Development and Validation of a Nocturnal Hypoglycaemia Risk Model for Patients With Type 2 Diabetes Mellitus

Overview

Journal Nurs Open

Specialty Nursing

Date 2024 Oct 4

PMID 39363560

Authors

Chen Gong

Tingting Cai

Ying Wang

Xuelian Xiong

Yunfeng Zhou

Tingting Zhou

Qi Sun

Huiqun Huang

Affiliations

Soon will be listed here.

Abstract

Aim: To develop and test different machine learning algorithms for predicting nocturnal hypoglycaemia in patients with type 2 diabetes mellitus.

Design: A retrospective study.

Methods: We collected data from dynamic blood glucose monitoring of patients with T2DM admitted to the Department of Endocrinology and Metabolism at a hospital in Shanghai, China, from November 2020 to January 2022. Patients undergone the continuous glucose monitoring (CGM) for ≥ 24 h were included in this study. Logistic regression, random forest and light gradient boosting machine algorithms were employed, and the models were validated and compared using AUC, accuracy, specificity, recall rate, precision, F1 score and the Kolmogorov-Smirnov test.

Results: A total of 4015 continuous glucose-monitoring data points from 440 patients were included, and 28 variables were selected to build the risk prediction model. The 440 patients had an average age of 62.7 years. Approximately 48.2% of the patients were female and 51.8% were male. Nocturnal hypoglycaemia appeared in 573 (14.30%) of 4015 continuous glucose monitoring data. The light gradient boosting machine model demonstrated the highest predictive performances: AUC (0.869), specificity (0.802), accuracy (0.801), precision (0.409), recall rate (0.797), F1 score (0.255) and Kolmogorov (0.603). The selected predictive factors included time below the target glucose range, duration of diabetes, insulin use before bed and dynamic blood glucose monitoring parameters from the previous day.

Patient Or Public Contribution: No Patient or Public Contribution.

References

Hu M, Shu X, Yu G, Wu X, Valimaki M, Feng H . A Risk Prediction Model Based on Machine Learning for Cognitive Impairment Among Chinese Community-Dwelling Elderly People With Normal Cognition: Development and Validation Study. J Med Internet Res. 2021; 23(2):e20298. PMC: 7946590. DOI: 10.2196/20298. View

Schultes B, Jauch-Chara K, Gais S, Hallschmid M, Reiprich E, Kern W . Defective awakening response to nocturnal hypoglycemia in patients with type 1 diabetes mellitus. PLoS Med. 2007; 4(2):e69. PMC: 1808097. DOI: 10.1371/journal.pmed.0040069. View

Ling Q, Lu J, Li X, Qiao C, Zhu D, Bi Y . Value of Capillary Glucose Profiles in Assessing Risk of Nocturnal Hypoglycemia in Type 1 Diabetes Based on Continuous Glucose Monitoring. Diabetes Ther. 2020; 11(4):915-925. PMC: 7136363. DOI: 10.1007/s13300-020-00787-0. View

Hou N, Li M, He L, Xie B, Wang L, Zhang R . Predicting 30-days mortality for MIMIC-III patients with sepsis-3: a machine learning approach using XGboost. J Transl Med. 2020; 18(1):462. PMC: 7720497. DOI: 10.1186/s12967-020-02620-5. View

Mathioudakis N, Abusamaan M, Shakarchi A, Sokolinsky S, Fayzullin S, McGready J . Development and Validation of a Machine Learning Model to Predict Near-Term Risk of Iatrogenic Hypoglycemia in Hospitalized Patients. JAMA Netw Open. 2021; 4(1):e2030913. PMC: 7794667. DOI: 10.1001/jamanetworkopen.2020.30913. View

Danne T, Nimri R, Battelino T, Bergenstal R, Close K, DeVries J . International Consensus on Use of Continuous Glucose Monitoring. Diabetes Care. 2017; 40(12):1631-1640. PMC: 6467165. DOI: 10.2337/dc17-1600. View

Cichosz S, Jensen M, Olesen S . Development and Validation of a Machine Learning Model to Predict Weekly Risk of Hypoglycemia in Patients with Type 1 Diabetes Based on Continuous Glucose Monitoring. Diabetes Technol Ther. 2024; 26(7):457-466. DOI: 10.1089/dia.2023.0532. View

Bragd J, Adamson U, Backlund L, Lins P, Moberg E, Oskarsson P . Can glycaemic variability, as calculated from blood glucose self-monitoring, predict the development of complications in type 1 diabetes over a decade?. Diabetes Metab. 2008; 34(6 Pt 1):612-6. DOI: 10.1016/j.diabet.2008.04.005. View

Thompson J, Hu J, Mudaranthakam D, Streeter D, Neums L, Park M . Relevant Word Order Vectorization for Improved Natural Language Processing in Electronic Health Records. Sci Rep. 2019; 9(1):9253. PMC: 6592944. DOI: 10.1038/s41598-019-45705-y. View

10.

Jensen M, Dethlefsen C, Vestergaard P, Hejlesen O . Prediction of Nocturnal Hypoglycemia From Continuous Glucose Monitoring Data in People With Type 1 Diabetes: A Proof-of-Concept Study. J Diabetes Sci Technol. 2019; 14(2):250-256. PMC: 7196854. DOI: 10.1177/1932296819868727. View

11.

Gomez A, Munoz O, Marin A, Fonseca M, Rondon M, Gomez M . Different Indexes of Glycemic Variability as Identifiers of Patients with Risk of Hypoglycemia in Type 2 Diabetes Mellitus. J Diabetes Sci Technol. 2018; 12(5):1007-1015. PMC: 6134628. DOI: 10.1177/1932296818758105. View

12.

Cichosz S, Frystyk J, Tarnow L, Fleischer J . Combining information of autonomic modulation and CGM measurements enables prediction and improves detection of spontaneous hypoglycemic events. J Diabetes Sci Technol. 2014; 9(1):132-7. PMC: 4495539. DOI: 10.1177/1932296814549830. View

13.

Cryer P, Davis S, Shamoon H . Hypoglycemia in diabetes. Diabetes Care. 2003; 26(6):1902-12. DOI: 10.2337/diacare.26.6.1902. View

14.

Akirov A, Amitai O, Masri-Iraqi H, Diker-Cohen T, Shochat T, Eizenberg Y . Predictors of hypoglycemia in hospitalized patients with diabetes mellitus. Intern Emerg Med. 2018; 13(3):343-350. DOI: 10.1007/s11739-018-1787-0. View

15.

Agiostratidou G, Anhalt H, Ball D, Blonde L, Gourgari E, Harriman K . Standardizing Clinically Meaningful Outcome Measures Beyond HbA for Type 1 Diabetes: A Consensus Report of the American Association of Clinical Endocrinologists, the American Association of Diabetes Educators, the American Diabetes Association, the.... Diabetes Care. 2017; 40(12):1622-1630. PMC: 5864122. DOI: 10.2337/dc17-1624. View

16.

Djulbegovic B, Hozo I . Using Decision Curve Analysis to Evaluate Testing and/or Predictive Modeling. Cancer Treat Res. 2023; 189:77-84. DOI: 10.1007/978-3-031-37993-2_6. View

17.

Collins G, Reitsma J, Altman D, Moons K . Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): the TRIPOD statement. BMJ. 2015; 350:g7594. DOI: 10.1136/bmj.g7594. View

18.

Mathioudakis N, Everett E, Routh S, Pronovost P, Yeh H, Golden S . Development and validation of a prediction model for insulin-associated hypoglycemia in non-critically ill hospitalized adults. BMJ Open Diabetes Res Care. 2018; 6(1):e000499. PMC: 5841507. DOI: 10.1136/bmjdrc-2017-000499. View

19.

St-Onge M, Cherta-Murillo A, Darimont C, Mantantzis K, Martin F, Owen L . The interrelationship between sleep, diet, and glucose metabolism. Sleep Med Rev. 2023; 69:101788. PMC: 10247426. DOI: 10.1016/j.smrv.2023.101788. View

20.

Pilla S, Kraschnewski J, Lehman E, Kong L, Francis E, Poger J . Hospital utilization for hypoglycemia among patients with type 2 diabetes using pooled data from six health systems. BMJ Open Diabetes Res Care. 2021; 9(Suppl 1). PMC: 8679092. DOI: 10.1136/bmjdrc-2021-002153. View