版权所有:内蒙古大学图书馆 技术提供:维普资讯• 智图
内蒙古自治区呼和浩特市赛罕区大学西街235号 邮编: 010021
作者机构:Univ Torino Computat Biomed Unit Dept Med Sci Via Santena 19 I-10126 Turin Italy IRCCS Humanitas Res Hosp Via Manzoni 56 I-20089 Rozzano Milan Italy Train Srl via Alessandro Manzoni 56 I-20089 Rozzano Milan Italy Univ Bologna Dept Med & Surg Sci DIMEC I-40126 Bologna Italy IRCCS Ist Sci Neurol Bologna I-40138 Bologna Italy Hop St Louis Hematol Bone Marrow Transplantat Paris France Univ Hosp Leipzig Med Clin & Policlin 1 Hematol & Cellular Therapy Leipzig Germany Hosp Univ Salamanca Hematol Dept Salamanca Spain MLL Munich Leukemia Lab Max Lebsche Pl 31 Munich Germany IRCCS Azienda Osped Univ Bologna S Orsola I-40138 Bologna Italy Humanitas Univ Dept Biomed Sci Via Montalcini 4 I-20072 Pieve Emanuele Milan Italy
出 版 物:《COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE》 (Comput. Methods Programs Biomed.)
年 卷 期:2025年第261卷
页 面:108605-108605页
核心收录:
学科分类:0831[工学-生物医学工程(可授工学、理学、医学学位)] 1001[医学-基础医学(可授医学、理学学位)] 0812[工学-计算机科学与技术(可授工学、理学学位)] 10[医学]
基 金:GenoMed4All consortium PNRR AIRC fellowship for Italy
主 题:Survival analysis Deep Learning Variational Autoencoder Myelodysplastic syndrome Genetic-based clustering
摘 要:Background and Objectives Several computational pipelines for biomedical data have been proposed to stratify patients and to predict their prognosis through survival analysis. However, these analyses are usually performed independently, without integrating the information derived from each of them. Clustering of survival data is an underexplored problem, and current approaches are limited for biomedical applications, whose data are usually heterogeneous and multimodal, with poor scalability for high-dimensionality. Methods We introduce VAE-Surv, a multimodal computational framework for patients stratification and prognosis prediction. VAE-Surv integrates a Variational Autoencoder (VAE), which reduces the high-dimensional space characterizing the molecular data, with a deep survival model, which combines the embedded information with the clinical features. The VAE embedding step prioritizes local coherence within the feature space to detect potential nonlinear relationships among the molecular markers. The latent representation is then exploited to perform K-means clustering. To test the clinical robustness of the algorithm, VAE-Surv was applied to the Genomed4all cohort of Myelodysplastic Syndromes (MDS), comparing the identified subtypes with the World Health Organization (WHO) classification. The survival outcome was compared with the state-of-the-art Cox model and its penalized versions. Finally, to assess the generalizability of the results, the method was also validated on an external MDS cohort. Results Tested on 2,043 patients in the GenomMed4All cohort, VAE-Surv achieved a median C-index of 0.78, outperforming classical approaches. In addition, the latent space enhanced the clustering performance compared to a traditional approach that applies the clustering directly to the input data. Compared to the WHO 2016 MDS subtypes, the analysis of the identified clusters showed that the proposed framework can capture existing clinical categorizations while also sug