and 0.906, respectively. The model based on SVM yielded the best AUC value, higher differentiation and better prediction performance, while LR performed the worst among them. Conclusion The performances of the prediction model of postoperative sepsis mortality based on GBDTT, RF, SVM and AdaBoost are all better than that of traditional LR model, which may help to assist clinical decision making and improve adverse outcomes.

Objective To establish a risk model for predicting postoperative cognitive dysfunction (POCD) after non-cardiac surgery using preoperative indicators based on machine learning algorithm. Methods A case-control study was designed, and conducted on the POCD patients after non-cardiac surgery in the medical big data platform of our hospital from January 2014 to January 2019. Finally, 92 patients were included in the POCD group. According to surgical type and age matched of the POCD group, another 276 patients who did not develop POCD after surgery and discharged from the hospital during the same time period from the same big data platform were assigned into the non-POCD group at a ratio of 1∶3. At the same time, these 368 patients were randomly divided into modeling group (n=259) and validation group (n=109) at a ratio of 7∶3. After data preprocessing and feature selection of preoperative clinical indicators (general data, relevant scoring scales, surgical-related data and results of preoperative laboratory tests), the risk prediction model of POCD for non-cardiac surgery was established based on 3 machine learning algorithms, that is, logistic regression (LR), support vector machine (SVM) and Decision Tree. The model efficacy was evaluated by sensitivity, specificity, F1 score, and the area under the receiver operating characteristic curve (AUC). Results The SVM algorithm was the best model among the 3 machine learning algorithms to predict the risk of POCD after non-cardiac surgery. The AUC value of the model in the validation group was 0.957 (95%CI: 0.905~1.000), with a sensitivity and specificity of 92.6% and 98.8%, respectively. Conclusion A prediction model of POCD after non-cardiac surgery is successfully established based on machine learning algorithm. This model shows good predictive performance for POCD. [Key words] machine learning , prediction model , postoperative cognitive dysfunction,

Objective To understand the knowledge, skill status, general self-efficacy and the correlation of care burden of community elderly patients with skin pressure injuries and their informal caregivers. Methods A total of 280 community elderly informal nurses from 8 tertiary hospitals, 1 community hospital and 1 social medical institution in Shanghai were assessed with general information, knowledge questionnaire, behavior questionnaire, General Self-Efficacy Scale and Caregiver Burden Scale. Results The average score of informal nursing staff's care knowledge and behavior was (17. 25±2. 90) and (35. 27±6. 82) respectively, and the score of self-efficacy was (2. 33±0. 61). The score of caregiver's burden was relatively high ( 65. 12±14. 93). The general self-efficacy of caregivers on pressure injuries was positively correlated with the total score and all dimensions of care behavior (P＜0. 001). The general self-efficacy and co- caregivers, development limitation, emotional burden, average time spent caring for patients every day and caregiver knowledge questionnaire score were the influencing factors of care behavior of pressure injuries. Conclusion The level of nursing knowledge and behavior of informal nursing staff needs to be improved, the level of self-efficacy is general, and the burden of care is heavy. It is suggested to improve their knowledge, skills, behavior and self-efficacy from various aspects, the ultimate goal of promoting the healing and reducing the recurrence of stress injury of the community elderly is to build up the confidence of coping with care work. (目的 了解长期卧床伴皮肤压力性损伤的社区老年患者及其非正式护理人员主要照顾者的知识、技能现状、一般自我效能及照顾负担的相关性。方法 对上海8家三级医院、1家社区医院、1家社会办医机构合计280位长期卧床社区老年人及其非正式护理人员进行一般资料、压力性损伤的知识问卷、行为问卷、一般自我效能量表及照顾者负担量表的测评。结果 非正式护理人员照顾知识及行为得分平均分情况为(17. 25±2. 90)分及(35. 27±6. 82)分, 自我效能得分为(2. 33±0. 61)分; 照顾者负担得分较高为(65. 12±14. 93)分; 照顾者压力性损伤一般自我效能与照顾行为总分及各维度均呈现显著正相关(P＜0. 001); 一般自我效能、是否有共同照顾者、发展受限性、情感性负担、平均每天照顾患者耗时及照护者知识问卷得分6个变量是压力性损伤照顾行为的影响因素。结论 非正式护理人员照顾知识及行为水平有待提高, 自我效能水平一般, 照顾负担较重。建议从多种方面入手, 提高其知识技能行为水平及自我效能水平, 树立起应对照顾工作的信心, 从而达到促进社区老年人压力性损伤愈合及降低再发生情况的最终目标。)

Central retinal artery occlusion (CRAO; retinal stroke or eye stroke) is an under-recognized, disabling form of acute ischemic stroke which causes severe visual loss in one eye. The classical risk factor for CRAO is ipsilateral carotid stenosis; however, nearly half of patients with CRAO do not have high-grade carotid stenosis, suggesting that other cardiovascular risk factors may exist for CRAO. Specifically, prior studies have suggested that cardioembolism, driven by underlying atrial fibrillation, may predispose patients to CRAO. We describe the design of an observational, population-based study in this protocol. We evaluate two specific objectives: 1) To determine if atrial fibrillation is an independent risk factor for CRAO after adjusting for medical and cardiovascular risk; 2) To determine if use of oral anticoagulation can modify the risk of CRAO for patients with atrial fibrillation. This protocol lays out our strategy for cohort definition, case and control definition, comorbidity ascertainment, and statistical methods. [ABSTRACT FROM AUTHOR]