A multi-locus predictiveness curve and its summary assessment for genetic risk prediction

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Wei, Changshuai, Li, Ming, Wen, Yalu, Ye, Chengyin, Lu, Qing
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908292369874944
author Wei, Changshuai
Li, Ming
Wen, Yalu
Ye, Chengyin
Lu, Qing
author_facet Wei, Changshuai
Li, Ming
Wen, Yalu
Ye, Chengyin
Lu, Qing
contents With the advance of high-throughput genotyping and sequencing technologies, it becomes feasible to comprehensive evaluate the role of massive genetic predictors in disease prediction. There exists, therefore, a critical need for developing appropriate statistical measurements to access the combined effects of these genetic variants in disease prediction. Predictiveness curve is commonly used as a graphical tool to measure the predictive ability of a risk prediction model on a single continuous biomarker. Yet, for most complex diseases, risk prediciton models are formed on multiple genetic variants. We therefore propose a multi-marker predictiveness curve and provide a non-parametric method to construct the curve for case-control studies. We further introduce a global predictiveness U and a partial predictiveness U to summarize prediction curve across the whole population and sub-population of clinical interest, respectively. We also demonstrate the connections of predictiveness curve with ROC curve and Lorenz curve. Through simulation, we compared the performance of the predictiveness U to other three summary indices: R square, Total Gain, and Average Entropy, and showed that Predictiveness U outperformed the other three indexes in terms of unbiasedness and robustness. Moreover, we simulated a series of rare-variants disease model, found partial predictiveness U performed better than global predictiveness U. Finally, we conducted a real data analysis, using predictiveness curve and predictiveness U to evaluate a risk prediction model for Nicotine Dependence.
format Preprint
id arxiv_https___arxiv_org_abs_2504_00024
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A multi-locus predictiveness curve and its summary assessment for genetic risk prediction
Wei, Changshuai
Li, Ming
Wen, Yalu
Ye, Chengyin
Lu, Qing
Methodology
Artificial Intelligence
Machine Learning
With the advance of high-throughput genotyping and sequencing technologies, it becomes feasible to comprehensive evaluate the role of massive genetic predictors in disease prediction. There exists, therefore, a critical need for developing appropriate statistical measurements to access the combined effects of these genetic variants in disease prediction. Predictiveness curve is commonly used as a graphical tool to measure the predictive ability of a risk prediction model on a single continuous biomarker. Yet, for most complex diseases, risk prediciton models are formed on multiple genetic variants. We therefore propose a multi-marker predictiveness curve and provide a non-parametric method to construct the curve for case-control studies. We further introduce a global predictiveness U and a partial predictiveness U to summarize prediction curve across the whole population and sub-population of clinical interest, respectively. We also demonstrate the connections of predictiveness curve with ROC curve and Lorenz curve. Through simulation, we compared the performance of the predictiveness U to other three summary indices: R square, Total Gain, and Average Entropy, and showed that Predictiveness U outperformed the other three indexes in terms of unbiasedness and robustness. Moreover, we simulated a series of rare-variants disease model, found partial predictiveness U performed better than global predictiveness U. Finally, we conducted a real data analysis, using predictiveness curve and predictiveness U to evaluate a risk prediction model for Nicotine Dependence.
title A multi-locus predictiveness curve and its summary assessment for genetic risk prediction
topic Methodology
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2504.00024