Current best evidence for clinical care (more info)
Patients with severe COVID-19 have overwhelmed healthcare systems worldwide. We hypothesized that machine learning (ML) models could be used to predict risks at different stages of management and thereby provide insights into drivers and prognostic markers of disease progression and death. From a cohort of approx. 2.6 million citizens in Denmark, SARS-CoV-2 PCR tests were performed on subjects suspected for COVID-19 disease; 3944 cases had at least one positive test and were subjected to further analysis. SARS-CoV-2 positive cases from the United Kingdom Biobank was used for external validation. The ML models predicted the risk of death (Receiver Operation Characteristics-Area Under the Curve, ROC-AUC) of 0.906 at diagnosis, 0.818, at hospital admission and 0.721 at Intensive Care Unit (ICU) admission. Similar metrics were achieved for predicted risks of hospital and ICU admission and use of mechanical ventilation. Common risk factors, included age, body mass index and hypertension, although the top risk features shifted towards markers of shock and organ dysfunction in ICU patients. The external validation indicated fair predictive performance for mortality prediction, but suboptimal performance for predicting ICU admission. ML may be used to identify drivers of progression to more severe disease and for prognostication patients in patients with COVID-19. We provide access to an online risk calculator based on these findings.
|Discipline / Specialty Area||Score|
|Family Medicine (FM)/General Practice (GP)||
|General Internal Medicine-Primary Care(US)||
This is a potentially useful tool and nice use of machine learning. Predictive factors may be similar to those used by experienced clinicians.
This machine based model is comprehensive and validated. It doesn't give any new risk factors and is difficult to implement in resource poor countries.
The ML affirms clinical evidence of common risk factors; age, body mass index and hypertension, and the shift to markers of shock and organ dysfunction in ICU patients. The external validation showing fair predictive performance for mortality prediction, but suboptimal performance for predicting ICU admission is of clinical interest as caveats where ML is utilised to predict potential admission to ICU.
As long as we have limited possibilities for treating our patients and only have the ability to react to the symptoms, a predictive model is great but with limited value for daily practice. As soon as we have the possibilities to treat a patient in this way that this patient won't suffer from hard adverse effects, a predictive model will be from great and important value (preemptive treatment).