Search

Background: Intensive care unit (ICU) resources are inadequate for the large population in China, so it is essential for physicians to evaluate the condition of patients at admission. In this study, our objective was to construct a machine-learning risk prediction model for mortality in respiratory intensive care units (RICUs). Methods: This study involved 817 patients who made 1,063 visits and who were admitted to the RICU from 2012 to 2017. Potential predictors such as demographic information, laboratory results, vital signs and clinical characteristics were considered. We constructed eXtreme Gradient Boosting (XGBoost) models and compared performances with random forest models, logistic regression models and clinical scores such as Acute Physiology and Chronic Health Evaluation II (APACHE II) and the sequential organ failure assessment (SOFA) system. The model was externally validated using data from Medical Information Mart for Intensive Care (MIMIC-III) database. A web-based calculator was developed for practical use. Results: Among the 1,063 visits, the RICU mortality rate was 13.5%. The XGBoost model achieved the best performance with the area under the receiver operating characteristics curve (AUROC) of 0.860 (95% confidence interval (CI): 0.808 - 0.909) in the test set, which was significantly greater than APACHE II (0.749, 95% CI: 0.674 - 0.820; P = 0.015) and SOFA (0.751, 95% CI: 0.669 - 0.818; P = 0.018). The Hosmer-Lemeshow test indicated a good calibration of our predictive model in the test set with a P-value of 0.176. In the external validation dataset, the AUROC of XGBoost model was 0.779 (95% CI: 0.714 - 0.813). The final model contained variables that were previously known to be associated with mortality, but it also included some features absent from the clinical scores. The mean N-terminal pro-B-type natriuretic peptide (NTproBNP) of survivors was significantly lower than that of the non-survival group (2066.43 pg/mL vs. 8232.81 pg/mL; P < 0.001). Conclusions: Our results showed that the XGBoost model could be a suitable model for predicting RICU mortality with easy-to-collect variables at admission and help intensivists improve clinical decision-making for RICU patients. We found that higher NT-proBNP can be a good indicator of poor prognosis.

Retinal health indices were suggested to be related to psychopathological symptoms, such as depressive symptoms. However, large-scale studies using optical coherence tomography (OCT) are missing to investigate the associations among them.

Supplemental Digital Content is Available in the Text. An explainable artificial intelligence framework based on a deep learning method was developed for identifying multiple retinal lesions at image level and performing an explainable macular disease diagnosis at eye level in volumetric optical coherence tomography images. The performance of the integrated framework was evaluated and compared with human experts.

Background:Renal fibrosis is a key driver of progression in chronic kidney disease (CKD). Recent advances in diagnostic imaging techniques have shown promising results for the noninvasive assessment of renal fibrosis. However, the specificity and accuracy of these techniques are controversial because they indirectly assess renal fibrosis. This limits fibrosis assessment by imaging in CKD for clinical practice. To validate magnetic resonance imaging (MRI) assessment for fibrosis, we derived representative models by mapping histology-proven renal fibrosis and imaging in CKD. Methods:Ninety-seven adult Chinese CKD participants with histology were studied. The kidney cortex interstitial extracellular matrix volume was calculated by the Aperio ScanScope system using Masson’s trichrome slices. The kidney cortex microcirculation was quantitatively assessed by peritubular capillary density using CD34 staining. The imaging techniques included intravoxel incoherent motion diffusion-weighted imaging and magnetic resonance elastography (MRE) imaging. Relevant analyses were performed to evaluate the correlations between MRI parameters and histology variables. Multiple linear regression models were used to describe the relationships between a response variable and other variables. The best-fit lines, which minimize the sum of squared residuals of the multiple linear regression models, were generated. Results:MRE values were negatively associated with the interstitial extracellular matrix volume (Rho= −0.397, p< 0.001). The best mapping model of extracellular matrix volume with the MRE value and estimated glomerular filtration rate (eGFR) we obtained was as follows: Interstitial extracellular matrix volume = 218.504 – 14.651 × In(MRE) – 18.499 × In(eGFR). DWI-fraction values were positively associated with peritubular capillary density (Rho= 0.472, p< 0.001). The best mapping model of peritubular capillary density with DWI-fraction value and eGFR was as follows: Peritubular capillaries density = 17.914 + 9.403 × (DWI – fraction) + 0.112 × (eGFR). Conclusions:The study provides histological evidence to support that MRI can effectively evaluate fibrosis in the kidney. These findings picture the graphs of the mapping model from imaging and eGFR into fibrosis, which has significant value for clinical implementation.

Background:Artificial intelligence (AI) now plays a critical role in almost every area of our daily lives and academic disciplines due to the growth of computing power, advances in methods and techniques, and the explosion of the amount of data; medicine is not an exception. Rather than replacing clinicians, AI is augmenting the intelligence of clinicians in diagnosis, prognosis, and treatment decisions. Summary:Kidney disease is a substantial medical and public health burden globally, with both acute kidney injury and chronic kidney disease bringing about high morbidity and mortality as well as a huge economic burden. Even though the existing research and applied works have made certain contributions to more accurate prediction and better understanding of histologic pathology, there is a lot more work to be done and problems to solve. Key Messages:AI applications of diagnostics and prognostics for high-prevalence and high-morbidity types of nephropathy in medical-resource-inadequate areas need special attention; high-volume and high-quality data need to be collected and prepared; a consensus on ethics and safety in the use of AI technologies needs to be built.

Background: Prediction of bleeding is critical for acute myocardial infarction (AMI) patients after percutaneous coronary intervention (PCI). Machine learning methods can automatically select the combination of the important features and learn their underlying relationship with the outcome.Objectives: We aimed to evaluate the predictive value of machine learning methods to predict in-hospital bleeding for AMI patients.Design: We used data from the multicenter China Acute Myocardial Infarction (CAMI) registry. The cohort was randomly partitioned into derivation set (50%) and validation set (50%). We applied a state-of-art machine learning algorithm, eXtreme Gradient Boosting (XGBoost), to automatically select features from 98 candidate variables and developed a risk prediction model to predict in-hospital bleeding (Bleeding Academic Research Consortium [BARC] 3 or 5 definition).Results: A total of 16,736 AMI patients who underwent PCI were finally enrolled. 45 features were automatically selected and were used to construct the prediction model. The developed XGBoost model showed ideal prediction results. The area under the receiver-operating characteristic curve (AUROC) on the derivation data set was 0.941 (95% CI = 0.909–0.973, p< 0.001); the AUROC on the validation set was 0.837 (95% CI = 0.772–0.903, p< 0.001), which was better than the CRUSADE score (AUROC: 0.741; 95% CI = 0.654–0.828, p< 0.001) and ACUITY-HORIZONS score (AUROC: 0.731; 95% CI = 0.641–0.820, p< 0.001). We also developed an online calculator with 12 most important variables (http://101.89.95.81:8260/), and AUROC still reached 0.809 on the validation set.Conclusion: For the first time, we developed the CAMI bleeding model using machine learning methods for AMI patients after PCI.Trial registration: NCT01874691. Registered 11 Jun 2013.

Importance of the field:To optimize drug development processes, pharmaceutical companies require principled approaches to integrate disparate data on a unified infrastructure, such as the web. The semantic web, developed on the web technology, provides a common, open framework capable of harmonizing diversified resources to enable networked and collaborative drug discovery.Areas covered in this review:We survey the state of art of utilizing web ontologies and other semantic web technologies to interlink both data and people to support integrated drug discovery across domains and multiple disciplines. Particularly, the survey covers three major application categories including: i) semantic integration and open data linking; ii) semantic web service and scientific collaboration and iii) semantic data mining and integrative network analysis.What the reader will gain:The reader will gain: i) basic knowledge of the semantic web technologies; ii) an overview of the web ontology landscape for drug discovery and iii) a basic understanding of the values and benefits of utilizing the web ontologies in drug discovery.Take home message:i) The semantic web enables a network effect for linking open data for integrated drug discovery; ii) The semantic web service technology can support instant ad hoccollaboration to improve pipeline productivity and iii) The semantic web encourages publishing data in a semantic way such as resource description framework attributes and thus helps move away from a reliance on pure textual content analysis toward more efficient semantic data mining.