A Survival Prediction Algorithm for Covid-19 Patients Admitted to a
District General Hospital
Abstract
OBJECTIVE: To collect and review data from consecutive patients admitted
to Queen’s Hospital, Burton on Trent for treatment of Covid-19
infection, with the aim of developing a predictive algorithm that can
help identify those patients likely to survive. DESIGN: Consecutive
patient data was collected from all admissions to hospital for treatment
of Covid-19. Data was manually extracted from the electronic patient
record for statistical analysis. RESULTS: Data, including outcome data
(discharged alive / died) was extracted for 487 consecutive patients,
admitted for treatment. Overall, patients who died were older, had very
significantly lower Oxygen saturation (SpO2) on admission, and higher
CRP as evidenced by a Bonferroni-corrected P<0.0056).
Evaluated individually, platelets and lymphocyte count were not
statistically significant but when used in a logistic regression to
develop a predictive score, platelet count did add predictive value. The
prediction algorithm we developed was: P(survival) =
___________________1______________________
1+e-1(-16.7104-3.3810LN(age)+6.5592LN(SpO2)-0.4584LN(CRP)+0.7183LN(Plt))
CONCLUSION: Age, SpO2 on Admmission, CRP and platelets were an effective
marker combination that helped identify patients who would be likely to
survive. The AUC under the ROC Plot was 0.737 (95% Conf. Interval
0.689-0.784; P< 0.001). Further research adding extra markers,
is underway.