{rfName}
A

Indexed in

Citations

3

Altmetrics

Analysis of institutional authors

Santamaria LpAuthorGarcia GlAuthorZanin MAuthorRuíz EmAuthorRodríguez-González AAuthor

Share

February 17, 2022
Publications
>
Proceedings Paper
No

A meta-path-based prediction method for disease comorbidities

Publicated to: Proceedings of the IEEE Symposium on Computer-Based Medical Systems. 2021-June 219-224 - 2021-01-01 2021-June(), DOI: 10.1109/CBMS52027.2021.00022

Authors:

del Valle, EPG; Santamaría, LP; García, GL; Zanin, M; Ruiz, EM; Rodríguez-González, A
[+]

Affiliations

CSIC UIB, Inst Fis Interdisciplinar & Sistemas Complejos IF, Campus UIB, Palma De Mallorca, Spain - Author
CSIC-UIB - Instituto de Fisica Interdisciplinar y Sistemas Complejos (IFISC) - Author
Univ Politecn Madrid, Ctr Tecnol Biomed, Madrid, Spain - Author
Univ Politecn Madrid, ETS Ingn Infonnat, Ctr Tecnol Biomed, Madrid, Spain - Author
Univ Politecn Madrid, ETS Ingn Informat, Madrid, Spain - Author
Universidad Politécnica de Madrid - Author
See more

Abstract

The simultaneous presence of diseases worsens the prognosis of patients and makes their treatment difficult. Identifying the co-occurrence of diseases is key to improving the situation of patients and designing effective therapeutic strategies. On the one hand, the increasing availability of clinical information opens new ways to unveil hidden relationships between diseases. On the other hand, heterogeneous information networks have been used in recent years to discover novel knowledge from disease data, including symptoms, genes or drugs. The use of meta-paths allows the complex semantics of the relationships between the different types of nodes to be included in heterogeneous networks. In this study, we propose a system to predict disease comorbidities through the use of meta-paths in a heterogeneous network of diseases and symptoms, built from textual sources of public access. The results obtained improve those of similar studies based on biological data, and the predictions calculated for diabetes and Crohn's disease are supported by medical literature. Both the used data and the obtained prediction model are publicly accessible.
[+]

Keywords

graph structure learningheterogeneous disease networksmedical text miningmeta pathsDisease comorbidityGraph structure learningHeterogeneous disease networksInflammatory-bowel-diseaseMedical text miningMeta-paths

Quality index

Bibliometric impact. Analysis of the contribution and dissemination channel

The work has been published in the journal Proceedings of the IEEE Symposium on Computer-Based Medical Systems, Q3 Agency Scopus (SJR), its regional focus and specialization in Computer Science Applications, give it significant recognition in a specific niche of scientific knowledge at an international level.

Independientemente del impacto esperado determinado por el canal de difusión, es importante destacar el impacto real observado de la propia aportación.

Según las diferentes agencias de indexación, el número de citas acumuladas por esta publicación hasta la fecha 2026-04-05:

  • Scopus: 3
[+]

Impact and social visibility

From the perspective of influence or social adoption, and based on metrics associated with mentions and interactions provided by agencies specializing in calculating the so-called "Alternative or Social Metrics," we can highlight as of 2026-04-05:

  • The use of this contribution in bookmarks, code forks, additions to favorite lists for recurrent reading, as well as general views, indicates that someone is using the publication as a basis for their current work. This may be a notable indicator of future more formal and academic citations. This claim is supported by the result of the "Capture" indicator, which yields a total of: 1 (PlumX).
[+]

Leadership analysis of institutional authors

There is a significant leadership presence as some of the institution’s authors appear as the first or last signer, detailed as follows: First Author (Del Valle EPG) and Last Author (GARCÍA DEL VALLE, EDUARDO PANTALEÓN).

the author responsible for correspondence tasks has been Del Valle EPG.

[+]

Project objectives

El presente estudio persigue los siguientes objetivos: analizar la coocurrencia de enfermedades para mejorar el pronóstico y tratamiento de pacientes; evaluar la utilidad de la información clínica disponible para descubrir relaciones ocultas entre enfermedades; desarrollar un sistema de predicción de comorbilidades mediante meta-paths en redes heterogéneas de enfermedades y síntomas construidas a partir de fuentes textuales públicas; comparar los resultados obtenidos con estudios previos basados en datos biológicos; y validar las predicciones para diabetes y enfermedad de Crohn mediante evidencia médica. Además, se busca garantizar la accesibilidad pública tanto de los datos utilizados como del modelo predictivo generado.
[+]

Most relevant results

El estudio presenta un método basado en meta-paths para predecir comorbilidades de enfermedades mediante una red heterogénea de enfermedades y síntomas construida a partir de fuentes textuales públicas. Los resultados más relevantes son: la mejora en la predicción de comorbilidades respecto a estudios similares basados en datos biológicos; la validación de las predicciones para diabetes y enfermedad de Crohn mediante literatura médica; la incorporación de la semántica compleja de relaciones entre nodos mediante meta-paths; y la disponibilidad pública tanto de los datos empleados como del modelo predictivo desarrollado. Estos hallazgos contribuyen a la identificación precisa de co-ocurrencias patológicas.
[+]