In this chapter, we explore the potential applications of machine learning to brain disorders. Specifically, we illustrate why the use of machine learning in brain disorders is attracting so much interest among researchers and clinicians by highlighting three key applications: prediction of illness onset, assistance with diagnosis, and prediction of longitudinal outcomes. After illustrating these applications, we discuss the challenges that need to be overcome for a successful translational implementation of machine learning in everyday psychiatric and neurologic care. In particular, we identify three main pitfalls in the absence of biomarkers, the unreliability of clinical diagnosis, and the heterogeneity of the patients. In the final part of the chapter, we consider the requirements a machine learning algorithm needs to fulfill to be eligible for clinical use and discuss potential future directions.

Applications of machine learning to brain disorders

Scarpazza C.;Mechelli A.
2019

Abstract

In this chapter, we explore the potential applications of machine learning to brain disorders. Specifically, we illustrate why the use of machine learning in brain disorders is attracting so much interest among researchers and clinicians by highlighting three key applications: prediction of illness onset, assistance with diagnosis, and prediction of longitudinal outcomes. After illustrating these applications, we discuss the challenges that need to be overcome for a successful translational implementation of machine learning in everyday psychiatric and neurologic care. In particular, we identify three main pitfalls in the absence of biomarkers, the unreliability of clinical diagnosis, and the heterogeneity of the patients. In the final part of the chapter, we consider the requirements a machine learning algorithm needs to fulfill to be eligible for clinical use and discuss potential future directions.
2019
Machine Learning: Methods and Applications to Brain Disorders
9780128157398
File in questo prodotto:
Non ci sono file associati a questo prodotto.
Pubblicazioni consigliate

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/11577/3356186
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 11
  • ???jsp.display-item.citation.isi??? ND
  • OpenAlex ND
social impact