Derivation and validation of the clinical prediction model for COVID-19

Abstract

The epidemic phase of Coronavirus disease 2019 (COVID-19) made the Worldwide health system struggle against a severe interstitial pneumonia requiring high-intensity care settings for respiratory failure. A rationalisation of resources and a specific treatment path were necessary. The study suggests a predictive model drawing on clinical data gathered by 119 consecutive patients with laboratory-confirmed COVID-19 admitted in Busto Arsizio hospital. We derived a score that identifies the risk of clinical evolution and in-hospital mortality clustering patients into four groups. The study outcomes have been compared across the derivation and validation samples. The prediction rule is based on eight simple patient characteristics that were independently associated with study outcomes. It is able to stratify COVID-19 patients into four severity classes, with in-hospital mortality rates of 0% in group 1, 6–12.5% in group 2, 7–20% in group 3 and 60–86% in group 4 across the derivation and validation sample. The prediction model derived in this study identifies COVID-19 patients with low risk of in-hospital mortality and ICU admission. The prediction model that the study presents identifies COVID-19 patients with low risk of in-hospital mortality and admission to ICU. Moreover, it establishes an intermediate portion of patients that should be treated accurately in order to avoid an unfavourable clinical evolution. A further validation of the model is important before its implementation as a decision-making tool to guide the initial management of patients.

The Many Faces of Covid-19 at a Glance: A University Hospital Multidisciplinary Account From Milan, Italy

“…Mortality in other Italian hospitals in northern Italy varied between 43.6% (74) and 23.2% (75). In other hospitals in the Lombardy area, mortality ranged from 14.4 to 36.7% (75)(76)(77)(78)(79)(80). Including our data, during the first epidemic wave the overall average in-hospital mortality in Italy therefore ranged around 30%.…”

Clinical risk scores for the early prediction of severe outcomes in patients hospitalized for COVID-19

“…The SIMI score has the advantage of a clear definition of the outcome, as in the latter score from China, and of the use of fewer variables, which potentially makes it more suited for daily clinical practice in the Emergency Room. A clinical prediction model with 8 variables was recently proposed by an Italian group [ 13 ]. Despite promising results, the model was tested on a small sample of patients and requires further validation.…”

Clinical Management of Adult Patients with COVID-19 Outside Intensive Care Units: Guidelines from the Italian Society of Anti-Infective Therapy (SITA) and the Italian Society of Pulmonology (SIP)

“…The National Early Warning Score-2 (NEWS-2) based on six physiological parameters was also evaluated for its prognostic performance in hospitalized patients with COVID-19, but any possible impact on hospitalization decisions remains to be assessed [33,37,38]. Besides the aforementioned, also many other prognostic scores/models have been proposed that, for the purpose of the present question, suffer from the same limitation, i.e., it is not possible to directly extrapolate their performance to hospitalization decisions [39][40][41][42][43][44][45][46][47][48][49][50][51][52][53].…”