Chapter Supporting decision-makers in healthcare domain. A comparative study of two interpretative proposals for Random Forests

The growing success of Machine Learning (ML) is making significant improvements to predictive models, facilitating their integration in various application fields, especially the healthcare context. However, it still has limitations and drawbacks, such as the lack of interpretability which does not...

Πλήρης περιγραφή

Αποθηκεύτηκε σε:
Λεπτομέρειες βιβλιογραφικής εγγραφής
Κύριοι συγγραφείς: Aria, Massimo, Cuccurullo, Corrado, Gnasso, Agostino
Μορφή: Online
Γλώσσα:Αγγλικά
Έκδοση: Firenze University Press 2022
Θέματα:
Διαθέσιμο Online:ONIX_20220601_9788855184618_561
Ετικέτες: Προσθήκη ετικέτας
Δεν υπάρχουν, Καταχωρήστε ετικέτα πρώτοι!
_version_ 1869528350920278016
author Aria, Massimo
Cuccurullo, Corrado
Gnasso, Agostino
author_browse Aria, Massimo
Cuccurullo, Corrado
Gnasso, Agostino
author_facet Aria, Massimo
Cuccurullo, Corrado
Gnasso, Agostino
author_sort Aria, Massimo
collection Directory of Open Access Books
description The growing success of Machine Learning (ML) is making significant improvements to predictive models, facilitating their integration in various application fields, especially the healthcare context. However, it still has limitations and drawbacks, such as the lack of interpretability which does not allow users to understand how certain decisions are made. This drawback is identified with the term "Black-Box", as well as models that do not allow to interpret the internal work of certain ML techniques, thus discouraging their use. In a highly regulated and risk-averse context such as healthcare, although "trust" is not synonymous with decision and adoption, trusting an ML model is essential for its adoption. Many clinicians and health researchers feel uncomfortable with black box ML models, even if they achieve high degrees of diagnostic or prognostic accuracy. Therefore more and more research is being conducted on the functioning of these models. Our study focuses on the Random Forest (RF) model. It is one of the most performing and used methodologies in the context of ML approaches, in all fields of research from hard sciences to humanities. In the health context and in the evaluation of health policies, their use is limited by the impossibility of obtaining an interpretation of the causal links between predictors and response. This explains why we need to develop new techniques, tools, and approaches for reconstructing the causal relationships and interactions between predictors and response used in a RF model. Our research aims to perform a machine learning experiment on several medical datasets through a comparison between two methodologies, which are inTrees and NodeHarvest. They are the main approaches in the rules extraction framework. The contribution of our study is to identify, among the approaches to rule extraction, the best proposal for suggesting the appropriate choice to decision-makers in the health domain.
format Online
id doab-20.500.12854ir-83864
institution Directory of Open Access Books
language eng
publishDate 2022
publishDateRange 2022
publishDateSort 2022
publisher Firenze University Press
publisherStr Firenze University Press
record_format ojs
spelling doab-20.500.12854ir-838642022-06-02T04:40:52Z Chapter Supporting decision-makers in healthcare domain. A comparative study of two interpretative proposals for Random Forests Aria, Massimo Cuccurullo, Corrado Gnasso, Agostino Random Forest Model Interpretation Health domain Rule Extraction The growing success of Machine Learning (ML) is making significant improvements to predictive models, facilitating their integration in various application fields, especially the healthcare context. However, it still has limitations and drawbacks, such as the lack of interpretability which does not allow users to understand how certain decisions are made. This drawback is identified with the term "Black-Box", as well as models that do not allow to interpret the internal work of certain ML techniques, thus discouraging their use. In a highly regulated and risk-averse context such as healthcare, although "trust" is not synonymous with decision and adoption, trusting an ML model is essential for its adoption. Many clinicians and health researchers feel uncomfortable with black box ML models, even if they achieve high degrees of diagnostic or prognostic accuracy. Therefore more and more research is being conducted on the functioning of these models. Our study focuses on the Random Forest (RF) model. It is one of the most performing and used methodologies in the context of ML approaches, in all fields of research from hard sciences to humanities. In the health context and in the evaluation of health policies, their use is limited by the impossibility of obtaining an interpretation of the causal links between predictors and response. This explains why we need to develop new techniques, tools, and approaches for reconstructing the causal relationships and interactions between predictors and response used in a RF model. Our research aims to perform a machine learning experiment on several medical datasets through a comparison between two methodologies, which are inTrees and NodeHarvest. They are the main approaches in the rules extraction framework. The contribution of our study is to identify, among the approaches to rule extraction, the best proposal for suggesting the appropriate choice to decision-makers in the health domain. 2022-06-02T04:40:51Z 2022-06-02T04:40:51Z 2022-06-01T12:21:07Z 2021 chapter ONIX_20220601_9788855184618_561 2704-5846 https://library.oapen.org/handle/20.500.12657/56376 9788855184618 https://directory.doabooks.org/handle/20.500.12854/83864 eng Proceedings e report open access image/jpeg Attribution 4.0 International https://library.oapen.org/bitstream/20.500.12657/56376/1/26252.pdf Firenze University Press 10.36253/978-88-5518-461-8.34 10.36253/978-88-5518-461-8.34 2ec4474d-93b1-4cfa-b313-9c6019b51b1a 9788855184618 6 Florence open access
spellingShingle Random Forest
Model Interpretation
Health domain
Rule Extraction
Aria, Massimo
Cuccurullo, Corrado
Gnasso, Agostino
Chapter Supporting decision-makers in healthcare domain. A comparative study of two interpretative proposals for Random Forests
title Chapter Supporting decision-makers in healthcare domain. A comparative study of two interpretative proposals for Random Forests
title_full Chapter Supporting decision-makers in healthcare domain. A comparative study of two interpretative proposals for Random Forests
title_fullStr Chapter Supporting decision-makers in healthcare domain. A comparative study of two interpretative proposals for Random Forests
title_full_unstemmed Chapter Supporting decision-makers in healthcare domain. A comparative study of two interpretative proposals for Random Forests
title_short Chapter Supporting decision-makers in healthcare domain. A comparative study of two interpretative proposals for Random Forests
title_sort chapter supporting decision makers in healthcare domain a comparative study of two interpretative proposals for random forests
topic Random Forest
Model Interpretation
Health domain
Rule Extraction
topic_facet Random Forest
Model Interpretation
Health domain
Rule Extraction
url ONIX_20220601_9788855184618_561
work_keys_str_mv AT ariamassimo chaptersupportingdecisionmakersinhealthcaredomainacomparativestudyoftwointerpretativeproposalsforrandomforests
AT cuccurullocorrado chaptersupportingdecisionmakersinhealthcaredomainacomparativestudyoftwointerpretativeproposalsforrandomforests
AT gnassoagostino chaptersupportingdecisionmakersinhealthcaredomainacomparativestudyoftwointerpretativeproposalsforrandomforests