Back to Search
Start Over
Complete hazard ranking to analyze right-censored data: An ALS survival study
- Source :
- PLoS Computational Biology, Vol 13, Iss 12, p e1005887 (2017), PLoS Computational Biology
- Publication Year :
- 2017
- Publisher :
- Public Library of Science (PLoS), 2017.
-
Abstract
- Survival analysis represents an important outcome measure in clinical research and clinical trials; further, survival ranking may offer additional advantages in clinical trials. In this study, we developed GuanRank, a non-parametric ranking-based technique to transform patients' survival data into a linear space of hazard ranks. The transformation enables the utilization of machine learning base-learners including Gaussian process regression, Lasso, and random forest on survival data. The method was submitted to the DREAM Amyotrophic Lateral Sclerosis (ALS) Stratification Challenge. Ranked first place, the model gave more accurate ranking predictions on the PRO-ACT ALS dataset in comparison to Cox proportional hazard model. By utilizing right-censored data in its training process, the method demonstrated its state-of-the-art predictive power in ALS survival ranking. Its feature selection identified multiple important factors, some of which conflicts with previous studies.<br />Author summary We present a novel rank-based algorithm that outputs the survival likelihood of the ALS patients from the survival data. This novel method enabled us to adopt commonplace machine learning base-learners in survival analysis of ALS and provided insight into the disease.
- Subjects :
- Male
Databases, Factual
Computer science
Normal Distribution
Kaplan-Meier Estimate
01 natural sciences
Machine Learning
Motor Neuron Diseases
010104 statistics & probability
0302 clinical medicine
Mathematical and Statistical Techniques
Lasso (statistics)
Statistics
Medicine and Health Sciences
lcsh:QH301-705.5
Ecology
Applied Mathematics
Simulation and Modeling
Regression analysis
Neurodegenerative Diseases
Computational Theory and Mathematics
Neurology
Research Design
Modeling and Simulation
Physical Sciences
Regression Analysis
Learning to rank
Female
Algorithms
Statistics (Mathematics)
Research Article
Computer and Information Sciences
Drug Research and Development
Clinical Research Design
Feature selection
Research and Analysis Methods
Statistics, Nonparametric
03 medical and health sciences
Cellular and Molecular Neuroscience
Machine Learning Algorithms
Artificial Intelligence
Ranking Algorithms
Genetics
Humans
Clinical Trials
0101 mathematics
Statistical Methods
Molecular Biology
Ecology, Evolution, Behavior and Systematics
Survival analysis
Proportional Hazards Models
Pharmacology
Proportional hazards model
Amyotrophic Lateral Sclerosis
Computational Biology
Survival Analysis
Ranking
lcsh:Biology (General)
Clinical Medicine
030217 neurology & neurosurgery
Mathematics
Forecasting
Subjects
Details
- Language :
- English
- ISSN :
- 15537358
- Volume :
- 13
- Issue :
- 12
- Database :
- OpenAIRE
- Journal :
- PLoS Computational Biology
- Accession number :
- edsair.doi.dedup.....e401afe676cda640e0bd3dc6ce01fd00