Predicting misdiagnosed adult-onset type 1 diabetes using machine learning

It is now understood that almost half of newly diagnosed cases of type 1 diabetes are adult-onset. However, type 1 and type 2 diabetes are difficult to initially distinguish clinically in adults, potentially leading to ineffective care. In this study a machine learning model was developed to identif...

Full description

Saved in:
Bibliographic Details
Published in:Diabetes research and clinical practice Vol. 191; p. 110029
Main Authors: Cheheltani, Rabee, King, Nicholas, Lee, Suyin, North, Benjamin, Kovarik, Danny, Evans-Molina, Carmella, Leavitt, Nadejda, Dutta, Sanjoy
Format: Journal Article
Language:English
Published: Ireland Elsevier B.V 01.09.2022
Subjects:
Adult
Adult-onset type 1 diabetes
Blood Glucose
Clinical decision support tool
Diabetes Mellitus, Type 1 - diagnosis
Diabetes Mellitus, Type 1 - epidemiology
Diabetes Mellitus, Type 2 - diagnosis
Diabetes Mellitus, Type 2 - drug therapy
Diabetes Mellitus, Type 2 - epidemiology
Diagnostic Errors
Glycated Hemoglobin
Humans
Machine Learning
Misdiagnosis
Predictive algorithm
Retrospective Studies
Misdiagnosis
AI
Clinical decision support tool
Adult-onset type 1 diabetes
Predictive algorithm
Machine learning
ISSN:0168-8227, 1872-8227, 1872-8227
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:It is now understood that almost half of newly diagnosed cases of type 1 diabetes are adult-onset. However, type 1 and type 2 diabetes are difficult to initially distinguish clinically in adults, potentially leading to ineffective care. In this study a machine learning model was developed to identify type 1 diabetes patients misdiagnosed as type 2 diabetes. In this retrospective study, a machine learning model was developed to identify misdiagnosed type 1 diabetes patients from a population of patients with a prior type 2 diabetes diagnosis. Using Ambulatory Electronic Medical Records (AEMR), features capturing relevant information on age, demographics, risk factors, symptoms, treatments, procedures, vitals, or lab results were extracted from patients' medical history. The model identified age, BMI/weight, therapy history, and HbA1c/blood glucose values among top predictors of misdiagnosis. Model precision at low levels of recall (10 %) was 17 %, compared to <1 % incidence rate of misdiagnosis at the time of the first type 2 diabetes encounter in AEMR. This algorithm shows potential for being translated into screening guidelines or a clinical decision support tool embedded directly in an EMR system to reduce misdiagnosis of adult-onset type 1 diabetes and implement effective care at the outset.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:0168-8227
1872-8227
1872-8227
DOI:10.1016/j.diabres.2022.110029