1
|
Xu H, Yu H, Cheng Z, Mu C, Bao D, Li X, Xing Q. Development and validation of a prediction model for self-reported hypoglycemia risk in patients with type 2 diabetes: A longitudinal cohort study. J Diabetes Investig 2024; 15:468-482. [PMID: 38243656 PMCID: PMC10981142 DOI: 10.1111/jdi.14135] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 06/25/2023] [Revised: 10/21/2023] [Accepted: 12/09/2023] [Indexed: 01/21/2024] Open
Abstract
AIMS/INTRODUCTION To develop and validate a simple prediction model for hypoglycemia risk in patients with type 2 diabetes. MATERIALS AND METHODS We prospectively analyzed the data of 1,303 subjects in a third-class hospital in Tianjin and followed up their hypoglycemia events at 3 and 6 months. The hypoglycemia risk prediction models for 3 and 6 months were developed and the model performance was evaluated. RESULTS A total of 340 (28.4%) patients experienced hypoglycemia within 3 months and 462 (37.2%) within 6 months during the follow-up period. Age, central obesity, intensive insulin therapy, frequency of hypoglycemia in the past year, and hypoglycemia prevention education entered both model3month and model6month. The area under the receiver operating characteristic curve of model3month and model6month were 0.711 and 0.723, respectively. The Youden index was 0.315 and 0.361, while the sensitivities were 0.615 and 0.714, and the specificities were 0.717 and 0.631. The calibration curves showed that the models were similar to reality. The decision curves implied that the clinical net benefit of the model was clear. CONCLUSIONS The study developed 3 and 6 month hypoglycemia risk prediction models for patients with type 2 diabetes. The discrimination and calibration of the two prediction models were good, and might help to improve clinical decision-making and guide patients to more reasonable self-care and hypoglycemia prevention at home.
Collapse
Affiliation(s)
- Hongmei Xu
- NHC Key Laboratory of Hormones and Development, Tianjin Key Laboratory of Metabolic Diseases, Chu Hsien‐I Memorial Hospital & Tianjin Institute of EndocrinologyTianjin Medical UniversityTianjinChina
| | - Hangqing Yu
- Department of Respiratory and Critical CareThe Second Affiliated Hospital of Zhejiang University School of MedicineHangzhouChina
| | - Zhengnan Cheng
- Department of NursingTianjin Medical CollegeTianjinChina
| | - Chun Mu
- NHC Key Laboratory of Hormones and Development, Tianjin Key Laboratory of Metabolic Diseases, Chu Hsien‐I Memorial Hospital & Tianjin Institute of EndocrinologyTianjin Medical UniversityTianjinChina
| | - Di Bao
- NHC Key Laboratory of Hormones and Development, Tianjin Key Laboratory of Metabolic Diseases, Chu Hsien‐I Memorial Hospital & Tianjin Institute of EndocrinologyTianjin Medical UniversityTianjinChina
| | - Xiaohui Li
- NHC Key Laboratory of Hormones and Development, Tianjin Key Laboratory of Metabolic Diseases, Chu Hsien‐I Memorial Hospital & Tianjin Institute of EndocrinologyTianjin Medical UniversityTianjinChina
| | - Qiuling Xing
- NHC Key Laboratory of Hormones and Development, Tianjin Key Laboratory of Metabolic Diseases, Chu Hsien‐I Memorial Hospital & Tianjin Institute of EndocrinologyTianjin Medical UniversityTianjinChina
| |
Collapse
|
2
|
Ma S, Alvear A, Schreiner PJ, Seaquist ER, Kirsh T, Chow LS. Development and Validation of an Electronic Health Record-Based Risk Assessment Tool for Hypoglycemia in Patients With Type 2 Diabetes Mellitus. J Diabetes Sci Technol 2023:19322968231184497. [PMID: 37381607 DOI: 10.1177/19322968231184497] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 06/30/2023]
Abstract
BACKGROUND The recent availability of high-quality data from clinical trials, together with machine learning (ML) techniques, presents exciting opportunities for developing prediction models for clinical outcomes. METHODS As a proof-of-concept, we translated a hypoglycemia risk model derived from the Action to Control Cardiovascular Risk in Diabetes (ACCORD) study into the HypoHazardScore, a risk assessment tool applicable to electronic health record (EHR) data. To assess its performance, we conducted a 16-week clinical study at the University of Minnesota where participants (N = 40) with type 2 diabetes mellitus (T2DM) had hypoglycemia assessed prospectively by continuous glucose monitoring (CGM). RESULTS The HypoHazardScore combines 16 risk factors commonly found within the EHR. The HypoHazardScore successfully predicted (area under the curve [AUC] = 0.723) whether participants experienced least one CGM-assessed hypoglycemic event (glucose <54 mg/dL for ≥15 minutes from two CGMs) while significantly correlating with frequency of CGM-assessed hypoglycemic events (r = 0.38) and percent time experiencing CGM-assessed hypoglycemia (r = 0.39). Compared to participants with a low HypoHazardScore (N = 19, score <4, median score of 4), participants with a high HypoHazardScore (N = 21, score ≥4) had more frequent CGM-assessed hypoglycemic events (high: 1.6 ± 2.2 events/week; low: 0.3 ± 0.5 events/week) and experienced more CGM-assessed hypoglycemia (high: 1.4% ± 2.0%; low: 0.2% ± 0.4% time) during the 16-week follow-up. CONCLUSIONS We demonstrated that a hypoglycemia risk model can be successfully adapted from the ACCORD data to the EHR, with validation by a prospective study using CGM-assessed hypoglycemia. The HypoHazardScore represents a significant advancement toward implementing an EHR-based decision support system that can help reduce hypoglycemia in patients with T2DM.
Collapse
Affiliation(s)
- Sisi Ma
- Institute for Health Informatics, University of Minnesota, Minneapolis, MN, USA
| | - Alison Alvear
- Department of Medicine, University of Minnesota, Minneapolis, MN, USA
| | - Pamela J Schreiner
- Division of Epidemiology & Community Health, University of Minnesota, Minneapolis, MN, USA
| | | | - Thomas Kirsh
- Institute for Health Informatics, University of Minnesota, Minneapolis, MN, USA
| | - Lisa S Chow
- Department of Medicine, University of Minnesota, Minneapolis, MN, USA
| |
Collapse
|
3
|
Zhang L, Yang L, Zhou Z. Data-based modeling for hypoglycemia prediction: Importance, trends, and implications for clinical practice. Front Public Health 2023; 11:1044059. [PMID: 36778566 PMCID: PMC9910805 DOI: 10.3389/fpubh.2023.1044059] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/14/2022] [Accepted: 01/10/2023] [Indexed: 01/27/2023] Open
Abstract
Background and objective Hypoglycemia is a key barrier to achieving optimal glycemic control in people with diabetes, which has been proven to cause a set of deleterious outcomes, such as impaired cognition, increased cardiovascular disease, and mortality. Hypoglycemia prediction has come to play a role in diabetes management as big data analysis and machine learning (ML) approaches have become increasingly prevalent in recent years. As a result, a review is needed to summarize the existing prediction algorithms and models to guide better clinical practice in hypoglycemia prevention. Materials and methods PubMed, EMBASE, and the Cochrane Library were searched for relevant studies published between 1 January 2015 and 8 December 2022. Five hypoglycemia prediction aspects were covered: real-time hypoglycemia, mild and severe hypoglycemia, nocturnal hypoglycemia, inpatient hypoglycemia, and other hypoglycemia (postprandial, exercise-related). Results From the 5,042 records retrieved, we included 79 studies in our analysis. Two major categories of prediction models are identified by an overview of the chosen studies: simple or logistic regression models based on clinical data and data-based ML models (continuous glucose monitoring data is most commonly used). Models utilizing clinical data have identified a variety of risk factors that can lead to hypoglycemic events. Data-driven models based on various techniques such as neural networks, autoregressive, ensemble learning, supervised learning, and mathematical formulas have also revealed suggestive features in cases of hypoglycemia prediction. Conclusion In this study, we looked deep into the currently established hypoglycemia prediction models and identified hypoglycemia risk factors from various perspectives, which may provide readers with a better understanding of future trends in this topic.
Collapse
|
4
|
Wu Y, Li R, Zhang Y, Long T, Zhang Q, Li M. Prediction Models for Prognosis of Hypoglycemia in Patients with Diabetes: A Systematic Review and Meta-Analysis. Biol Res Nurs 2023; 25:41-50. [PMID: 35839096 DOI: 10.1177/10998004221115856] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/14/2022]
Abstract
OBJECTIVE To systematically summarize the reported prediction models for hypoglycemia in patients with diabetes, compare their performance, and evaluate their applicability in clinical practice. METHODS We selected studies according to the PRISMA, appraised studies according to the Prediction model Risk of Bias Assessment Tool (PROBAST), and extracted and synthesized the data according to the CHARMS. The databases of PubMed, Web of Science, Embase, and Cochrane Library were searched from inception to 31 October 2021 using a systematic review approach to capture all eligible studies developing and/or validating a prognostic prediction model for hypoglycemia in patients with diabetes. The risk bias and clinical applicability were assessed using the PROBAST. The meta-analysis of the performance of the prediction models were also conducted. The protocol of this study was recorded in PROSPERO (CRD42022309852). RESULTS Sixteen studies with 22 models met the eligible criteria. The predictors with the high frequency of occurrence among all models were age, HbA1c, history of hypoglycemia, and insulin use. A meta-analysis of C-statistic was performed for 21 prediction models, and the summary C-statistic and its 95% confidence interval and prediction interval were 0.7699 (0.7299-0.8098), 0.7699 (0.5862-0.9536), respectively. Heterogeneity exists between different hypoglycemia prediction models (τ2 was 0.00734≠0). CONCLUSIONS The existing predictive models are not recommended for widespread clinical use. A high-quality hypoglycemia screening tool should be developed in future studies.
Collapse
Affiliation(s)
- Yi Wu
- Peking University Health Science Center, Beijing, China.,School of Nursing, 540405Peking University, Beijing, China.,Peking University Health Science Centre for Evidence-Based Nursing, A Joanna Briggs Institute Affiliated Group, Beijing, China
| | - Ruxue Li
- Peking University Health Science Center, Beijing, China.,School of Nursing, 540405Peking University, Beijing, China.,Peking University Health Science Centre for Evidence-Based Nursing, A Joanna Briggs Institute Affiliated Group, Beijing, China
| | - Yating Zhang
- Peking University Health Science Center, Beijing, China.,School of Nursing, 540405Peking University, Beijing, China.,Peking University Health Science Centre for Evidence-Based Nursing, A Joanna Briggs Institute Affiliated Group, Beijing, China
| | - Tianxue Long
- Peking University Health Science Center, Beijing, China.,School of Nursing, 540405Peking University, Beijing, China.,Peking University Health Science Centre for Evidence-Based Nursing, A Joanna Briggs Institute Affiliated Group, Beijing, China
| | - Qi Zhang
- Peking University Health Science Center, Beijing, China.,School of Nursing, 540405Peking University, Beijing, China.,Peking University Health Science Centre for Evidence-Based Nursing, A Joanna Briggs Institute Affiliated Group, Beijing, China
| | - Mingzi Li
- Peking University Health Science Center, Beijing, China.,School of Nursing, 540405Peking University, Beijing, China.,Peking University Health Science Centre for Evidence-Based Nursing, A Joanna Briggs Institute Affiliated Group, Beijing, China
| |
Collapse
|
5
|
Pan Q, Li Y, Wan H, Wang J, Xu B, Wang G, Jiang C, Liang L, Feng W, Liu J, Wang T, Zhang X, Cui N, Mu Y, Guo L. Efficacy and safety of a basal insulin + 2-3 oral antihyperglycaemic drugs regimen versus a twice-daily premixed insulin + metformin regimen after short-term intensive insulin therapy in individuals with type 2 diabetes: The multicentre, open-label, randomized controlled BEYOND-V trial. Diabetes Obes Metab 2022; 24:1957-1966. [PMID: 35642463 PMCID: PMC9543477 DOI: 10.1111/dom.14780] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/24/2022] [Revised: 05/18/2022] [Accepted: 05/26/2022] [Indexed: 11/30/2022]
Abstract
AIM To compare the efficacy and safety of basal insulin glargine 100 units/ml (Gla) + 2-3 oral antihyperglycaemic drugs (OADs) with twice-daily premixed insulin aspart 70/30 (Asp30) + metformin (MET) after short-term intensive insulin therapy in adults with type 2 diabetes in China. MATERIALS AND METHODS This open-label trial enrolled insulin-naïve adults with type 2 diabetes and an HbA1c of 7.5%-11.0% (58-97 mmol/mol) despite treatment with 2-3 OADs. All participants stopped previous OADs except MET, then received short-term intensive insulin therapy during the run-in period, when those with a fasting plasma glucose of less than 7.0 mmol/L and 2-hour postprandial glucose of less than 10.0 mmol/L were randomized to Gla + MET + a dipeptidyl peptidase-4 inhibitor or twice-daily Asp30 + MET. If HbA1c was more than 7.0% (>53 mmol/mol) at week 12, participants in the Gla group were added repaglinide or acarbose, at the physician's discretion, and participants in the Asp30 group continued to titrate insulin dose. The change in HbA1c from baseline to week 24 was assessed in the per protocol (PP) population (primary endpoint). RESULTS There were 384 enrollees (192 each to Gla and Asp30); 367 were included in the PP analysis. The threshold for non-inferiority of Gla + OADs versus Asp30 + MET was met, with a least squares mean change from baseline in HbA1c of -1.72% and -1.70% (-42.2 and -42.1 mmol/mol), respectively (estimated difference -0.01%; 95% CI -0.20%, 0.17% [-0.1 mmol/mol; 95% CI -2.2, 1.9]). Achievement of HbA1c less than 7.0% (<53 mmol/mol) was comparable between the groups (60% vs. 57%). The proportion of participants with any (24% vs. 38%; P = .003), symptomatic (19% vs. 31%; P = .007) or confirmed hypoglycaemia (18% vs. 33%; P < .001) was lower in the Gla + OADs group. CONCLUSIONS Compared with Asp30 + MET, Gla + 2-3 OADs showed similar efficacy but a lower hypoglycaemia risk in Chinese individuals with type 2 diabetes who had undergone short-term intensive insulin therapy.
Collapse
Affiliation(s)
- Qi Pan
- Department of Endocrinology, Beijing HospitalNational Center of GerontologyBeijingChina
| | - Yijun Li
- Department of EndocrinologyThe First Medical Center of Chinese PLA General HospitalBeijingChina
| | - Hailong Wan
- Department of EndocrinologyPanjin Central HospitalPanjinChina
| | - Junfen Wang
- Department of EndocrinologySecond Hospital of ShijiazhuangShijiazhuangChina
| | - Binhua Xu
- Department of EndocrinologyHarbin the First HospitalHarbinChina
| | - Guoping Wang
- Department of EndocrinologySecond Affiliated Hospital of Baotou Medical CollegeBaotouChina
| | - Chengxia Jiang
- Department of EndocrinologyThe Second People's Hospital of YibinYibinChina
| | - Li Liang
- Department of EndocrinologyPeople's Hospital of Liaoning ProvinceShenyangChina
| | - Wei Feng
- Medical DepartmentSanofiShanghaiChina
| | | | - Ting Wang
- Medical DepartmentSanofiShanghaiChina
| | - Xia Zhang
- Medical DepartmentSanofiShanghaiChina
| | - Nan Cui
- Medical DepartmentSanofiShanghaiChina
| | - Yiming Mu
- Department of EndocrinologyThe First Medical Center of Chinese PLA General HospitalBeijingChina
| | - Lixin Guo
- Department of Endocrinology, Beijing HospitalNational Center of GerontologyBeijingChina
| | | |
Collapse
|