透明机器学习预测决定2型糖尿病患者开始胰岛素治疗的关键驱动因素
Abstract 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 pati...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2023-03-01
|
| Series: | Journal of Diabetes |
| Subjects: | |
| Online Access: | https://doi.org/10.1111/1753-0407.13361 |
| _version_ | 1827980780501991424 |
|---|---|
| author | Nicoletta Musacchio Rita Zilich Paola Ponzani Giacomo Guaita Carlo Giorda Rebeca Heidbreder Pierluigi Santin Graziano Di Cianni |
| author_facet | Nicoletta Musacchio Rita Zilich Paola Ponzani Giacomo Guaita Carlo Giorda Rebeca Heidbreder Pierluigi Santin Graziano Di Cianni |
| author_sort | Nicoletta Musacchio |
| collection | DOAJ |
| description | Abstract 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. |
| first_indexed | 2024-04-09T21:58:44Z |
| format | Article |
| id | doaj.art-8669c8bb40824221a1c05938b8cfd6dd |
| institution | Directory Open Access Journal |
| issn | 1753-0393 1753-0407 |
| language | English |
| last_indexed | 2024-04-09T21:58:44Z |
| publishDate | 2023-03-01 |
| publisher | Wiley |
| record_format | Article |
| series | Journal of Diabetes |
| spelling | doaj.art-8669c8bb40824221a1c05938b8cfd6dd2023-03-24T03:20:06ZengWileyJournal of Diabetes1753-03931753-04072023-03-0115322423610.1111/1753-0407.13361透明机器学习预测决定2型糖尿病患者开始胰岛素治疗的关键驱动因素Nicoletta Musacchio0Rita Zilich1Paola Ponzani2Giacomo Guaita3Carlo Giorda4Rebeca Heidbreder5Pierluigi Santin6Graziano Di Cianni7AMD past President ‐ AMD AI National Group Coordinator Milan ItalyMix‐x SRL Ivrea ItalyDiabetes and Endocrinology Unit Local Health Autlhority 4 Chiavari Chiavari ItalyDiabetes and Endocrinology Unit ASL SULCIS Iglesias ItalyDiabetes and Endocrinology Unit ASL TO5 Chieri ItalyPsychResearchCenter, LLC Powhatan Virginia USADeimos Udine ItalyUSL Tuscany Northwest Location Livorno, Diabetes and Metabolic Disease Livorno ItalyAbstract 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.https://doi.org/10.1111/1753-0407.133612型糖尿病治疗惯性机器学习人工智能 |
| spellingShingle | Nicoletta Musacchio Rita Zilich Paola Ponzani Giacomo Guaita Carlo Giorda Rebeca Heidbreder Pierluigi Santin Graziano Di Cianni 透明机器学习预测决定2型糖尿病患者开始胰岛素治疗的关键驱动因素 Journal of Diabetes 2型糖尿病 治疗惯性 机器学习 人工智能 |
| title | 透明机器学习预测决定2型糖尿病患者开始胰岛素治疗的关键驱动因素 |
| title_full | 透明机器学习预测决定2型糖尿病患者开始胰岛素治疗的关键驱动因素 |
| title_fullStr | 透明机器学习预测决定2型糖尿病患者开始胰岛素治疗的关键驱动因素 |
| title_full_unstemmed | 透明机器学习预测决定2型糖尿病患者开始胰岛素治疗的关键驱动因素 |
| title_short | 透明机器学习预测决定2型糖尿病患者开始胰岛素治疗的关键驱动因素 |
| title_sort | 透明机器学习预测决定2型糖尿病患者开始胰岛素治疗的关键驱动因素 |
| topic | 2型糖尿病 治疗惯性 机器学习 人工智能 |
| url | https://doi.org/10.1111/1753-0407.13361 |
| work_keys_str_mv | AT nicolettamusacchio tòumíngjīqìxuéxíyùcèjuédìng2xíngtángniàobìnghuànzhěkāishǐyídǎosùzhìliáodeguānjiànqūdòngyīnsù AT ritazilich tòumíngjīqìxuéxíyùcèjuédìng2xíngtángniàobìnghuànzhěkāishǐyídǎosùzhìliáodeguānjiànqūdòngyīnsù AT paolaponzani tòumíngjīqìxuéxíyùcèjuédìng2xíngtángniàobìnghuànzhěkāishǐyídǎosùzhìliáodeguānjiànqūdòngyīnsù AT giacomoguaita tòumíngjīqìxuéxíyùcèjuédìng2xíngtángniàobìnghuànzhěkāishǐyídǎosùzhìliáodeguānjiànqūdòngyīnsù AT carlogiorda tòumíngjīqìxuéxíyùcèjuédìng2xíngtángniàobìnghuànzhěkāishǐyídǎosùzhìliáodeguānjiànqūdòngyīnsù AT rebecaheidbreder tòumíngjīqìxuéxíyùcèjuédìng2xíngtángniàobìnghuànzhěkāishǐyídǎosùzhìliáodeguānjiànqūdòngyīnsù AT pierluigisantin tòumíngjīqìxuéxíyùcèjuédìng2xíngtángniàobìnghuànzhěkāishǐyídǎosùzhìliáodeguānjiànqūdòngyīnsù AT grazianodicianni tòumíngjīqìxuéxíyùcèjuédìng2xíngtángniàobìnghuànzhěkāishǐyídǎosùzhìliáodeguānjiànqūdòngyīnsù |