Cargando…

Transparent machine learning suggests a key driver in the decision to start insulin therapy in individuals with type 2 diabetes

AIMS: The objective of this study is to establish a predictive model using transparent machine learning (ML) to identify any drivers that characterize therapeutic inertia. METHODS: Data in the form of both descriptive and dynamic variables collected from electronic records of 1.5 million patients se...

Descripción completa

Detalles Bibliográficos
Autores principales: Musacchio, Nicoletta, Zilich, Rita, Ponzani, Paola, Guaita, Giacomo, Giorda, Carlo, Heidbreder, Rebeca, Santin, Pierluigi, Di Cianni, Graziano
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Wiley Publishing Asia Pty Ltd 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10036260/
https://www.ncbi.nlm.nih.gov/pubmed/36889912
http://dx.doi.org/10.1111/1753-0407.13361
_version_ 1784911612115681280
author Musacchio, Nicoletta
Zilich, Rita
Ponzani, Paola
Guaita, Giacomo
Giorda, Carlo
Heidbreder, Rebeca
Santin, Pierluigi
Di Cianni, Graziano
author_facet Musacchio, Nicoletta
Zilich, Rita
Ponzani, Paola
Guaita, Giacomo
Giorda, Carlo
Heidbreder, Rebeca
Santin, Pierluigi
Di Cianni, Graziano
author_sort Musacchio, Nicoletta
collection PubMed
description AIMS: The objective of this study is to establish a predictive model using transparent machine learning (ML) to identify any drivers that characterize therapeutic inertia. METHODS: Data in the form of both descriptive and dynamic variables collected from electronic records of 1.5 million patients seen at clinics within the Italian Association of Medical Diabetologists between 2005–2019 were analyzed using logic learning machine (LLM), a “clear box” ML technique. Data were subjected to a first stage of modeling to allow ML to automatically select the most relevant factors related to inertia, and then four further modeling steps individuated key variables that discriminated the presence or absence of inertia. RESULTS: The LLM model revealed a key role for average glycated hemoglobin (HbA1c) threshold values correlated with the presence or absence of insulin therapeutic inertia with an accuracy of 0.79. The model indicated that a patient's dynamic rather than static glycemic profile has a greater effect on therapeutic inertia. Specifically, the difference in HbA1c between two consecutive visits, what we call the HbA1c gap, plays a crucial role. Namely, insulin therapeutic inertia is correlated with an HbA1c gap of <6.6 mmol/mol (0.6%), but not with an HbA1c gap of >11 mmol/mol (1.0%). CONCLUSIONS: The results reveal, for the first time, the interrelationship between a patient's glycemic trend defined by sequential HbA1c measurements and timely or delayed initiation of insulin therapy. The results further demonstrate that LLM can provide insight in support of evidence‐based medicine using real world data.
format Online
Article
Text
id pubmed-10036260
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Wiley Publishing Asia Pty Ltd
record_format MEDLINE/PubMed
spelling pubmed-100362602023-03-25 Transparent machine learning suggests a key driver in the decision to start insulin therapy in individuals with type 2 diabetes Musacchio, Nicoletta Zilich, Rita Ponzani, Paola Guaita, Giacomo Giorda, Carlo Heidbreder, Rebeca Santin, Pierluigi Di Cianni, Graziano J Diabetes Original Articles AIMS: The objective of this study is to establish a predictive model using transparent machine learning (ML) to identify any drivers that characterize therapeutic inertia. METHODS: Data in the form of both descriptive and dynamic variables collected from electronic records of 1.5 million patients seen at clinics within the Italian Association of Medical Diabetologists between 2005–2019 were analyzed using logic learning machine (LLM), a “clear box” ML technique. Data were subjected to a first stage of modeling to allow ML to automatically select the most relevant factors related to inertia, and then four further modeling steps individuated key variables that discriminated the presence or absence of inertia. RESULTS: The LLM model revealed a key role for average glycated hemoglobin (HbA1c) threshold values correlated with the presence or absence of insulin therapeutic inertia with an accuracy of 0.79. The model indicated that a patient's dynamic rather than static glycemic profile has a greater effect on therapeutic inertia. Specifically, the difference in HbA1c between two consecutive visits, what we call the HbA1c gap, plays a crucial role. Namely, insulin therapeutic inertia is correlated with an HbA1c gap of <6.6 mmol/mol (0.6%), but not with an HbA1c gap of >11 mmol/mol (1.0%). CONCLUSIONS: The results reveal, for the first time, the interrelationship between a patient's glycemic trend defined by sequential HbA1c measurements and timely or delayed initiation of insulin therapy. The results further demonstrate that LLM can provide insight in support of evidence‐based medicine using real world data. Wiley Publishing Asia Pty Ltd 2023-03-08 /pmc/articles/PMC10036260/ /pubmed/36889912 http://dx.doi.org/10.1111/1753-0407.13361 Text en © 2023 Associazione Medici Diabetologi (AMD). Journal of Diabetes published by Ruijin Hospital, Shanghai JiaoTong University School of Medicine and John Wiley & Sons Australia, Ltd. https://creativecommons.org/licenses/by/4.0/This is an open access article under the terms of the http://creativecommons.org/licenses/by/4.0/ (https://creativecommons.org/licenses/by/4.0/) License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.
spellingShingle Original Articles
Musacchio, Nicoletta
Zilich, Rita
Ponzani, Paola
Guaita, Giacomo
Giorda, Carlo
Heidbreder, Rebeca
Santin, Pierluigi
Di Cianni, Graziano
Transparent machine learning suggests a key driver in the decision to start insulin therapy in individuals with type 2 diabetes
title Transparent machine learning suggests a key driver in the decision to start insulin therapy in individuals with type 2 diabetes
title_full Transparent machine learning suggests a key driver in the decision to start insulin therapy in individuals with type 2 diabetes
title_fullStr Transparent machine learning suggests a key driver in the decision to start insulin therapy in individuals with type 2 diabetes
title_full_unstemmed Transparent machine learning suggests a key driver in the decision to start insulin therapy in individuals with type 2 diabetes
title_short Transparent machine learning suggests a key driver in the decision to start insulin therapy in individuals with type 2 diabetes
title_sort transparent machine learning suggests a key driver in the decision to start insulin therapy in individuals with type 2 diabetes
topic Original Articles
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10036260/
https://www.ncbi.nlm.nih.gov/pubmed/36889912
http://dx.doi.org/10.1111/1753-0407.13361
work_keys_str_mv AT musacchionicoletta transparentmachinelearningsuggestsakeydriverinthedecisiontostartinsulintherapyinindividualswithtype2diabetes
AT zilichrita transparentmachinelearningsuggestsakeydriverinthedecisiontostartinsulintherapyinindividualswithtype2diabetes
AT ponzanipaola transparentmachinelearningsuggestsakeydriverinthedecisiontostartinsulintherapyinindividualswithtype2diabetes
AT guaitagiacomo transparentmachinelearningsuggestsakeydriverinthedecisiontostartinsulintherapyinindividualswithtype2diabetes
AT giordacarlo transparentmachinelearningsuggestsakeydriverinthedecisiontostartinsulintherapyinindividualswithtype2diabetes
AT heidbrederrebeca transparentmachinelearningsuggestsakeydriverinthedecisiontostartinsulintherapyinindividualswithtype2diabetes
AT santinpierluigi transparentmachinelearningsuggestsakeydriverinthedecisiontostartinsulintherapyinindividualswithtype2diabetes
AT diciannigraziano transparentmachinelearningsuggestsakeydriverinthedecisiontostartinsulintherapyinindividualswithtype2diabetes