Cargando…

The Performance of Different Artificial Intelligence Models in Predicting Breast Cancer among Individuals Having Type 2 Diabetes Mellitus

Objective: Early reports indicate that individuals with type 2 diabetes mellitus (T2DM) may have a greater incidence of breast malignancy than patients without T2DM. The aim of this study was to investigate the effectiveness of three different models for predicting risk of breast cancer in patients...

Descripción completa

Detalles Bibliográficos
Autores principales: Hsieh, Meng-Hsuen, Sun, Li-Min, Lin, Cheng-Li, Hsieh, Meng-Ju, Hsu, Chung Y., Kao, Chia-Hung
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2019
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6895886/
https://www.ncbi.nlm.nih.gov/pubmed/31717292
http://dx.doi.org/10.3390/cancers11111751
_version_ 1783476654918598656
author Hsieh, Meng-Hsuen
Sun, Li-Min
Lin, Cheng-Li
Hsieh, Meng-Ju
Hsu, Chung Y.
Kao, Chia-Hung
author_facet Hsieh, Meng-Hsuen
Sun, Li-Min
Lin, Cheng-Li
Hsieh, Meng-Ju
Hsu, Chung Y.
Kao, Chia-Hung
author_sort Hsieh, Meng-Hsuen
collection PubMed
description Objective: Early reports indicate that individuals with type 2 diabetes mellitus (T2DM) may have a greater incidence of breast malignancy than patients without T2DM. The aim of this study was to investigate the effectiveness of three different models for predicting risk of breast cancer in patients with T2DM of different characteristics. Study design and methodology: From 2000 to 2012, data on 636,111 newly diagnosed female T2DM patients were available in the Taiwan’s National Health Insurance Research Database. By applying their data, a risk prediction model of breast cancer in patients with T2DM was created. We also collected data on potential predictors of breast cancer so that adjustments for their effect could be made in the analysis. Synthetic Minority Oversampling Technology (SMOTE) was utilized to increase data for small population samples. Each datum was randomly assigned based on a ratio of about 39:1 into the training and test sets. Logistic Regression (LR), Artificial Neural Network (ANN) and Random Forest (RF) models were determined using recall, accuracy, F(1) score and area under the receiver operating characteristic curve (AUC). Results: The AUC of the LR (0.834), ANN (0.865), and RF (0.959) models were found. The largest AUC among the three models was seen in the RF model. Conclusions: Although the LR, ANN, and RF models all showed high accuracy predicting the risk of breast cancer in Taiwanese with T2DM, the RF model performed best.
format Online
Article
Text
id pubmed-6895886
institution National Center for Biotechnology Information
language English
publishDate 2019
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-68958862019-12-24 The Performance of Different Artificial Intelligence Models in Predicting Breast Cancer among Individuals Having Type 2 Diabetes Mellitus Hsieh, Meng-Hsuen Sun, Li-Min Lin, Cheng-Li Hsieh, Meng-Ju Hsu, Chung Y. Kao, Chia-Hung Cancers (Basel) Article Objective: Early reports indicate that individuals with type 2 diabetes mellitus (T2DM) may have a greater incidence of breast malignancy than patients without T2DM. The aim of this study was to investigate the effectiveness of three different models for predicting risk of breast cancer in patients with T2DM of different characteristics. Study design and methodology: From 2000 to 2012, data on 636,111 newly diagnosed female T2DM patients were available in the Taiwan’s National Health Insurance Research Database. By applying their data, a risk prediction model of breast cancer in patients with T2DM was created. We also collected data on potential predictors of breast cancer so that adjustments for their effect could be made in the analysis. Synthetic Minority Oversampling Technology (SMOTE) was utilized to increase data for small population samples. Each datum was randomly assigned based on a ratio of about 39:1 into the training and test sets. Logistic Regression (LR), Artificial Neural Network (ANN) and Random Forest (RF) models were determined using recall, accuracy, F(1) score and area under the receiver operating characteristic curve (AUC). Results: The AUC of the LR (0.834), ANN (0.865), and RF (0.959) models were found. The largest AUC among the three models was seen in the RF model. Conclusions: Although the LR, ANN, and RF models all showed high accuracy predicting the risk of breast cancer in Taiwanese with T2DM, the RF model performed best. MDPI 2019-11-08 /pmc/articles/PMC6895886/ /pubmed/31717292 http://dx.doi.org/10.3390/cancers11111751 Text en © 2019 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Hsieh, Meng-Hsuen
Sun, Li-Min
Lin, Cheng-Li
Hsieh, Meng-Ju
Hsu, Chung Y.
Kao, Chia-Hung
The Performance of Different Artificial Intelligence Models in Predicting Breast Cancer among Individuals Having Type 2 Diabetes Mellitus
title The Performance of Different Artificial Intelligence Models in Predicting Breast Cancer among Individuals Having Type 2 Diabetes Mellitus
title_full The Performance of Different Artificial Intelligence Models in Predicting Breast Cancer among Individuals Having Type 2 Diabetes Mellitus
title_fullStr The Performance of Different Artificial Intelligence Models in Predicting Breast Cancer among Individuals Having Type 2 Diabetes Mellitus
title_full_unstemmed The Performance of Different Artificial Intelligence Models in Predicting Breast Cancer among Individuals Having Type 2 Diabetes Mellitus
title_short The Performance of Different Artificial Intelligence Models in Predicting Breast Cancer among Individuals Having Type 2 Diabetes Mellitus
title_sort performance of different artificial intelligence models in predicting breast cancer among individuals having type 2 diabetes mellitus
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6895886/
https://www.ncbi.nlm.nih.gov/pubmed/31717292
http://dx.doi.org/10.3390/cancers11111751
work_keys_str_mv AT hsiehmenghsuen theperformanceofdifferentartificialintelligencemodelsinpredictingbreastcanceramongindividualshavingtype2diabetesmellitus
AT sunlimin theperformanceofdifferentartificialintelligencemodelsinpredictingbreastcanceramongindividualshavingtype2diabetesmellitus
AT linchengli theperformanceofdifferentartificialintelligencemodelsinpredictingbreastcanceramongindividualshavingtype2diabetesmellitus
AT hsiehmengju theperformanceofdifferentartificialintelligencemodelsinpredictingbreastcanceramongindividualshavingtype2diabetesmellitus
AT hsuchungy theperformanceofdifferentartificialintelligencemodelsinpredictingbreastcanceramongindividualshavingtype2diabetesmellitus
AT kaochiahung theperformanceofdifferentartificialintelligencemodelsinpredictingbreastcanceramongindividualshavingtype2diabetesmellitus
AT hsiehmenghsuen performanceofdifferentartificialintelligencemodelsinpredictingbreastcanceramongindividualshavingtype2diabetesmellitus
AT sunlimin performanceofdifferentartificialintelligencemodelsinpredictingbreastcanceramongindividualshavingtype2diabetesmellitus
AT linchengli performanceofdifferentartificialintelligencemodelsinpredictingbreastcanceramongindividualshavingtype2diabetesmellitus
AT hsiehmengju performanceofdifferentartificialintelligencemodelsinpredictingbreastcanceramongindividualshavingtype2diabetesmellitus
AT hsuchungy performanceofdifferentartificialintelligencemodelsinpredictingbreastcanceramongindividualshavingtype2diabetesmellitus
AT kaochiahung performanceofdifferentartificialintelligencemodelsinpredictingbreastcanceramongindividualshavingtype2diabetesmellitus