arXiv subjects

Catalina A. Vallejos

Publications and source records attributed to Catalina A. Vallejos.

9 recordsLinked to original sources

arXiv2026

A reproducible and extensible framework for benchmarking competing risks survival models

A wide range of statistical and machine learning methods have been proposed for survival analysis with competing risks, where the occurrence of one event (i.e., cancer death) precludes the occurrence of other events (i.e., cardiovascular disease death). Despite these methodological advances, their systematic evaluation and adoption are limited by the lack of comprehensive, reproducible and extensible benchmarking frameworks. We developed an open-source benchmarking framework for competing risks models that enables their systematic comparison across multiple datasets under different aspects of performance; calibration, discrimination, overall prediction error and clinical utility. We additionally introduce an extension of SHAP for competing risks, allowing model-agnostic interpretability of covariates contributions over time. All our code is publicly available via GitHub:https://github.com/BBolosSierra/CompRisksBenchmark

stat.ML↗

arXiv2026

Landmarking with Latent Class Mixed Models for Dynamic Prediction of Time-to-event Data with Heterogeneous Biomarker Trajectories

The increasing ability to securely access electronic health records (EHR) has created unprecedented opportunities to monitor the health trajectories of large heterogeneous patient populations throughout their lifetime. Repeated measurements of time-varying covariates (such as biomarkers measured via routine blood tests) can inform dynamic risk prediction of time-to-event outcomes, updating risk estimates as new information becomes available. Existing dynamic risk prediction approaches often assume homogeneous longitudinal trajectories across individuals. This assumption is not met when there is heterogeneity driven by latent subgroup structure (e.g. due to unobserved confounders), as is often the case with real-world biomedical data. At present, accounting for such heterogeneity is only available in joint latent class models for longitudinal and time-to-event data, but they are computationally intensive, often prohibitively so for large-scale data, such as those present in EHR settings. To address these challenges, we propose a novel landmarking approach that integrates latent class mixed models (LCMMs) to capture latent heterogeneity in longitudinal trajectories. Our method is implemented in a modular R package, landmaRk, which is available on CRAN and allows users to flexibly specify the components of a landmarking analysis, beyond our proposed approach. Through simulation studies, we demonstrate improvements in prediction performance in the presence of latent heterogeneity compared to traditional landmarking strategies, while remaining computationally efficient for large datasets. We also provide a proof-of-concept illustration using real data.

stat.ME↗

arXiv2025

The C-index Multiverse

Quantifying out-of-sample discrimination performance for time-to-event outcomes is a fundamental step for model evaluation and selection in the context of predictive modelling. The concordance index, or C-index, is a widely used metric for this purpose, particularly with the growing development of machine learning methods. Beyond differences between proposed C-index estimators (e.g. Harrell's, Uno's and Antolini's), we demonstrate the existence of a C-index multiverse among available R and python software, where seemingly equal implementations can yield different results. This can undermine reproducibility and complicate fair comparisons across models and studies. Key variation sources include tie handling and adjustment to censoring. Additionally, the absence of a standardised approach to summarise risk from survival distributions, result in another source of variation dependent on input types. We demonstrate the consequences of the C-index multiverse when quantifying predictive performance for several survival models (from Cox proportional hazards to recent deep learning approaches) on publicly available breast cancer data, and semi-synthetic examples. Our work emphasises the need for better reporting to improve transparency and reproducibility. This article aims to be a useful guideline, helping analysts when navigating the multiverse, providing unified documentation and highlighting potential pitfalls of existing software. All code is publicly available at: www.github.com/BBolosSierra/CindexMultiverse.

stat.ML↗

arXiv2024

AMUSE: Adaptive Model Updating using a Simulated Environment

Prediction models frequently face the challenge of concept drift, in which the underlying data distribution changes over time, weakening performance. Examples can include models which predict loan default, or those used in healthcare contexts. Typical management strategies involve regular model updates or updates triggered by concept drift detection. However, these simple policies do not necessarily balance the cost of model updating with improved classifier performance. We present AMUSE (Adaptive Model Updating using a Simulated Environment), a novel method leveraging reinforcement learning trained within a simulated data generating environment, to determine update timings for classifiers. The optimal updating policy depends on the current data generating process and ongoing drift process. Our key idea is that we can train an arbitrarily complex model updating policy by creating a training environment in which possible episodes of drift are simulated by a parametric model, which represents expectations of possible drift patterns. As a result, AMUSE proactively recommends updates based on estimated performance improvements, learning a policy that balances maintaining model performance with minimizing update costs. Empirical results confirm the effectiveness of AMUSE in simulated data.

cs.LG↗

arXiv2022

A review on competing risks methods for survival analysis

When modelling competing risks survival data, several techniques have been proposed in both the statistical and machine learning literature. State-of-the-art methods have extended classical approaches with more flexible assumptions that can improve predictive performance, allow high dimensional data and missing values, among others. Despite this, modern approaches have not been widely employed in applied settings. This article aims to aid the uptake of such methods by providing a condensed compendium of competing risks survival methods with a unified notation and interpretation across approaches. We highlight available software and, when possible, demonstrate their usage via reproducible R vignettes. Moreover, we discuss two major concerns that can affect benchmark studies in this context: the choice of performance metrics and reproducibility.

stat.ME↗

arXiv2019

Design choices for productive, secure, data-intensive research at scale in the cloud

We present a policy and process framework for secure environments for productive data science research projects at scale, by combining prevailing data security threat and risk profiles into five sensitivity tiers, and, at each tier, specifying recommended policies for data classification, data ingress, software ingress, data egress, user access, user device control, and analysis environments. By presenting design patterns for security choices for each tier, and using software defined infrastructure so that a different, independent, secure research environment can be instantiated for each project appropriate to its classification, we hope to maximise researcher productivity and minimise risk, allowing research organisations to operate with confidence.

cs.CR↗

arXiv2018

Shrinkage estimation of large covariance matrices using multiple shrinkage targets

Linear shrinkage estimators of a covariance matrix --- defined by a weighted average of the sample covariance matrix and a pre-specified shrinkage target matrix --- are popular when analysing high-throughput molecular data. However, their performance strongly relies on an appropriate choice of target matrix. This paper introduces a more flexible class of linear shrinkage estimators that can accommodate multiple shrinkage target matrices, directly accounting for the uncertainty regarding the target choice. This is done within a conjugate Bayesian framework, which is computationally efficient. Using both simulated and real data, we show that the proposed estimator is less sensitive to target misspecification and can outperform state-of-the-art (nonparametric) single-target linear shrinkage estimators. Using protein expression data from The Cancer Proteome Atlas we illustrate how multiple sources of prior information (obtained from more than 30 different cancer types) can be incorporated into the proposed multi-target linear shrinkage estimator. In particular, it is shown that the target-specific weights can provide insights into the differences and similarities between cancer types. Software for the method is freely available as an R-package at http://github.com/HGray384/TAS.

stat.ME↗

arXiv2014

Bayesian Survival Modelling of University Outcomes

The aim of this paper is to model the length of registration at university and its associated academic outcome for undergraduate students at the Pontificia Universidad Católica de Chile. Survival time is defined as the time until the end of the enrollment period, which can relate to different reasons - graduation or two types of dropout - that are driven by different processes. Hence, a competing risks model is employed for the analysis. The issue of separation of the outcomes (which precludes maximum likelihood estimation) is handled through the use of Bayesian inference with an appropriately chosen prior. We are interested in identifying important determinants of university outcomes and the associ- ated model uncertainty is formally addressed through Bayesian model averaging. The methodology introduced for modelling university outcomes is applied to three selected degree programmes, which are particularly affected by dropout and late graduation.

stat.AP↗

arXiv2013

On posterior propriety for the Student-$t$ linear regression model under Jeffreys priors

Regression models with fat-tailed error terms are an increasingly popular choice to obtain more robust inference to the presence of outlying observations. This article focuses on Bayesian inference for the Student-$t$ linear regression model under objective priors that are based on the Jeffreys rule. Posterior propriety results presented in Fonseca et al. (2008) are revisited and corrected. In particular, it is shown that the standard Jeffreys-rule prior precludes the existence of a proper posterior distribution.

stat.ME↗