scholarly journals Radiologists can visually predict mortality risk based on the gestalt of chest radiographs comparable to a deep learning network

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Jakob Weiss ◽  
Jana Taron ◽  
Zexi Jin ◽  
Thomas Mayrhofer ◽  
Hugo J. W. L. Aerts ◽  
...  
Keyword(s):  
Deep Learning ◽  
Chest Radiograph ◽  
Patient Characteristics ◽  
Mortality Prediction ◽  
Chest Radiographs ◽  
Prognostic Accuracy ◽  
Testing Dataset ◽  
Clinical Benefits ◽  
Traditional Risk Factors ◽  
Deep Learning Network

AbstractDeep learning convolutional neural network (CNN) can predict mortality from chest radiographs, yet, it is unknown whether radiologists can perform the same task. Here, we investigate whether radiologists can visually assess image gestalt (defined as deviation from an unremarkable chest radiograph associated with the likelihood of 6-year mortality) of a chest radiograph to predict 6-year mortality. The assessment was validated in an independent testing dataset and compared to the performance of a CNN developed for mortality prediction. Results are reported for the testing dataset only (n = 100; age 62.5 ± 5.2; male 55%, event rate 50%). The probability of 6-year mortality based on image gestalt had high accuracy (AUC: 0.68 (95% CI 0.58–0.78), similar to that of the CNN (AUC: 0.67 (95% CI 0.57–0.77); p = 0.90). Patients with high/very high image gestalt ratings were significantly more likely to die when compared to those rated as very low (p ≤ 0.04). Assignment to risk categories was not explained by patient characteristics or traditional risk factors and imaging findings (p ≥ 0.2). In conclusion, assessing image gestalt on chest radiographs by radiologists renders high prognostic accuracy for the probability of mortality, similar to that of a specifically trained CNN. Further studies are warranted to confirm this concept and to determine potential clinical benefits.

scholarly journals Interpretable time-aware and co-occurrence-aware network for medical prediction

2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Chenxi Sun ◽  
Hongna Dui ◽  
Hongyan Li
Keyword(s):  
Deep Learning ◽  
Data Structure ◽  
Mortality Prediction ◽  
Disease Prediction ◽  
Medical Structure ◽  
Deep Learning Network ◽  
Future Work ◽  
Gated Recurrent Unit ◽  
Novel Model ◽  
Time Aware

Abstract Background Disease prediction based on electronic health records (EHRs) is essential for personalized healthcare. But it’s hard due to the special data structure and the interpretability requirement of methods. The structure of EHR is hierarchical: each patient has a sequence of admissions, and each admission has some co-occurrence diagnoses. However, the existing methods only partially model these characteristics and lack the interpretation for non-specialists. Methods This work proposes a time-aware and co-occurrence-aware deep learning network (TCoN), which is not only suitable for EHR data structure but also interpretable: the co-occurrence-aware self-attention (CS-attention) mechanism and time-aware gated recurrent unit (T-GRU) can model multilevel relations; the interpretation path and the diagnosis graph can make the result interpretable. Results The method is tested on a real-world dataset for mortality prediction, readmission prediction, disease prediction, and next diagnoses prediction. Experimental results show that TCoN is better than baselines with 2.01% higher accuracy. Meanwhile, the method can give the interpretation of causal relationships and the diagnosis graph of each patient. Conclusions This work proposes a novel model—TCoN. It is an interpretable and effective deep learning method, that can model the hierarchical medical structure and predict medical events. The experiments show that it outperforms all state-of-the-art methods. Future work can apply the graph embedding technology based on more knowledge data such as doctor notes.

COVID-19 pneumonia diagnosis using a simple 2D deep learning framework with a single chest CT image (Preprint)

2020 ◽  
Author(s):  
Jinseok Lee
Keyword(s):  
Deep Learning ◽  
Diagnostic Performance ◽  
Ct Images ◽  
Chest Ct ◽  
University Hospital ◽  
Detection Accuracy ◽  
Ct Image ◽  
Test Dataset ◽  
Learning Framework ◽  
Testing Dataset

BACKGROUND The coronavirus disease (COVID-19) has explosively spread worldwide since the beginning of 2020. According to a multinational consensus statement from the Fleischner Society, computed tomography (CT) can be used as a relevant screening tool owing to its higher sensitivity for detecting early pneumonic changes. However, physicians are extremely busy fighting COVID-19 in this era of worldwide crisis. Thus, it is crucial to accelerate the development of an artificial intelligence (AI) diagnostic tool to support physicians. OBJECTIVE We aimed to quickly develop an AI technique to diagnose COVID-19 pneumonia and differentiate it from non-COVID pneumonia and non-pneumonia diseases on CT. METHODS A simple 2D deep learning framework, named fast-track COVID-19 classification network (FCONet), was developed to diagnose COVID-19 pneumonia based on a single chest CT image. FCONet was developed by transfer learning, using one of the four state-of-art pre-trained deep learning models (VGG16, ResNet50, InceptionV3, or Xception) as a backbone. For training and testing of FCONet, we collected 3,993 chest CT images of patients with COVID-19 pneumonia, other pneumonia, and non-pneumonia diseases from Wonkwang University Hospital, Chonnam National University Hospital, and the Italian Society of Medical and Interventional Radiology public database. These CT images were split into a training and a testing set at a ratio of 8:2. For the test dataset, the diagnostic performance to diagnose COVID-19 pneumonia was compared among the four pre-trained FCONet models. In addition, we tested the FCONet models on an additional external testing dataset extracted from the embedded low-quality chest CT images of COVID-19 pneumonia in recently published papers. RESULTS Of the four pre-trained models of FCONet, the ResNet50 showed excellent diagnostic performance (sensitivity 99.58%, specificity 100%, and accuracy 99.87%) and outperformed the other three pre-trained models in testing dataset. In additional external test dataset using low-quality CT images, the detection accuracy of the ResNet50 model was the highest (96.97%), followed by Xception, InceptionV3, and VGG16 (90.71%, 89.38%, and 87.12%, respectively). CONCLUSIONS The FCONet, a simple 2D deep learning framework based on a single chest CT image, provides excellent diagnostic performance in detecting COVID-19 pneumonia. Based on our testing dataset, the ResNet50-based FCONet might be the best model, as it outperformed other FCONet models based on VGG16, Xception, and InceptionV3.

scholarly journals UAVs in rail damage image diagnostics supported by deep-learning networks

2021 ◽  
Vol 11 (1) ◽  
pp. 339-348
Author(s):  
Piotr Bojarczak ◽  
Piotr Lesiak
Keyword(s):  
Deep Learning ◽  
Head Width ◽  
Learning Networks ◽  
Image Brightness ◽  
Learning Network ◽  
Rail Head ◽  
Image Recording ◽  
Python Language ◽  
Deep Learning Network ◽  
Efficiency Rate

Abstract The article uses images from Unmanned Aerial Vehicles (UAVs) for rail diagnostics. The main advantage of such a solution compared to traditional surveys performed with measuring vehicles is the elimination of decreased train traffic. The authors, in the study, limited themselves to the diagnosis of hazardous split defects in rails. An algorithm has been proposed to detect them with an efficiency rate of about 81% for defects not less than 6.9% of the rail head width. It uses the FCN-8 deep-learning network, implemented in the Tensorflow environment, to extract the rail head by image segmentation. Using this type of network for segmentation increases the resistance of the algorithm to changes in the recorded rail image brightness. This is of fundamental importance in the case of variable conditions for image recording by UAVs. The detection of these defects in the rail head is performed using an algorithm in the Python language and the OpenCV library. To locate the defect, it uses the contour of a separate rail head together with a rectangle circumscribed around it. The use of UAVs together with artificial intelligence to detect split defects is an important element of novelty presented in this work.

scholarly journals Real-World Outcomes of Ivacaftor Treatment in People with Cystic Fibrosis: A Systematic Review

2021 ◽  
Vol 10 (7) ◽  
pp. 1527
Author(s):  
Jamie Duckers ◽  
Beth Lesher ◽  
Teja Thorat ◽  
Eleanor Lucas ◽  
Lisa J. McGarry ◽  
...  
Keyword(s):  
Systematic Review ◽  
Cystic Fibrosis ◽  
Real World ◽  
Safety Profile ◽  
Clinical Trial Data ◽  
Patient Characteristics ◽  
Healthcare Resource Utilization ◽  
Patient Reported ◽  
Clinical Benefits

Cystic fibrosis (CF) is a rare, progressive, multi-organ genetic disease. Ivacaftor, a small-molecule CF transmembrane conductance regulator modulator, was the first medication to treat the underlying cause of CF. Since its approval, real-world clinical experience on the use of ivacaftor has been documented in large registries and smaller studies. Here, we systematically review data from real-world observational studies of ivacaftor treatment in people with CF (pwCF). Searches of MEDLINE and Embase identified 368 publications reporting real-world studies that enrolled six or more pwCF treated with ivacaftor published between January 2012 and September 2019. Overall, 75 publications providing data from 57 unique studies met inclusion criteria and were reviewed. Studies reporting within-group change for pwCF treated with ivacaftor consistently showed improvements in lung function, nutritional parameters, and patient-reported respiratory and sino-nasal symptoms. Benefits were evident as early as 1 month following ivacaftor initiation and were sustained over long-term follow-up. Decreases in pulmonary exacerbations, Pseudomonas aeruginosa prevalence, and healthcare resource utilization also were reported for up to 66 months following ivacaftor initiation. In studies comparing ivacaftor treatment to modulator untreated comparator groups, clinical benefits similarly were reported as were decreases in mortality, organ-transplantation, and CF-related complications. The safety profile of ivacaftor observed in these real-world studies was consistent with the well-established safety profile based on clinical trial data. Our systematic review of real-world studies shows ivacaftor treatment in pwCF results in highly consistent and sustained clinical benefit in both pulmonary and non-pulmonary outcomes across various geographies, study designs, patient characteristics, and follow-up durations, confirming and expanding upon evidence from clinical trials.

scholarly journals Prognostic biomarkers in predicting mortality in respiratory patients with ventilator-associated pneumonia

2021 ◽  
Vol 15 (1) ◽  
Author(s):  
Nermeen A. Abdelaleem ◽  
Hoda A. Makhlouf ◽  
Eman M. Nagiub ◽  
Hassan A. Bayoumi
Keyword(s):  
Sofa Score ◽  
Diagnostic Performance ◽  
Mortality Prediction ◽  
Ventilator Associated Pneumonia ◽  
Distribution Width ◽  
Mechanically Ventilated ◽  
Neutrophil Lymphocyte Ratio ◽  
Prognostic Accuracy ◽  
Severity Scores ◽  
Critical Patients

Abstract Background Ventilator-associated pneumonia (VAP) is the most common nosocomial infection. Red cell distribution width (RDW) and neutrophil-lymphocyte ratio (NLR) are prognostic factors to mortality in different diseases. The aim of this study is to evaluate prognostic efficiency RDW, NLR, and the Sequential Organ Failure Assessment (SOFA) score for mortality prediction in respiratory patients with VAP. Results One hundred thirty-six patients mechanically ventilated and developed VAP were included. Clinical characteristics and SOFA score on the day of admission and at diagnosis of VAP, RDW, and NLR were assessed and correlated to mortality. The average age of patients was 58.80 ± 10.53. These variables had a good diagnostic performance for mortality prediction AUC 0.811 for SOFA at diagnosis of VAP, 0.777 for RDW, 0.728 for NLR, and 0.840 for combined of NLR and RDW. The combination of the three parameters demonstrated excellent diagnostic performance (AUC 0.889). A positive correlation was found between SOFA at diagnosis of VAP and RDW (r = 0.446, P < 0.000) and with NLR (r = 0.220, P < 0.010). Conclusions NLR and RDW are non-specific inflammatory markers that could be calculated quickly and easily via routine hemogram examination. These markers have comparable prognostic accuracy to severity scores. Consequently, RDW and NLR are simple, yet promising markers for ICU physicians in monitoring the clinical course, assessment of organ dysfunction, and predicting mortality in mechanically ventilated patients. Therefore, this study recommends the use of blood biomarkers with the one of the simplest ICU score (SOFA score) in the rapid diagnosis of critical patients as a daily works in ICU.

Sign in / Sign up

Export Citation Format

Share Document