Brent Lockee
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Brent Lockee has a total of 34 co-authors. Here are the top co-authors by number of shared publications:
- Craig A. Vandervelden
Children’s Mercy Kansas City, Kansas City, MO, USA
7 shared publications - David D. Williams
Children’s Mercy Kansas City, Kansas City, MO, USA
7 shared publications - Erin M. Tallon
Children’s Mercy Kansas City, Kansas City, MO, USA
7 shared publications - Mark A. Clements
Division of Pediatric Endocrinology, Children’s Mercy Hospital, University of Missouri-Kansas City 16 , Kansas City, MO
7 shared publications - Susana R. Patton
Center for Healthcare Delivery Science, Nemours Children’s Health, Jacksonville, USA
6 shared publications - Cintya Schweisberger
Children’s Mercy Kansas City, Kansas City, MO, USA
4 shared publications
Latest Publications
- Open Access
A Data-Driven Pediatric Type 1 Diabetes Population Health Model Within Specialty Value-Based Care
Objective: Pediatric specialty value-based care (VBC) for chronic conditions remains under-described. We describe the design and early performance of a data-driven population health model for pediatric type 1 diabetes within a specialty VBC program. Research Design and Methods: Descriptive evaluation at a single academic pediatric medical center and clinically integrated network, 2021–2025, with formal VBC operation beginning in 2024. Participants were children and adolescents with type 1 diabetes attributed through commercial and Medicaid value-based agreements (n=786 in 2025). The program paired infrastructure funding with performance-dependent payments tied to clinical quality and utilization measures, supported by remote monitoring and care management. Measures: percentage receiving the chronic care intervention, population median HbA1c, percentage with HbA1c >9% (75 mmol/mol), percentage with ≥1 diabetic ketoacidosis (DKA) admission, and inpatient and emergency department (ED) visit rates per 1,000/month. Results: From 2021 to 2025, median HbA1c decreased from 8.6% (70 mmol/mol) to 7.9% (63 mmol/mol), HbA1c >9% (75 mmol/mol) decreased from 41.1% to 27.6%, and ≥1 DKA admission decreased from 9.1% to 5.6%. Inpatient admissions per 1,000/month decreased from 11.2 to 7.4 and ED visits from 10.0 to 7.6. The program met 3 of 6 targets in 2024 and all 6 in 2025. Conclusions: Pairing infrastructure funding with performance-dependent payments was feasible and associated with sustained improvements in glycemic control and reduced acute care utilization. Further multi-site evaluation is needed to determine impact, generalizability, and sustainability. Graphical
Open AccessA Data-Driven Pediatric Type 1 Diabetes Population Health Model Within Specialty Value-Based Care
Objective: Pediatric specialty value-based care (VBC) for chronic conditions remains under-described. We describe the design and early performance of a data-driven population health model for pediatric type 1 diabetes within a specialty VBC program. Research Design and Methods: Descriptive evaluation at a single academic pediatric medical center and clinically integrated network, 2021–2025, with formal VBC operation beginning in 2024. Participants were children and adolescents with type 1 diabetes attributed through commercial and Medicaid value-based agreements (n=786 in 2025). The program paired infrastructure funding with performance-dependent payments tied to clinical quality and utilization measures, supported by remote monitoring and care management. Measures: percentage receiving the chronic care intervention, population median HbA1c, percentage with HbA1c >9% (75 mmol/mol), percentage with ≥1 diabetic ketoacidosis (DKA) admission, and inpatient and emergency department (ED) visit rates per 1,000/month. Results: From 2021 to 2025, median HbA1c decreased from 8.6% (70 mmol/mol) to 7.9% (63 mmol/mol), HbA1c >9% (75 mmol/mol) decreased from 41.1% to 27.6%, and ≥1 DKA admission decreased from 9.1% to 5.6%. Inpatient admissions per 1,000/month decreased from 11.2 to 7.4 and ED visits from 10.0 to 7.6. The program met 3 of 6 targets in 2024 and all 6 in 2025. Conclusions: Pairing infrastructure funding with performance-dependent payments was feasible and associated with sustained improvements in glycemic control and reduced acute care utilization. Further multi-site evaluation is needed to determine impact, generalizability, and sustainability. Graphical
- 18 August 2026
- Published by Oxford University Press (OUP) in Journal of Pediatric Psychology
Confirmatory factor analysis of the parent and child problem areas in diabetes measures in a clinical sample of youth with type 1 diabetes
Objective: The Problem Areas in Diabetes Child version (PAID-C) and Parent version (P-PAID-C) have demonstrated initial validity and reliability in research samples; however, little is known about their performance in routine clinical settings. This study evaluated the factor structure of the PAID-C and P-PAID-C using clinic-based screening data from school-aged children (aged 8–12 years) with type 1 diabetes (T1D) and their parents. Methods: Children with T1D and their parents completed the PAID-C and P-PAID-C as part of standard clinic screening. We conducted confirmatory factor analyses using weighted least-squares mean and variance-adjusted estimation. We tested one-, two-, and four-factor models based on previous validation work and evaluated model fit using comparative fit index, Tucker–Lewis index, root mean square error of approximation, and standardized root mean squared residual. Results: Across approximately 24 months, 371 children completed the PAID-C and 893 parents completed the P-PAID-C. For the PAID-C, the one- and two-factor models both showed acceptable fit, with the two-factor model demonstrating the best fit. For the P-PAID-C, only the four-factor model reached acceptable fit after we correlated two similar error terms. Child PAID-C scores did not correlate with glycated hemoglobin (HbA1c), while parent P-PAID-C scores showed a small positive association with child HbA1c and were higher among parents of Hispanic children. Conclusions: Findings support the structural validity of the PAID-C and P-PAID-C when used in real-world clinical care. Results confirm diabetes distress as a multidimensional construct and reinforce the clinical utility of these brief measures for identifying specific distress domains and informing tailored interventions for children with T1D and their caregivers.
- 18 August 2026
- Published by Oxford University Press (OUP) in Journal of Pediatric Psychology
Confirmatory factor analysis of the parent and child problem areas in diabetes measures in a clinical sample of youth with type 1 diabetes
Objective: The Problem Areas in Diabetes Child version (PAID-C) and Parent version (P-PAID-C) have demonstrated initial validity and reliability in research samples; however, little is known about their performance in routine clinical settings. This study evaluated the factor structure of the PAID-C and P-PAID-C using clinic-based screening data from school-aged children (aged 8–12 years) with type 1 diabetes (T1D) and their parents. Methods: Children with T1D and their parents completed the PAID-C and P-PAID-C as part of standard clinic screening. We conducted confirmatory factor analyses using weighted least-squares mean and variance-adjusted estimation. We tested one-, two-, and four-factor models based on previous validation work and evaluated model fit using comparative fit index, Tucker–Lewis index, root mean square error of approximation, and standardized root mean squared residual. Results: Across approximately 24 months, 371 children completed the PAID-C and 893 parents completed the P-PAID-C. For the PAID-C, the one- and two-factor models both showed acceptable fit, with the two-factor model demonstrating the best fit. For the P-PAID-C, only the four-factor model reached acceptable fit after we correlated two similar error terms. Child PAID-C scores did not correlate with glycated hemoglobin (HbA1c), while parent P-PAID-C scores showed a small positive association with child HbA1c and were higher among parents of Hispanic children. Conclusions: Findings support the structural validity of the PAID-C and P-PAID-C when used in real-world clinical care. Results confirm diabetes distress as a multidimensional construct and reinforce the clinical utility of these brief measures for identifying specific distress domains and informing tailored interventions for children with T1D and their caregivers.
- Open Access
- 18 October 2025
- Published by SAGE Publications in Journal of Diabetes Science and Technology
- Vol. 20 (6) , 1788-1797
Establishment of a Diabetes-Tailored Data Intelligence Platform Enhances Clinical Care, Enables Risk-Based Monitoring, and Facilitates Population-Health-Based Approaches at a Pediatric Diabetes Network
Background: Patient-generated health data (PGHD) represents an opportunity to customize care, particularly in type 1 diabetes (T1D) care where continuous glucose monitor (CGM) and insulin pump usage continues to rise. Previous solutions to integrating CGM data into the electronic health record (EHR) have been limited in their ability to integrate data from multiple sources, ensure data fidelity, integrate data from multiple data streams, and rapidly adapt to changes in data output from numerous vendors. We developed a novel data infrastructure contained outside of the EHR to provide an alternative approach to PGHD integration, enable diabetes centers to identify and predict risk, and to facilitate research and quality improvement. Methods: We identified three key capabilities: ingesting and storing a wide variety of data, refining raw data into actionable insights, and visualizing and reporting to decision makers. To meet these requirements, we built a data intelligence platform we coined the diabetes data dock (D-data dock) in the Microsoft Azure cloud platform. Results: The D-data dock houses approximately 100 million CGM measurements, one million clinical events and insulin bolus records, and a near complete EHR record covering approximately 3000 patients per year from 2016 to 2023. We provide case studies detailing how the D-data dock allows timely monitoring of CGM data, enables novel study designs, and powers machine-learning-informed supplemental care interventions. Conclusions: The D-data dock is a novel approach to harnessing disparate data streams to improve patient care, enable timely interventions, and drive innovation to improve the lives and care of people with T1D.
- 18 October 2025
- Published by SAGE Publications in Journal of Diabetes Science and Technology
- Vol. 20 (6) , 1788-1797
Open AccessEstablishment of a Diabetes-Tailored Data Intelligence Platform Enhances Clinical Care, Enables Risk-Based Monitoring, and Facilitates Population-Health-Based Approaches at a Pediatric Diabetes Network
Background: Patient-generated health data (PGHD) represents an opportunity to customize care, particularly in type 1 diabetes (T1D) care where continuous glucose monitor (CGM) and insulin pump usage continues to rise. Previous solutions to integrating CGM data into the electronic health record (EHR) have been limited in their ability to integrate data from multiple sources, ensure data fidelity, integrate data from multiple data streams, and rapidly adapt to changes in data output from numerous vendors. We developed a novel data infrastructure contained outside of the EHR to provide an alternative approach to PGHD integration, enable diabetes centers to identify and predict risk, and to facilitate research and quality improvement. Methods: We identified three key capabilities: ingesting and storing a wide variety of data, refining raw data into actionable insights, and visualizing and reporting to decision makers. To meet these requirements, we built a data intelligence platform we coined the diabetes data dock (D-data dock) in the Microsoft Azure cloud platform. Results: The D-data dock houses approximately 100 million CGM measurements, one million clinical events and insulin bolus records, and a near complete EHR record covering approximately 3000 patients per year from 2016 to 2023. We provide case studies detailing how the D-data dock allows timely monitoring of CGM data, enables novel study designs, and powers machine-learning-informed supplemental care interventions. Conclusions: The D-data dock is a novel approach to harnessing disparate data streams to improve patient care, enable timely interventions, and drive innovation to improve the lives and care of people with T1D.
- Open Access
- 25 September 2025
- Published by JMIR Publications Inc. in JMIR Diabetes
- Vol. 10 (1) , e69142
Toward a Clinically Actionable, Electronic Health Record–Based Machine Learning Model to Forecast 90-Day Change in Hemoglobin A1c in Youth With Type 1 Diabetes: Feasibility and Model Development Study
Background: Clinicians currently lack an effective means for identifying youth with type 1 diabetes (T1D) who are at risk for experiencing glycemic deterioration between diabetes clinic visits. As a result, their ability to identify youth who may optimally benefit from targeted interventions designed to address rising glycemic levels is limited. Although electronic health records (EHR)–based risk predictions have been used to forecast health outcomes in T1D, no study has investigated the potential for using EHR data to identify youth with T1D who will experience a clinically significant rise in glycated hemoglobin (HbA1c) ≥0.3% (approximately 3 mmol/mol) between diabetes clinic visits. Objective: We aimed to evaluate the feasibility of using routinely collected EHR data to develop a machine learning model to predict 90-day unit-change in HbA1c (in % units) in youth (aged 9‐18 y) with T1D. We assessed our model’s ability to augment clinical decision-making by identifying a percent change cut point that optimized identification of youth who would experience a clinically significant rise in HbA1c. Methods: From a cohort of 2757 youth with T1D who received care from a network of pediatric diabetes clinics in the Midwestern United States (January 2012-August 2017), we identified 1743 youth with 9643 HbA1c observation windows (ie, 2 HbA1c measurements separated by 70‐110 d, approximating the 90-day time interval between routine diabetes clinic visits). We used up to 5 years of youths’ longitudinal EHR data to transform 17,466 features (demographics, laboratory results, vital signs, anthropometric measures, medications, diagnosis codes, procedure codes, and free-text data) for model training. We performed 3-fold cross-validation to train random forest regression models to predict 90-day unit-change in HbA1c(%). Results: Across all 3 folds of our cross-validation model, the average root-mean-square error was 0.88 (95% CI 0.85‐0.90). Predicted HbA1c(%) strongly correlated with true HbA1c(%) (r=0.79; 95% CI 0.78‐0.80). The top 10 features impacting model predictions included postal code, various metrics related to HbA1c, and the frequency of a diagnosis code indicating difficulty with treatment engagement. At a clinically significant percent rise threshold of ≥0.3% (approximately 3 mmol/mol), our model’s positive predictive value was 60.3%, indicating a 1.5-fold enrichment (relative to the observed frequency that youth experienced this outcome [3928/9643, 40.7%]). Model sensitivity and positive predictive value improved when thresholds for clinical significance included smaller changes in HbA1c, whereas specificity and negative predictive value improved when thresholds required larger changes in HbA1c. Conclusions: Routinely collected EHR data can be used to create an ML model for predicting unit-change in HbA1c between diabetes clinic visits among youth with T1D. Future work will focus on optimizing model performance and validating the model in additional cohorts and in other diabetes clinics.
- 25 September 2025
- Published by JMIR Publications Inc. in JMIR Diabetes
- Vol. 10 (1) , e69142
Open AccessToward a Clinically Actionable, Electronic Health Record–Based Machine Learning Model to Forecast 90-Day Change in Hemoglobin A1c in Youth With Type 1 Diabetes: Feasibility and Model Development Study
Background: Clinicians currently lack an effective means for identifying youth with type 1 diabetes (T1D) who are at risk for experiencing glycemic deterioration between diabetes clinic visits. As a result, their ability to identify youth who may optimally benefit from targeted interventions designed to address rising glycemic levels is limited. Although electronic health records (EHR)–based risk predictions have been used to forecast health outcomes in T1D, no study has investigated the potential for using EHR data to identify youth with T1D who will experience a clinically significant rise in glycated hemoglobin (HbA1c) ≥0.3% (approximately 3 mmol/mol) between diabetes clinic visits. Objective: We aimed to evaluate the feasibility of using routinely collected EHR data to develop a machine learning model to predict 90-day unit-change in HbA1c (in % units) in youth (aged 9‐18 y) with T1D. We assessed our model’s ability to augment clinical decision-making by identifying a percent change cut point that optimized identification of youth who would experience a clinically significant rise in HbA1c. Methods: From a cohort of 2757 youth with T1D who received care from a network of pediatric diabetes clinics in the Midwestern United States (January 2012-August 2017), we identified 1743 youth with 9643 HbA1c observation windows (ie, 2 HbA1c measurements separated by 70‐110 d, approximating the 90-day time interval between routine diabetes clinic visits). We used up to 5 years of youths’ longitudinal EHR data to transform 17,466 features (demographics, laboratory results, vital signs, anthropometric measures, medications, diagnosis codes, procedure codes, and free-text data) for model training. We performed 3-fold cross-validation to train random forest regression models to predict 90-day unit-change in HbA1c(%). Results: Across all 3 folds of our cross-validation model, the average root-mean-square error was 0.88 (95% CI 0.85‐0.90). Predicted HbA1c(%) strongly correlated with true HbA1c(%) (r=0.79; 95% CI 0.78‐0.80). The top 10 features impacting model predictions included postal code, various metrics related to HbA1c, and the frequency of a diagnosis code indicating difficulty with treatment engagement. At a clinically significant percent rise threshold of ≥0.3% (approximately 3 mmol/mol), our model’s positive predictive value was 60.3%, indicating a 1.5-fold enrichment (relative to the observed frequency that youth experienced this outcome [3928/9643, 40.7%]). Model sensitivity and positive predictive value improved when thresholds for clinical significance included smaller changes in HbA1c, whereas specificity and negative predictive value improved when thresholds required larger changes in HbA1c. Conclusions: Routinely collected EHR data can be used to create an ML model for predicting unit-change in HbA1c between diabetes clinic visits among youth with T1D. Future work will focus on optimizing model performance and validating the model in additional cohorts and in other diabetes clinics.
- Open Access
- 10 January 2025
- Published by JMIR Publications Inc. in JMIR Preprints
Towards a clinically actionable, electronic health record-based machine learning model to forecast 90-day change in hemoglobin A1c in youth with type 1 diabetes: Feasibility and model development study (Preprint)
BACKGROUND Clinicians currently lack an effective means for identifying youth with type 1 diabetes (T1D) who are at risk for experiencing glycemic deterioration between diabetes clinic visits. As a result, their ability to identify youth who may optimally benefit from targeted interventions designed to address rising glycemic levels is limited. Although electronic health records (EHR)-based risk predictions have been used to forecast some health outcomes in T1D, no study has investigated the potential for using EHR data to identify youth with T1D who will experience a clinically significant rise in HbA1c ≥0.3% (~3 mmol/mol) between diabetes clinic visits. OBJECTIVE We evaluated the feasibility of using routinely collected EHR data to develop a machine learning model to predict 90-day unit-change in HbA1c (in % units) in youth (ages 10-17) with T1D. We assessed our model's ability to augment clinical decision-making by identifying a percent change cut-point that optimized identification of youth who would experience a clinically significant rise in HbA1c. METHODS From a cohort of 2,757 youth with T1D who received care from a network of pediatric diabetes clinics in the Midwestern United States (January 2012-August 2017), we identified 1,743 youth with 9,643 HbA1c observation windows (i.e., 2 HbA1c measurements separated by 70-110 days, approximating the 90-day time interval between routine diabetes clinic visits). We used up to 5 years of youths' longitudinal EHR data to transform 17,466 features (demographics, laboratory results, vital signs, anthropometric measures, medications, diagnosis codes, procedure codes, and free text data) for model training. We performed three-fold cross-validation to train random forest regression models to predict 90-day unit-change in HbA1c(%). RESULTS Across all 3 folds of our cross-validation model, average root mean squared error was 0.88 (95% CI, 0.85-0.90). Predicted HbA1c(%) strongly correlated with true HbA1c(%) (r=0.79; 95% CI, 0.78-0.80). The top 10 features impacting model predictions included postal code, various metrics related to HbA1c, and the frequency of a diagnosis code indicating difficulty with treatment engagement. At a clinically significant percent rise threshold of ≥0.3% (~3 mmol/mol), our model's positive predictive value (PPV) was 60.3%, indicating a 1.5-fold enrichment (relative to the observed frequency that youth experienced this outcome [40.7%]). Model sensitivity and PPV improved when thresholds for clinical significance included smaller changes in HbA1c, whereas specificity and negative predictive value improved when thresholds required larger changes in HbA1c. CONCLUSIONS Routinely collected EHR data can be used to create an ML model for predicting unit-change in HbA1c between diabetes clinic visits among youth with T1D. Future work will focus on optimizing model performance and validating the model in additional cohorts and in other diabetes clinics.
- 10 January 2025
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessTowards a clinically actionable, electronic health record-based machine learning model to forecast 90-day change in hemoglobin A1c in youth with type 1 diabetes: Feasibility and model development study (Preprint)
BACKGROUND Clinicians currently lack an effective means for identifying youth with type 1 diabetes (T1D) who are at risk for experiencing glycemic deterioration between diabetes clinic visits. As a result, their ability to identify youth who may optimally benefit from targeted interventions designed to address rising glycemic levels is limited. Although electronic health records (EHR)-based risk predictions have been used to forecast some health outcomes in T1D, no study has investigated the potential for using EHR data to identify youth with T1D who will experience a clinically significant rise in HbA1c ≥0.3% (~3 mmol/mol) between diabetes clinic visits. OBJECTIVE We evaluated the feasibility of using routinely collected EHR data to develop a machine learning model to predict 90-day unit-change in HbA1c (in % units) in youth (ages 10-17) with T1D. We assessed our model's ability to augment clinical decision-making by identifying a percent change cut-point that optimized identification of youth who would experience a clinically significant rise in HbA1c. METHODS From a cohort of 2,757 youth with T1D who received care from a network of pediatric diabetes clinics in the Midwestern United States (January 2012-August 2017), we identified 1,743 youth with 9,643 HbA1c observation windows (i.e., 2 HbA1c measurements separated by 70-110 days, approximating the 90-day time interval between routine diabetes clinic visits). We used up to 5 years of youths' longitudinal EHR data to transform 17,466 features (demographics, laboratory results, vital signs, anthropometric measures, medications, diagnosis codes, procedure codes, and free text data) for model training. We performed three-fold cross-validation to train random forest regression models to predict 90-day unit-change in HbA1c(%). RESULTS Across all 3 folds of our cross-validation model, average root mean squared error was 0.88 (95% CI, 0.85-0.90). Predicted HbA1c(%) strongly correlated with true HbA1c(%) (r=0.79; 95% CI, 0.78-0.80). The top 10 features impacting model predictions included postal code, various metrics related to HbA1c, and the frequency of a diagnosis code indicating difficulty with treatment engagement. At a clinically significant percent rise threshold of ≥0.3% (~3 mmol/mol), our model's positive predictive value (PPV) was 60.3%, indicating a 1.5-fold enrichment (relative to the observed frequency that youth experienced this outcome [40.7%]). Model sensitivity and PPV improved when thresholds for clinical significance included smaller changes in HbA1c, whereas specificity and negative predictive value improved when thresholds required larger changes in HbA1c. CONCLUSIONS Routinely collected EHR data can be used to create an ML model for predicting unit-change in HbA1c between diabetes clinic visits among youth with T1D. Future work will focus on optimizing model performance and validating the model in additional cohorts and in other diabetes clinics.
- 7 May 2024
- Published by SAGE Publications in Journal of Diabetes Science and Technology
- Vol. 18 (4) , 771-778
Correlation Between the Glycemia Risk Index and Longitudinal Hemoglobin A1c in Children and Young Adults With Type 1 Diabetes
Background: The glycemia risk index (GRI) is a composite metric developed and used to estimate quality of glycemia in adults with diabetes who use continuous glucose monitor (CGM) devices. In a cohort of youth with type 1 diabetes (T1D), we examined the utility of the GRI for evaluating quality of glycemia between clinic visits by analyzing correlations between the GRI and longitudinal glycated hemoglobin A1c (HbA1c) measures. Method: Using electronic health records and CGM data, we conducted a retrospective cohort study to analyze the relationship between the GRI and longitudinal HbA1c measures in youth (T1D duration ≥1 year; ≥50% CGM wear time) receiving care from a Midwest pediatric diabetes clinic network (March 2016 to May 2022). Furthermore, we analyzed correlations between HbA1c and the GRI high and low components, which reflect time spent with high/very high and low/very low glucose, respectively. Results: In this cohort of 719 youth (aged = 2.5-18.0 years [median = 13.4; interquartile range [IQR] = 5.2]; 50.5% male; 83.7% non-Hispanic White; 68.0% commercial insurance), baseline GRI scores positively correlated with HbA1c measures at baseline and 3, 6, 9, and 12 months later (r = 0.68, 0.65, 0.60, 0.57, and 0.52, respectively). At all time points, strong positive correlations existed between HbA1c and time spent in hyperglycemia. Substantially weaker, negative correlations existed between HbA1c and time spent in hypoglycemia. Conclusions: In youth with T1D, the GRI may be useful for evaluating quality of glycemia between scheduled clinic visits. Additional CGM-derived metrics are needed to quantify risk for hypoglycemia in this population.
- 7 May 2024
- Published by SAGE Publications in Journal of Diabetes Science and Technology
- Vol. 18 (4) , 771-778
Correlation Between the Glycemia Risk Index and Longitudinal Hemoglobin A1c in Children and Young Adults With Type 1 Diabetes
Background: The glycemia risk index (GRI) is a composite metric developed and used to estimate quality of glycemia in adults with diabetes who use continuous glucose monitor (CGM) devices. In a cohort of youth with type 1 diabetes (T1D), we examined the utility of the GRI for evaluating quality of glycemia between clinic visits by analyzing correlations between the GRI and longitudinal glycated hemoglobin A1c (HbA1c) measures. Method: Using electronic health records and CGM data, we conducted a retrospective cohort study to analyze the relationship between the GRI and longitudinal HbA1c measures in youth (T1D duration ≥1 year; ≥50% CGM wear time) receiving care from a Midwest pediatric diabetes clinic network (March 2016 to May 2022). Furthermore, we analyzed correlations between HbA1c and the GRI high and low components, which reflect time spent with high/very high and low/very low glucose, respectively. Results: In this cohort of 719 youth (aged = 2.5-18.0 years [median = 13.4; interquartile range [IQR] = 5.2]; 50.5% male; 83.7% non-Hispanic White; 68.0% commercial insurance), baseline GRI scores positively correlated with HbA1c measures at baseline and 3, 6, 9, and 12 months later (r = 0.68, 0.65, 0.60, 0.57, and 0.52, respectively). At all time points, strong positive correlations existed between HbA1c and time spent in hyperglycemia. Substantially weaker, negative correlations existed between HbA1c and time spent in hypoglycemia. Conclusions: In youth with T1D, the GRI may be useful for evaluating quality of glycemia between scheduled clinic visits. Additional CGM-derived metrics are needed to quantify risk for hypoglycemia in this population.
- 6 May 2024
- Published by SAGE Publications in Journal of Diabetes Science and Technology
- Vol. 18 (4) , 779-786
The Glycemia Risk Index Predicts Performance of Diabetes Self-Management Habits in Youth With Type 1 Diabetes Mellitus
Background: The Glycemia Risk Index (GRI) was developed in adults with diabetes and is a validated metric of quality of glycemia. Little is known about the relationship between GRI and type 1 diabetes (T1D) self-management habits, a validated assessment of youths’ engagement in habits associated with glycemic outcomes. Method: We retrospectively examined the relationship between GRI and T1D self-management habits in youth with T1D who received care from a Midwest pediatric diabetes clinic network. The GRI was calculated using seven days of continuous glucose monitor (CGM) data, and T1D self-management habits were assessed ±seven days from the GRI score. A mixed-effects Poisson regression model was used to evaluate the total number of habits youth engaged in with GRI, glycated hemoglobin A1c (HbA1c), age, race, ethnicity, and insurance type as fixed effects and participant ID as a random effect to account for multiple clinic visits per individual. Results: The cohort included 1182 youth aged 2.5 to 18.0 years (mean = 13.8, SD = 3.5) comprising 50.8% male, 84.6% non-Hispanic White, and 64.8% commercial insurance users across a total of 6029 clinic visits. Glycemia Risk Index scores decreased as total number of habits performed increased, suggesting youth who performed more self-management habits achieved a higher quality of glycemia. Conclusions: In youth using CGMs, GRI may serve as an easily obtainable metric to help identify youth with above target glycemia, and engagement/disengagement in the T1D self-management habits may inform clinicians with suitable interventions for improving glycemic outcomes.
- 6 May 2024
- Published by SAGE Publications in Journal of Diabetes Science and Technology
- Vol. 18 (4) , 779-786
The Glycemia Risk Index Predicts Performance of Diabetes Self-Management Habits in Youth With Type 1 Diabetes Mellitus
Background: The Glycemia Risk Index (GRI) was developed in adults with diabetes and is a validated metric of quality of glycemia. Little is known about the relationship between GRI and type 1 diabetes (T1D) self-management habits, a validated assessment of youths’ engagement in habits associated with glycemic outcomes. Method: We retrospectively examined the relationship between GRI and T1D self-management habits in youth with T1D who received care from a Midwest pediatric diabetes clinic network. The GRI was calculated using seven days of continuous glucose monitor (CGM) data, and T1D self-management habits were assessed ±seven days from the GRI score. A mixed-effects Poisson regression model was used to evaluate the total number of habits youth engaged in with GRI, glycated hemoglobin A1c (HbA1c), age, race, ethnicity, and insurance type as fixed effects and participant ID as a random effect to account for multiple clinic visits per individual. Results: The cohort included 1182 youth aged 2.5 to 18.0 years (mean = 13.8, SD = 3.5) comprising 50.8% male, 84.6% non-Hispanic White, and 64.8% commercial insurance users across a total of 6029 clinic visits. Glycemia Risk Index scores decreased as total number of habits performed increased, suggesting youth who performed more self-management habits achieved a higher quality of glycemia. Conclusions: In youth using CGMs, GRI may serve as an easily obtainable metric to help identify youth with above target glycemia, and engagement/disengagement in the T1D self-management habits may inform clinicians with suitable interventions for improving glycemic outcomes.
- Open Access
- 18 July 2023
- Published by JMIR Publications Inc. in JMIR Diabetes
- Vol. 8 (1) , e47592
An “All-Data-on-Hand” Deep Learning Model to Predict Hospitalization for Diabetic Ketoacidosis in Youth With Type 1 Diabetes: Development and Validation Study
Background: Although prior research has identified multiple risk factors for diabetic ketoacidosis (DKA), clinicians continue to lack clinic-ready models to predict dangerous and costly episodes of DKA. We asked whether we could apply deep learning, specifically the use of a long short-term memory (LSTM) model, to accurately predict the 180-day risk of DKA-related hospitalization for youth with type 1 diabetes (T1D). Objective: We aimed to describe the development of an LSTM model to predict the 180-day risk of DKA-related hospitalization for youth with T1D. Methods: We used 17 consecutive calendar quarters of clinical data (January 10, 2016, to March 18, 2020) for 1745 youths aged 8 to 18 years with T1D from a pediatric diabetes clinic network in the Midwestern United States. The input data included demographics, discrete clinical observations (laboratory results, vital signs, anthropometric measures, diagnosis, and procedure codes), medications, visit counts by type of encounter, number of historic DKA episodes, number of days since last DKA admission, patient-reported outcomes (answers to clinic intake questions), and data features derived from diabetes- and nondiabetes-related clinical notes via natural language processing. We trained the model using input data from quarters 1 to 7 (n=1377), validated it using input from quarters 3 to 9 in a partial out-of-sample (OOS-P; n=1505) cohort, and further validated it in a full out-of-sample (OOS-F; n=354) cohort with input from quarters 10 to 15. Results: DKA admissions occurred at a rate of 5% per 180-days in both out-of-sample cohorts. In the OOS-P and OOS-F cohorts, the median age was 13.7 (IQR 11.3-15.8) years and 13.1 (IQR 10.7-15.5) years; median glycated hemoglobin levels at enrollment were 8.6% (IQR 7.6%-9.8%) and 8.1% (IQR 6.9%-9.5%); recall was 33% (26/80) and 50% (9/18) for the top-ranked 5% of youth with T1D; and 14.15% (213/1505) and 12.7% (45/354) had prior DKA admissions (after the T1D diagnosis), respectively. For lists rank ordered by the probability of hospitalization, precision increased from 33% to 56% to 100% for positions 1 to 80, 1 to 25, and 1 to 10 in the OOS-P cohort and from 50% to 60% to 80% for positions 1 to 18, 1 to 10, and 1 to 5 in the OOS-F cohort, respectively. Conclusions: The proposed LSTM model for predicting 180-day DKA-related hospitalization was valid in this sample. Future research should evaluate model validity in multiple populations and settings to account for health inequities that may be present in different segments of the population (eg, racially or socioeconomically diverse cohorts). Rank ordering youth by probability of DKA-related hospitalization will allow clinics to identify the most at-risk youth. The clinical implication of this is that clinics may then create and evaluate novel preventive interventions based on available resources.
- 18 July 2023
- Published by JMIR Publications Inc. in JMIR Diabetes
- Vol. 8 (1) , e47592
Open AccessAn “All-Data-on-Hand” Deep Learning Model to Predict Hospitalization for Diabetic Ketoacidosis in Youth With Type 1 Diabetes: Development and Validation Study
Background: Although prior research has identified multiple risk factors for diabetic ketoacidosis (DKA), clinicians continue to lack clinic-ready models to predict dangerous and costly episodes of DKA. We asked whether we could apply deep learning, specifically the use of a long short-term memory (LSTM) model, to accurately predict the 180-day risk of DKA-related hospitalization for youth with type 1 diabetes (T1D). Objective: We aimed to describe the development of an LSTM model to predict the 180-day risk of DKA-related hospitalization for youth with T1D. Methods: We used 17 consecutive calendar quarters of clinical data (January 10, 2016, to March 18, 2020) for 1745 youths aged 8 to 18 years with T1D from a pediatric diabetes clinic network in the Midwestern United States. The input data included demographics, discrete clinical observations (laboratory results, vital signs, anthropometric measures, diagnosis, and procedure codes), medications, visit counts by type of encounter, number of historic DKA episodes, number of days since last DKA admission, patient-reported outcomes (answers to clinic intake questions), and data features derived from diabetes- and nondiabetes-related clinical notes via natural language processing. We trained the model using input data from quarters 1 to 7 (n=1377), validated it using input from quarters 3 to 9 in a partial out-of-sample (OOS-P; n=1505) cohort, and further validated it in a full out-of-sample (OOS-F; n=354) cohort with input from quarters 10 to 15. Results: DKA admissions occurred at a rate of 5% per 180-days in both out-of-sample cohorts. In the OOS-P and OOS-F cohorts, the median age was 13.7 (IQR 11.3-15.8) years and 13.1 (IQR 10.7-15.5) years; median glycated hemoglobin levels at enrollment were 8.6% (IQR 7.6%-9.8%) and 8.1% (IQR 6.9%-9.5%); recall was 33% (26/80) and 50% (9/18) for the top-ranked 5% of youth with T1D; and 14.15% (213/1505) and 12.7% (45/354) had prior DKA admissions (after the T1D diagnosis), respectively. For lists rank ordered by the probability of hospitalization, precision increased from 33% to 56% to 100% for positions 1 to 80, 1 to 25, and 1 to 10 in the OOS-P cohort and from 50% to 60% to 80% for positions 1 to 18, 1 to 10, and 1 to 5 in the OOS-F cohort, respectively. Conclusions: The proposed LSTM model for predicting 180-day DKA-related hospitalization was valid in this sample. Future research should evaluate model validity in multiple populations and settings to account for health inequities that may be present in different segments of the population (eg, racially or socioeconomically diverse cohorts). Rank ordering youth by probability of DKA-related hospitalization will allow clinics to identify the most at-risk youth. The clinical implication of this is that clinics may then create and evaluate novel preventive interventions based on available resources.
- Open Access
- 25 March 2023
- Published by JMIR Publications Inc. in JMIR Preprints
An “All-Data-on-Hand” Deep Learning Model to Predict Hospitalization for Diabetic Ketoacidosis in Youth With Type 1 Diabetes: Development and Validation Study (Preprint)
BACKGROUND Although prior research has identified multiple risk factors for diabetic ketoacidosis (DKA), clinicians continue to lack clinic-ready models to predict dangerous and costly episodes of DKA. We asked whether we could apply deep learning, specifically the use of a long short-term memory (LSTM) model, to accurately predict the 180-day risk of DKA-related hospitalization for youth with type 1 diabetes (T1D). OBJECTIVE We aimed to describe the development of an LSTM model to predict the 180-day risk of DKA-related hospitalization for youth with T1D. METHODS We used 17 consecutive calendar quarters of clinical data (January 10, 2016, to March 18, 2020) for 1745 youths aged 8 to 18 years with T1D from a pediatric diabetes clinic network in the Midwestern United States. The input data included demographics, discrete clinical observations (laboratory results, vital signs, anthropometric measures, diagnosis, and procedure codes), medications, visit counts by type of encounter, number of historic DKA episodes, number of days since last DKA admission, patient-reported outcomes (answers to clinic intake questions), and data features derived from diabetes- and nondiabetes-related clinical notes via natural language processing. We trained the model using input data from quarters 1 to 7 (n=1377), validated it using input from quarters 3 to 9 in a partial out-of-sample (OOS-P; n=1505) cohort, and further validated it in a full out-of-sample (OOS-F; n=354) cohort with input from quarters 10 to 15. RESULTS DKA admissions occurred at a rate of 5% per 180-days in both out-of-sample cohorts. In the OOS-P and OOS-F cohorts, the median age was 13.7 (IQR 11.3-15.8) years and 13.1 (IQR 10.7-15.5) years; median glycated hemoglobin levels at enrollment were 8.6% (IQR 7.6%-9.8%) and 8.1% (IQR 6.9%-9.5%); recall was 33% (26/80) and 50% (9/18) for the top-ranked 5% of youth with T1D; and 14.15% (213/1505) and 12.7% (45/354) had prior DKA admissions (after the T1D diagnosis), respectively. For lists rank ordered by the probability of hospitalization, precision increased from 33% to 56% to 100% for positions 1 to 80, 1 to 25, and 1 to 10 in the OOS-P cohort and from 50% to 60% to 80% for positions 1 to 18, 1 to 10, and 1 to 5 in the OOS-F cohort, respectively. CONCLUSIONS The proposed LSTM model for predicting 180-day DKA-related hospitalization was valid in this sample. Future research should evaluate model validity in multiple populations and settings to account for health inequities that may be present in different segments of the population (eg, racially or socioeconomically diverse cohorts). Rank ordering youth by probability of DKA-related hospitalization will allow clinics to identify the most at-risk youth. The clinical implication of this is that clinics may then create and evaluate novel preventive interventions based on available resources.
- 25 March 2023
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessAn “All-Data-on-Hand” Deep Learning Model to Predict Hospitalization for Diabetic Ketoacidosis in Youth With Type 1 Diabetes: Development and Validation Study (Preprint)
BACKGROUND Although prior research has identified multiple risk factors for diabetic ketoacidosis (DKA), clinicians continue to lack clinic-ready models to predict dangerous and costly episodes of DKA. We asked whether we could apply deep learning, specifically the use of a long short-term memory (LSTM) model, to accurately predict the 180-day risk of DKA-related hospitalization for youth with type 1 diabetes (T1D). OBJECTIVE We aimed to describe the development of an LSTM model to predict the 180-day risk of DKA-related hospitalization for youth with T1D. METHODS We used 17 consecutive calendar quarters of clinical data (January 10, 2016, to March 18, 2020) for 1745 youths aged 8 to 18 years with T1D from a pediatric diabetes clinic network in the Midwestern United States. The input data included demographics, discrete clinical observations (laboratory results, vital signs, anthropometric measures, diagnosis, and procedure codes), medications, visit counts by type of encounter, number of historic DKA episodes, number of days since last DKA admission, patient-reported outcomes (answers to clinic intake questions), and data features derived from diabetes- and nondiabetes-related clinical notes via natural language processing. We trained the model using input data from quarters 1 to 7 (n=1377), validated it using input from quarters 3 to 9 in a partial out-of-sample (OOS-P; n=1505) cohort, and further validated it in a full out-of-sample (OOS-F; n=354) cohort with input from quarters 10 to 15. RESULTS DKA admissions occurred at a rate of 5% per 180-days in both out-of-sample cohorts. In the OOS-P and OOS-F cohorts, the median age was 13.7 (IQR 11.3-15.8) years and 13.1 (IQR 10.7-15.5) years; median glycated hemoglobin levels at enrollment were 8.6% (IQR 7.6%-9.8%) and 8.1% (IQR 6.9%-9.5%); recall was 33% (26/80) and 50% (9/18) for the top-ranked 5% of youth with T1D; and 14.15% (213/1505) and 12.7% (45/354) had prior DKA admissions (after the T1D diagnosis), respectively. For lists rank ordered by the probability of hospitalization, precision increased from 33% to 56% to 100% for positions 1 to 80, 1 to 25, and 1 to 10 in the OOS-P cohort and from 50% to 60% to 80% for positions 1 to 18, 1 to 10, and 1 to 5 in the OOS-F cohort, respectively. CONCLUSIONS The proposed LSTM model for predicting 180-day DKA-related hospitalization was valid in this sample. Future research should evaluate model validity in multiple populations and settings to account for health inequities that may be present in different segments of the population (eg, racially or socioeconomically diverse cohorts). Rank ordering youth by probability of DKA-related hospitalization will allow clinics to identify the most at-risk youth. The clinical implication of this is that clinics may then create and evaluate novel preventive interventions based on available resources.