Refine
Document Type
- Article (2)
Language
- English (2)
Has Fulltext
- yes (2)
Is part of the Bibliography
- no (2)
Keywords
- ARDS (1)
- COVID-19 (1)
- Critical care (1)
- Outcome (1)
- Prognostic models (1)
Institute
- Medizin (2)
Background: Although being considered as a rarely observed HIV-1 protease mutation in clinical isolates, the L76V-prevalence increased 1998-2008 in some European countries most likely due to the approval of Lopinavir, Amprenavir and Darunavir which can select L76V. Beside an enhancement of resistance, L76V is also discussed to confer hypersusceptibility to the drugs Atazanavir and Saquinavir which might enable new treatment strategies by trying to take advantage of particular mutations. Results: Based on a cohort of 47 L76V-positive patients, we examined if there might exist a clinical advantage for L76V-positive patients concerning long-term success of PI-containing regimens in patients with limited therapy options. Genotypic- and phenotypic HIV-resistance tests from 47 mostly multi-resistant, L76V-positive patients throughout Germany were accomplished retrospectively 1999-2009. Five genotype-based drug-susceptibility predictions received from online interpretation-tools for Atazanavir, Saquinavir, Amprenavir and Lopinavir, were compared to phenotype-based predictions that were determined by using a recombinant virus assay along with a Virtual Phenotype™(Virco). The clinical outcome of the L76V-adapted follow-up therapy was determined by monitoring viral load for 96 weeks. Conclusions: In this analysis, the mostly used interpretation systems overestimated the L76V-mutation concerning Atazanavir- and SQV resistance. In fact, a clear benefit in drug susceptibility for these drugs was observed in phenotype analysis after establishment of L76V. More importantly, long-term therapy success was significantly higher in patients receiving Atazanavir and/or Saquinavir plus one L76V-selecting drug compared to patients without L76V-selecting agents (p = 0.002). In case of L76V-occurrence ATV and/or SQV may represent encouraging options for patients in deep salvage situations.
Background: Intensive Care Resources are heavily utilized during the COVID-19 pandemic. However, risk stratification and prediction of SARS-CoV-2 patient clinical outcomes upon ICU admission remain inadequate. This study aimed to develop a machine learning model, based on retrospective & prospective clinical data, to stratify patient risk and predict ICU survival and outcomes. Methods: A Germany-wide electronic registry was established to pseudonymously collect admission, therapeutic and discharge information of SARS-CoV-2 ICU patients retrospectively and prospectively. Machine learning approaches were evaluated for the accuracy and interpretability of predictions. The Explainable Boosting Machine approach was selected as the most suitable method. Individual, non-linear shape functions for predictive parameters and parameter interactions are reported. Results: 1039 patients were included in the Explainable Boosting Machine model, 596 patients retrospectively collected, and 443 patients prospectively collected. The model for prediction of general ICU outcome was shown to be more reliable to predict “survival”. Age, inflammatory and thrombotic activity, and severity of ARDS at ICU admission were shown to be predictive of ICU survival. Patients’ age, pulmonary dysfunction and transfer from an external institution were predictors for ECMO therapy. The interaction of patient age with D-dimer levels on admission and creatinine levels with SOFA score without GCS were predictors for renal replacement therapy. Conclusions: Using Explainable Boosting Machine analysis, we confirmed and weighed previously reported and identified novel predictors for outcome in critically ill COVID-19 patients. Using this strategy, predictive modeling of COVID-19 ICU patient outcomes can be performed overcoming the limitations of linear regression models. Trial registration “ClinicalTrials” (clinicaltrials.gov) under NCT04455451.