ABSTRACT
[This corrects the article DOI: 10.3389/fonc.2024.1363812.].
ABSTRACT
Background: Artificial intelligence (AI) models, clinical models (CM), and the integrated model (IM) are utilized to evaluate the response to neoadjuvant chemotherapy (NACT) in patients diagnosed with gastric cancer. Objective: The objective is to identify the diagnostic test of the AI model and to compare the accuracy of AI, CM, and IM through a comprehensive summary of head-to-head comparative studies. Methods: PubMed, Web of Science, Cochrane Library, and Embase were systematically searched until September 5, 2023, to compile English language studies without regional restrictions. The quality of the included studies was evaluated using the Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2) criteria. Forest plots were utilized to illustrate the findings of diagnostic accuracy, while Hierarchical Summary Receiver Operating Characteristic curves were generated to estimate sensitivity (SEN) and specificity (SPE). Meta-regression was applied to analyze heterogeneity across the studies. To assess the presence of publication bias, Deeks' funnel plot and an asymmetry test were employed. Results: A total of 9 studies, comprising 3313 patients, were included for the AI model, with 7 head-to-head comparative studies involving 2699 patients. Across the 9 studies, the pooled SEN for the AI model was 0.75 (95% confidence interval (CI): 0.66, 0.82), and SPE was 0.77 (95% CI: 0.69, 0.84). Meta-regression was conducted, revealing that the cut-off value, approach to predicting response, and gold standard might be sources of heterogeneity. In the head-to-head comparative studies, the pooled SEN for AI was 0.77 (95% CI: 0.69, 0.84) with SPE at 0.79 (95% CI: 0.70, 0.85). For CM, the pooled SEN was 0.67 (95% CI: 0.57, 0.77) with SPE at 0.59 (95% CI: 0.54, 0.64), while for IM, the pooled SEN was 0.83 (95% CI: 0.79, 0.86) with SPE at 0.69 (95% CI: 0.56, 0.79). Notably, there was no statistical difference, except that IM exhibited higher SEN than AI, while maintaining a similar level of SPE in pairwise comparisons. In the Receiver Operating Characteristic analysis subgroup, the CT-based Deep Learning (DL) subgroup, and the National Comprehensive Cancer Network (NCCN) guideline subgroup, the AI model exhibited higher SEN but lower SPE compared to the IM. Conversely, in the training cohort subgroup and the internal validation cohort subgroup, the AI model demonstrated lower SEN but higher SPE than the IM. The subgroup analysis underscored that factors such as the number of cohorts, cohort type, cut-off value, approach to predicting response, and choice of gold standard could impact the reliability and robustness of the results. Conclusion: AI has demonstrated its viability as a tool for predicting the response of GC patients to NACT Furthermore, CT-based DL model in AI was sensitive to extract tumor features and predict the response. The results of subgroup analysis also supported the above conclusions. Large-scale rigorously designed diagnostic accuracy studies and head-to-head comparative studies are anticipated. Systematic review registration: PROSPERO, CRD42022377030.
ABSTRACT
Background: early-stage esophageal carcinoma (EC) patients lack typical clinical signs and symptoms and are often diagnosed and treated at a late stage, leading to a poor prognosis and a high incidence of metachronous esophageal squamous cell carcinoma (MESCC) and second primary carcinoma (SPC). The aims of the review were to identify and quantify risk factors for MESCC and analysis location of SPC in postoperative patients with EC; to predict incidence of MESCC over follow-up time. Methods: an electronic search of studies reporting potential risk factors, the incidence of MESCC, and the location of SPC were performed on PubMed, Web of Science, Cochrane Library, Embase, and Scopus from inception to 10 November 2022. The Newcastle-Ottawa scale was used to assess the study quality, and the qualitative strength of evidence rating of all items was provided. The meta-regression model was used to predict the incidence of MESCC over follow-up time, the location distribution of SPC was presented using clustered column chart, while the publication bias was assessed using funnel plots and Egger's test. Results: smoking, age, history of multiple other cancer, and Lugol-voiding lesions (LVLs) were determined to be the risk factors of MESCC. LVLs were qualitatively determined as "definite" and the history of multiple other cancer as "likely." The overall pooled MESCC incidence was 20.3% (95% CI: 13.8% to 26.8%), with an increase of 0.20% for each additional year of follow-up. The head and neck were the most common locations for SPC, followed by the esophagus. Conclusion: timely investigating the age of patients, previous history of cancer and monitoring the number of LVLs in the first 5 years after operation are of great significance to identify high-risk populations of MESCC for timely medical care. Education and behavior correction about smoking are advocated. Tumor markers should be regularly detected in the head and neck, esophagus, and stomach. Endoscopic resection was associated with a higher incidence of MESCC, which provided a reference for doctors to choose the removal method. Systematic review registration: https://www.crd.york.ac.uk/PROSPERO/, identifier CRD42022377030.
ABSTRACT
Background: There are 9 traditional Chinese medicines (TCMs) combined with standard quadruple (SQ) available for the treatment of Helicobacter pylori (Hp)-associated gastritis, but their relative efficacy and best options in clinical decision making are unknown due to a lack of high-quality head-to-head randomized controlled trials (RCTs). This study aimed to explore which formulas are the most effective and/or safest for Hp-associated gastritis. Methods: We performed a search of electronic databases including PubMed, Web of Science, Cochrane Library, Embase, Chinese databases and South Korean database from inception to March 2022 to identify all relevant RCTs on the comparison between TCM combined with SQ and SQ for Hp-associated gastritis. Efficacy outcomes were the eradication rate of Hp and therapeutic response rate, and safety outcome was incidence of adverse reactions. Publication bias was assessed quantitatively using Egger's regression analysis and qualitatively using trim-and-fill method. Quality assessment was performed using Cochrane Risk of Bias, version 2 (ROB 2) tool. The Bayesian methods were applied to compare each treatment. Results: A total of 55 trials with 6,187 patients were involved. The experimental group included 9 TCMs combined with SQ. The control group was SQ. The pair-wise meta-analysis demonstrated that compared with control group, 8 TCMs combined with SQ could statistically improve the eradication rate of Hp in patients with gastritis, 9 TCMs combined with SQ could significantly improve the therapeutic response rate. Additionally, Banxia Xiexin decoction combined with SQ (BXS) could statistically decrease the incidence of adverse reactions. The network meta-analysis results showed that BXS, Xiangsha Liujunzi combined with SQ (XSS), and Huangqi Jianzhong decoction combined with SQ (HQS) was the best measures to effectively eradicate Hp, enhance therapeutic effect, and decrease adverse reactions, respectively. The results of trim-and-fill method indicated that the results were stable and less affected by publication bias. Conclusions: Compared with SQ, TCM combined with SQ generally has a better clinical effect and higher safety in patients with Hp-associated gastritis. BXS, XSS, and HQS are recommended based on the patient's condition and needs in clinical practice. Further high-quality double-blinded RCTs are warranted to validate the conclusions.
