Survival Analysis Modeling On Risk Of Malaria Death

In this study the theoretical basis, model fitting, variable selection, and hypothesis testing of survival analysis models were explored and applied to real data to demonstrate how the model could be used to ascertain linkages between exposure to the mosquito parasite and health hazards. Malaria cases from admission to destination state (death or censored), due to causal factors (level of exposure to malaria parasite) were collected over a four month period from four hospitals within a district in Ghana and analyzed using survival analysis modeling techniques. Out of the 1793 patients sampled,405 representing 22.6%were using insecticide treated nets while the majority (77.4%) was using other types of nets like window netting and ordinary treated nets. It was established that among those using insecticide treated nets,16% died within the four months study period, while 84% survived; but among the non-users of insecticide treated nets,23% died while 77% survived within the same study period. The survival experiences of males and females were approximately the same; this implies that the gender of the patients does not contribute significantly to death due to malaria. The hazard ratio HR(t|exposed group,less exposed group)= 1.5, shows that exposed group was at a higher risk of malaria-death than less exposed group. The Kaplan-Meier curves revealed that patients who subscribed to insecticide treated nets (ITNs) as means of reducing exposure to the malaria parasite had better and longer survival prognosis than non-subscribers. The graphical test conducted on the biomedical data for the two levels of exposure was parallel; this parallelism of the log-log graph is a litmus test for assessing the proportional hazards (PH) assumption.The life table survival probabilities also show that patients who subscribed to the use of ITNs as means of preventing exposure to the parasite had a longer and better survival experiences than non-subscribers of ITNs. The results of the outcome of the hypothesis testing was also profound; firstly, we note from the results of the log-rank test (p-value=0.0020<0.0500) that the survival curves of the exposed (non users of ITNs) and the less exposed (users of ITNs) were significantly different, this implies that if we had included all population elements into the study, and examined association between level of exposure to malaria parasite and health hazards for the two groups, the survival curves for less-exposed and exposed would have been different with less-exposed group having longer time of surviving health hazards than exposed group.; secondly, we note that if the entire population of patients who had been diagnosed of malaria were included in the study, the survival experiences of the users and non-users of ITN would have been significantly different; thirdly, we note from the p-value (0.0035< 0.0500) of the likelihood ratio test that the method of estimation adopted by the residents to prevent exposure to the parasite was significant, the results revealed that using ITN as means of reducing exposure to the parasite was significant. Fourthly, we note from the Wald's statistics that the method of protection adopted by the residents to prevent exposure to the parasite was significant after adjusting for the sex variables. Finally, we note from the Mantel-Cox residual test that the correlation between the ranked failure times and the Schoenfeld residual was significant at both the 0.05 and 0.01 levels of significance. These results are enough grounds to show that ITN's are efficacious in preventing risk of malaria-death. The result further calls for health care professionals and individuals to access ITN as a means to prevent the scourge of malaria.