The abundance of modern health data provides many opportunities for the use of machine learning techniques to build better statistical models to improve clinical decision making. Predicting time-to-event distributions, also known as survival analysis, plays a key role in many clinical applications. We introduce a variational time-to-event prediction model, named Variational Survival Inference (VSI), which builds upon recent advances in distribution learning techniques and deep neural networks. VSI addresses the challenges of non-parametric distribution estimation by ($i$) relaxing the restrictive modeling assumptions made in classical models, and ($ii$) efficiently handling the censored observations, {\it i.e.}, events that occur outside the observation window, all within the variational framework. To validate the effectiveness of our approach, an extensive set of experiments on both synthetic and real-world datasets is carried out, showing improved performance relative to competing solutions.
Causal structures for observational survival data provide crucial information regarding the relationships between covariates and time-to-event. We derive motivation from the information theoretic source coding argument, and show that incorporating the knowledge of the directed acyclic graph (DAG) can be beneficial if suitable source encoders are employed. As a possible source encoder in this context, we derive a variational inference based conditional variational autoencoder for causal structured survival prediction, which we refer to as DAGSurv. We illustrate the performance of DAGSurv on low…
Survival analysis, or time-to-event modelling, is a classical statistical problem that has garnered a lot of interest for its practical use in epidemiology, demographics or actuarial sciences. Recent advances on the subject from the point of view of machine learning have been concerned with precise per-individual predictions instead of population studies, driven by the rise of individualized medicine. We introduce here a conditional normalizing flow based estimate of the time-to-event density as a way to model highly flexible and individualized conditional survival distributions. We use a nove…
Conventional survival analysis approaches estimate risk scores or individualized time-to-event distributions conditioned on covariates. In practice, there is often great population-level phenotypic heterogeneity, resulting from (unknown) subpopulations with diverse risk profiles or survival distributions. As a result, there is an unmet need in survival analysis for identifying subpopulations with distinct risk profiles, while jointly accounting for accurate individualized time-to-event predictions. An approach that addresses this need is likely to improve characterization of individual outcome…
With the ever-growing complexity of primary health care system, proactive patient failure management is an effective way to enhancing the availability of health care resource. One key enabler is the dynamic prediction of time-to-event outcomes. Conventional explanatory statistical approach lacks the capability of making precise individual level prediction, while the data adaptive binary predictors does not provide nominal survival curves for biologically plausible survival analysis. The purpose of this article is to elucidate that the knowledge of explanatory survival analysis can significantl…
Crossing survival curves complicate how we interpret results from a clinical trial's primary endpoint. We find the function to determine a crossing point's location depends exponentially on individual survival curves. This exponential relationship between survival curves and the crossing point transforms small survival curve errors into large crossing point errors. In most cases, crossing points are sensitive to individual survival errors and may make accurately locating a crossing point unsuccessful. We argue more complicated analyses for mitigating crossing points should be reserved only aft…
Accurate models of patient survival probabilities provide important information to clinicians prescribing care for life-threatening and terminal ailments. A recently developed class of models - known as individual survival distributions (ISDs) - produces patient-specific survival functions that offer greater descriptive power of patient outcomes than was previously possible. Unfortunately, at the time of writing, ISD models almost universally lack uncertainty quantification. In this paper, we demonstrate that an existing method for estimating simultaneous prediction intervals from samples can …
The call for patient-focused drug development is loud and clear, as expressed in the 21st Century Cures Act and in recent guidelines and initiatives of regulatory agencies. Among the factors contributing to modernized drug development and improved health-care activities are easily interpretable measures of clinical benefit. In addition, special care is needed for cancer trials with time-to-event endpoints if the treatment effect is not constant over time. We propose the predictive individual effect which is a patient-centric and tangible measure of clinical benefit under a wide variety of scen…
Understanding Long-Term Dynamics of Individual Metro Usage: A Hidden Semi-Markov State Framework with Survival Analysis
Tongji University（同济大学）；Shanghai Key Laboratory of Rail Infrastructure Durability and System Safety, Tongji University（同济大学上海轨道交通基础设施耐久性与系统安全重点实验室）；Politecnico di Milano（米兰理工大学）；MOX Laboratory - Department of Mathematics, Politecnico di Milano（米兰理工大学数学系MOX实验室）；Department of Management, Economics and Industrial Engineering, Politecnico di Milano（米兰理工大学管理、经济与工业工程系）；Dipartimento di Elettronica, Informazione e Bioingegneria (DEIB), Politecnico di Milano（米兰理工大学电子、信息与生物工程系）；Technical Center of Shanghai Shentong Metro Group Co., Ltd.（上海申通地铁集团有限公司技术中心）
A personalized Uncertainty Quantification framework for patient survival models: estimating individual uncertainty of patients with metastatic brain tumors in the absence of ground truth
Kernel survival analysis methods predict subject-specific survival curves and times using information about which training subjects are most similar to a test subject. These most similar training subjects could serve as forecast evidence. How similar any two subjects are is given by the kernel function. In this paper, we present the first neural network framework that learns which kernel functions to use in kernel survival analysis. We also show how to use kernel functions to construct prediction intervals of survival time estimates that are statistically valid for individuals similar to a tes…
Modelling customer churn for the retail industry in a deep learning based sequential framework
University of Essex（埃塞克斯大学）；Profusion Media Ltd.（Profusion传媒有限公司）；Essex Business School（埃塞克斯商学院）；Friedrich-Alexander University Erlangen-Nuremberg（埃尔朗根-纽伦堡弗里德里希-亚历山大大学）
Unobserved individual heterogeneity is a common challenge in population cancer survival studies. This heterogeneity is usually associated with the combination of model misspecification and the failure to record truly relevant variables. We investigate the effects of unobserved individual heterogeneity in the context of excess hazard models, one of the main tools in cancer epidemiology. We propose an individual excess hazard frailty model to account for individual heterogeneity. This represents an extension of frailty modelling to the relative survival framework. In order to facilitate the infe…
Dana–Farber Cancer Institute（达纳-法伯癌症研究所）；Harvard Medical School（哈佛医学院）；University of Oxford（牛津大学）；Improbable（Improbable公司）
Survival models are a popular tool for the analysis of time to event data with applications in medicine, engineering, economics, and many more. Advances like the Cox proportional hazard model have enabled researchers to better describe hazard rates for the occurrence of single fatal events, but are unable to accurately model competing events and transitions. Common phenomena are often better described through multiple states, for example: the progress of a disease modeled as healthy, sick and dead instead of healthy and dead, where the competing nature of death and disease has to be taken into…
Balanced representation learning methods have been applied successfully to counterfactual inference from observational data. However, approaches that account for survival outcomes are relatively limited. Survival data are frequently encountered across diverse medical applications, i.e., drug development, risk profiling, and clinical trials, and such data are also relevant in fields like manufacturing (e.g., for equipment monitoring). When the outcome of interest is a time-to-event, special precautions for handling censored events need to be taken, as ignoring censored outcomes may lead to bias…
Multilevel network meta-regression for multistate models: Population-adjusted joint synthesis of progression and survival data from individual and aggregate evidence
University of California, San Francisco（旧金山加利福尼亚大学）；UCSF Helen Diller Family Comprehensive Cancer Center（UCSF海伦·迪勒家族综合癌症中心）；The Philip R. Lee Institute for Health Policy Studies（菲利普·李健康政策研究所）；Precision AQ
Organizations interact with the environment and with other organizations, and these interactions constitute an important way of learning and evolution. To overcome the problems that they face during their existence, organizations must certainly adopt survival strategies, both individually and in group. The aim of this study is to evaluate the effect of a set of prognostic factors (organizational, size, collaborate strategies, etc.) in the survival of organizational networks. Statistical methods for time to event data were used to analyze the data. We have used the Kaplan-Meier product-limit me…
We present a general approach to synthesizing evidence of time-to-event endpoints in meta-analyses of aggregate data (AD). Our work goes beyond most previous meta-analytic research by using reconstructed survival data as a source of information. A Bayesian multilevel regression model, called the "meta-analysis of reconstructed survival data" (MARS), is introduced, by modeling and integrating reconstructed survival information with other types of summary data, to estimate the hazard ratio function and survival probabilities. The method attempts to reduce selection bias, and relaxes the presumpt…
Google Research（谷歌研究院）；Carnegie Mellon University（卡内基梅隆大学）
Survival analysis is a challenging variation of regression modeling because of the presence of censoring, where the outcome measurement is only partially known, due to, for example, loss to follow up. Such problems come up frequently in medical applications, making survival analysis a key endeavor in biostatistics and machine learning for healthcare, with Cox regression models being amongst the most commonly employed models. We describe a new approach for survival analysis regression models, based on learning mixtures of Cox regressions to model individual survival distributions. We propose an…
Most papers implicitly assume competing risks to be induced by residual cohort heterogeneity, i.e. heterogeneity that is not captured by the recorded covariates. Based on this observation we develop a generic statistical description of competing risks that unifies the main schools of thought. Assuming heterogeneity-induced competing risks is much weaker than assuming risk independence. However, we show that it still imposes sufficient constraints to solve the competing risk problem, and derive exact formulae for decontaminated primary risk hazard rates and cause-specific survival functions. Th…
Estimating individualized treatment rules is a central task for personalized medicine. [zhao2012estimating] and [zhang2012robust] proposed outcome weighted learning to estimate individualized treatment rules directly through maximizing the expected outcome without modeling the response directly. In this paper, we extend the outcome weighted learning to right censored survival data without requiring either an inverse probability of censoring weighting or a semiparametric modeling of the censoring and failure times as done in [zhao2015doubly]. To accomplish this, we take advantage of the tree ba…
Medical investigations focusing on patient survival often generate not only a failure time for each patient but also a sequence of measurements on patient health at annual or semi-annual check-ups while the patient remains alive. Such a sequence of random length accompanied by a survival time is called a survival process. Ordinarily robust health is associated with longer survival, so the two parts of a survival process cannot be assumed independent. This paper is concerned with a general technique---time reversal---for constructing statistical models for survival processes. A revival model is…
Memorial Sloan Kettering Cancer Center（纪念斯隆·凯特琳癌症中心）
Accurate and robust cell nuclei classification is the cornerstone for a wider range of tasks in digital and Computational Pathology. However, most machine learning systems require extensive labeling from expert pathologists for each individual problem at hand, with no or limited abilities for knowledge transfer between datasets and organ sites. In this paper we implement and evaluate a variety of deep neural network models and model ensembles for nuclei classification in renal cell cancer (RCC) and prostate cancer (PCa). We propose a convolutional neural network system based on residual learni…
Tree-based methods for length-biased survival data
National Cancer Center（韩国国立癌症中心）；Yonsei University（延世大学）；Seoul National University College of Medicine（首尔大学医学院）；Seoul Metropolitan Government-Seoul National University Boramae Medical Center（首尔市政府-首尔大学八良医疗中心）；Ewha Womans University（梨花女子大学）
ETH Zürich（苏黎世联邦理工学院）；Human Technopole（人类技术园）；University Hospital Basel（巴塞尔大学医院）；University Children’s Hospital Basel（巴塞尔大学儿童医院）；University of Zürich（苏黎世大学）；Politecnico di Milano（米兰理工大学）；St. Gallen Cantonal Hospital（圣加仑州立医院）
In this work, we study the problem of clustering survival data $-$ a challenging and so far under-explored task. We introduce a novel semi-supervised probabilistic approach to cluster survival data by leveraging recent advances in stochastic gradient variational inference. In contrast to previous work, our proposed method employs a deep generative model to uncover the underlying distribution of both the explanatory variables and censored survival times. We compare our model to the related work on clustering and mixture models for survival data in comprehensive experiments on a wide range of sy…
Medical practitioners use survival models to explore and understand the relationships between patients' covariates (e.g. clinical and genetic features) and the effectiveness of various treatment options. Standard survival models like the linear Cox proportional hazards model require extensive feature engineering or prior medical knowledge to model treatment interaction at an individual level. While nonlinear survival methods, such as neural networks and survival forests, can inherently model these high-level interaction terms, they have yet to be shown as effective treatment recommender system…
For estimating conditional survival functions, non-parametric estimators can be preferred to parametric and semi-parametric estimators due to relaxed assumptions that enable robust estimation. Yet, even when misspecified, parametric and semi-parametric estimators can possess better operating characteristics in small sample sizes due to smaller variance than non-parametric estimators. Fundamentally, this is a bias-variance tradeoff situation in that the sample size is not large enough to take advantage of the low bias of non-parametric estimation. Stacked survival models estimate an optimally w…
Many researchers have investigated first hitting times as models for survival data. First hitting times arise naturally in many types of stochastic processes, ranging from Wiener processes to Markov chains. In a survival context, the state of the underlying process represents the strength of an item or the health of an individual. The item fails or the individual experiences a clinical endpoint when the process reaches an adverse threshold state for the first time. The time scale can be calendar time or some other operational measure of degradation or disease progression. In many applications,…
Extended cure survival models enable to separate covariates that affect the probability of an event (or `long-term' survival) from those only affecting the event timing (or `short-term' survival). We propose to generalize the bounded cumulative hazard model to handle additive terms for time-varying (exogenous) covariates jointly impacting long- and short-term survival. The selection of the penalty parameters is a challenge in that framework. A fast algorithm based on Laplace approximations in Bayesian P-spline models is proposed. The methodology is motivated by fertility studies where women's …
Tree-based methods are popular nonparametric tools in studying time-to-event outcomes. In this article, we introduce a novel framework for survival trees and ensembles, where the trees partition the dynamic survivor population and can handle time-dependent covariates. Using the idea of randomized tests, we develop generalized time-dependent Receiver Operating Characteristic (ROC) curves for evaluating the performance of survival trees. The tree-building algorithm is guided by decision-theoretic criteria based on ROC, targeting specifically for prediction accuracy. To address the instability is…
A model for competing (resp. complementary) risks survival data where the failure time can be left (resp. right) censored is proposed. Product-limit estimators for the survival functions of the individual risks are derived. We deduce the strong convergence of our estimators on the whole real half-line without any additional assumptions and their asymptotic normality under conditions concerning only the observed distribution. When the observations are generated according to the double censoring model introduced by Turnbull, the product-limit estimators represent upper and lower bounds for Turnb…
Many medical decisions involve the use of dynamic information collected on individual patients toward predicting likely transitions in their future health status. If accurate predictions are developed, then a prognostic mode can identify patients at greatest risk for future adverse events, and may be used clinically to define populations appropriate for targeted intervention. In practice, a prognostic model is often used to guide decisions at multiple time points over the course of disease, and classification performance, i.e. sensitivity and specificity, for distinguishing high-risk versus lo…
A treatment regime is a deterministic function that dictates personalized treatment based on patients' individual prognostic information. There is a fast-growing interest in finding optimal treatment regimes to maximize expected long-term clinical outcomes of patients for complex diseases, such as cancer and AIDS. For many clinical studies with survival time as a primary endpoint, a main goal is to maximize patients' survival probabilities given treatments. In this article, we first propose two nonparametric estimators for survival function of patients following a given treatment regime. Then,…
Colorectal cancer (CRC) is the third most frequent malignant disease in the world. In some countries with established screening programs, its incidence and mortality have decreased, and survival has improved. AIMS: To obtain reliable data about the epidemiology of CRC in Chile, we analyzed the trends in the last ten years and the influence of observable factors on survival, including explicit guarantees in CRC treatment access (GES program). Publicly available data published by the Health Ministry and National Institute of Statistics were used. Data were obtained from registries of mortality a…
An accurate model of a patient's individual survival distribution can help determine the appropriate treatment for terminal patients. Unfortunately, risk scores (e.g., from Cox Proportional Hazard models) do not provide survival probabilities, single-time probability models (e.g., the Gail model, predicting 5 year probability) only provide for a single time point, and standard Kaplan-Meier survival curves provide only population averages for a large class of patients meaning they are not specific to individual patients. This motivates an alternative class of tools that can learn a model which …
University Hospital Bern（伯尔尼大学医院）；Auckland City Hospital（奥克兰市医院）；Swiss Institute of Bioinformatics（瑞士生物信息研究所）
Dynamic assessment of mortality risk in the intensive care unit (ICU) can be used to stratify patients, inform about treatment effectiveness or serve as part of an early-warning system. Static risk scoring systems, such as APACHE or SAPS, have recently been supplemented with data-driven approaches that track the dynamic mortality risk over time. Recent works have focused on enhancing the information delivered to clinicians even further by producing full survival distributions instead of point predictions or fixed horizon risks. In this work, we propose a non-parametric ensemble model, Weighted…
LaMME（拉梅实验室）；Paris Saclay University / UEVE（巴黎萨克雷大学/埃夫里大学）；LaMME - CNRS（拉梅实验室-法国国家科学研究中心）；IBISC（IBISC实验室）
Individual Treatment Effects (ITE) estimation methods have risen in popularity in the last years. Most of the time, individual effects are better presented as Conditional Average Treatment Effects (CATE). Recently, representation balancing techniques have gained considerable momentum in causal inference from observational data, still limited to continuous (and binary) outcomes. However, in numerous pathologies, the outcome of interest is a (possibly censored) survival time. Our paper proposes theoretical guarantees for a representation balancing framework applied to counterfactual inference in…
