Long-term cancer survival prediction using multimodal deep learning

Abstract The age of precision medicine demands powerful computational techniques to handle high-dimensional patient data. We present MultiSurv, a multimodal deep learning method for long-term pan-cancer survival prediction. MultiSurv uses dedicated submodels to establish feature representations of c...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Luís A. Vale-Silva, Karl Rohr
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/2d62f466731f45de90e5884414084733
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:2d62f466731f45de90e5884414084733
record_format	dspace
spelling	oai:doaj.org-article:2d62f466731f45de90e58844140847332021-12-02T18:18:58ZLong-term cancer survival prediction using multimodal deep learning10.1038/s41598-021-92799-42045-2322https://doaj.org/article/2d62f466731f45de90e58844140847332021-06-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-92799-4https://doaj.org/toc/2045-2322Abstract The age of precision medicine demands powerful computational techniques to handle high-dimensional patient data. We present MultiSurv, a multimodal deep learning method for long-term pan-cancer survival prediction. MultiSurv uses dedicated submodels to establish feature representations of clinical, imaging, and different high-dimensional omics data modalities. A data fusion layer aggregates the multimodal representations, and a prediction submodel generates conditional survival probabilities for follow-up time intervals spanning several decades. MultiSurv is the first non-linear and non-proportional survival prediction method that leverages multimodal data. In addition, MultiSurv can handle missing data, including single values and complete data modalities. MultiSurv was applied to data from 33 different cancer types and yields accurate pan-cancer patient survival curves. A quantitative comparison with previous methods showed that Multisurv achieves the best results according to different time-dependent metrics. We also generated visualizations of the learned multimodal representation of MultiSurv, which revealed insights on cancer characteristics and heterogeneity.Luís A. Vale-SilvaKarl RohrNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-12 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Luís A. Vale-Silva Karl Rohr Long-term cancer survival prediction using multimodal deep learning
description	Abstract The age of precision medicine demands powerful computational techniques to handle high-dimensional patient data. We present MultiSurv, a multimodal deep learning method for long-term pan-cancer survival prediction. MultiSurv uses dedicated submodels to establish feature representations of clinical, imaging, and different high-dimensional omics data modalities. A data fusion layer aggregates the multimodal representations, and a prediction submodel generates conditional survival probabilities for follow-up time intervals spanning several decades. MultiSurv is the first non-linear and non-proportional survival prediction method that leverages multimodal data. In addition, MultiSurv can handle missing data, including single values and complete data modalities. MultiSurv was applied to data from 33 different cancer types and yields accurate pan-cancer patient survival curves. A quantitative comparison with previous methods showed that Multisurv achieves the best results according to different time-dependent metrics. We also generated visualizations of the learned multimodal representation of MultiSurv, which revealed insights on cancer characteristics and heterogeneity.
format	article
author	Luís A. Vale-Silva Karl Rohr
author_facet	Luís A. Vale-Silva Karl Rohr
author_sort	Luís A. Vale-Silva
title	Long-term cancer survival prediction using multimodal deep learning
title_short	Long-term cancer survival prediction using multimodal deep learning
title_full	Long-term cancer survival prediction using multimodal deep learning
title_fullStr	Long-term cancer survival prediction using multimodal deep learning
title_full_unstemmed	Long-term cancer survival prediction using multimodal deep learning
title_sort	long-term cancer survival prediction using multimodal deep learning
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/2d62f466731f45de90e5884414084733
work_keys_str_mv	AT luisavalesilva longtermcancersurvivalpredictionusingmultimodaldeeplearning AT karlrohr longtermcancersurvivalpredictionusingmultimodaldeeplearning
_version_	1718378144350601216

Long-term cancer survival prediction using multimodal deep learning

Ejemplares similares