Artificial intelligence with temporal features outperforms machine learning in predicting diabetes.

Diabetes mellitus type 2 is increasingly being called a modern preventable pandemic, as even with excellent available treatments, the rate of complications of diabetes is rapidly increasing. Predicting diabetes and identifying it in its early stages could make it easier to prevent, allowing enough t...

Full description

Bibliographic Details
Main Authors: Iqra Naveed, Muhammad Farhat Kaleem, Karim Keshavjee, Aziz Guergachi
Format: Article
Language:English
Published: Public Library of Science (PLoS) 2023-10-01
Series:PLOS Digital Health
Online Access:https://doi.org/10.1371/journal.pdig.0000354
_version_ 1797349348526260224
author Iqra Naveed
Muhammad Farhat Kaleem
Karim Keshavjee
Aziz Guergachi
author_facet Iqra Naveed
Muhammad Farhat Kaleem
Karim Keshavjee
Aziz Guergachi
author_sort Iqra Naveed
collection DOAJ
description Diabetes mellitus type 2 is increasingly being called a modern preventable pandemic, as even with excellent available treatments, the rate of complications of diabetes is rapidly increasing. Predicting diabetes and identifying it in its early stages could make it easier to prevent, allowing enough time to implement therapies before it gets out of control. Leveraging longitudinal electronic medical record (EMR) data with deep learning has great potential for diabetes prediction. This paper examines the predictive competency of deep learning models in contrast to state-of-the-art machine learning models to incorporate the time dimension of risk. The proposed research investigates a variety of deep learning models and features for predicting diabetes. Model performance was appraised and compared in relation to predominant features, risk factors, training data density and visit history. The framework was implemented on the longitudinal EMR records of over 19K patients extracted from the Canadian Primary Care Sentinel Surveillance Network (CPCSSN). Empirical findings demonstrate that deep learning models consistently outperform other state-of-the-art competitors with prediction accuracy of above 91%, without overfitting. Fasting blood sugar, hemoglobin A1c and body mass index are the key predictors of future onset of diabetes. Overweight, middle aged patients and patients with hypertension are more vulnerable to developing diabetes, consistent with what is already known. Model performance improves as training data density or the visit history of a patient increases. This study confirms the ability of the LSTM deep learning model to incorporate the time dimension of risk in its predictive capabilities.
first_indexed 2024-03-08T12:28:06Z
format Article
id doaj.art-2d924e59504d49d8bd6dee0acf42ce8d
institution Directory Open Access Journal
issn 2767-3170
language English
last_indexed 2024-03-08T12:28:06Z
publishDate 2023-10-01
publisher Public Library of Science (PLoS)
record_format Article
series PLOS Digital Health
spelling doaj.art-2d924e59504d49d8bd6dee0acf42ce8d2024-01-22T05:31:41ZengPublic Library of Science (PLoS)PLOS Digital Health2767-31702023-10-01210e000035410.1371/journal.pdig.0000354Artificial intelligence with temporal features outperforms machine learning in predicting diabetes.Iqra NaveedMuhammad Farhat KaleemKarim KeshavjeeAziz GuergachiDiabetes mellitus type 2 is increasingly being called a modern preventable pandemic, as even with excellent available treatments, the rate of complications of diabetes is rapidly increasing. Predicting diabetes and identifying it in its early stages could make it easier to prevent, allowing enough time to implement therapies before it gets out of control. Leveraging longitudinal electronic medical record (EMR) data with deep learning has great potential for diabetes prediction. This paper examines the predictive competency of deep learning models in contrast to state-of-the-art machine learning models to incorporate the time dimension of risk. The proposed research investigates a variety of deep learning models and features for predicting diabetes. Model performance was appraised and compared in relation to predominant features, risk factors, training data density and visit history. The framework was implemented on the longitudinal EMR records of over 19K patients extracted from the Canadian Primary Care Sentinel Surveillance Network (CPCSSN). Empirical findings demonstrate that deep learning models consistently outperform other state-of-the-art competitors with prediction accuracy of above 91%, without overfitting. Fasting blood sugar, hemoglobin A1c and body mass index are the key predictors of future onset of diabetes. Overweight, middle aged patients and patients with hypertension are more vulnerable to developing diabetes, consistent with what is already known. Model performance improves as training data density or the visit history of a patient increases. This study confirms the ability of the LSTM deep learning model to incorporate the time dimension of risk in its predictive capabilities.https://doi.org/10.1371/journal.pdig.0000354
spellingShingle Iqra Naveed
Muhammad Farhat Kaleem
Karim Keshavjee
Aziz Guergachi
Artificial intelligence with temporal features outperforms machine learning in predicting diabetes.
PLOS Digital Health
title Artificial intelligence with temporal features outperforms machine learning in predicting diabetes.
title_full Artificial intelligence with temporal features outperforms machine learning in predicting diabetes.
title_fullStr Artificial intelligence with temporal features outperforms machine learning in predicting diabetes.
title_full_unstemmed Artificial intelligence with temporal features outperforms machine learning in predicting diabetes.
title_short Artificial intelligence with temporal features outperforms machine learning in predicting diabetes.
title_sort artificial intelligence with temporal features outperforms machine learning in predicting diabetes
url https://doi.org/10.1371/journal.pdig.0000354
work_keys_str_mv AT iqranaveed artificialintelligencewithtemporalfeaturesoutperformsmachinelearninginpredictingdiabetes
AT muhammadfarhatkaleem artificialintelligencewithtemporalfeaturesoutperformsmachinelearninginpredictingdiabetes
AT karimkeshavjee artificialintelligencewithtemporalfeaturesoutperformsmachinelearninginpredictingdiabetes
AT azizguergachi artificialintelligencewithtemporalfeaturesoutperformsmachinelearninginpredictingdiabetes