Patients diagnosed with chronic conditions are visited multiple times over the years. The medical reports produced during these visits often include valuable knowledge in the form of free text. To help physician access and review this knowledge, natural language processing and aggregation techniques are needed. In this work, we propose a system that extracts and summarizes information from medical reports written in Italian. For each patient, the system builds and visualizes a timeline of the extracted events. The proposed approach has the potential to enhance the process of reviewing patient clinical histories, reducing the time needed to access large amounts of data. In the future, an extension of the visualized timeline and an extrinsic evaluation will be performed. © 2017 IEEE.

Clinical timelines development from textual medical reports in Italian

Viani, Natalia;Sacchi, Lucia;Tibollo, Valentina;Napolitano, Carlo;Priori, Silvia G;Bellazzi, Riccardo
2017-01-01

Abstract

Patients diagnosed with chronic conditions are visited multiple times over the years. The medical reports produced during these visits often include valuable knowledge in the form of free text. To help physician access and review this knowledge, natural language processing and aggregation techniques are needed. In this work, we propose a system that extracts and summarizes information from medical reports written in Italian. For each patient, the system builds and visualizes a timeline of the extracted events. The proposed approach has the potential to enhance the process of reviewing patient clinical histories, reducing the time needed to access large amounts of data. In the future, an extension of the visualized timeline and an extrinsic evaluation will be performed. © 2017 IEEE.
2017
9781538639061
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11571/1234306
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? 0
social impact