People are generating an enormous amount of social data to describe their health care experiences, and continuously search information about diseases, symptoms, diagnoses, doctors, treatment options, and medicines. This data can be used to extract the “social phenotype” of diseases, i.e., a subjective and unfiltered picture of perceptions, health conditions, feelings, and lifestyles of people affected by a given disease, taking into account the experience lived outside the traditional syndromic care and monitoring structures, the symptoms that are perceived as more limiting, the greater or lesser tolerance to drugs. In this chapter we present an innovative approach based on an Auto-ML pipeline to optimize the classification of relevant messages and threads, and on a cooperative deep learning topic detection model, to characterize the social phenotype of patients affected by widespread diseases, such as diabetes and hypothyroidism.

AIM in Health Blogs / Velardi, Paola; Lenzi, Andrea. - (2021), pp. 1-18. [10.1007/978-3-030-58080-3_255-1].

AIM in Health Blogs

Velardi, Paola
;
2021

Abstract

People are generating an enormous amount of social data to describe their health care experiences, and continuously search information about diseases, symptoms, diagnoses, doctors, treatment options, and medicines. This data can be used to extract the “social phenotype” of diseases, i.e., a subjective and unfiltered picture of perceptions, health conditions, feelings, and lifestyles of people affected by a given disease, taking into account the experience lived outside the traditional syndromic care and monitoring structures, the symptoms that are perceived as more limiting, the greater or lesser tolerance to drugs. In this chapter we present an innovative approach based on an Auto-ML pipeline to optimize the classification of relevant messages and threads, and on a cooperative deep learning topic detection model, to characterize the social phenotype of patients affected by widespread diseases, such as diabetes and hypothyroidism.
978-3-030-58080-3
978-3-030-58080-3
File allegati a 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: http://hdl.handle.net/11573/1571063
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact