ABSTRACT
Gastroesophageal reflux disease (GERD) is a disorder that usually presents with heartburn. GERD is diagnosed clinically, but most patients are misdiagnosed due to atypical presentations. The increased use of artificial intelligence (AI) in healthcare has provided multiple ways of diagnosing and treating patients accurately. In this review, multiple studies in which AI models were used to diagnose GERD are discussed. According to the studies, using AI models helped to diagnose GERD in patients accurately. AI, although considered one of the most potent emerging aspects of medicine with its accuracy in patient diagnosis, presents limitations of its own, which explains why healthcare providers may hesitate to use AI in patient care. The challenges and limitations should be addressed before AI is fully incorporated into the healthcare system.
ABSTRACT
E-cigarettes have been known to cause varied poor health outcomes prior to coronavirus disease 2019 (COVID-19), but after the impact of COVID-19, evidence came out that was, in some instances, not as expected regarding the severity of COVID-19 among e-cigarette users (vapers). A meta-analysis was performed on the available evidence to comprehensively find the effect of COVID-19 on existing or past e-cigarette users (vapers). The Meta-analysis of Observational Studies in Epidemiology (MOOSE) guidelines were used to perform this meta-analysis. PubMed was searched for observational studies that described outcomes after COVID-19 positivity from December 1, 2019, to December 2023. Medical Subject Headings (MeSH) keywords were used for searching the relevant studies highlighting the relationship between COVID-19 and e-cigarette users. Calculations for pooled prevalence, 95% confidence interval (95% CI), weights for current e-cigarette users and vapers, and outcomes (events) were made. To analyze the data, Review Manager V.5.4 was used. The I² statistic was used to assess statistical heterogeneity. The I² statistic of >50% was considered significant heterogeneity. The "leave-one-out" method was used for sensitivity analysis. Out of 3231 studies, four studies reported data on vaping and non-vaping status and composite outcomes, resulting in a sample size of 653 COVID-19-positive cases. The pooled prevalence of being COVID-19 positive, having symptoms, or visiting an emergency room was 7.78% (653/8392). COVID-19 patients with current vaping status had decreased odds of poor outcomes compared to non-smokers, with a pooled odds ratio (OR) of 0.09 (95% CI 0.00-2.42; p>0.05) with heterogeneity between studies (I²=99%, p=0.15). Because of difficulties related to data collection and other factors, this meta-analysis was unable to conclusively establish the correlation between e-cigarette usage and severe COVID-19 outcomes such as hospitalization, admission to the intensive care unit, and fatality. Additional research using more detailed data is necessary to fully understand this correlation.
