Objective: We aim to investigate the application and accuracy of artificial intelligence (AI) methods for automated medical literature screening for systematic reviews. Materials and Methods: We systematically searched PubMed, Embase, and IEEE Xplore Digital Library to identify potentially relevant studies. We included studies in automated literature screening that reported study question, source of dataset, and developed algorithm models for literature screening. The literature screening results by human investigators were considered to be the reference standard. Quantitative synthesis of the accuracy was conducted using a bivariate model. Results: Eighty-six studies were included in our systematic review and 17 studies were further included for meta-analysis. The combined recall, specificity, and precision were 0.928 [95% confidence interval (CI), 0.878–0.958], 0.647 (95% CI, 0.442–0.809), and 0.200 (95% CI, 0.135–0.287) when achieving maximized recall, but were 0.708 (95% CI, 0.570–0.816), 0.921 (95% CI, 0.824–0.967), and 0.461 (95% CI, 0.375–0.549) when achieving maximized precision in the AI models. No significant difference was found in recall among subgroup analyses including the algorithms, the number of screened literatures, and the fraction of included literatures. Discussion and Conclusion: This systematic review and meta-analysis study showed that the recall is more important than the specificity or precision in literature screening, and a recall over 0.95 should be prioritized. We recommend to report the effectiveness indices of automatic algorithms separately. At the current stage manual literature screening is still indispensable for medical systematic reviews.

Diseases not only manifest as internal structural and functional abnormalities, but also have facial characteristics and appearance deformities. Specific facial phenotypes are potential diagnostic markers, especially for endocrine and metabolic syndromes, genetic disorders, facial neuromuscular diseases, etc. The technology of facial recognition (FR) has been developed for more than a half century, but research in automated identification applied in clinical medicine has exploded only in the last decade. Artificial-intelligence-based FR has been found to have superior performance in diagnosis of diseases. This interdisciplinary field is promising for the optimization of the screening and diagnosis process and assisting in clinical evaluation and decision-making. However, only a few instances have been translated to practical use, and there is need of an overview for integration and future perspectives. This review mainly focuses on the leading edge of technology and applications in varieties of disease, and discusses implications for further exploration.

Pituitary neuroendocrine tumors (PitNETs) can be invasive or aggressive, yet the mechanisms behind these behaviors remain poorly understood, impeding treatment advancements. Here, we integrat single-cell RNA sequencing and spatial transcriptomics, analyzing over 177,000 cells and 35,000 spots across 57 tissue samples. This comprehensive approach facilitates the identification of PitNETs tumor populations and characterizes the reconfiguration of the tumor microenvironment (TME) as PitNETs progress and invade. We trace the trajectory of TPIT-lineage PitNETs and identify an aggressive tumor cluster marked by elevated p53-mediated proliferation and a higher Trouillas classification, both associated with tumor progression. Additionally, we document the heterogeneity of immune stromal cells within PitNETs, particularly noting the enrichment of SPP1+ tumor associated macrophages (TAMs) in invasive tumors. These TAMs facilitate tumor invasion through the SPP1-ITGAV/ITGB1 signaling pathway. Our in-depth single-cell and spatial analysis of PitNETs uncovers the molecular dynamics within the TME, suggesting potential targets for therapeutic intervention.

Background and Objective: Although anti-programmed cell death protein 1 (PD-1) antibodies have exerted remarkable anticancer activity in non-small cell lung cancer (NSCLC), it remains a challenge to identify patients who can benefit from these treatments. Immune-related adverse events (irAEs) may be associated with improved clinical outcomes after immune checkpoint inhibition. However, no conclusive evidence of this correlation has been summarized in patients with NSCLC receiving PD-1 inhibitors. We performed a systematic review and meta-analysis to evaluate the association between irAEs induced by anti-PD-1 antibodies and clinical outcomes in patients with NSCLC.Methods: Various databases were searched from their inception to January 9, 2021, followed by screening of eligible studies. Hazard ratios were used for the pooled analysis of overall survival (OS) and progression-free survival (PFS), while odds ratios (ORs) were utilized to pool objective response rates (ORRs) and disease control rates (DCRs). A random-effects model was applied to all analyses.Results: A total of 26 cohorts, including 8,452 patients with NSCLC receiving anti-PD-1 antibodies, were enrolled in the study. Significantly improved OS (HR: 0.51; 95% CI: 0.44-0.60; P < 0.01) and PFS (HR: 0.50; 95% CI: 0.43-0.58; P < 0.01) were found to be correlated with irAEs. In addition, patients with NSCLC who developed irAEs after PD-1 inhibition demonstrated better responses to therapies, confirmed by pooled ORs of ORRs (OR: 3.41; 95% CI: 2.66-4.35; P < 0.01) and DCRs (OR: 4.08; 95% CI: 2.30-7.24; P < 0.01). Furthermore, subgroup analysis suggested that both skin and endocrine irAEs are closely correlated with a reduced risk of death, whereas pulmonary irAEs showed no association with longer OS.Conclusions: In patients with NSCLC treated with anti-PD-1 therapies, the presence of irAEs was strongly correlated with better survival and response, suggesting its potential role as a predictive biomarker for outcomes after PD-1 inhibition.

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).