TY - JOUR
T1 - Development and validation of a machine learning model for classification of next glucose measurement in hospitalized patients
AU - Zale, Andrew D.
AU - Abusamaan, Mohammed S.
AU - McGready, John
AU - Mathioudakis, Nestoras
N1 - Funding Information:
This study was supported by grant K23DK111986 from the National Institute for Diabetes and Digestive and Kidney Diseases (Drs Mathioudakis, Abusamaan, and McGready).
Funding Information:
We would like to thank Sam Sokolinsky and Shamil Fayzullin from the Johns Hopkins Health System Quality and Clinical Analytics for their assistance with data extraction from the electronic medical record. NM and MA contributed to study concept and design, data extraction and assessment, verified the underlying data, statistical synthesis, interpretation of data, and drafted the manuscript. AZ contributed to study concept and design, statistical analysis, interpretation of data, and drafted the manuscript. JM contributed to study design and concept, statistical analysis, and critical revision of the manuscript. All authors reviewed and edited the manuscript, This study was supported by grant K23DK111986 from the National Institute for Diabetes and Digestive and Kidney Diseases (Drs Mathioudakis, Abusamaan, and McGready). The data underlying this article will be shared on reasonable request to the corresponding author.
Publisher Copyright:
© 2022 The Author(s)
PY - 2022/2
Y1 - 2022/2
N2 - Background: Inpatient glucose management can be challenging due to evolving factors that influence a patient's blood glucose (BG) throughout hospital admission. The purpose of our study was to predict the category of a patient's next BG measurement based on electronic medical record (EMR) data. Methods: EMR data from 184,361 admissions containing 4,538,418 BG measurements from five hospitals in the Johns Hopkins Health System were collected from patients who were discharged between January 1, 2015 and May 31, 2019. Index BGs used for prediction included the 5th to penultimate BG measurements (N = 2,740,539). The outcome was category of next BG measurement: hypoglycemic (BG ≤ 70 mg/dl), controlled (BG 71–180 mg/dl), or hyperglycemic (BG > 180 mg/dl). A random forest algorithm that included a broad range of clinical covariates predicted the outcome and was validated internally and externally. Findings: In our internal validation test set, 72·8%, 25·7%, and 1·5% of BG measurements occurring after the index BG were controlled, hyperglycemic, and hypoglycemic respectively. The sensitivity/specificity for prediction of controlled, hyperglycemic, and hypoglycemic were 0·77/0·81, 0·77/0·89, and 0·73/0·91, respectively. On external validation in four hospitals, the ranges of sensitivity/specificity for prediction of controlled, hyperglycemic, and hypoglycemic were 0·64–0·70/0·80–0·87, 0·75–0·80/0·82–0·84, and 0·76–0·78/0·87–0·90, respectively. Interpretation: A machine learning algorithm using EMR data can accurately predict the category of a hospitalized patient's next BG measurement. Further studies should determine the effectiveness of integration of this model into the EMR in reducing rates of hypoglycemia and hyperglycemia.
AB - Background: Inpatient glucose management can be challenging due to evolving factors that influence a patient's blood glucose (BG) throughout hospital admission. The purpose of our study was to predict the category of a patient's next BG measurement based on electronic medical record (EMR) data. Methods: EMR data from 184,361 admissions containing 4,538,418 BG measurements from five hospitals in the Johns Hopkins Health System were collected from patients who were discharged between January 1, 2015 and May 31, 2019. Index BGs used for prediction included the 5th to penultimate BG measurements (N = 2,740,539). The outcome was category of next BG measurement: hypoglycemic (BG ≤ 70 mg/dl), controlled (BG 71–180 mg/dl), or hyperglycemic (BG > 180 mg/dl). A random forest algorithm that included a broad range of clinical covariates predicted the outcome and was validated internally and externally. Findings: In our internal validation test set, 72·8%, 25·7%, and 1·5% of BG measurements occurring after the index BG were controlled, hyperglycemic, and hypoglycemic respectively. The sensitivity/specificity for prediction of controlled, hyperglycemic, and hypoglycemic were 0·77/0·81, 0·77/0·89, and 0·73/0·91, respectively. On external validation in four hospitals, the ranges of sensitivity/specificity for prediction of controlled, hyperglycemic, and hypoglycemic were 0·64–0·70/0·80–0·87, 0·75–0·80/0·82–0·84, and 0·76–0·78/0·87–0·90, respectively. Interpretation: A machine learning algorithm using EMR data can accurately predict the category of a hospitalized patient's next BG measurement. Further studies should determine the effectiveness of integration of this model into the EMR in reducing rates of hypoglycemia and hyperglycemia.
UR - http://www.scopus.com/inward/record.url?scp=85124002170&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85124002170&partnerID=8YFLogxK
U2 - 10.1016/j.eclinm.2022.101290
DO - 10.1016/j.eclinm.2022.101290
M3 - Article
C2 - 35169690
AN - SCOPUS:85124002170
SN - 2589-5370
VL - 44
JO - EClinicalMedicine
JF - EClinicalMedicine
M1 - 101290
ER -