Diagnostic algorithm for glioma grading using dynamic susceptibility contrast­enhanced magnetic resonance perfusion and proton magnetic resonance spectroscopy.

The present retrospective study aimed to investigate the diagnostic capacity of and design a diagnostic algorithm for dynamic susceptibility contrast-enhanced MRI (DSCE-MRI) and proton magnetic resonance spectroscopy (1H-MRS) in grading low-grade glioma (LGG) and high-grade glioma (HGG). This retrospective study enrolled 57 patients, of which 14 had LGG and 43 had HGG, five had World Health Organization grade 1, nine had grade 2, 20 had grade 3 and 23 had grade 4 glioma. All subjects underwent a standard 3T MRI brain tumor protocol with conventional MRI (cMRI) and advanced techniques, including DSCE-MRI and 1H-MRS. The associations of grade categorization with parameters in tumor and peritumor regions in the DSCE-MRI were examined, including tumor relative cerebral blood volume (TrCBV) and peripheral relative (Pr)CBV, as well as Tr and Pr cerebral blood flow (CBF) and 1H-MRS, including the creatine (Cr) and N-acetyl aspartate (NAA) ratios of choline (Cho), i.e. the TCho/NAA, PCho/NAA, TCho/Cr and PCho/Cr metabolite ratios. The data were compared using the Mann-Whitney U-test, independent samples t-test, Chi-square test, Fisher's exact test and receiver operating characteristic curve analyses. Decision tree analysis established an algorithm based on cutoffs for specified significant parameters. The PrCBF had the highest performance in the preoperative prediction of histological glioma grading, followed by the TrCBV, PrCBF, TrCBV, PCho/NAA, PCho/Cr, TCho/NAA and TCho/Cr. An algorithm based on TrCBV, PrCBF and TCho/Cr had a diagnostic accuracy of 100% for LGG and 90.7% for HGG and a misclassification risk of 7%. The cutoffs (sensitivity and specificity) were 2.48 (86 and 100%) for TrCBV, 1.26 (83.7 and 100%) for PrCBF and 3.18 (69.8 and 78.6%) for TCho/Cr. In conclusion, the diagnostic algorithm using TrCBV, PrCBF and TCho/Cr values, which were obtained from DSCE-MRI and 1H-MRS, increased diagnostic accuracy to 100% for LGGs and 90.7% for HGGs compared to previous studies using conventional MRI. This non-invasive advanced MRI diagnostic algorithm is recommended for clinical application for constructing preoperative strategies and prognosis of patients with glioma.

Adaptation of Autoencoder for Sparsity Reduction From Clinical Notes Representation Learning.

When dealing with clinical text classification on a small dataset, recent studies have confirmed that a well-tuned multilayer perceptron outperforms other generative classifiers, including deep learning ones. To increase the performance of the neural network classifier, feature selection for the learning representation can effectively be used. However, most feature selection methods only estimate the degree of linear dependency between variables and select the best features based on univariate statistical tests. Furthermore, the sparsity of the feature space involved in the learning representation is ignored. GOAL: Our aim is, therefore, to access an alternative approach to tackle the sparsity by compressing the clinical representation feature space, where limited French clinical notes can also be dealt with effectively. METHODS: This study proposed an autoencoder learning algorithm to take advantage of sparsity reduction in clinical note representation. The motivation was to determine how to compress sparse, high-dimensional data by reducing the dimension of the clinical note representation feature space. The classification performance of the classifiers was then evaluated in the trained and compressed feature space. RESULTS: The proposed approach provided overall performance gains of up to 3% for each test set evaluation. Finally, the classifier achieved 92% accuracy, 91% recall, 91% precision, and 91% f1-score in detecting the patient's condition. Furthermore, the compression working mechanism and the autoencoder prediction process were demonstrated by applying the theoretic information bottleneck framework. Clinical and Translational Impact Statement- An autoencoder learning algorithm effectively tackles the problem of sparsity in the representation feature space from a small clinical narrative dataset. Significantly, it can learn the best representation of the training data because of its lossless compression capacity compared to other approaches. Consequently, its downstream classification ability can be significantly improved, which cannot be done using deep learning models.

Splenic Artery Embolization in Conservative Management of Blunt Splenic Injury Graded by 2018 AAST-OIS: Results from a Hospital in Vietnam.

Purpose: This study was conducted to evaluate the results of conservative management of blunt splenic trauma according to the American Association for the Surgery of Trauma-Organ Injury Scale (AAST-OIS) in 2018 by embolization. Methods: This observational study included 50 patients (42 men and 8 women) with splenic injury who underwent multidetector computed tomography (MDCT) and embolization. Results: According to the 2018 AAST-OIS, 27 cases had higher grades than they did according to the 1994 AAST-OIS. The grades of two cases of grade II increased to grade IV; those of 15 cases of grade III increased to grade IV; and four cases of grade IV increased to grade V. As a result, all patients underwent successful splenic embolization and were stable at discharge. No patients required re-embolization or conversion to splenectomy. The mean hospital stay was 11.8±7 days (range, 6-44 days), with no difference in length of hospital stay among grades of splenic injury (p >0.05). Conclusion: Compared with the AAST-OIS 1994, the AAST-OIS 2018 classification is useful in making embolization decisions, regardless of the degree of blunt splenic injury with vascular lacerations visible on MDCT.

Detecting of a Patient's Condition From Clinical Narratives Using Natural Language Representation.

The rapid progress in clinical data management systems and artificial intelligence approaches enable the era of personalized medicine. Intensive care units (ICUs) are ideal clinical research environments for such development because they collect many clinical data and are highly computerized. Goal: We designed a retrospective clinical study on a prospective ICU database using clinical natural language to help in the early diagnosis of heart failure in critically ill children. Methods: The methodology consisted of empirical experiments of a learning algorithm to learn the hidden interpretation and presentation of the French clinical note data. This study included 1386 patients' clinical notes with 5444 single lines of notes. There were 1941 positive cases (36% of total) and 3503 negative cases classified by two independent physicians using a standardized approach. Results: The multilayer perceptron neural network outperforms other discriminative and generative classifiers. Consequently, the proposed framework yields an overall classification performance with 89% accuracy, 88% recall, and 89% precision. Conclusions: This study successfully applied learning representation and machine learning algorithms to detect heart failure in a single French institution from clinical natural language. Further work is needed to use the same methodology in other languages and institutions.

Percutaneous balloon-assisted ultrasound-guided direct glue embolization of deep femoral artery pseudoaneurysm rupture.

Deep femoral artery pseudoaneurysm is commonly caused by arterial access in endovascular procedures. Some therapeutic options have been applied for this lesion such as: surgery, ultrasound-guided compression, direct thrombin injection, covered stent, coil embolization. One of the effective therapeutic for treatment of femoral artery pseudoaneurysm but uncommon use is percutaneous direct glue injection. We hereby report a case of right deep femoral artery pseudoaneurysm after 2-week placement of the femoral tunneled hemodialysis catheter which was successfully treated by balloon-assisted percutaneous ultrasound-guided direct glue embolization.

Pneumatosis intestinalis with pneumoperitoneum: Not always a surgical emergency.

Pneumatosis intestinalis (PI) and pneumoperitoneum are commonly recognized as severe signs of gastrointestinal diseases that require emergency surgery. However, these symptoms can also be caused by benign conditions. We describe 4 cases of benign PI and pneumoperitoneum that were detected in different clinical situations (accidental discovery in bilan of aortic dissection (case #1), bilateral pulmonary embolism (case #2), overflow diarrhea due to fecal impaction (case #3), and in follow-up postbiliary digestive anastomosis surgery (case #4), which were addressed with exploratory surgery (case #1) or conservative treatment (the remaining cases), with favorable outcomes. Because PI and pneumoperitoneum can be associated with both life-threatening causes and benign conditions, treatment decisions should be based on the correspondence between clinical and paraclinical features, rather than imaging alone.