Skip to main content
 
Notice: Users may be experiencing issues with displaying some pages on stanfordhealthcare.org. We are working closely with our technical teams to resolve the issue as quickly as possible. Thank you for your patience.
 

See our updated masking policy »

Stanford Health Care

Scalable Deep Learning Algorithm to Compute Percent Pulmonary Contusion among Patients with Rib Fractures. The journal of trauma and acute care surgery Choi, J., Mavrommati, K., Li, N. Y., Patil, A., Chan, K., Hindin, D. I., Forrester, J. D. 2022

Abstract

Pulmonary contusion exists along a spectrum of severity, yet is commonly binarily classified as present or absent. We aimed to develop a deep learning algorithm to automate percent pulmonary contusion computation and exemplify how transfer learning could facilitate large-scale validation. We hypothesized our deep learning algorithm could automate percent pulmonary contusion computation and that greater percent contusion would be associated with higher odds of adverse inpatient outcomes among patients with rib fractures.We evaluated admission-day chest computed tomography (CT) scans of adults aged =18 years admitted to our institution with multiple rib fractures and pulmonary contusions (2010-2020). We adapted a pre-trained convolutional neural network that segments 3-dimensional lung volumes and segmented contused lung parenchyma, pulmonary blood vessels, and computed percent pulmonary contusion. Exploratory analysis evaluated associations between percent pulmonary contusion (quartiles) and odds of mechanical ventilation, mortality, and prolonged hospital length-of-stay using multivariable logistic regression. Sensitivity analysis included pulmonary blood vessel volumes during percent contusion computation.A total of 332 patients met inclusion criteria (median 5 rib fractures), among whom 28% underwent mechanical ventilation and 6% died. The study population's median (IQR) percent pulmonary contusion was 4(2-8)%. Compared to the lowest quartile of percent pulmonary contusion, each increasing quartile was associated with higher adjusted odds of undergoing mechanical ventilation (OR[95%CI]: 1.5[1.1-2.1]) and prolonged hospitalization (OR[95%CI]: 1.6[1.1-2.2]), but not with mortality (OR[95%CI]: 1.1 [0.6-2.0]. Findings were similar on sensitivity analysis.We developed a scalable deep learning algorithm to automate percent pulmonary contusion calculating using chest CTs of adults admitted with rib fractures. Open code sharing and collaborative research is needed to validate our algorithm and exploratory analysis at large scale. Transfer learning can help harness the full potential of big data and high-performing algorithms to bring precision medicine to the bedside.IV.

View details for DOI 10.1097/TA.0000000000003619

View details for PubMedID 35319542