1
|
Marcus Y, Eldor R, Yaron M, Shaklai S, Ish-Shalom M, Shefer G, Stern N, Golan N, Dvir AZ, Pele O, Gonen M. Improving blood glucose level predictability using machine learning. Diabetes Metab Res Rev 2020; 36:e3348. [PMID: 32445286 DOI: 10.1002/dmrr.3348] [Citation(s) in RCA: 10] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 09/15/2019] [Revised: 05/12/2020] [Accepted: 05/18/2020] [Indexed: 01/17/2023]
Abstract
This study was designed to improve blood glucose level predictability and future hypoglycemic and hyperglycemic event alerts through a novel patient-specific supervised-machine-learning (SML) analysis of glucose level based on a continuous-glucose-monitoring system (CGM) that needs no human intervention, and minimises false-positive alerts. The CGM data over 7 to 50 non-consecutive days from 11 type-1 diabetic patients aged 18 to 39 with a mean HbA1C of 7.5% ± 1.2% were analysed using four SML models. The algorithm was constructed to choose the best-fit model for each patient. Several statistical parameters were calculated to aggregate the magnitudes of the prediction errors. The personalised solutions provided by the algorithm were effective in predicting glucose levels 30 minutes after the last measurement. The average root-mean-square-error was 20.48 mg/dL and the average absolute-mean-error was 15.36 mg/dL when the best-fit model was selected for each patient. Using the best-fit-model, the true-positive-hypoglycemia-prediction-rate was 64%, whereas the false-positive- rate was 4.0%, and the false-negative-rate was 0.015%. Similar results were found even when only CGM samples below 70 were considered. The true-positive-hyperglycemia-prediction-rate was 61%. State-of-the-art SML tools are effective in predicting the glucose level values of patients with type-1diabetes and notifying these patients of future hypoglycemic and hyperglycemic events, thus improving glycemic control. The algorithm can be used to improve the calculation of the basal insulin rate and bolus insulin, and suitable for a closed loop "artificial pancreas" system. The algorithm provides a personalised medical solution that can successfully identify the best-fit method for each patient.
Collapse
Affiliation(s)
- Yonit Marcus
- The Institute of Endocrinology, Metabolism and Hypertension, Tel-Aviv Sourasky Medical Centre, Tel Aviv, Israel
- The Sackler Faculty of Medicine, Tel Aviv University, Tel Aviv, Israel
| | - Roy Eldor
- The Institute of Endocrinology, Metabolism and Hypertension, Tel-Aviv Sourasky Medical Centre, Tel Aviv, Israel
- The Sackler Faculty of Medicine, Tel Aviv University, Tel Aviv, Israel
| | - Mariana Yaron
- The Institute of Endocrinology, Metabolism and Hypertension, Tel-Aviv Sourasky Medical Centre, Tel Aviv, Israel
- The Sackler Faculty of Medicine, Tel Aviv University, Tel Aviv, Israel
| | - Sigal Shaklai
- The Institute of Endocrinology, Metabolism and Hypertension, Tel-Aviv Sourasky Medical Centre, Tel Aviv, Israel
- The Sackler Faculty of Medicine, Tel Aviv University, Tel Aviv, Israel
| | - Maya Ish-Shalom
- The Institute of Endocrinology, Metabolism and Hypertension, Tel-Aviv Sourasky Medical Centre, Tel Aviv, Israel
- The Sackler Faculty of Medicine, Tel Aviv University, Tel Aviv, Israel
| | - Gabi Shefer
- The Institute of Endocrinology, Metabolism and Hypertension, Tel-Aviv Sourasky Medical Centre, Tel Aviv, Israel
- The Sackler Faculty of Medicine, Tel Aviv University, Tel Aviv, Israel
| | - Naftali Stern
- The Institute of Endocrinology, Metabolism and Hypertension, Tel-Aviv Sourasky Medical Centre, Tel Aviv, Israel
- The Sackler Faculty of Medicine, Tel Aviv University, Tel Aviv, Israel
| | - Nehor Golan
- The Department of Computer Science, Ariel University, Ariel, Israel
- Ariel Cyber Innovation Centre, Ariel University, Ariel, Israel
| | - Amit Z Dvir
- The Department of Computer Science, Ariel University, Ariel, Israel
- Ariel Cyber Innovation Centre, Ariel University, Ariel, Israel
| | - Ofir Pele
- The Department of Computer Science, Ariel University, Ariel, Israel
| | - Mira Gonen
- The Department of Computer Science, Ariel University, Ariel, Israel
| |
Collapse
|
2
|
Woldaregay AZ, Årsand E, Walderhaug S, Albers D, Mamykina L, Botsis T, Hartvigsen G. Data-driven modeling and prediction of blood glucose dynamics: Machine learning applications in type 1 diabetes. Artif Intell Med 2019; 98:109-134. [DOI: 10.1016/j.artmed.2019.07.007] [Citation(s) in RCA: 54] [Impact Index Per Article: 10.8] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/26/2018] [Revised: 08/22/2018] [Accepted: 07/19/2019] [Indexed: 10/26/2022]
|
3
|
Mirshekarian S, Bunescu R, Marling C, Schwartz F. Using LSTMs to learn physiological models of blood glucose behavior. ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. ANNUAL INTERNATIONAL CONFERENCE 2018; 2017:2887-2891. [PMID: 29060501 DOI: 10.1109/embc.2017.8037460] [Citation(s) in RCA: 34] [Impact Index Per Article: 5.7] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 02/03/2023]
Abstract
For people with type 1 diabetes, good blood glucose control is essential to keeping serious disease complications at bay. This entails carefully monitoring blood glucose levels and taking corrective steps whenever they are too high or too low. If blood glucose levels could be accurately predicted, patients could take proactive steps to prevent blood glucose excursions from occurring. However, accurate predictions require complex physiological models of blood glucose behavior. Factors such as insulin boluses, carbohydrate intake, and exercise influence blood glucose in ways that are difficult to capture through manually engineered equations. In this paper, we describe a recursive neural network (RNN) approach that uses long short-term memory (LSTM) units to learn a physiological model of blood glucose. When trained on raw data from real patients, the LSTM networks (LSTMs) obtain results that are competitive with a previous state-of-the-art model based on manually engineered physiological equations. The RNN approach can incorporate arbitrary physiological parameters without the need for sophisticated manual engineering, thus holding the promise of further improvements in prediction accuracy.
Collapse
|
4
|
Barazandegan M, Ekram F, Kwok E, Gopaluni B, Tulsyan A. Assessment of type II diabetes mellitus using irregularly sampled measurements with missing data. Bioprocess Biosyst Eng 2014; 38:615-29. [PMID: 25348655 DOI: 10.1007/s00449-014-1301-7] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/27/2014] [Accepted: 10/06/2014] [Indexed: 10/24/2022]
Abstract
Diabetes mellitus is one of the leading diseases in the developed world. In order to better regulate blood glucose in a diabetic patient, improved modelling of insulin-glucose dynamics is a key factor in the treatment of diabetes mellitus. In the current work, the insulin-glucose dynamics in type II diabetes mellitus can be modelled by using a stochastic nonlinear state-space model. Estimating the parameters of such a model is difficult as only a few blood glucose and insulin measurements per day are available in a non-clinical setting. Therefore, developing a predictive model of the blood glucose of a person with type II diabetes mellitus is important when the glucose and insulin concentrations are only available at irregular intervals. To overcome these difficulties, we resort to online sequential Monte Carlo (SMC) estimation of states and parameters of the state-space model for type II diabetic patients under various levels of randomly missing clinical data. Our results show that this method is efficient in monitoring and estimating the dynamics of the peripheral glucose, insulin and incretins concentration when 10, 25 and 50% of the simulated clinical data were randomly removed.
Collapse
Affiliation(s)
- Melissa Barazandegan
- Chemical and Biological Engineering Department, University of British Columbia, Vancouver, BC, V6T 1Z3, Canada,
| | | | | | | | | |
Collapse
|