Announcement Date: February 7, 2017
Several observational studies reported that Oseltamivir (Tamiﬂu) reduced mortality in
infected and hospitalized patients. Due to the restriction of observation to hospital stay
and time-dependent treatment assignment, such ﬁndings were prone to common types
of survival bias (length, time-dependent and competing risk bias).
British hospital data from the FLU-CIN study group were used which included 1391
patients with conﬁrmed pandemic inﬂuenza A/H1N1 2009 infection. We used a multistate
model approach with following states: hospital admission, Oseltamivir treatment,
discharge and death. Time origin is inﬂuenza onset. We displayed individual data, risk
sets, hazards and probabilities from multi-state models to study the impact of these
three common survival biases.
The correct hazard ratio of Oseltamivir for death was 1.03 (95%-CI: 0.64-1.66) and
for discharge 1.89 (95%-CI: 1.65-2.16). Length bias increased both hazard ratios:
HR(death)= 1.82 (95%-CI:1.12-2.98) and HR(discharge)= 4.44 (95%-CI: 3.90-5.05)
whereas the time-dependent bias reduced them: HR(death)= 0.62 (95%-CI:0.39-1.00)
and HR(discharge)= 0.85 (95%-CI:0.75-0.97). Length and time-dependent bias were
less pronounced in terms of probabilities. Ignoring discharge as a competing event for
hospital death led to a remarkable overestimation of hospital mortality and failed to
detect the reducing effect of Oseltamivir on hospital stay.
The impact of each of the three survival biases was remarkable and it can make NI appear
more effective or even harmful. Incorrect and misclassiﬁed risk sets were primary
the source of biased hazard rates.