Abstract:
Background: In many clinical trials, patients who are followed up over time may typically
experience multiple events. Ignoring such competing risk events in time-to-event analyses can lead
to biased risk estimates. In this context, we presented joint modeling of functional ability measures
and the competing risk among stroke patients at FHCSH Bahir Dar, Ethiopia.
Methods: We considered 400 stroke patients under the medical ward outpatient stroke at FHCSH
who started treatment from September 2018 to August 2021 by a retrospective cohort study design,
patients with CT scan or MRI confirmation, patients with age greater than or equal to 18 years,
and patients with at least three visits were included in this study. For this purpose, we employed a
joint model of longitudinal ordinal with competing risk.
Result: Among different candidates of demographic and clinical variables, age, diabetes, blood
urea nitrogen, Glasgow coma scale, white blood cell count, and stroke complication were
statistically significant predictors in the longitudinal sub-model for functional ability. Likewise,
age, diabetes, cholesterol level, white blood cell count, atrial fibrillation, types of strokes, and
stroke complications were statistically significant predictors in the cause-specific hazard sub model for time to death and dropouts. Finally, age, diabetes, white blood cell count, and stroke
complication were statistically significant predictors that jointly affected the two sub-model.
Additionally, associations between both joint model and competing risk were statistically
significant.
Conclusion: The joint competing risk modeling approach, provides wide-ranging information
about the transition pattern of the disease, with associated improved knowledge of disease
etiology.
Recommendation: The results of the study can be used as a motivation for future scholars. since
stroke is one of the most frequent diseases in Ethiopia as well as in the world, it needs more
attention and study in a wider study area.
Keywords:- modified Rankin Scale, Proportional Hazard, Cause-Specific, Cumulative Incidence
Function, Partial-Proportional Odds