Early post-traumatic pulmonary embolism in intensive care unit: incidence, risks factors, and impact outcome.

BACKGROUND: Venous thromboembolism (VTE) is a well-established complication of trauma. Recent studies suggest that pulmonary embolism (PE) may occur very early, and even immediately, after injury. The aim of this study is to analyze the incidence, risk factors and prognosis of early PE among ICU trauma patients. PATIENTS AND METHODS: We conducted a twenty-month-long prospective cohort study, including all trauma patients with a confirmed PE diagnosis admitted to our ICU between January 1st, 2017 and August 31st, 2018. Early post traumatic PE was defined as pulmonary embolism diagnosed within the first 72 hrs of injury. All the patients who were included were systematically screened for early PE on day 3. RESULTS: During the study period, 365 trauma patients were admitted. The diagnosis of post-traumatic PE was confirmed in 66 patients (18%). In our study, 27 patients (41.5%) developed a PE within 72 hrs of trauma. According to our analysis, the factors associated with the development of early post-traumatic PE in multivariate analysis were obesity (P=0.049; OR=4.04), high SOFA score (P=0.003; OR=1.67), and the use of surgical procedures (P=0.033; OR=4.87). Furthermore, sepsis and ventilator-acquired pneumonia were associated with late PE (P=0.019; OR=5.87). Overall, the mortality rate was at 19.7%. Yet, the patients who were diagnosed with early PE had a higher mortality rate compared to the late PE group (33% vs. 10.2%, respectively). We found that the only independent predictive factor of mortality among the patients with early post-traumatic PE included in this study was the APACHEII score on ICU admission (P=0.011; OR=1.44). CONCLUSION: Our study cohort showed that many of the post-traumatic PEs occur early in the post-traumatic period. To the best of our knowledge, this is the first prospective study conducted in an ICU to apply a systematic screening protocol for post-traumatic PE diagnosis. Further studies with larger patient populations are required to create more accurate predictive models.

Intraoperative margin assessment of human breast tissue in optical coherence tomography images using deep neural networks.

Assessing the surgical margin during breast lumpectomy operations can avoid the need for additional surgery. Optical coherence tomography (OCT) is an imaging technique that has been proven to be efficient for this purpose. However, to avoid overloading the surgeon during the operation, automatic cancer detection at the surface of the removed tissue is needed. This work explores automated margin assessment on a sample of patient data collected at the Pathology Department, Severance Hospital (Seoul, South Korea). Some methods based on the spatial statistics of the images have been developed, but the obtained results are still far from human performance. In this work, we investigate the possibility to use deep neural networks (DNNs) for real time margin assessment, demonstrating performance significantly better than the reported literature and close to the level of a human expert. Since the goal is to detect the presence of cancer, a patch-based classification method is proposed, as it is sufficient for detection, and requires training data that is easier and cheaper to collect than for other approaches such as segmentation. For that purpose, we train a DNN architecture that was proved to be efficient for small images on patches extracted from images containing only cancer or only normal tissue as determined by pathologists in a university hospital. As the number of available images in all such studies is by necessity small relative to other deep network applications such as ImageNet, a good regularization method is needed. In this work, we propose to use a recently introduced function norm regularization that attempts to directly control the function complexity, in contrast to classical approaches such as weight decay and DropOut. As neither the code nor the data of previous results are publicly available, the obtained results are compared with reported results in the literature for a conservative comparison. Moreover, our method is applied to locally collected data on several data configurations. The reported results are the average over the different trials. The experimental results show that the use of DNNs yields significantly better results than other techniques when evaluated in terms of sensitivity, specificity, F1 score, G-mean and Matthews correlation coefficient. Function norm regularization yielded higher and more robust results than competing regularization methods. We have demonstrated a system that shows high promise for (partially) automated margin assessment of human breast tissue, Equal error rate (EER) is reduced from approximately 12% (the lowest reported in the literature) to 5% - a 58% reduction. The method is computationally feasible for intraoperative application (less than 2 s per image) at the only cost of a longer offline training time.