Machine learning for prediction of acute kidney injury in patients diagnosed with sepsis in critical care.

BACKGROUND AND OBJECTIVE: Acute Kidney Injury (AKI) is a common and severe complication in patients diagnosed with sepsis. It is associated with higher mortality rates, prolonged hospital stays, increased utilization of medical resources, and financial burden on patients' families. This study aimed to establish and validate predictive models using machine learning algorithms to accurately predict the occurrence of AKI in patients diagnosed with sepsis. METHODS: This retrospective study utilized real observational data from the Medical Information Mart for Intensive Care IV (MIMIC-IV) database. It included patients aged 18 to 90 years diagnosed with sepsis who were admitted to the ICU for the first time and had hospital stays exceeding 48 hours. Predictive models, employing various machine learning algorithms including Light Gradient Boosting Machine (LightGBM), EXtreme Gradient Boosting (XGBoost), Random Forest (RF), Decision Tree (DT), Artificial Neural Network (ANN), Support Vector Machine (SVM), and Logistic Regression (LR), were developed. The dataset was randomly divided into training and test sets at a ratio of 4:1. RESULTS: A total of 10,575 sepsis patients were included in the analysis, of whom 8,575 (81.1%) developed AKI during hospitalization. A selection of 47 variables was utilized for model construction. The models derived from LightGBM, XGBoost, RF, DT, ANN, SVM, and LR achieved AUCs of 0.801, 0.773, 0.772, 0.737, 0.720, 0.765, and 0.776, respectively. Among these models, LightGBM demonstrated the most superior predictive performance. CONCLUSIONS: These machine learning models offer valuable predictive capabilities for identifying AKI in patients diagnosed with sepsis. The LightGBM model, with its superior predictive capability, could aid clinicians in early identification of high-risk patients.

Multi-omics characterization of RNA binding proteins reveals disease comorbidities and potential drugs in COVID-19.

The COVID-19 has led to a devastating global health crisis, which emphasizes the urgent need to deepen our understanding of the molecular mechanism and identifying potential antiviral drugs. Here, we comprehensively analyzed the transcriptomic and proteomic profiles of 178 COVID-19 patients, ranging from asymptomatic to critically ill. Our analyses found that the RNA binding proteins (RBPs) were likely to be perturbed in infection. Interactome analysis revealed that RBPs interact with virus proteins and the viral interacting RBPs were likely to locate in central regions of human protein-protein interaction network. Functional enrichment analysis revealed that the viral interacting RBPs were likely to be enriched in RNA transport, apoptosis and viral genome replication-related pathways. Based on network proximity analyses of 299 human complex-disease genes and COVID-19-related RBPs in the human interactome, we revealed the significant associations between complex diseases and COVID-19. Network analysis also implicated potential antiviral drugs for treatment of COVID-19. In summary, our integrative characterization of COVID-19 patients may thus help providing evidence regarding pathophysiology and potential therapeutic strategies for COVID-19.

HCDT: an integrated highly confident drug-target resource.

Drug-target association plays an important role in drug discovery, drug repositioning, drug synergy prediction, etc. Currently, a lot of drug-related databases, such as DrugBank and BindingDB, have emerged. However, these databases are separate, incomplete and non-uniform with different criteria. Here, we integrated eight drug-related databases; collected, filtered and supplemented drugs, target genes and experimentally validated (highly confident) associations and built a highly confident drug-target (HCDT: http://hainmu-biobigdata.com/hcdt) database. HCDT database includes 500 681 HCDT associations between 299 458 drugs and 5618 target genes. Compared to individual databases, HCDT database contains 1.1 to 254.2 times drugs, 1.8-5.5 times target genes and 1.4-27.7 times drug-target associations. It is normative, publicly available and easy for searching, browsing and downloading. Together with multi-omics data, it will be a good resource in analyzing the drug functional mechanism, mining drug-related biological pathways, predicting drug synergy, etc. Database URL: http://hainmu-biobigdata.com/hcdt.

A Clinical Decision Support Framework for Heterogeneous Data Sources.

To keep pace with the developments in medical informatics, health medical data is being collected continually. But, owing to the diversity of its categories and sources, medical data has become so complicated in many hospitals that it now needs a clinical decision support (CDS) system for its management. To effectively utilize the accumulating health data, we propose a CDS framework that can integrate heterogeneous health data from different sources such as laboratory test results, basic information of patients, and health records into a consolidated representation of features of all patients. Using the electronic health medical data so created, multilabel classification was employed to recommend a list of diseases and thus assist physicians in diagnosing or treating their patients' health issues more efficiently. Once the physician diagnoses the disease of a patient, the next step is to consider the likely complications of that disease, which can lead to more diseases. Previous studies reveal that correlations do exist among some diseases. Considering these correlations, a k-nearest neighbors algorithm is improved for multilabel learning by using correlations among labels (CML-kNN). The CML- kNN algorithm first exploits the dependence between every two labels to update the origin label matrix and then performs multilabel learning to estimate the probabilities of labels by using the integrated features. Finally, it recommends the top N diseases to the physicians. Experimental results on real health medical data establish the effectiveness and practicability of the proposed CDS framework.