A prognostic model for use before elective surgery to estimate the risk of postoperative pulmonary complications (GSU-Pulmonary Score): a development and validation study in three international cohorts

Pulmonary and functional hallmarks after SARS-CoV-2 infection across three WHO severity level-groups: an observational study

Background

The manifestations of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection range from flu-like symptoms to severe lung disease. The consequences of this inflammatory process impact overall function, which can be detected through both short- to long-term assessments. This study aimed to assess the pulmonary functional and structural characteristics of post-SARS-CoV-2 infection in patients with mild/moderate, severe, and critical clinical presentations.

Methods

An observational, analytical, and cross-sectional study was conducted between 2020 and 2022, including participants with a confirmed diagnosis of coronavirus disease (COVID)-19, with mild/moderate (G1), severe (G2), and critical (G3) clinical presentations, all evaluated at least 3 months after acute infection. Spirometry, impulse oscillometry, fractional exhaled nitric oxide (FeNO), chest computed tomography, the 6-min walk test (6MWT), hand grip strength, maximum inspiratory pressure, and maximum expiratory pressure were assessed.

Results

We enrolled 210 participants aged 18-70 years, 32.6% of whom were male, with older age observed in G3. The participants were grouped as follows: G1 (42.3%), G2 (25.7%), and G3 (31.9%). Percentage of predicted X5 differed between G1 and G2, being higher in G1. The percentage of predicted forced vital capacity (FVC) according to the Global Lung Function Initiative and its z-score were higher in G1. The FVC by Pereira was lower in G3 compared to G1. The percentage of predicted forced expiratory volume in 1 s (FEV1) by Pereira was also lower in G3. The Tiffeneau (FEV1/FVC) index was different among groups, increasing with disease severity. The percentage of predicted forced expiratory flow rate at 25-75% (FEF25-75%) of the FVC and FeNO were both higher in G2 than G1. Chest computed tomography revealed the presence of interstitial abnormalities, associated with disease severity. The respiratory muscle strength evaluation showed an association between higher maximum expiratory pressure values in G3 compared to G1, but no association with maximum inspiratory pressure was observed. The 6MWT distance covered decreased with increasing severity, with a lower percentage of predicted values in G3 compared to G1. The right-hand grip strength was also lower in G3 compared to G1.

Conclusion

Alterations in pulmonary and functional markers were observed in post-COVID-19 evaluations, increasing with disease severity, as seen in G2 and G3. These findings highlight the complexity of post-COVID-19 functional assessments, given the long-term pulmonary sequelae and the consequent impairment of functional capacity.

Bidirectional cohort study protocol to construct and validate a prediction model for perioperative pulmonary complications in elderly hip fracture patients

Elderly adults with hip fractures are particularly vulnerable to perioperative pulmonary complications (POPCs) throughout the surgical process. While most studies have focused on predicting postoperative pulmonary complications (PPCs), there has been a lack of focus on preoperative and intraoperative phases. To address this gap, this bidirectional cohort study aims to develop and validate a predictive model for POPCs across all surgical stages in elderly patients with hip fracture. This study will involve 3481 patients, with 1914 in the retrospective dataset and 1567 in the prospective dataset, and will analyse 44 perioperative risk factors. LASSO and multiple logistic regression will be used to identify key predictors, and nomogram prediction models will be constructed via the RMS packages. The accuracy and variability of the model will be assessed using receiver operating characteristic (ROC) curve analysis and calibration plots. The primary outcome measure is the incidence of pulmonary complications from hospital admission to 30 days post-surgery, and the secondary outcomes include complications such as heart failure, myocardial infarction, renal failure, deep venous thrombosis, stroke, and death within 30 days post-surgery. This study aims to construct a comprehensive model for predicting POPCs in this patient population and verify its accuracy and ability to differentiate POPCs using both internal and external data.

Predicting postoperative pulmonary infection risk in patients with diabetes using machine learning

Background

Patients with diabetes face an increased risk of postoperative pulmonary infection (PPI). However, precise predictive models specific to this patient group are lacking.

Objective

To develop and validate a machine learning model for predicting PPI risk in patients with diabetes.

Methods

This retrospective study enrolled 1,269 patients with diabetes who underwent elective non-cardiac, non-neurological surgeries at our institution from January 2020 to December 2023. Predictive models were constructed using nine different machine learning algorithms. Feature selection was conducted using Least Absolute Shrinkage and Selection Operator (LASSO) logistic regression. Model performance was assessed via the Area Under the Curve (AUC), precision, accuracy, specificity and F1-score.

Results

The Ada Boost classifier (ADA) model exhibited the best performance with an AUC of 0.901, Accuracy of 0.91, Precision of 0.82, specificity of 0.98, PPV of 0.82, and NPV of 0.82. LASSO feature selection identified six optimal predictive factors: postoperative transfer to the ICU, Age, American Society of Anesthesiologists (ASA) physical status score, chronic obstructive pulmonary disease (COPD) status, surgical department, and duration of surgery.

Conclusion

Our study developed a robust predictive model using six clinical features, offering a valuable tool for clinical decision-making and personalized prevention strategies for PPI in patients with diabetes.