Browsing by Subject "Survival Analysis"

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    Open Access
    A comparison of the conditional inference survival forest model to random survival forests based on a simulation study as well as on two applications with time-to-event data
    (2017) Nasejje, Justine B; Mwambi, Henry; Sabur, Natasha F; Lesosky, Maia
    Abstract Background Random survival forest (RSF) models have been identified as alternative methods to the Cox proportional hazards model in analysing time-to-event data. These methods, however, have been criticised for the bias that results from favouring covariates with many split-points and hence conditional inference forests for time-to-event data have been suggested. Conditional inference forests (CIF) are known to correct the bias in RSF models by separating the procedure for the best covariate to split on from that of the best split point search for the selected covariate. Methods In this study, we compare the random survival forest model to the conditional inference model (CIF) using twenty-two simulated time-to-event datasets. We also analysed two real time-to-event datasets. The first dataset is based on the survival of children under-five years of age in Uganda and it consists of categorical covariates with most of them having more than two levels (many split-points). The second dataset is based on the survival of patients with extremely drug resistant tuberculosis (XDR TB) which consists of mainly categorical covariates with two levels (few split-points). Results The study findings indicate that the conditional inference forest model is superior to random survival forest models in analysing time-to-event data that consists of covariates with many split-points based on the values of the bootstrap cross-validated estimates for integrated Brier scores. However, conditional inference forests perform comparably similar to random survival forests models in analysing time-to-event data consisting of covariates with fewer split-points. Conclusion Although survival forests are promising methods in analysing time-to-event data, it is important to identify the best forest model for analysis based on the nature of covariates of the dataset in question.
  • Thumbnail Image
    Item
    Open Access
    Glycosyltransferase gene expression profiles classify cancer types and propose prognostic subtypes
    (2016) Ashkani, Jahanshah; Naidoo, Kevin J
    Aberrant glycosylation in tumours stem from altered glycosyltransferase (GT) gene expression but can the expression profiles of these signature genes be used to classify cancer types and lead to cancer subtype discovery? The differential structural changes to cellular glycan structures are predominantly regulated by the expression patterns of GT genes and are a hallmark of neoplastic cell metamorphoses. We found that the expression of 210 GT genes taken from 1893 cancer patient samples in The Cancer Genome Atlas (TCGA) microarray data are able to classify six cancers; breast, ovarian, glioblastoma, kidney, colon and lung. The GT gene expression profiles are used to develop cancer classifiers and propose subtypes. The subclassification of breast cancer solid tumour samples illustrates the discovery of subgroups from GT genes that match well against basal-like and HER2-enriched subtypes and correlates to clinical, mutation and survival data. This cancer type glycosyltransferase gene signature finding provides foundational evidence for the centrality of glycosylation in cancer.
  • Thumbnail Image
    Item
    Open Access
    Predicting mortality in damage control surgery for major abdominal trauma
    (2010) Timmermans, Joep; Nicol, Andrew; Kairinos, Nick; Teijink, Joep; Prins, Martin; Navsaria, Pradeep
    BACKGROUND: Damage control surgery (DCS) has become well established in the past decade as the surgical strategy to be employed in the unstable trauma patient. The aim of this study was to determine which factors played a predictive role in determining mortality in patients undergoing a damage control laparotomy. MATERIALS AND METHODS: A retrospective review of all patients undergoing a laparotomy and DCS in a level 1 trauma centre over a 3-year period was performed. Twenty-nine potentially predictive variables for mortality were analysed. RESULTS: Of a total of 1 274 patients undergoing a laparotomy for trauma, 74 (6%) required a damage control procedure. The mean age was 28 years (range 14 - 53 years). The mechanism of injury was gunshot wounds in 57 cases (77%), blunt trauma in 14 (19%) and stabs in 3 (4%). Twenty patients died, giving an overall mortality rate of 27%. Factors significantly associated with increased mortality were increasing age (p=0.001), low base excess (p=0.002), pH (p<0.001), core temperature (p=0.002), and high blood transfusion requirement over 24 hours (p=0.002). CONCLUSION: The overall survival of patients after damage control procedures for abdominal trauma was excellent (73%). The main factors that are useful in deciding when to initiate DCS are age, base excess, pH and the core temperature.