Competing Accelerated Failure Time Models for Multiple Concurrent Failure Mechanisms

The rising prevalence of complex diseases characterised by multiple coexisting and interacting etiological processes poses critical challenges for survival analysis and precision medicine, particularly as population ageing renders mutually exclusive models increasingly untenable.

We propose a competing accelerated failure time (cAFT) framework to understand the individual-specific temporal dynamics of disease competition and interaction based on a first-to-fail principle.

Specifically, we introduce an individualised, time-varying winning probability to quantify the relative contributions of latent causes and provide an interpretable basis for patient stratification within distinct subtypes.

Consistency and asymptotic normality are established for the maximum likelihood estimation of the parameters, with practical implementation via an expectation-maximisation (EM) algorithm.

We illustrate the model's effectiveness and efficiency through numerical simulations and real-world applications, including biomarker discovery for 28-day survival in sepsis and overall survival in lung adenocarcinoma.

Compared with standard AFT and Cox proportional hazards models, the cAFT model consistently improves predictive accuracy (C-index and iAUC gains of 5--10%) and reveals subtype-dependent gene effects within distinct biological pathways across heterogeneous patient subgroups.

Conclusively, the cAFT model provides deeper insights into patient prognosis and potential personalised therapeutic strategies.