Refine
Document Type
- Article (4) (remove)
Language
- English (4)
Has Fulltext
- yes (4)
Is part of the Bibliography
- no (4) (remove)
Keywords
- Critical care (4) (remove)
Institute
- Medizin (4)
Highlights
• Artificial intelligence systems for mechanically ventilated patients are increasing.
• The clinical and financial impact of these models are often unexamined.
• We developed a generic health-economic model for artificial intelligence systems.
• This model assesses the cost-effectiveness for many different scenarios.
• The developed framework is easily adjustable to other (clinical) situations.
Abstract
Purpose: The health and economic consequences of artificial intelligence (AI) systems for mechanically ventilated intensive care unit patients often remain unstudied. Early health technology assessments (HTA) can examine the potential impact of AI systems by using available data and simulations. Therefore, we developed a generic health-economic model suitable for early HTA of AI systems for mechanically ventilated patients.
Materials and methods: Our generic health-economic model simulates mechanically ventilated patients from their hospitalisation until their death. The model simulates two scenarios, care as usual and care with the AI system, and compares these scenarios to estimate their cost-effectiveness.
Results: The generic health-economic model we developed is suitable for estimating the cost-effectiveness of various AI systems. By varying input parameters and assumptions, the model can examine the cost-effectiveness of AI systems across a wide range of different clinical settings.
Conclusions: Using the proposed generic health-economic model, investors and innovators can easily assess whether implementing a certain AI system is likely to be cost-effective before an exact clinical impact is determined. The results of the early HTA can aid investors and innovators in deployment of AI systems by supporting development decisions, informing value-based pricing, clinical trial design, and selection of target patient groups.
Background: Fingolimod is used for immune therapy in patients with multiple sclerosis. Long-term treatment is associated with a small increase in the risk of herpes virus reactivation and respiratory tract infections. Patients with coronavirus disease 2019 (COVID-19) under Fingolimod treatment have not been described.
Methods and results. We report a 57-year old female patient with a relapsing remitting multiple sclerosis under fingolimod treatment who experienced a severe COVID-19 infection in March 2020 (Extended Disability Status Scale: 2.0). Having peripheral lymphopenia typical for fingolimod treatment (total lymphocytes 0.39/nL [reference range 1.22-3.56]), the patient developed bilateral interstitial pneumonia with multiple ground-glass opacities on chest CT. Fingolimod medication was stopped. On the intensive care unit, non-invasive ventilation was used to provide oxygen and ventilation support regularly. Over the following two days, oxygenation improved, and the patient was transferred to a normal ward five days after admission.
Conclusion: The implications fingolimod has on COVID-19 are complex. As an S1P analogue, fingolimod might enhance lung endothelial cell integrity. In addition, in case of a so-called cytokine storm, immunomodulation might be beneficial to reduce mortality. Future studies are needed to explore the risks and therapeutic effects of fingolimod in COVID-19 patients.
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.