Refine
Has Fulltext
- yes (2)
Is part of the Bibliography
- yes (2)
Document Type
- Journal article (2)
Language
- English (2)
Keywords
- ARDS (1)
- C-reactive protein (1)
- COVID-19 (1)
- Trousseau's syndrome (1)
- critical care (1)
- desmoplastic small round cell tumor (1)
- maintenance therapy (1)
- outcome (1)
- prognostic models (1)
- soft tissue sarcoma (1)
EU-Project number / Contract (GA) number
- 101015930 (1)
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.
Background
To evaluate optimal therapy and potential risk factors.
Methods
Data of DSRCT patients <40 years treated in prospective CWS trials 1997-2015 were analyzed.
Results
Median age of 60 patients was 14.5 years. Male:female ratio was 4:1. Tumors were abdominal/retroperitoneal in 56/60 (93%). 6/60 (10%) presented with a localized mass, 16/60 (27%) regionally disseminated nodes, and 38/60 (63%) with extraperitoneal metastases. At diagnosis, 23/60 (38%) patients had effusions, 4/60 (7%) a thrombosis, and 37/54 (69%) elevated CRP. 40/60 (67%) patients underwent tumor resection, 21/60 (35%) macroscopically complete. 37/60 (62%) received chemotherapy according to CEVAIE (ifosfamide, vincristine, actinomycin D, carboplatin, epirubicin, etoposide), 15/60 (25%) VAIA (ifosfamide, vincristine, adriamycin, actinomycin D) and, 5/60 (8%) P6 (cyclophosphamide, doxorubicin, vincristine, ifosfamide, etoposide). Nine received high-dose chemotherapy, 6 received regional hyperthermia, and 20 received radiotherapy. Among 25 patients achieving complete remission, 18 (72%) received metronomic therapies. Three-year event-free (EFS) and overall survival (OS) were 11% (±8 confidence interval [CI] 95%) and 30% (±12 CI 95%), respectively, for all patients and 26.7% (±18.0 CI 95%) and 56.9% (±20.4 CI 95%) for 25 patients achieving remission. Extra-abdominal site, localized disease, no effusion or ascites only, absence of thrombosis, normal CRP, complete tumor resection, and chemotherapy with VAIA correlated with EFS in univariate analysis. In multivariate analysis, significant factors were no thrombosis and chemotherapy with VAIA. In patients achieving complete remission, metronomic therapy with cyclophosphamide/vinblastine correlated with prolonged time to relapse.
Conclusion
Pleural effusions, venous thrombosis, and CRP elevation were identified as potential risk factors. The VAIA scheme showed best outcome. Maintenance therapy should be investigated further.