Background
The differential diagnosis of tuberculous pleural effusion (TPE) is challenging. In recent years, artificial intelligence (AI) machine learning algorithms have started being used to an increasing extent in disease diagnosis due to the high level of efficiency, objectivity, and accuracy that they offer.
Methods
Data samples on 192 patients with TPE, 54 patients with parapneumonic pleural effusion (PPE), and 197 patients with malignant pleural effusion (MPE) were retrospectively collected. Based on 28 different features obtained via statistical analysis, TPE diagnostic models using four machine learning algorithms (MLAs), namely logistic regression, k-nearest neighbors (KNN), support vector machine (SVM) and random forest (RF) were established and their respective diagnostic performances were calculated. The respective diagnostic performances of each of the four algorithmic models were compared with that of pleural fluid adenosine deaminase (pfADA). Based on 12 features with the most significant impacts on the accuracy of the RF model, a new RF model was designed for clinical application. To demonstrate its external validity, a prospective study was conducted and the diagnostic performance of the RF model was calculated.
Results
The respective sensitivity and specificity of each of the four TPE diagnostic models were as follows: logistic regression – 80.5 and 84.8%; KNN– 78.6 and 86.6%; SVM – 83.2 and 85.9%; and RF – 89.1 and 93.6%. The sensitivity and specificity of pfADA were 85.4 and 84.1%, respectively, at the best cut-off value of 17.5 U/L. RF was the superior method among the four MLAs, and was also superior to pfADA. The newly designed RF model (based on 12 out of 28 features) exhibited an acceptable performance rate for the diagnosis of TPE with a sensitivity and specificity of 90.6 and 92.3%, respectively. In the prospective study, its sensitivity and specificity were 100.0 and 90.0%, respectively.
Conclusions
Establishing a model for the diagnosis of TPE using RF resulted in a more effective, economical, and faster diagnostic method. This method could enable clinicians to diagnose and treat TPE more effectively.
BackgroundThe novel coronavirus diseases (COVID-19) has led to a pandemic and affected people's lives greatly, including their health seeking behavior. We aimed to evaluate the impact of the current COVID-19 pandemic on characteristics and trends of emergency department (ED) visits in Shanghai, China.MethodsThis was a retrospective observational study using medical record databases from the Shanghai Sixth People's Hospital (East Campus) for years 2016 through 2020. All the patients referred to the ED between January 2016 and June 2020 were retrospectively reviewed. January 1, 2020, was chosen as the cutoff date for the statistical analysis and data of January and February in 2020 was compared with the same period of 2019.ResultsDuring the first two months of 2020, there was a 60.9% decline in ED visits when compared with the same period of 2019 (9,904 vs. 25,316, respectively), and the waiting time in ED has been greatly reduced correspondingly (12±4 vs. 66±19 min, p < 0.001); ED visits for acute ischemic stroke (AIS) and acute coronary syndrome(ACS) decreased by 53.9% and 41.2% respectively; proportion of intravenous thrombolysis for AIS has dropped(42.1% vs. 11.4%, p = 0.003), and percutaneous coronary intervention for ACS was similar (70.6% vs. 63.3%, p = 0.668); and onset-to-door time (ODT) of these patients increased significantly (AIS: 217(136-374) vs. 378(260-510)min, ACS: 135(85-195) vs. 226(155-368)min, all p < 0.001).ConclusionThe outbreak of COVID-19 pandemic was correlated with a significant decline in the number of ED visits including AIS and ACS patients when compared to the pre-COVID-19 period. ODT of AIS and ACS patients increased significantly. Raising public awareness is necessary to avoid serious healthcare and economic consequences of undiagnosed and untreated stroke and myocardial infarction attack.
Background The novel coronavirus diseases (COVID-19) has led to a pandemic and affected people's lives greatly, including their health seeking behavior. We aimed to evaluate the impact of the current COVID-19 pandemic on characteristics and trends of emergency department (ED) visits in Shanghai, China.Methods This was a retrospective observational study using medical record databases from the Shanghai Sixth People's Hospital (East Campus) for years 2016 through 2020. All the patients referred to the ED between January 2016 and June 2020 were retrospectively reviewed. January 1, 2020, was chosen as the cutoff date for the statistical analysis and data of January and February in 2020 was compared with the same period of 2019.Results During the first two months of 2020, there was a 60.9% decline in ED visits when compared with the same period of 2019 (9,904 vs. 25,316, respectively), and the waiting time in ED has been greatly reduced correspondingly (12±4 vs. 66±19 min, p < 0.001); ED visits for acute ischemic stroke (AIS) and acute coronary syndrome(ACS) decreased by 53.9% and 41.2% respectively; proportion of intravenous thrombolysis for AIS has dropped(42.1% vs. 11.4%, p = 0.003), and percutaneous coronary intervention for ACS was similar (70.6% vs. 63.3%, p = 0.668); and onset-to-door time (ODT) of these patients increased significantly (AIS: 217(136-374) vs. 378(260-510)min, ACS: 135(85-195) vs. 226(155-368)min, all p < 0.001).Conclusion The outbreak of COVID-19 pandemic was correlated with a significant decline in the number of ED visits including AIS and ACS patients when compared to the pre-COVID-19 period. ODT of AIS and ACS patients increased significantly. Raising public awareness is necessary to avoid serious healthcare and economic consequences of undiagnosed and untreated stroke and myocardial infarction attack.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.