No abstract

No abstract

No abstract

S pontaneous intracerebral hemorrhage (ICH) accounts for 10% to 15% of all strokes and is one of the leading causes of stroke-related mortality and morbidity worldwide. Patients with ICH are generally at risk of developing stroke-associated pneumonia (SAP) during acute hospitalization. Evidence has shown that SAP not only increases the length of hospital stay (LOS) and medical cost 1,2 but also is an important risk factor of mortality and morbidity after acute stroke. 3,4 Several risk factors for SAP have been identified, such as older age, 4-12 male sex, 5,6,10,11,13 current smoking, 12 diabetes mellitus, 6 hypertension, 14 atrial fibrillation, 7,10,12 congestive heart failure, 7,12,13,15 chronic obstructive pulmonary disease, 8,[12][13][14] preexisting dependency, 8,12,13,16 stroke severity, 5,6,8,12,17,18 dysphagia, [8][9][10][11][12]14,[18][19][20] and blood glucose. 12 Meanwhile, based on these risk factors, a few risk models have been developed for SAP after acute ischemic stroke. [8][9][10][11][12] Currently, no valid scoring system is available for predicting SAP after ICH in routine clinical practice or clinical trial. We hypothesized that there might be some common grounds for the development of pneumonia after acute ischemic stroke and ICH, and those predictors for SAP after acute ischemic stroke might also be useful for predicting SAP after ICH. For clinical practice, an effective risk-stratification and prognostic model for SAP after ICH would be helpful to identify vulnerable patients, allocate relevant medical resources, and implement tailored preventive strategies. In addition, for clinical trial, it could be used in nonrandomized studies to control for case-mix variation and in controlled studies as a selection criterion.Background and Purpose-We aimed to develop a risk score (intracerebral hemorrhage-associated pneumonia score, ICH-APS) for predicting hospital-acquired stroke-associated pneumonia (SAP) after ICH. Methods-The ICH-APS was developed based on the China National Stroke Registry (CNSR), in which eligible patients were randomly divided into derivation (60%) and validation (40%) cohorts. Variables routinely collected at presentation were used for predicting SAP after ICH. For testing the added value of hematoma volume measure, we separately developed 2 models with (ICH-APS-B) and without (ICH-APS-A) hematoma volume included. Multivariable logistic regression was performed to identify independent predictors. The area under the receiver operating characteristic curve (AUROC), Hosmer-Lemeshow goodness-of-fit test, and integrated discrimination index were used to assess model discrimination, calibration, and reclassification, respectively. Results-The SAP was 16.4% and 17.7% in the overall derivation (n=2998) and validation (n=2000) cohorts, respectively.A 23-point ICH-APS-A was developed based on a set of predictors and showed good discrimination in the overall derivation (AUROC, 0.75; 95% confidence interval, 0. Ji et al Risk Score to Predict SAP After ICH 2621In the study, we aimed to ...

Background: Due to different treatment method and prognosis of different subtypes of lung adenocarcinomas appearing as ground-glass nodules (GGNs) on computed tomography (CT) scan, it is important to classify invasive adenocarcinomas from non-invasive adenocarcinomas. The purpose of this paper is to build and evaluate the performance of deep learning networks on the differentiation the invasiveness of lung adenocarcinoma appearing as GGNs. Methods: This retrospective study included 886 GGNs from 794 pathological confirmed patients with lung adenocarcinoma for training and testing the proposed networks. Three deep learning networks, namely XimaNet (deep learning-based classification model), XimaSharp (classification and nodule segmentation model), and Deep-RadNet (deep learning and radiomics combined classification model, i.e., deep radiomics) were built. Three classification tasks, namely task 1: classification of AAH/AIS and MIA, task 2: classification of MIA and IAC, and task 3: classification of non-invasive adenocarcinomas and invasive adenocarcinomas (AAH/AIS&MIA and IAC) were conducted to evaluate the model performance. The Z-test was used to compare the model performance. Results: The AUC for classification of AAH/AIS with MIA were 0.891, 0.841 and 0.779 for Deep-RadNet, XimaNet and XimaSharp respectively. The AUC for classification of MIA with IAC were 0.889, 0.785 and 0.778 for three networks and AUC for classification of AAH/AIS&MIA with IAC were 0.941, 0.892 and 0.827 respectively. The performance of deep_RadNet was better than the other two models with the Z-test (P<0.05). Conclusions: Deep-RadNet with the visual heat map could evaluate the invasiveness of GGNs accurately and intuitively, providing a theoretical basis for individualized and accurate medical treatment of patients with GGNs.