• Clinical decision support system
• Corticosteroids
• Machine learning
• Sensitive or resistant
• Sepsis

• Humans
• Sepsis/diagnosis
• Sepsis/drug therapy
• Adrenal Cortex Hormones/therapeutic use
• Incidence
• Machine Learning
• Data Mining

• artificial intelligence
• corticosteroids
• eHealth
• personalised medication recommendation algorithms
• post-COVID syndrome
• prediction model
• respiratory system

• NU22-A-105 Ministry of Health of the Czech Republic

Liver disease indicates any pathology that can harm or destroy the liver or prevent it from normal functioning. The global community has recently witnessed an increase in the mortality rate due to liver disease. This could be attributed to many factors, among which are human habits, awareness issues, poor healthcare, and late detection. To curb the growing threats from liver disease, early detection is critical to help reduce the risks and improve treatment outcome. Emerging technologies such as machine learning, as shown in this study, could be deployed to assist in enhancing its prediction and treatment.

To present a more efficient system for timely prediction of liver disease using a hybrid eXtreme Gradient Boosting model with hyperparameter tuning with a view to assist in early detection, diagnosis, and reduction of risks and mortality associated with the disease.

The dataset used in this study consisted of 416 people with liver problems and 167 with no such history. The data were collected from the state of Andhra Pradesh, India, through https://www.kaggle.com/datasets/uciml/indian-liver-patient-records. The population was divided into two sets depending on the disease state of the patient. This binary information was recorded in the attribute "is_patient".

The results indicated that the chi-square automated interaction detection and classification and regression trees models achieved an accuracy level of 71.36% and 73.24%, respectively, which was much better than the conventional method. The proposed solution would assist patients and physicians in tackling the problem of liver disease and ensuring that cases are detected early to prevent it from developing into cirrhosis (scarring) and to enhance the survival of patients. The study showed the potential of machine learning in health care, especially as it concerns disease prediction and monitoring.

This study contributed to the knowledge of machine learning application to health and to the efforts toward combating the problem of liver disease. However, relevant authorities have to invest more into machine learning research and other health technologies to maximize their potential.

• Liver infection
• Machine learning
• Chi-square automated interaction detection
• Classification and regression trees
• Decision tree
• XGBoost
• Hyperparameter tuning

• Humans
• Treatment Outcome
• Liver Diseases/diagnosis
• Liver Diseases/therapy
• India/epidemiology

Among the IL-6 inhibitors, tocilizumab is the most widely used therapeutic option in patients with SARS-CoV-2-associated severe respiratory failure (SRF). The aim of our study was to provide evidence on predictors of poor outcome in patients with COVID-19 treated with tocilizumab, using machine learning (ML) techniques. We conducted a retrospective study, analyzing the clinical, laboratory and sociodemographic data of patients admitted for severe COVID-19 with SRF, treated with tocilizumab. The extreme gradient boost (XGB) method had the highest balanced accuracy (93.16%). The factors associated with a worse outcome of tocilizumab use in terms of mortality were: baseline situation at the start of tocilizumab treatment requiring invasive mechanical ventilation (IMV), elevated ferritin, lactate dehydrogenase (LDH) and glutamate-pyruvate transaminase (GPT), lymphopenia, and low PaFi [ratio between arterial oxygen pressure and inspired oxygen fraction (PaO₂/FiO₂)] values. The factors associated with a worse outcome of tocilizumab use in terms of hospital stay were: baseline situation at the start of tocilizumab treatment requiring IMV or supplemental oxygen, elevated levels of ferritin, glutamate-oxaloacetate transaminase (GOT), GPT, C-reactive protein (CRP), LDH, lymphopenia, and low PaFi values. In our study focused on patients with severe COVID-19 treated with tocilizumab, the factors that were weighted most strongly in predicting worse clinical outcome were baseline status at the start of tocilizumab treatment requiring IMV and hyperferritinemia.

• COVID-19
• SARS-CoV-2
• cytokine release syndrome
• machine learning
• tocilizumab

• COVID-19
• Computational sciences
• Drug repurposing
• Protein targets
• SARS-CoV-2
• Variants of concern

Remdesivir (RDV) reduces time to clinical improvement in hospitalized COVID -19 patients requiring supplemental oxygen. Dexamethasone improves survival in those requiring oxygen support. Data is lacking on the efficacy of combination therapy in patients on mechanical ventilation. We analyzed for comparative outcomes between Corticosteroid (CS) therapy with combined Corticosteroid and Remdesivir (CS-RDV) therapy. We conducted an observational cohort study of patients aged 18 to 90 with COVID-19 requiring ventilatory support using TriNetX (COVID-19 Research Network) between January 20, 2020, and February 9, 2021. We compared patients who received at least 48 hours of CS-RDV combination therapy to CS monotherapy. The primary outcome was 28-day all-cause mortality rates in propensity-matched (PSM) cohorts. Secondary outcomes were Length of Stay (LOS), Secondary Bacterial Infections (SBI), and MRSA (Methicillin-Resistant Staphylococcus aureus), and Pseudomonas infections. We used univariate and multivariate Cox proportional hazards models and stratified log-rank tests. Of 388 patients included, 91 (23.5%) received CS-RDV therapy, and 297 (76.5%) received CS monotherapy. After propensity score matching, with 74 patients in each cohort, all-cause mortality was 36.4% and 29.7% in the CS-RDV and CS therapy, respectively (P = 0.38). We used a Kaplan-Meier with a log-rank test on follow up period (P = 0.23), and a Hazards Ratio model (P = 0.26). SBI incidence was higher in the CS group (13.5% vs. 35.1%, P = 0.02) with a similar LOS (13.4 days vs. 13.4 days, P = 1.00) and similar incidence of MRSA/Pseudomonas infections (13.5% vs. 13.5%, P = 1.00) in both the groups. Therefore, CS-RDV therapy is non-inferior to CS therapy in reducing 28-day all-cause in-hospital mortality but associated with a significant decrease in the incidence of SBI in critically ill COVID-19 patients.

• Adenosine Monophosphate/analogs & derivatives
• Adenosine Monophosphate/therapeutic use
• Adrenal Cortex Hormones/therapeutic use
• Aged
• Alanine/analogs & derivatives
• Alanine/therapeutic use
• COVID-19/complications
• COVID-19/mortality
• COVID-19/virology
• Cohort Studies
• Drug Therapy, Combination
• Female
• Hospital Mortality
• Humans
• Incidence
• Kaplan-Meier Estimate
• Length of Stay
• Male
• Middle Aged
• Proportional Hazards Models
• Pseudomonas Infections/diagnosis
• Pseudomonas Infections/epidemiology
• Pseudomonas Infections/etiology
• Respiration, Artificial
• SARS-CoV-2/isolation & purification
• Staphylococcal Infections/diagnosis
• Staphylococcal Infections/epidemiology
• Staphylococcal Infections/etiology
• Treatment Outcome
• COVID-19 Drug Treatment

• Artificial Intelligence
• Humans
• Pharmacogenetics
• Precision Medicine