Citations

Background: Lactic acidosis is the most common cause of anion gap metabolic acidosis in the intensive care unit (ICU), associated with poor outcomes including mortality. We sought to compare machine learning (ML) approaches versus logistic regression analysis for prediction of mortality in lactic acidosis patients admitted to the ICU. Methods: We used the Medical Information Mart for Intensive Care (MIMIC-III) database to identify ICU adult patients with lactic acidosis (serum lactate ≥4 mmol/L). The outcome of interest was hospital mortality. We developed prediction models using four ML approaches consisting of random forest (RF), decision tree (DT), extreme gradient boosting (XGBoost), artificial neural network (ANN), and statistical modeling with forward stepwise logistic regression using the testing dataset. We then assessed model performance using area under the receiver operating characteristic curve (AUROC), accuracy, precision, error rate, Matthews correlation coefficient (MCC), F1 score, and assessed model calibration using the Brier score, in the independent testing dataset. Results: Of 1919 lactic acidosis ICU patients, 1535 and 384 were included in the training and testing dataset, respectively. Hospital mortality was 30%. RF had the highest AUROC at 0.83, followed by logistic regression 0.81, XGBoost 0.81, ANN 0.79, and DT 0.71. In addition, RF also had the highest accuracy (0.79), MCC (0.45), F1 score (0.56), and lowest error rate (21.4%). The RF model was the most well-calibrated. The Brier score for RF, DT, XGBoost, ANN, and multivariable logistic regression was 0.15, 0.19, 0.18, 0.19, and 0.16, respectively. The RF model outperformed multivariable logistic regression model, SOFA score (AUROC 0.74), SAP II score (AUROC 0.77), and Charlson score (AUROC 0.69). Conclusion: The ML prediction model using RF algorithm provided the highest predictive performance for hospital mortality among ICU patient with lactic acidosis.

Introduction In the unprecedented era of COVID-19, ongoing research and evolution of evidence has led to ever-changing guidelines for clinical monitoring and therapeutic options. Formulating treatment protocols requires the understanding and application of the evolving research. Objective The primary objective of this study is to present a systematic evidence-based approach to synthesize the necessary data in order to optimize the management of COVID-19. Methods At Mayo Clinic Florida, we developed a multidisciplinary centralized COVID Treatment Review Panel (TRP) of expert pulmonologists, intensivists, infectious disease specialists, anesthesiologists, hematologists, rheumatologists, and hospitalists that in real-time reviews the latest evidence in peer-reviewed journals, the available clinical trials, and help guide the rapid application of therapeutics or interventions to the patient and the bedside provider. Results/Conclusions The multi-disciplinary team approach of synthesizing clinical data and coordinating care is effective in responding to rapidly evolving and changing evidence. Systematic data collection and evidence-based treatment algorithms enable physicians to rapidly translate the current literature to clinical practice, and improve care and outcomes of patients.

Renal vein thrombosis is a rare, but potentially serious complication in patients with renal transplantation as it can lead to non-reversible graft injury and failure. Often this clinical entity is found in the early transplantation period, and the available management strategies are associated with favourable patient outcomes. The incidence, pathophysiology and outcomes for the delayed occurrence of renal vein thrombosis are unknown. The case here describes a unique situation with an excellent clinical outcome related to early diagnosis and appropriate care.

Immune checkpoint inhibitors have revolutionised cancer therapy in the past decade. Although they have been indicated to treat a diverse range of malignant neoplasms, they are also associated with various immune-related adverse effects. We report the case of a 74-year-old man with a history of urothelial carcinoma who had atezolizumab-induced myocarditis and myositis resulting in acute hypercapnic respiratory failure, despite the discontinuation of atezolizumab and aggressive treatment with corticosteroids. This case highlights the importance of a multidisciplinary approach for early diagnosis and treatment of immune-related adverse events. Physicians must be aware of the risks associated with immune checkpoint inhibitors and have a basic knowledge regarding their management.

Mortality remains high in septic shock with few new treatment options. Angiotensin II has been recently approved for use in septic shock due to promising results in the ATHOS-3 trial. However, patients with neutropenia were excluded in the trial. This patient population is becoming increasingly common in the intensive care unit as there is an increase in novel biologic therapies and stem cell transplantations for haematological and solid organ malignancies. We present a case of a patient with T-cell acute lymphoblastic leukaemia who received chemotherapy, resulting in neutropenia and septic shock. There was persistent hypotension despite initiating multiple conventional vasopressors. Angiotensin II was attempted with immediate improvement in the blood pressure which resulted in weaning of other vasopressors. This positive haemodynamic response suggests that angiotensin II can successfully be used in neutropenic patients without increasing the overall catecholamine burden of septic shock.