Background: Systematic review is an indispensable tool for optimal evidence collection and evaluation in evidence-based medicine. However, the explosive increase of the original literatures makes it difficult to accomplish critical appraisal and regular update. Artificial intelligence (AI) algorithms have been applied to automate the literature screening procedure in medical systematic reviews. In these studies, different algorithms were used and results with great variance were reported. It is therefore imperative to systematically review and analyse the developed automatic methods for literature screening and their effectiveness reported in current studies. Methods: An electronic search will be conducted using PubMed, Embase, ACM Digital Library, and IEEE Xplore Digital Library databases, as well as literatures found through supplementary search in Google scholar, on automatic methods for literature screening in systematic reviews. Two reviewers will independently conduct the primary screening of the articles and data extraction, in which nonconformities will be solved by discussion with a methodologist. Data will be extracted from eligible studies, including the basic characteristics of study, the information of training set and validation set, and the function and performance of AI algorithms, and summarised in a table. The risk of bias and applicability of the eligible studies will be assessed by the two reviewers independently based on Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2). Quantitative analyses, if appropriate, will also be performed. Discussion: Automating systematic review process is of great help in reducing workload in evidence-based practice. Results from this systematic review will provide essential summary of the current development of AI algorithms for automatic literature screening in medical evidence synthesis and help to inspire further studies in this field. Systematic review registration: PROSPERO CRD42020170815 (28 April 2020).

Background: Sodium fluctuation is independently associated with clinical deterioration. We developed and validated a prognostic index based on sodium fluctuation for risk stratification and in-hospital monitoring. Methods: This study included 33,323 adult patients hospitalized at a tertiary care hospital in 2014. The first 28,279 hospitalizations were analyzed to develop the model and then the validity of the model was tested using data from 5044 subsequent hospitalizations. We predict in-hospital mortality using age, comorbidity, range of sodium fluctuation, and duration of sodium fluctuation, abbreviated as CARDS. Results: In-hospital mortality was similar in the derivation (0.6%) and validation (0.4%) cohorts. In the derivation cohort, four independent risk factors for mortality were identified using logistic regression: age (66–75, 2 points; >75, 3 points); Charlson comorbidity index (>2, 5 points); range of sodium fluctuation (7–10, 4 points; >10, 10 points); and duration of fluctuation (≤3, 3 points). The AUC was 0.907 (95% CI: 0.885–0.928) in the derivation cohort and 0.932 (95% CI: 0.895–0.970) in the validation cohort. In the derivation cohort, in-hospital mortality was 0.106% in the low-risk group (0–7 points), 1.076% in the intermediate-risk group (8–14 points), and 8.463% in the high-risk group (15–21 points). In the validation cohort, in-hospital mortality was 0.049% in the low-risk group, 1.064% in the intermediate-risk group, and 8.403% in the high-risk group. Conclusions: These results suggest that patients at low, intermediate, and high risk for in-hospital mortality may be identified by CARDS mainly based on sodium fluctuation.