Decision tree algorithm to predict mortality in incurable cancer: a new prognostic model

Abstract

ObjectivesTo develop and validate a new prognostic model to predict 90-day mortality in patients with incurable cancer.MethodsIn this prospective cohort study, patients with incurable cancer receiving palliative care (n = 1322) were randomly divided into two groups: development (n = 926, 70%) and validation (n = 396, 30%). A decision tree algorithm was used to develop a prognostic model with clinical variables. The accuracy and applicability of the proposed model were assessed by the C-statistic, calibration and receiver operating characteristic (ROC) curve.ResultsAlbumin (75.2%), C reactive protein (CRP) (47.7%) and Karnofsky Performance Status (KPS) ≥50% (26.5%) were the variables that most contributed to the classification power of the prognostic model, named Simple decision Tree algorithm for predicting mortality in patients with Incurable Cancer (acromion STIC). This was used to identify three groups of increasing risk of 90-day mortality: STIC-1 - low risk (probability of death: 0.30): albumin ≥3.6 g/dL, CRP <7.8 mg/dL and KPS ≥50%; STIC-2 - medium risk (probability of death: 0.66 to 0.69): albumin ≥3.6 g/dL, CRP <7.8 mg/dL and KPS <50%, or albumin ≥3.6 g/dL and CRP ≥7.8 mg/dL; STIC-3 - high risk (probability of death: 0.79): albumin <3.6 g/dL. In the validation dataset, good accuracy (C-statistic ≥0.71), Hosmer-Lemeshow p=0.12 and area under the ROC curve=0.707 were found.ConclusionsSTIC is a valid, practical tool for stratifying patients with incurable cancer into three risk groups for 90-day mortality.