The value of postoperative chest radiology after major abdominal surgery

Deep Learning-Based Computer-Aided Detection System for Preoperative Chest Radiographs to Predict Postoperative Pneumonia

RATIONALE AND OBJECTIVES

The role of preoperative chest radiography (CR) for prediction of postoperative pneumonia remains uncertain. We aimed to develop and validate a prediction model for postoperative pneumonia incorporating findings of preoperative CRs evaluated by a deep learning-based computer-aided detection (DL-CAD) system MATERIALS AND METHODS: This retrospective study included consecutive patients who underwent surgery between January 2019 and March 2020 and divided into development (surgery in 2019) and validation (surgery between January and March 2020) cohorts. Preoperative CRs obtained within 1-month before surgery were analyzed with a commercialized DL-CAD that provided probability values for the presence of 10 different abnormalities in CRs. Logistic regression models to predict postoperative pneumonia were built using clinical variables (clinical model), and both clinical variables and DL-CAD results for preoperative CRs (DL-CAD model). The discriminative performances of the models were evaluated by area under the receiver operating characteristic curves.

RESULTS

In development cohort (n = 19,349; mean age, 57 years; 11,392 men), DL-CAD results for pulmonary nodules (odds ratio [OR, for 1% increase in probability value], 1.007; p = 0.021), consolidation (OR, 1.019; p < 0.001), and cardiomegaly (OR, 1.013; p < 0.001) were independent predictors of postoperative pneumonia and were included in the DL-CAD model. In validation cohort (n = 4957; mean age, 56 years; 2848 men), the DL-CAD model exhibited a higher AUROC than the clinical model (0.843 vs. 0.815; p = 0.012).

CONCLUSION

Abnormalities in preoperative CRs evaluated by a DL-CAD were independent risk factors for postoperative pneumonia. Using DL-CAD results for preoperative CRs led to an improved prediction of postoperative pneumonia.

Sore throat incidence with the laryngeal mask: A comparison with orotracheal intubation

The incidence of sore throat was evaluated among 80 healthy (ASA 1 and 2) nonpremedicated adult patients undergoing general anesthesia for general, plastic, urologic, gynecologic, and orthopedic surgery. The patients were randomly allocated in two groups: group one (n=39) consisted of patients in whom the airway was maintained by a laryngeal mask, and in group 2 (n=40), orotracheal intubation was performed. Both groups were similar in age, gender, site of surgery, and time of airway cannulation. Intraperitoneal surgery of the upper abdomen, and insertion of a nasogastric tube were exclusion criteria. The severity of sore throat was graded by the patients themselves using a visual analogue 100 mm scale, varying from 0 (no sore throat) to 10 (extremely sore). The sore throat incidence, severity and duration were significantly lower in the laryngeal mask group in comparison with the endotracheal intubation group.

Atelectasis and lung function in the postoperative period

Thirteen patients with healthy hearts and lungs, and with a mean age of 68 years, who were scheduled for lower abdominal surgery during isoflurane anaesthesia with muscular paralysis, were investigated with arterial blood gases, spirometry, pulmonary x-ray and computed tomography (CT) of the chest before and during anaesthesia, as well as during the first 4 postoperative days. Before anaesthesia, lung function and gas exchange were normal in all patients. Pulmonary x-ray and CT scans of the lungs were also normal. During anaesthesia, 6 of 13 patients developed atelectasis (mean 1.0% of intrathoracic transverse area in all patients). Two hours postoperatively, 11 of 13 patients had atelectasis and the mean atelectatic area was 1.8%. Pao2 was significantly reduced by 2.1 kPa to 9.8 kPa. On the first postoperative day, the mean atelectasis was unaltered (1.8%). None of the atelectasis found on CT scanning could be detected on standard pulmonary x-ray. Forced vital capacity (FVC) and forced expired volume in 1 s (FEV1) were significantly decreased to 2/3 of preoperative level. Pao2 was significantly reduced to less than 80% of the preoperative level (mean 9.4 kPa). There were significant correlations between the atelectatic area and the impairment in FVC, FEV1, and Pao2. Spirometry and blood gases improved during the succeeding postoperative days, and atelectasis decreased. No patient suffered from pulmonary complications, as judged from clinical criteria and pulmonary x-ray, in contrast to the findings of atelectasis in 85% of the patients by computed tomography.