ABSTRACT
Introduction: Machine learning (ML) techniques have gained increasing attention in the field of healthcare, including predicting outcomes in patients with lung cancer. ML has the potential to enhance prognostication in lung cancer patients and improve clinical decision-making. In this systematic review and meta-analysis, we aimed to evaluate the performance of ML models compared to logistic regression (LR) models in predicting overall survival in patients with lung cancer. Methods: We followed the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) statement. A comprehensive search was conducted in Medline, Embase, and Cochrane databases using a predefined search query. Two independent reviewers screened abstracts and conflicts were resolved by a third reviewer. Inclusion and exclusion criteria were applied to select eligible studies. Risk of bias assessment was performed using predefined criteria. Data extraction was conducted using the Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modeling Studies (CHARMS) checklist. Meta-analytic analysis was performed to compare the discriminative ability of ML and LR models. Results: The literature search resulted in 3,635 studies, and 12 studies with a total of 211,068 patients were included in the analysis. Six studies reported confidence intervals and were included in the meta-analysis. The performance of ML models varied across studies, with C-statistics ranging from 0.60 to 0.85. The pooled analysis showed that ML models had higher discriminative ability compared to LR models, with a weighted average C-statistic of 0.78 for ML models compared to 0.70 for LR models. Conclusion: Machine learning models show promise in predicting overall survival in patients with lung cancer, with superior discriminative ability compared to logistic regression models. However, further validation and standardization of ML models are needed before their widespread implementation in clinical practice. Future research should focus on addressing the limitations of the current literature, such as potential bias and heterogeneity among studies, to improve the accuracy and generalizability of ML models for predicting outcomes in patients with lung cancer. Further research and development of ML models in this field may lead to improved patient outcomes and personalized treatment strategies.
ABSTRACT
INTRODUCTION: Thoracentesis is one of the most commonly performed procedures in the inpatient setting. Although coagulation profile is usually evaluated prior to thoracentesis, bleeding is a rare complication, occurring in less than 1% of the cases. Several society guidelines recommend holding antiplatelet medications and anticoagulants prior to thoracentesis. Clinical practice guidelines also recommend correcting international normalised ratios of more than two and platelet counts <50 X10â§9/L. METHODS: This is a retrospective descriptive study that included 292 patients who underwent thoracentesis in the inpatient setting at Ascension St John Hospital in Detroit, Michigan, USA from 2016 to 2018. We identified patients who had uncorrected risk for bleeding and collected data about their demographics, comorbidities, use of antiplatelet or anticoagulants and procedural details including complications. We looked for any postprocedural bleeding events to study their relation to the already established bleeding risk. RESULTS: Two hundred and ninety-two thoracenteses were performed, 95.5% (n=279) were performed by interventional radiology. Majority of patients were at risk of bleeding 83% (n=242). No bleeding events occurred. Medications that were not held prior to thoracentesis included: clopidogrel 11% (n=32), novel anticoagulants 8.2% (n=24) and unfractionated heparin 50% (n=146). Use of ultrasound guidance decreased the amount of haemoglobin decline from 1 to 2 g/L (p=0.029). Seventeen patients suffered pneumothorax, eight of which required intervention. DISCUSSION: Our study suggests that performing thoracentesis without correction of underlying coagulopathy may be safe. This may prevent consequences of holding essential medications and reduce the amount of blood products administered to patients in need of thoracentesis.
