Background: Artificial intelligence, particularly chatbot systems, is becoming an instrumental tool in health care, aiding clinical decision-making and patient engagement. Objective: This study aims to analyze the performance of ChatGPT-3.5 and ChatGPT-4 in addressing complex clinical and ethical dilemmas, and to illustrate their potential role in health care decision-making while comparing seniors’ and residents’ ratings, and specific question types. Methods: A total of 4 specialized physicians formulated 176 real-world clinical questions. A total of 8 senior physicians and residents assessed responses from GPT-3.5 and GPT-4 on a 1-5 scale across 5 categories: accuracy, relevance, clarity, utility, and comprehensiveness. Evaluations were conducted within internal medicine, emergency medicine, and ethics. Comparisons were made globally, between seniors and residents, and across classifications. Results: Both GPT models received high mean scores (4.4, SD 0.8 for GPT-4 and 4.1, SD 1.0 for GPT-3.5). GPT-4 outperformed GPT-3.5 across all rating dimensions, with seniors consistently rating responses higher than residents for both models. Specifically, seniors rated GPT-4 as more beneficial and complete (mean 4.6 vs 4.0 and 4.6 vs 4.1, respectively; P<.001), and GPT-3.5 similarly (mean 4.1 vs 3.7 and 3.9 vs 3.5, respectively; P<.001). Ethical queries received the highest ratings for both models, with mean scores reflecting consistency across accuracy and completeness criteria. Distinctions among question types were significant, particularly for the GPT-4 mean scores in completeness across emergency, internal, and ethical questions (4.2, SD 1.0; 4.3, SD 0.8; and 4.5, SD 0.7, respectively; P<.001), and for GPT-3.5’s accuracy, beneficial, and completeness dimensions. Conclusions: ChatGPT’s potential to assist physicians with medical issues is promising, with prospects to enhance diagnostics, treatments, and ethics. While integration into clinical workflows may be valuable, it must complement, not replace, human expertise. Continued research is essential to ensure safe and effective implementation in clinical environments.

Background: Gastric cancer (GC), a significant health burden worldwide, is typically diagnosed in the advanced stages due to its non-specific symptoms and complex morphological features. Deep learning (DL) has shown potential for improving and standardizing early GC detection. This systematic review aims to evaluate the current status of DL in pre-malignant, early-stage, and gastric neoplasia analysis. Methods: A comprehensive literature search was conducted in PubMed/MEDLINE for original studies implementing DL algorithms for gastric neoplasia detection using endoscopic images. We adhered to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. The focus was on studies providing quantitative diagnostic performance measures and those comparing AI performance with human endoscopists. Results: Our review encompasses 42 studies that utilize a variety of DL techniques. The findings demonstrate the utility of DL in GC classification, detection, tumor invasion depth assessment, cancer margin delineation, lesion segmentation, and detection of early-stage and pre-malignant lesions. Notably, DL models frequently matched or outperformed human endoscopists in diagnostic accuracy. However, heterogeneity in DL algorithms, imaging techniques, and study designs precluded a definitive conclusion about the best algorithmic approach. Conclusions: The promise of artificial intelligence in improving and standardizing gastric neoplasia detection, diagnosis, and segmentation is significant. This review is limited by predominantly single-center studies and undisclosed datasets used in AI training, impacting generalizability and demographic representation. Further, retrospective algorithm training may not reflect actual clinical performance, and a lack of model details hinders replication efforts. More research is needed to substantiate these findings, including larger-scale multi-center studies, prospective clinical trials, and comprehensive technical reporting of DL algorithms and datasets, particularly regarding the heterogeneity in DL algorithms and study designs.

Background: COVID-19 is a heterogenous disease resulting in long-term sequela in predisposed individuals. It is not uncommon that recovering patients endure non-respiratory ill-defined manifestations, including anosmia, and neurological and cognitive deficit persisting beyond recovery—a constellation of conditions that are grouped under the umbrella of long-term COVID-19 syndrome. Association between COVID-19 and autoimmune responses in predisposed individuals was shown in several studies. Aim and methods: To investigate autoimmune responses against neuronal and CNS autoantigens in SARS-CoV-2-infected patients, we performed a cross-sectional study with 246 participants, including 169 COVID-19 patients and 77 controls. Levels of antibodies against the acetylcholine receptor, glutamate receptor, amyloid β peptide, alpha-synucleins, dopamine 1 receptor, dopamine 2 receptor, tau protein, GAD-65, N-methyl D-aspartate (NMDA) receptor, BDNF, cerebellar, ganglioside, myelin basic protein, myelin oligodendrocyte glycoprotein, S100-B, glial fibrillary acidic protein, and enteric nerve were measured using an Enzyme-Linked Immunosorbent Assay (ELISA). Circulating levels of autoantibodies were compared between healthy controls and COVID-19 patients and then classified by disease severity (mild [n = 74], severe [n = 65], and requiring supplemental oxygen [n = 32]). Results: COVID-19 patients were found to have dysregulated autoantibody levels correlating with the disease severity, e.g., IgG to dopamine 1 receptor, NMDA receptors, brain-derived neurotrophic factor, and myelin oligodendrocyte glycoprotein. Elevated levels of IgA autoantibodies against amyloid β peptide, acetylcholine receptor, dopamine 2 receptor, myelin basic protein, and α-synuclein were detected in COVID-19 patients compared with healthy controls. Lower IgA autoantibody levels against NMDA receptors, and IgG autoantibodies against glutamic acid decarboxylase 65, amyloid β peptide, tau protein, enteric nerve, and S100-B were detected in COVID-19 patients versus healthy controls. Some of these antibodies have known clinical correlations with symptoms commonly reported in the long COVID-19 syndrome. Conclusions: Overall, our study shows a widespread dysregulation in the titer of various autoantibodies against neuronal and CNS-related autoantigens in convalescent COVID-19 patients. Further research is needed to provide insight into the association between these neuronal autoantibodies and the enigmatic neurological and psychological symptoms reported in COVID-19 patients.

Background: West Nile virus is an arbovirus responsible for an infection that tends to peak during the late summer and early fall. Tools monitoring Web searches are emerging as powerful sources of data, especially concerning infectious diseases such as West Nile virus. Objective: This study aimed at exploring the potential predictive power of West Nile virus–related Web searches. Methods: Different novel data streams, including Google Trends, WikiTrends, YouTube, and Google News, were used to extract search trends. Data regarding West Nile virus cases were obtained from the Centers for Disease Control and Prevention. Data were analyzed using regression, times series analysis, structural equation modeling, and clustering analysis. Results: In the regression analysis, an association between Web searches and “real-world” epidemiological figures was found. The best seasonal autoregressive integrated moving average model with explicative variable (SARIMAX) was found to be (0,1,1)x(0,1,1)4. Using data from 2004 to 2015, we were able to predict data for 2016. From the structural equation modeling, the consumption of West Nile virus–related news fully mediated the relation between Google Trends and the consumption of YouTube videos, as well as the relation between the latter variable and the number of West Nile virus cases. Web searches fully mediated the relation between epidemiological figures and the consumption of YouTube videos, as well as the relation between epidemiological data and the number of accesses to the West Nile virus–related Wikipedia page. In the clustering analysis, the consumption of news was most similar to the Web searches pattern, which was less close to the consumption of YouTube videos and least similar to the behavior of accessing West Nile virus–related Wikipedia pages. Conclusions: Our study demonstrated an association between epidemiological data and search patterns related to the West Nile virus. Based on this correlation, further studies are needed to examine the practicality of these findings.