Department of Statistics / Government College University, Faisalabad, Pakistan.
Faisalabad Medical University, Allied Hospital, Faisalabad, Pakistan.
PLoS One. 2019 Feb 19;14(2):e0210602. doi: 10.1371/journal.pone.0210602. eCollection 2019.
The objective of this study was to build and assess the performance of survival prediction models using the gender-specific informative risk factors for patients with left ventricular systolic dysfunction.
A lasso approach was used to decide the informative predictors for building semi-parametric proportional hazards Cox model. Separate models were built for all patients [N = 299], male patients [Nmale = 194 (64.88%)], and female patients [Nfemale = 105 (35.12%)], to observe the risk factors associated with the individual's risk of death. The likelihood- ratio test was used to test the goodness of fit of the selected model, and the C-index was used to assess the predictive performance of the selected model(s) with respect to the overall model with all observed risk factors.
The survival prediction model for females is notably different from that for males. For males, smoking, diabetes, and anaemia, whereas for females, ejection fraction, sodium, and platelets count are non-informative with zero regression coefficients. The goodness of fit of the selected models with respect to the general model with all observed risk factors is tested using the likelihood-ratio test. The results are in favor of the selected models with p-values 0.51,0.61, and 0.70 for all patients, male patients, and female patients, respectively. The same values of C-index for the full model and the selected models for overall data, for males, and for females (0.72, 0.73, and 0.77 for overall data, male data, and female data, respectively) indicate that the selected models are as good as the corresponding overall models regarding their predictive performance.
There is a substantial difference in the survival prediction models for heart failure (HF) of male and female patients in this study. More studies are needed in Pakistan for confirming this striking male-female difference regarding the potential risk factors to predict survival with heart failure.
本研究的目的是构建并评估使用特定于性别且对左心室收缩功能障碍患者具有信息性的风险因素的生存预测模型，并对其进行评估。
使用套索法（lasso approach）来确定构建半参数比例风险 Cox 模型的信息性预测因子。为所有患者[N=299]、男性患者[Nmale=194（64.88%）]和女性患者[Nfemale=105（35.12%）]分别构建单独的模型，以观察与个体死亡风险相关的风险因素。使用似然比检验（likelihood-ratio test）来检验所选模型的拟合优度，使用 C 指数（C-index）来评估所选模型相对于包含所有观察到的风险因素的整体模型的预测性能。
女性的生存预测模型与男性明显不同。对于男性，吸烟、糖尿病和贫血是非信息性的，回归系数为零；而对于女性，射血分数、钠和血小板计数则没有回归系数。使用似然比检验来检验所选模型相对于包含所有观察到的风险因素的一般模型的拟合优度。结果表明，对于所有患者、男性患者和女性患者，所选模型的 p 值分别为 0.51、0.61 和 0.70，支持所选模型。对于整体数据、男性数据和女性数据，全模型和所选模型的 C 指数相同（分别为 0.72、0.73 和 0.77），这表明所选模型在预测性能方面与相应的整体模型一样好。
本研究中，男性和女性心力衰竭患者的生存预测模型存在显著差异。需要在巴基斯坦进行更多的研究，以确认这种关于潜在风险因素的显著的男女差异，以预测心力衰竭的生存情况。
