The Concordance Index Decomposition: A Measure for a Deeper Understanding of Survival Prediction Models
Uloženo v:
| Název: | The Concordance Index Decomposition: A Measure for a Deeper Understanding of Survival Prediction Models |
|---|---|
| Autoři: | Alabdallah, Abdallah, 1979, Ohlsson, Mattias, 1967, Pashami, Sepideh, 1985, Rögnvaldsson, Thorsteinn, 1963 |
| Zdroj: | Artificial Intelligence in Medicine. 148:1-10 |
| Témata: | Survival Analysis, Evaluation Metric, Concordance Index, Variational Encoder-Decoder |
| Popis: | The Concordance Index (C-index) is a commonly used metric in Survival Analysis for evaluating the performance of a prediction model. This paper proposes a decomposition of the C-index into a weighted harmonic mean of two quantities: one for ranking observed events versus other observed events, and the other for ranking observed events versus censored cases. This decomposition enables a more fine-grained analysis of the strengths and weaknesses of survival prediction methods. The usefulness of this decomposition is demonstrated through benchmark comparisons against state-of-the-art and classical models, together with a new variational generative neural-network-based method (SurVED), which is also proposed in this paper. Performance is assessed using four publicly available datasets with varying levels of censoring. The analysis using the C-index decomposition and synthetic censoring shows that deep learning models utilize the observed events more effectively than other models, allowing them to keep a stable C-index in different censoring levels. In contrast, classical machine learning models deteriorate when the censoring level decreases due to their inability to improve on ranking the events versus other events. © 2024 The Author(s) |
| Popis souboru: | |
| Přístupová URL adresa: | https://urn.kb.se/resolve?urn=urn:nbn:se:hh:diva-52259 https://doi.org/10.1016/j.artmed.2024.102781 |
| Databáze: | SwePub |
Full Text Finder 
Nájsť tento článok vo Web of Science | Abstrakt: | The Concordance Index (C-index) is a commonly used metric in Survival Analysis for evaluating the performance of a prediction model. This paper proposes a decomposition of the C-index into a weighted harmonic mean of two quantities: one for ranking observed events versus other observed events, and the other for ranking observed events versus censored cases. This decomposition enables a more fine-grained analysis of the strengths and weaknesses of survival prediction methods. The usefulness of this decomposition is demonstrated through benchmark comparisons against state-of-the-art and classical models, together with a new variational generative neural-network-based method (SurVED), which is also proposed in this paper. Performance is assessed using four publicly available datasets with varying levels of censoring. The analysis using the C-index decomposition and synthetic censoring shows that deep learning models utilize the observed events more effectively than other models, allowing them to keep a stable C-index in different censoring levels. In contrast, classical machine learning models deteriorate when the censoring level decreases due to their inability to improve on ranking the events versus other events. © 2024 The Author(s) |
|---|---|
| ISSN: | 09333657 |
| DOI: | 10.1016/j.artmed.2024.102781 |