Effective Ways to Build and Evaluate Individual Survival Distributions

11/28/2018
by   Humza Haider, et al.
0

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 provides an individual survival distribution which gives survival probabilities across all times - such as extensions to the Cox model, Accelerated Failure Time, an extension to Random Survival Forests, and Multi-Task Logistic Regression. This paper first motivates such "individual survival distribution" (ISD) models, and explains how they differ from standard models. It then discusses ways to evaluate such models - namely Concordance, 1-Calibration, Brier score, and various versions of L1-loss - and then motivates and defines a novel approach "D-Calibration", which determines whether a model's probability estimates are meaningful. We also discuss how these measures differ, and use them to evaluate several ISD prediction tools, over a range of survival datasets.

READ FULL TEXT

page 15

page 28

research
05/29/2017

Deep Learning for Patient-Specific Kidney Graft Survival Analysis

An accurate model of patient-specific kidney graft survival distribution...
research
09/02/2020

Analysis of survival data with non-proportional hazards: A comparison of propensity score weighted methods

One of the most common ways researchers compare survival outcomes across...
research
09/13/2023

Predicting Survival Time of Ball Bearings in the Presence of Censoring

Ball bearings find widespread use in various manufacturing and mechanica...
research
12/19/2022

Discrimination, calibration, and point estimate accuracy of GRU-D-Weibull architecture for real-time individualized endpoint prediction

Real-time individual endpoint prediction has always been a challenging t...
research
08/14/2023

GRU-D-Weibull: A Novel Real-Time Individualized Endpoint Prediction

Accurate prediction models for individual-level endpoints and time-to-en...
research
03/19/2020

Uncertainty Estimation in Cancer Survival Prediction

Survival models are used in various fields, such as the development of c...
research
02/05/2015

A mixture Cox-Logistic model for feature selection from survival and classification data

This paper presents an original approach for jointly fitting survival ti...

Please sign up or login with your details

Forgot password? Click here to reset