Machine learning for the prediction of pathologic pneumatosis intestinalis.

BACKGROUND: The radiographic finding of pneumatosis intestinalis can indicate a spectrum of underlying processes ranging from a benign finding to a life-threatening condition. Although radiographic pneumatosis intestinalis is relatively common, there is no validated clinical tool to guide surgical management. METHODS: Using a retrospective cohort of 300 pneumatosis intestinalis cases from a single institution, we developed 3 machine learning models for 2 clinical tasks: (1) the distinction of benign from pathologic pneumatosis intestinalis cases and (2) the determination of patients who would benefit from an operation. The 3 models are (1) an imaging model based on radiomic features extracted from computed tomography scans, (2) a clinical model based on clinical variables, and (3) a combination model using both the imaging and clinical variables. RESULTS: The combination model achieves an area under the curve of 0.91 (confidence interval: 0.87-0.94) for task I and an area under the curve of 0.84 (confidence interval: 0.79-0.88) for task II. The combination model significantly (P < .05) outperforms the imaging model and the clinical model for both tasks. The imaging model achieves an area under the curve of 0.72 (confidence interval: 0.57-0.87) for task I and 0.68 (confidence interval: 0.61-0.74) for task II. The clinical model achieves an area under the curve of 0.87 (confidence interval: 0.83-0.91) for task I and 0.76 (confidence interval: 0.70-0.81) for task II. CONCLUSION: This study suggests that combined radiographic and clinical features can identify pathologic pneumatosis intestinalis and aid in patient selection for surgery. This tool may better inform the surgical decision-making process for patients with pneumatosis intestinalis.

Improved Understanding of Acute Incisional Hernia Incarceration: Implications for Addressing the Excess Mortality of Emergent Repair.

BACKGROUND: Incisional hernia develops in up to 20% of patients undergoing abdominal operations. We sought to identify characteristics associated with poor outcomes after acute incisional hernia incarceration. STUDY DESIGN: We performed a retrospective cohort study of adult patients with incisional hernias undergoing elective repair or with acute incarceration between 2010 and 2017. The primary end point was 30-day mortality. Logistic regression was used to determine adjusted odds associated with 30-day mortality. The American College of Surgeons Surgical Risk Calculator was used to estimate outcomes had these patients undergone elective repair. RESULTS: A total of 483 patients experienced acute incarceration; 30-day mortality was 9.52%. Increasing age (adjusted odds ratio 1.05; 95% CI, 1.02 to 1.08) and bowel resection (adjusted odds ratio 3.18; 95% CI, 1.45 to 6.95) were associated with mortality. Among those with acute incarceration, 231 patients (47.9%) had no documentation of an earlier surgical evaluation and 252 (52.2%) had been evaluated but had not undergone elective repair. Among patients 80 years and older, 30-day mortality after emergent repair was high (22.9%) compared with estimated 30-day mortality for elective repair (0.73%), based on the American College of Surgeons Surgical Risk Calculator. Estimated mortality was comparable with observed elective repair mortality (0.82%) in an age-matched cohort. Similar mortality trends were noted for patients younger than 60 years and aged 60 to 79 years. CONCLUSIONS: Comparison of predicted elective repair and observed emergent repair mortality in patients with acute incarceration suggests that acceptable outcomes could have been achieved with elective repair. Almost one-half of acute incarceration patients had no earlier surgical evaluation, therefore, targeted interventions to address surgical referral can potentially result in fewer incarceration-related deaths.