Iatrogenic pneumothorax related to mechanical ventilation

Automated detection of moderate and large pneumothorax on frontal chest X-rays using deep convolutional neural networks: A retrospective study

BACKGROUND

Pneumothorax can precipitate a life-threatening emergency due to lung collapse and respiratory or circulatory distress. Pneumothorax is typically detected on chest X-ray; however, treatment is reliant on timely review of radiographs. Since current imaging volumes may result in long worklists of radiographs awaiting review, an automated method of prioritizing X-rays with pneumothorax may reduce time to treatment. Our objective was to create a large human-annotated dataset of chest X-rays containing pneumothorax and to train deep convolutional networks to screen for potentially emergent moderate or large pneumothorax at the time of image acquisition.

METHODS AND FINDINGS

In all, 13,292 frontal chest X-rays (3,107 with pneumothorax) were visually annotated by radiologists. This dataset was used to train and evaluate multiple network architectures. Images showing large- or moderate-sized pneumothorax were considered positive, and those with trace or no pneumothorax were considered negative. Images showing small pneumothorax were excluded from training. Using an internal validation set (n = 1,993), we selected the 2 top-performing models; these models were then evaluated on a held-out internal test set based on area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and positive predictive value (PPV). The final internal test was performed initially on a subset with small pneumothorax excluded (as in training; n = 1,701), then on the full test set (n = 1,990), with small pneumothorax included as positive. External evaluation was performed using the National Institutes of Health (NIH) ChestX-ray14 set, a public dataset labeled for chest pathology based on text reports. All images labeled with pneumothorax were considered positive, because the NIH set does not classify pneumothorax by size. In internal testing, our "high sensitivity model" produced a sensitivity of 0.84 (95% CI 0.78-0.90), specificity of 0.90 (95% CI 0.89-0.92), and AUC of 0.94 for the test subset with small pneumothorax excluded. Our "high specificity model" showed sensitivity of 0.80 (95% CI 0.72-0.86), specificity of 0.97 (95% CI 0.96-0.98), and AUC of 0.96 for this set. PPVs were 0.45 (95% CI 0.39-0.51) and 0.71 (95% CI 0.63-0.77), respectively. Internal testing on the full set showed expected decreased performance (sensitivity 0.55, specificity 0.90, and AUC 0.82 for high sensitivity model and sensitivity 0.45, specificity 0.97, and AUC 0.86 for high specificity model). External testing using the NIH dataset showed some further performance decline (sensitivity 0.28-0.49, specificity 0.85-0.97, and AUC 0.75 for both). Due to labeling differences between internal and external datasets, these findings represent a preliminary step towards external validation.

CONCLUSIONS

We trained automated classifiers to detect moderate and large pneumothorax in frontal chest X-rays at high levels of performance on held-out test data. These models may provide a high specificity screening solution to detect moderate or large pneumothorax on images collected when human review might be delayed, such as overnight. They are not intended for unsupervised diagnosis of all pneumothoraces, as many small pneumothoraces (and some larger ones) are not detected by the algorithm. Implementation studies are warranted to develop appropriate, effective clinician alerts for the potentially critical finding of pneumothorax, and to assess their impact on reducing time to treatment.

Patient Safety: Identifying and Managing Complications of Mechanical Ventilation

Mechanical ventilation is a fundamental aspect of critical care practice to help meet the respiratory needs of critically ill patients. Complications can occur though, as a direct result of being mechanically ventilated, or indirectly because of a secondary process. Preventing, identifying, and managing these complications significantly contribute to the role and responsibilities of critical care nurses in promoting patient safety. This article reviews common ventilator-associated events, including both infectious (eg, ventilator-associated pneumonia) and noninfectious causes (eg, acute respiratory distress syndrome, pulmonary edema, pleural effusion, and atelectasis).

Prevalence and risk factors of pneumothorax among patients admitted to a Pediatric Intensive Care Unit

OBJECTIVE

Pneumothorax should be considered a medical emergency and requires a high index of suspicion and prompt recognition and intervention.

AIMS

The objective of the study was to evaluate cases developing pneumothorax following admission to a Pediatric Intensive Care Unit (PICU) over a 5-year period.

SETTINGS AND DESIGN

Case notes of all PICU patients (n = 1298) were reviewed, revealing that 135 cases (10.4%) developed pneumothorax, and these were compared with those patients who did not. The most common tool for diagnosis used was chest X-ray followed by a clinical examination.

SUBJECTS AND METHODS

Case notes of 1298 patients admitted in PICU over 1-year study.

RESULTS

Patients with pneumothorax had higher mortality rate (P < 0.001), longer length of stay (P < 0.001), higher need for mechanical ventilation (MV) (P < 0.001), and were of younger age (P < 0.001), lower body weight (P < 0.001), higher pediatric index of mortality 2 score on admission (P < 0.001), higher pediatric logistic organ dysfunction score (P < 0.001), compared to their counterpart. Iatrogenic pneumothorax (IP) represented 95% of episodes of pneumothorax. The most common causes of IP were barotrauma secondary to MV, central vein catheter insertion, and other (69.6%, 13.2%, and 17.2%, respectively). Compared to ventilated patients without pneumothorax, ventilated patients who developed pneumothorax had a longer duration of MV care (P < 0.001) and higher nonconventional and high-frequency oscillatory ventilation settings (P < 0.001).

CONCLUSIONS

This study demonstrated that pneumothorax is common in Alexandria University PICU patients, especially in those on MV and emphasized the importance of the strict application of protective lung strategies among ventilated patients to minimize the risk of pneumothorax.

An in silico framework for integrating epidemiologic and genetic evidence with health care applications: ventilation-related pneumothorax as a case illustration

OBJECTIVE

To illustrate an in silico integration of epidemiologic and genetic evidence that is being developed at the Center for Devices and Radiological Health/US Food and Drug Administration as part of regulatory research on postmarket device performance. In addition to using conventional epidemiologic evidence from registries, this innovative approach explores the vast potential of open-access omics databases for identifying genetic evidence pertaining to devices.

MATERIAL AND METHODS

A retrospective analysis of Agency for Healthcare Research and Quality (AHRQ)/Healthcare Cost and Utilization Project (HCUPNet) data (2002-2011) was focused on the ventilation-related iatrogenic pneumothorax (Vent-IP) outcome in discharges with mechanical ventilation (MV) and continuous positive airway pressure (CPAP). The derived epidemiologic evidence was analyzed in conjunction with pre-existing genomic data from Gene Expression Omnibus/National Center for Biotechnology Information and other databases.

RESULTS

AHRQ/HCUPNet epidemiologic evidence showed that annual occurrence of Vent-IP did not decrease over a decade. While the Vent-IP risk associated with noninvasive CPAP comprised about 0.5%, the Vent-IP risk due to longer-term MV reached 2%. Along with MV posing an independent risk for Vent-IP, female sex and white race were found to be effect modifiers, resulting in the highest Vent-IP risk among mechanically ventilated white females. The Vent-IP risk was also potentiated by comorbidities associated with spontaneous pneumothorax (SP) and fibrosis. Consistent with the epidemiologic evidence, expression profiling in a number of animal models showed that the expression of several collagens and other SP/fibrosis-related genes was modified by ventilation settings.

CONCLUSION

Integration of complementary genetic evidence into epidemiologic analysis can lead to a cost- and time-efficient discovery of the risk predictors and markers and thus can facilitate more efficient marker-based evaluation of medical product performance.

Intraoperative Tension Pneumothorax in a Patient With Remote Trauma and Previous Tracheostomy

Many trauma patients present with a combination of cranial and thoracic injury. Anesthesia for these patients carries the risk of intraoperative hemodynamic instability and respiratory complications during mechanical ventilation. Massive air leakage through a lacerated lung will result in inadequate ventilation and hypoxemia and, if left undiagnosed, may significantly compromise the hemodynamic function and create a life-threatening situation. Even though these complications are more characteristic for the early phase of trauma management, in some cases, such a scenario may develop even months after the initial trauma. We report a case of a 25-year-old patient with remote thoracic trauma, who developed an intraoperative tension pneumothorax and hemodynamic instability while undergoing an elective cranioplasty. The intraoperative patient assessment was made even more challenging by unexpected massive blood loss from the surgical site. Timely recognition and management of intraoperative pneumothorax along with adequate blood replacement stabilized the patient and helped avoid an unfavorable outcome. This case highlights the risks of intraoperative pneumothorax in trauma patients, which may develop even months after injury. A high index of suspicion and timely decompression can be life saving in this type of situation.

Thoracic trauma in horses

Traumatic injuries involving the thorax can be superficial, necessitating only routine wound care, or they may extend to deeper tissue planes and disrupt structures immediately vital to respiratory and cardiac function. Diagnostic imaging, especially ultrasound, should be considered part of a comprehensive examination, both at admission and during follow-up. Horses generally respond well to diligent monitoring, intervention for complications, and appropriate medical or surgical care after sustaining traumatic wounds of the thorax. This article reviews the various types of thoracic injury and their management.

Pleural puncture that excludes the ablation zone decreases the risk of pneumothorax after percutaneous microwave ablation in porcine lung

PURPOSE

To test the hypothesis that the geometry of probe placement with respect to the pleural puncture site affects the risk of pneumothorax after microwave (MW) ablation in the lung.

MATERIALS AND METHODS

Computed tomography-guided MW ablation of the lung was performed in 8 swine under general anesthesia and mechanical ventilation. The orientation of the 17-gauge probe was either perpendicular (90°) or parallel (< 30°) with respect to the pleural puncture site, and the ablation power was 30 W or 65 W for 5 minutes. After MW ablation, swine were euthanized, and histopathologic changes were assessed. Frequency and factors affecting pneumothorax were evaluated by multivariate analysis.

RESULTS

Among 62 lung MW ablations, 13 (21%) pneumothoraces occurred. No statistically significant difference was noted in the rate of pneumothorax between the perpendicular and the parallel orientations of the probe (31% vs 14%; odds ratio [OR], 2.8; P = .11). The pneumothorax rate was equal for 65-W and 30-W ablation powers (21% and 21%; OR, 1.0; P = .94). Under multivariate analysis, 2 factors were independent positive predictors of pneumothorax: ablation zone inclusive of pleural insertion point (OR, 7.7; P = .02) and time since intubation (hours) (OR, 2.7; P = .02).

CONCLUSIONS

Geometries where the pleural puncture site excluded the ablation zone decreased pneumothorax in swine undergoing MW ablation in the lung. Treatment planning to ensure that the pleural puncture site excludes the subsequent ablation zone may reduce the rate of pneumothorax in patients undergoing MW ablation in the lung.