EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Stacked Long Short-Term Memory Approach for Predictive Blood Glucose Monitoring in Women with Gestational Diabetes Mellitus

Huiqi Y Lu iD, Ping Lu iD, Jane E Hirst, Lucy Mackillop iD, David A Clifton

Sensors · 20.09.2023 · 23 (18) · 7990

DOI: 10.3390/s23187990 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 20.09.2023. Verfasst von Huiqi Y Lu und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Engineering Science, University of Oxford, Oxford OX3 7DQ, UK. Hauptthemen laut MEDLINE: Diabetes, Gestational. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 23 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Wellcome Trust, Medical Research Council, Royal Academy of Engineering Daphne Jackson Trust Fellowship.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Gestational diabetes mellitus (GDM) is a subtype of diabetes that develops during pregnancy. Managing blood glucose (BG) within the healthy physiological range can reduce clinical complications for women with gestational diabetes. The objectives of this study are to (1) develop benchmark glucose prediction models with long short-term memory (LSTM) recurrent neural network models using time-series data collected from the GDm-Health platform, (2) compare the prediction accuracy with published results, and (3) suggest an optimized clinical review schedule with the potential to reduce the overall number of blood tests for mothers with stable and within-range glucose measurements. A total of 190,396 BG readings from 1110 patients were used for model development, validation and testing under three different prediction schemes: 7 days of BG readings to predict the next 7 or 14 days and 14 days to predict 14 days. Our results show that the optimized BG schedule based on a 7-day observational window to predict the BG of the next 14 days achieved the accuracies of the root mean square error (RMSE) = 0.958 ± 0.007, 0.876 ± 0.003, 0.898 ± 0.003, 0.622 ± 0.003, 0.814 ± 0.009 and 0.845 ± 0.005 for the after-breakfast, after-lunch, after-dinner, before-breakfast, before-lunch and before-dinner predictions, respectively. This is the first machine learning study that suggested an optimized blood glucose monitoring frequency, which is 7 days to monitor the next 14 days based on the accuracy of blood glucose prediction. Moreover, the accuracy of our proposed model based on the fingerstick blood glucose test is on par with the prediction accuracies compared with the benchmark performance of one-hour prediction models using continuous glucose monitoring (CGM) readings. In conclusion, the stacked LSTM model is a promising approach for capturing the patterns in time-series data, resulting in accurate predictions of BG levels. Using a deep learning model with routine fingerstick glucose collection is a promising, predictable and low-cost solution for BG monitoring for women with gestational diabetes.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Diabetes, GestationalPregnancyHumansFemaleBlood GlucoseBlood Glucose Self-MonitoringGlucoseNeural Networks, Computer

Stichwörter der Autor:innen

clinical machine learninggestational diabetesmedical informaticspatient monitoringpregnancy care

Substanzen

Blood GlucoseGlucose

Autor:innen und Institutionen

  • Department of Engineering Science, University of Oxford, Oxford OX3 7DQ, UK.
  • Women's Centre, Oxford University Hospitals NHS Foundation Trust, Oxford OX3 9DU, UK.
  • George Institute for Global Health, Imperial College London, London W12 7RZ, UK.
  • Oxford Suzhou Centre for Advanced Research, Suzhou 215123, China.

ORCID-Profile: Huiqi Y Lu, Ping Lu, Lucy Mackillop

Förderung

  • Wellcome Trust
  • Medical Research Council
  • Royal Academy of Engineering Daphne Jackson Trust Fellowship
  • UKRI Future Leaders Fellowship grant
  • NIHR Oxford Biomedical Research Centre
  • NIHR Research Professorship
  • RAEng Research Chair
  • InnoHK Hong Kong Centre for Cerebrocardiovascular Health Engineering

Zitieren

APA

Lu, H. Y., Lu, P., Hirst, J. E., Mackillop, L., & Clifton, D. A. (2023). A Stacked Long Short-Term Memory Approach for Predictive Blood Glucose Monitoring in Women with Gestational Diabetes Mellitus. Sensors, 23(18), 7990. https://doi.org/10.3390/s23187990

Vancouver

Lu HY, Lu P, Hirst JE, Mackillop L, Clifton DA. A Stacked Long Short-Term Memory Approach for Predictive Blood Glucose Monitoring in Women with Gestational Diabetes Mellitus. Sensors. 2023;23(18):7990. doi:10.3390/s23187990

BibTeX
@article{Lu2023,
  author = {Lu, Huiqi Y and Lu, Ping and Hirst, Jane E and Mackillop, Lucy and Clifton, David A},
  title = {A Stacked Long Short-Term Memory Approach for Predictive Blood Glucose Monitoring in Women with Gestational Diabetes Mellitus},
  journal = {Sensors},
  year = {2023},
  volume = {23},
  number = {18},
  pages = {7990},
  doi = {10.3390/s23187990}
}
Kostenlos starten →