1
|
Thapa A, Chibvunde S, Schwartz L, Trujillo C, Ferrari G, Drown L, Gomber A, Park PH, Matanje B, Msekandiana A, Kachimanga C, Bukhman G, Ruderman T, Adler AJ. Appropriateness and acceptability of continuous glucose monitoring in people with type 1 diabetes at rural first-level hospitals in Malawi: a qualitative study. BMJ Open 2024; 14:e075559. [PMID: 38719287 PMCID: PMC11086409 DOI: 10.1136/bmjopen-2023-075559] [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: 05/11/2023] [Accepted: 04/19/2024] [Indexed: 05/12/2024] Open
Abstract
OBJECTIVES The purpose of this qualitative study is to describe the acceptability and appropriateness of continuous glucose monitoring (CGM) in people living with type 1 diabetes (PLWT1D) at first-level (district) hospitals in Malawi. DESIGN We conducted semistructured qualitative interviews among PLWT1D and healthcare providers participating in the study. Standardised interview guides elicited perspectives on the appropriateness and acceptability of CGM use for PLWT1D and their providers, and provider perspectives on the effectiveness of CGM use in Malawi. Data were coded using Dedoose software and analysed using a thematic approach. SETTING First-level hospitals in Neno district, Malawi. PARTICIPANTS Participants were part of a randomised controlled trial focused on CGM at first-level hospitals in Neno district, Malawi. Pretrial and post-trial interviews were conducted for participants in the CGM and usual care arms, and one set of interviews was conducted with providers. RESULTS Eleven PLWT1D recruited for the CGM randomised controlled trial and five healthcare providers who provided care to participants with T1D were included. Nine PLWT1D were interviewed twice, two were interviewed once. Of the 11 participants with T1D, six were from the CGM arm and five were in usual care arm. Key themes emerged regarding the appropriateness and effectiveness of CGM use in lower resource setting. The four main themes were (a) patient provider relationship, (b) stigma and psychosocial support, (c) device usage and (d) clinical management. CONCLUSIONS Participants and healthcare providers reported that CGM use was appropriate and acceptable in the study setting, although the need to support it with health education sessions was highlighted. This research supports the use of CGM as a component of personalised diabetes treatment for PLWT1D in resource constraint settings. TRIAL REGISTRATION NUMBER PACTR202102832069874; Post-results.
Collapse
Affiliation(s)
- Ada Thapa
- Center for Integration Science, Division of Global Health Equity, Brigham and Women's Hospital, Boston, Massachusetts, USA
| | | | - Leah Schwartz
- Department of Obstetrics, Gynecology, and Reproductive Biology, Massachusetts General Hospital, Boston, Massachusetts, USA
| | - Celina Trujillo
- Center for Integration Science, Division of Global Health Equity, Brigham and Women's Hospital, Boston, Massachusetts, USA
- Partners In Health, Boston, Massachusetts, USA
| | - Gina Ferrari
- Center for Integration Science, Division of Global Health Equity, Brigham and Women's Hospital, Boston, Massachusetts, USA
- Partners In Health, Boston, Massachusetts, USA
| | - Laura Drown
- Center for Integration Science, Division of Global Health Equity, Brigham and Women's Hospital, Boston, Massachusetts, USA
| | - Apoorva Gomber
- Center for Integration Science, Division of Global Health Equity, Brigham and Women's Hospital, Boston, Massachusetts, USA
| | - Paul H Park
- Center for Integration Science, Division of Global Health Equity, Brigham and Women's Hospital, Boston, Massachusetts, USA
| | | | | | | | - Gene Bukhman
- Center for Integration Science, Division of Global Health Equity, Brigham and Women's Hospital, Boston, Massachusetts, USA
- Partners In Health, Boston, Massachusetts, USA
- Program in Global Noncommunicable Disease and Social Change, Department of Global Health and Social Medicine, Harvard Medical School, Boston, Massachusetts, USA
| | | | - Alma J Adler
- Center for Integration Science, Division of Global Health Equity, Brigham and Women's Hospital, Boston, Massachusetts, USA
- Program in Global Noncommunicable Disease and Social Change, Department of Global Health and Social Medicine, Harvard Medical School, Boston, Massachusetts, USA
| |
Collapse
|
2
|
Kronborg T, Hangaard S, Hejlesen O, Vestergaard P, Jensen MH. Bedtime Prediction of Nocturnal Hypoglycemia in Insulin-Treated Type 2 Diabetes Patients. J Diabetes Sci Technol 2024; 18:592-597. [PMID: 36514195 PMCID: PMC11089861 DOI: 10.1177/19322968221141736] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 12/15/2022]
Abstract
BACKGROUND AND AIMS Hypoglycemia may lead to anxiety, poor adherence, and hypoglycemia unawareness and is especially a threat during the night in patients with insulin-treated type 2 diabetes (T2D). It would therefore be beneficial to warn patients at risk of hypoglycemia at bedtime so they can react accordingly and avoid the episode. Hence, the aim of the present study was to develop a model for predicting nocturnal hypoglycemia. METHODS Continuous glucose monitoring (CGM), mealtime, and insulin data were collected from 67 insulin-treated patients with T2D (NCT01819129). Data were structured into 24-hour periods and labeled as nocturnal hypoglycemia or not depending on whether 15 consecutive minutes were spent below 3.0 mmol/L (54 mg/dL) during the following night. Each period was divided into "last night," "morning," "day," and "evening" for feature extraction purposes, and 72 potential features were extracted for every period. A five-fold cross-validation was used to select features by forward selection and for training and validating a model based on logistic regression. RESULTS The prediction model was based on 30 patients with 60/496 periods resulting in nocturnal hypoglycemia. Forward selection revealed that the best features were based on CGM and involved the last value and mean value during the evening, as well as the relative difference in maximum value during the day between the present period and previous periods. The model obtained a mean area under the receiver operating characteristics curve (AUC) of 0.82 with an accuracy of 0.79. CONCLUSIONS The model was able to predict nocturnal hypoglycemia with an acceptable accuracy and could therefore prevent such cases.
Collapse
Affiliation(s)
- Thomas Kronborg
- Steno Diabetes Center North Denmark, Aalborg University Hospital, Aalborg, Denmark
- Department of Health Science and Technology, Aalborg University, Aalborg, Denmark
| | - Stine Hangaard
- Steno Diabetes Center North Denmark, Aalborg University Hospital, Aalborg, Denmark
- Department of Health Science and Technology, Aalborg University, Aalborg, Denmark
| | - Ole Hejlesen
- Steno Diabetes Center North Denmark, Aalborg University Hospital, Aalborg, Denmark
| | - Peter Vestergaard
- Steno Diabetes Center North Denmark, Aalborg University Hospital, Aalborg, Denmark
- Department of Endocrinology, Aalborg University Hospital, Aalborg, Denmark
- Department of Clinical Medicine, Aalborg University Hospital, Aalborg, Denmark
| | - Morten Hasselstrøm Jensen
- Steno Diabetes Center North Denmark, Aalborg University Hospital, Aalborg, Denmark
- Department of Health Science and Technology, Aalborg University, Aalborg, Denmark
| |
Collapse
|
3
|
Kozinetz RM, Berikov VB, Semenova JF, Klimontov VV. Machine Learning and Deep Learning Models for Nocturnal High- and Low-Glucose Prediction in Adults with Type 1 Diabetes. Diagnostics (Basel) 2024; 14:740. [PMID: 38611653 PMCID: PMC11011674 DOI: 10.3390/diagnostics14070740] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/27/2023] [Revised: 03/06/2024] [Accepted: 03/28/2024] [Indexed: 04/14/2024] Open
Abstract
Glucose management at night is a major challenge for people with type 1 diabetes (T1D), especially for those managed with multiple daily injections (MDIs). In this study, we developed machine learning (ML) and deep learning (DL) models to predict nocturnal glucose within the target range (3.9-10 mmol/L), above the target range, and below the target range in subjects with T1D managed with MDIs. The models were trained and tested on continuous glucose monitoring data obtained from 380 subjects with T1D. Two DL algorithms-multi-layer perceptron (MLP) and a convolutional neural network (CNN)-as well as two classic ML algorithms, random forest (RF) and gradient boosting trees (GBTs), were applied. The resulting models based on the DL and ML algorithms demonstrated high and similar accuracy in predicting target glucose (F1 metric: 96-98%) and above-target glucose (F1: 93-97%) within a 30 min prediction horizon. Model performance was poorer when predicting low glucose (F1: 80-86%). MLP provided the highest accuracy in low-glucose prediction. The results indicate that both DL (MLP, CNN) and ML (RF, GBTs) algorithms operating CGM data can be used for the simultaneous prediction of nocturnal glucose values within the target, above-target, and below-target ranges in people with T1D managed with MDIs.
Collapse
Affiliation(s)
| | | | | | - Vadim V. Klimontov
- Laboratory of Endocrinology, Research Institute of Clinical and Experimental Lymphology—Branch of the Institute of Cytology and Genetics, Siberian Branch of Russian Academy of Sciences (RICEL–Branch of IC&G SB RAS), 630060 Novosibirsk, Russia; (R.M.K.); (V.B.B.); (J.F.S.)
| |
Collapse
|
4
|
Jacobs PG, Herrero P, Facchinetti A, Vehi J, Kovatchev B, Breton MD, Cinar A, Nikita KS, Doyle FJ, Bondia J, Battelino T, Castle JR, Zarkogianni K, Narayan R, Mosquera-Lopez C. Artificial Intelligence and Machine Learning for Improving Glycemic Control in Diabetes: Best Practices, Pitfalls, and Opportunities. IEEE Rev Biomed Eng 2024; 17:19-41. [PMID: 37943654 DOI: 10.1109/rbme.2023.3331297] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/12/2023]
Abstract
OBJECTIVE Artificial intelligence and machine learning are transforming many fields including medicine. In diabetes, robust biosensing technologies and automated insulin delivery therapies have created a substantial opportunity to improve health. While the number of manuscripts addressing the topic of applying machine learning to diabetes has grown in recent years, there has been a lack of consistency in the methods, metrics, and data used to train and evaluate these algorithms. This manuscript provides consensus guidelines for machine learning practitioners in the field of diabetes, including best practice recommended approaches and warnings about pitfalls to avoid. METHODS Algorithmic approaches are reviewed and benefits of different algorithms are discussed including importance of clinical accuracy, explainability, interpretability, and personalization. We review the most common features used in machine learning applications in diabetes glucose control and provide an open-source library of functions for calculating features, as well as a framework for specifying data sets using data sheets. A review of current data sets available for training algorithms is provided as well as an online repository of data sources. SIGNIFICANCE These consensus guidelines are designed to improve performance and translatability of new machine learning algorithms developed in the field of diabetes for engineers and data scientists.
Collapse
|
5
|
Duckworth C, Guy MJ, Kumaran A, O’Kane AA, Ayobi A, Chapman A, Marshall P, Boniface M. Explainable Machine Learning for Real-Time Hypoglycemia and Hyperglycemia Prediction and Personalized Control Recommendations. J Diabetes Sci Technol 2024; 18:113-123. [PMID: 35695284 PMCID: PMC10899844 DOI: 10.1177/19322968221103561] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 11/15/2022]
Abstract
BACKGROUND The occurrences of acute complications arising from hypoglycemia and hyperglycemia peak as young adults with type 1 diabetes (T1D) take control of their own care. Continuous glucose monitoring (CGM) devices provide real-time glucose readings enabling users to manage their control proactively. Machine learning algorithms can use CGM data to make ahead-of-time risk predictions and provide insight into an individual's longer term control. METHODS We introduce explainable machine learning to make predictions of hypoglycemia (<70 mg/dL) and hyperglycemia (>270 mg/dL) up to 60 minutes ahead of time. We train our models using CGM data from 153 people living with T1D in the CITY (CGM Intervention in Teens and Young Adults With Type 1 Diabetes)survey totaling more than 28 000 days of usage, which we summarize into (short-term, medium-term, and long-term) glucose control features along with demographic information. We use machine learning explanations (SHAP [SHapley Additive exPlanations]) to identify which features have been most important in predicting risk per user. RESULTS Machine learning models (XGBoost) show excellent performance at predicting hypoglycemia (area under the receiver operating curve [AUROC]: 0.998, average precision: 0.953) and hyperglycemia (AUROC: 0.989, average precision: 0.931) in comparison with a baseline heuristic and logistic regression model. CONCLUSIONS Maximizing model performance for glucose risk prediction and management is crucial to reduce the burden of alarm fatigue on CGM users. Machine learning enables more precise and timely predictions in comparison with baseline models. SHAP helps identify what about a CGM user's glucose control has led to predictions of risk which can be used to reduce their long-term risk of complications.
Collapse
Affiliation(s)
- Christopher Duckworth
- Electronics and Computer Science, IT Innovation Centre, University of Southampton, Southampton, UK
| | - Matthew J. Guy
- Department of Medical Physics, University Hospital Southampton NHS Foundation Trust, Southampton, UK
- Human-Computer Interaction for Health, University of Bristol, Bristol, UK
| | - Anitha Kumaran
- Child Health, Department of Endocrinology, University Hospital Southampton NHS Foundation Trust, Southampton, UK
| | - Aisling Ann O’Kane
- Human-Computer Interaction for Health, University of Bristol, Bristol, UK
- UCL Interaction Centre, University College London, London, UK
| | - Amid Ayobi
- Human-Computer Interaction for Health, University of Bristol, Bristol, UK
| | - Adriane Chapman
- Electronics and Computer Science, University of Southampton, Southampton, UK
| | - Paul Marshall
- Human-Computer Interaction for Health, University of Bristol, Bristol, UK
- UCL Interaction Centre, University College London, London, UK
| | - Michael Boniface
- Electronics and Computer Science, IT Innovation Centre, University of Southampton, Southampton, UK
| |
Collapse
|
6
|
Mosquera-Lopez C, Roquemen-Echeverri V, Tyler NS, Patton SR, Clements MA, Martin CK, Riddell MC, Gal RL, Gillingham M, Wilson LM, Castle JR, Jacobs PG. Combining uncertainty-aware predictive modeling and a bedtime Smart Snack intervention to prevent nocturnal hypoglycemia in people with type 1 diabetes on multiple daily injections. J Am Med Inform Assoc 2023; 31:109-118. [PMID: 37812784 PMCID: PMC10746320 DOI: 10.1093/jamia/ocad196] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/27/2023] [Accepted: 09/25/2023] [Indexed: 10/11/2023] Open
Abstract
OBJECTIVE Nocturnal hypoglycemia is a known challenge for people with type 1 diabetes, especially for physically active individuals or those on multiple daily injections. We developed an evidential neural network (ENN) to predict at bedtime the probability and timing of nocturnal hypoglycemia (0-4 vs 4-8 h after bedtime) based on several glucose metrics and physical activity patterns. We utilized these predictions in silico to prescribe bedtime carbohydrates with a Smart Snack intervention specific to the predicted minimum nocturnal glucose and timing of nocturnal hypoglycemia. MATERIALS AND METHODS We leveraged free-living datasets collected from 366 individuals from the T1DEXI Study and Glooko. Inputs to the ENN used to model nocturnal hypoglycemia were derived from demographic information, continuous glucose monitoring, and physical activity data. We assessed the accuracy of the ENN using area under the receiver operating curve, and the clinical impact of the Smart Snack intervention through simulations. RESULTS The ENN achieved an area under the receiver operating curve of 0.80 and 0.71 to predict nocturnal hypoglycemic events during 0-4 and 4-8 h after bedtime, respectively, outperforming all evaluated baseline methods. Use of the Smart Snack intervention reduced probability of nocturnal hypoglycemia from 23.9 ± 14.1% to 14.0 ± 13.3% and duration from 7.4 ± 7.0% to 2.4 ± 3.3% in silico. DISCUSSION Our findings indicate that the ENN-based Smart Snack intervention has the potential to significantly reduce the frequency and duration of nocturnal hypoglycemic events. CONCLUSION A decision support system that combines prediction of minimum nocturnal glucose and proactive recommendations for bedtime carbohydrate intake might effectively prevent nocturnal hypoglycemia and reduce the burden of glycemic self-management.
Collapse
Affiliation(s)
- Clara Mosquera-Lopez
- Artificial Intelligence for Medical Systems (AIMS) Lab, Department of Biomedical Engineering, Oregon Health & Science University, Portland, OR 97239, United States
| | - Valentina Roquemen-Echeverri
- Artificial Intelligence for Medical Systems (AIMS) Lab, Department of Biomedical Engineering, Oregon Health & Science University, Portland, OR 97239, United States
| | - Nichole S Tyler
- Artificial Intelligence for Medical Systems (AIMS) Lab, Department of Biomedical Engineering, Oregon Health & Science University, Portland, OR 97239, United States
| | - Susana R Patton
- Center for Healthcare Delivery Science, Nemours Children’s Health, Jacksonville, FL 32207, United States
| | - Mark A Clements
- Children’s Mercy Hospital, Kansas City, MO 64111, United States
- Glooko Inc., Palo Alto, CA 94301, United States
| | - Corby K Martin
- Pennington Biomedical Research Center, Louisiana State University, Baton Rouge, LA 70808, United States
| | - Michael C Riddell
- Muscle Health Research Centre, York University, Toronto, ON M3J1P3, Canada
| | - Robin L Gal
- Jaeb Center for Health Research, Tampa, FL 33647, United States
| | - Melanie Gillingham
- Molecular and Medical Genetics, School of Medicine, Oregon Health & Science University, Portland, OR 97239, United States
| | - Leah M Wilson
- Harold Schnitzer Diabetes Health Center, Oregon Health & Science University, Portland, OR 97239, United States
| | - Jessica R Castle
- Harold Schnitzer Diabetes Health Center, Oregon Health & Science University, Portland, OR 97239, United States
| | - Peter G Jacobs
- Artificial Intelligence for Medical Systems (AIMS) Lab, Department of Biomedical Engineering, Oregon Health & Science University, Portland, OR 97239, United States
| |
Collapse
|
7
|
Liu K, Li L, Ma Y, Jiang J, Liu Z, Ye Z, Liu S, Pu C, Chen C, Wan Y. Machine Learning Models for Blood Glucose Level Prediction in Patients With Diabetes Mellitus: Systematic Review and Network Meta-Analysis. JMIR Med Inform 2023; 11:e47833. [PMID: 37983072 PMCID: PMC10696506 DOI: 10.2196/47833] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/03/2023] [Revised: 08/21/2023] [Accepted: 10/12/2023] [Indexed: 11/21/2023] Open
Abstract
BACKGROUND Machine learning (ML) models provide more choices to patients with diabetes mellitus (DM) to more properly manage blood glucose (BG) levels. However, because of numerous types of ML algorithms, choosing an appropriate model is vitally important. OBJECTIVE In a systematic review and network meta-analysis, this study aimed to comprehensively assess the performance of ML models in predicting BG levels. In addition, we assessed ML models used to detect and predict adverse BG (hypoglycemia) events by calculating pooled estimates of sensitivity and specificity. METHODS PubMed, Embase, Web of Science, and Institute of Electrical and Electronics Engineers Explore databases were systematically searched for studies on predicting BG levels and predicting or detecting adverse BG events using ML models, from inception to November 2022. Studies that assessed the performance of different ML models in predicting or detecting BG levels or adverse BG events of patients with DM were included. Studies with no derivation or performance metrics of ML models were excluded. The Quality Assessment of Diagnostic Accuracy Studies tool was applied to assess the quality of included studies. Primary outcomes were the relative ranking of ML models for predicting BG levels in different prediction horizons (PHs) and pooled estimates of the sensitivity and specificity of ML models in detecting or predicting adverse BG events. RESULTS In total, 46 eligible studies were included for meta-analysis. Regarding ML models for predicting BG levels, the means of the absolute root mean square error (RMSE) in a PH of 15, 30, 45, and 60 minutes were 18.88 (SD 19.71), 21.40 (SD 12.56), 21.27 (SD 5.17), and 30.01 (SD 7.23) mg/dL, respectively. The neural network model (NNM) showed the highest relative performance in different PHs. Furthermore, the pooled estimates of the positive likelihood ratio and the negative likelihood ratio of ML models were 8.3 (95% CI 5.7-12.0) and 0.31 (95% CI 0.22-0.44), respectively, for predicting hypoglycemia and 2.4 (95% CI 1.6-3.7) and 0.37 (95% CI 0.29-0.46), respectively, for detecting hypoglycemia. CONCLUSIONS Statistically significant high heterogeneity was detected in all subgroups, with different sources of heterogeneity. For predicting precise BG levels, the RMSE increases with a rise in the PH, and the NNM shows the highest relative performance among all the ML models. Meanwhile, current ML models have sufficient ability to predict adverse BG events, while their ability to detect adverse BG events needs to be enhanced. TRIAL REGISTRATION PROSPERO CRD42022375250; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=375250.
Collapse
Affiliation(s)
- Kui Liu
- Department of Health Service, Air Force Medical University, Xi'an, Shaanxi, China
| | - Linyi Li
- Department of Health Service, Air Force Medical University, Xi'an, Shaanxi, China
| | - Yifei Ma
- Department of Health Service, Air Force Medical University, Xi'an, Shaanxi, China
| | - Jun Jiang
- Department of Health Service, Air Force Medical University, Xi'an, Shaanxi, China
| | - Zhenhua Liu
- Department of Health Service, Air Force Medical University, Xi'an, Shaanxi, China
| | - Zichen Ye
- Department of Health Service, Air Force Medical University, Xi'an, Shaanxi, China
| | - Shuang Liu
- Department of Health Service, Air Force Medical University, Xi'an, Shaanxi, China
| | - Chen Pu
- Department of Health Service, Air Force Medical University, Xi'an, Shaanxi, China
| | - Changsheng Chen
- Department of Health Statistics, Air Force Medical University, Xi'an, Shaanxi, China
| | - Yi Wan
- Department of Health Service, Air Force Medical University, Xi'an, Shaanxi, China
| |
Collapse
|
8
|
Afentakis I, Unsworth R, Herrero P, Oliver N, Reddy M, Georgiou P. Development and Validation of Binary Classifiers to Predict Nocturnal Hypoglycemia in Adults With Type 1 Diabetes. J Diabetes Sci Technol 2023:19322968231185796. [PMID: 37434362 DOI: 10.1177/19322968231185796] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 07/13/2023]
Abstract
BACKGROUND One of the biggest challenges for people with type 1 diabetes (T1D) using multiple daily injections (MDIs) is nocturnal hypoglycemia (NH). Recurrent NH can lead to serious complications; hence, prevention is of high importance. In this work, we develop and externally validate, device-agnostic Machine Learning (ML) models to provide bedtime decision support to people with T1D and minimize the risk of NH. METHODS We present the design and development of binary classifiers to predict NH (blood glucose levels occurring below 70 mg/dL). Using data collected from a 6-month study of 37 adult participants with T1D under free-living conditions, we extract daytime features from continuous glucose monitor (CGM) sensors, administered insulin, meal, and physical activity information. We use these features to train and test the performance of two ML algorithms: Random Forests (RF) and Support Vector Machines (SVMs). We further evaluate our model in an external population of 20 adults with T1D using MDI insulin therapy and wearing CGM and flash glucose monitoring sensors for two periods of eight weeks each. RESULTS At population-level, SVM outperforms RF algorithm with a receiver operating characteristic-area under curve (ROC-AUC) of 79.36% (95% CI: 76.86%, 81.86%). The proposed SVM model generalizes well in an unseen population (ROC-AUC = 77.06%), as well as between the two different glucose sensors (ROC-AUC = 77.74%). CONCLUSIONS Our model shows state-of-the-art performance, generalizability, and robustness in sensor devices from different manufacturers. We believe it is a potential viable approach to inform people with T1D about their risk of NH before it occurs.
Collapse
Affiliation(s)
- Ioannis Afentakis
- UK Research and Innovation Centre for Doctoral Training in Artificial Intelligence for Healthcare, Imperial College London, London, UK
- Department of Computing, Imperial College London, London, UK
| | | | - Pau Herrero
- Department of Electronic and Electrical Engineering, Imperial College London, London, UK
| | - Nick Oliver
- Department of Medicine, Imperial College London, London, UK
| | - Monika Reddy
- Department of Medicine, Imperial College London, London, UK
| | - Pantelis Georgiou
- Department of Electronic and Electrical Engineering, Imperial College London, London, UK
| |
Collapse
|
9
|
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
|
10
|
Worth C, Nutter PW, Salomon-Estebanez M, Auckburally S, Dunne MJ, Banerjee I, Harper S. The behaviour change behind a successful pilot of hypoglycaemia reduction with HYPO-CHEAT. Digit Health 2023; 9:20552076231192011. [PMID: 37545627 PMCID: PMC10403985 DOI: 10.1177/20552076231192011] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/21/2022] [Accepted: 07/18/2023] [Indexed: 08/08/2023] Open
Abstract
Background Children with hypoglycaemia disorders, such as congenital hyperinsulinism (CHI), are at constant risk of hypoglycaemia (low blood sugars) with the attendant risk of brain injury. Current approaches to hypoglycaemia detection and prevention vary from fingerprick glucose testing to the provision of continuous glucose monitoring (CGM) to machine learning (ML) driven glucose forecasting. Recent trends for ML have had limited success in preventing free-living hypoglycaemia, due to a focus on increasingly accurate glucose forecasts and a failure to acknowledge the human in the loop and the essential step of changing behaviour. The wealth of evidence from the fields of behaviour change and persuasive technology (PT) allows for the creation of a theory-informed and technologically considered approach. Objectives We aimed to create a PT that would overcome the identified barriers to hypoglycaemia prevention for those with CHI to focus on proactive prevention rather than commonly used reactive approaches. Methods We used the behaviour change technique taxonomy and persuasive systems design models to create HYPO-CHEAT (HYpoglycaemia-Prevention-thrOugh-Cgm-HEatmap-Assisted-Technology): a novel approach that presents aggregated CGM data in simple visualisations. The resultant ease of data interpretation is intended to facilitate behaviour change and subsequently reduce hypoglycaemia. Results HYPO-CHEAT was piloted in 10 patients with CHI over 12 weeks and successfully identified weekly patterns of hypoglycaemia. These patterns consistently correlated with identifiable behaviours and were translated into both a change in proximal fingerprick behaviour and ultimately, a significant reduction in aggregated hypoglycaemia from 7.1% to 5.4% with four out of five patients showing clinically meaningful reductions in hypoglycaemia. Conclusions We have provided pilot data of a new approach to hypoglycaemia prevention that focuses on proactive prevention and behaviour change. This approach is personalised for individual patients with CHI and is a first step in changing our approach to hypoglycaemia prevention in this group.
Collapse
Affiliation(s)
- Chris Worth
- Department of Computer Science, University of Manchester, Manchester, UK
- Department of Paediatric Endocrinology, Royal Manchester Children's Hospital, Manchester, UK
| | - Paul W Nutter
- Department of Computer Science, University of Manchester, Manchester, UK
| | - Maria Salomon-Estebanez
- Department of Paediatric Endocrinology, Royal Manchester Children's Hospital, Manchester, UK
| | - Sameera Auckburally
- Department of Paediatric Endocrinology, Royal Manchester Children's Hospital, Manchester, UK
- Faculty of Health and Medicine, Lancaster University, Lancaster, UK
| | - Mark J Dunne
- Faculty of Biology, Medicine and Health, University of Manchester, Manchester, UK
| | - Indraneel Banerjee
- Department of Paediatric Endocrinology, Royal Manchester Children's Hospital, Manchester, UK
- Faculty of Biology, Medicine and Health, University of Manchester, Manchester, UK
| | - Simon Harper
- Department of Computer Science, University of Manchester, Manchester, UK
| |
Collapse
|
11
|
Afsaneh E, Sharifdini A, Ghazzaghi H, Ghobadi MZ. Recent applications of machine learning and deep learning models in the prediction, diagnosis, and management of diabetes: a comprehensive review. Diabetol Metab Syndr 2022; 14:196. [PMID: 36572938 PMCID: PMC9793536 DOI: 10.1186/s13098-022-00969-9] [Citation(s) in RCA: 6] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 10/06/2022] [Accepted: 12/16/2022] [Indexed: 12/28/2022] Open
Abstract
Diabetes as a metabolic illness can be characterized by increased amounts of blood glucose. This abnormal increase can lead to critical detriment to the other organs such as the kidneys, eyes, heart, nerves, and blood vessels. Therefore, its prediction, prognosis, and management are essential to prevent harmful effects and also recommend more useful treatments. For these goals, machine learning algorithms have found considerable attention and have been developed successfully. This review surveys the recently proposed machine learning (ML) and deep learning (DL) models for the objectives mentioned earlier. The reported results disclose that the ML and DL algorithms are promising approaches for controlling blood glucose and diabetes. However, they should be improved and employed in large datasets to affirm their applicability.
Collapse
|
12
|
Worth C, Nutter PW, Dunne MJ, Salomon-Estebanez M, Banerjee I, Harper S. HYPO-CHEAT's aggregated weekly visualisations of risk reduce real world hypoglycaemia. Digit Health 2022; 8:20552076221129712. [PMID: 36276186 PMCID: PMC9580093 DOI: 10.1177/20552076221129712] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/28/2022] [Accepted: 10/13/2021] [Indexed: 11/05/2022] Open
Abstract
Background Children with congenital hyperinsulinism (CHI) are at constant risk of hypoglycaemia with the attendant risk of brain injury. Current hypoglycaemia prevention methods centre on the prediction of a continuous glucose variable using machine learning (ML) processing of continuous glucose monitoring (CGM). This approach ignores repetitive and predictable behavioural factors and is dependent upon ongoing CGM. Thus, there has been very limited success in reducing real-world hypoglycaemia with a ML approach in any condition. Objectives We describe the development of HYPO-CHEAT (HYpoglycaemia-Prevention-thrOugh-CGM-HEatmap-Technology), which is designed to overcome these limitations by describing weekly hypoglycaemia risk. We tested HYPO-CHEAT in a real-world setting to evaluate change in hypoglycaemia. Methods HYPO-CHEAT aggregates individual CGM data to identify weekly hypoglycaemia patterns. These are visualised via a hypoglycaemia heatmap along with actionable interpretations and targets. The algorithm is iterative and reacts to anticipated changing patterns of hypoglycaemia. HYPO-CHEAT was compared with Dexcom Clarity's pattern identification and Facebook Prophet's forecasting algorithm using data from 10 children with CHI using CGM for 12 weeks. HYPO-CHEAT's efficacy was assessed via change in time below range (TBR). Results HYPO-CHEAT identified hypoglycaemia patterns in all patients. Dexcom Clarity identified no patterns. Predictions from Facebook Prophet were inconsistent and difficult to interpret. Importantly, the patterns identified by HYPO-CHEAT matched the lived experience of all patients, generating new and actionable understanding of the cause of hypos. This facilitated patients to significantly reduce their time in hypoglycaemia from 7.1% to 5.4% even when real-time CGM data was removed. Conclusions HYPO-CHEAT's personalised hypoglycaemia heatmaps reduced total and targeted TBR even when CGM was reblinded. HYPO-CHEAT offers a highly effective and immediately available personalised approach to prevent hypoglycaemia and empower patients to self-care.
Collapse
Affiliation(s)
- Chris Worth
- Department of Computer Science, University of Manchester, Manchester, UK,Department of Paediatric Endocrinology, Royal Manchester Children's Hospital, Manchester, UK,Chris Worth, Department of Paediatric Endocrinology, Royal Manchester Children's Hospital, Oxford Road, Manchester, M13 9WL, UK.
| | - Paul W Nutter
- Department of Computer Science, University of Manchester, Manchester, UK
| | - Mark J Dunne
- Faculty of Biology, Medicine and Health, University of Manchester, Manchester, UK
| | - Maria Salomon-Estebanez
- Department of Paediatric Endocrinology, Royal Manchester Children's Hospital, Manchester, UK
| | - Indraneel Banerjee
- Department of Paediatric Endocrinology, Royal Manchester Children's Hospital, Manchester, UK,Faculty of Biology, Medicine and Health, University of Manchester, Manchester, UK
| | - Simon Harper
- Department of Computer Science, University of Manchester, Manchester, UK
| |
Collapse
|
13
|
Berikov VB, Kutnenko OA, Semenova JF, Klimontov VV. Machine Learning Models for Nocturnal Hypoglycemia Prediction in Hospitalized Patients with Type 1 Diabetes. J Pers Med 2022; 12:jpm12081262. [PMID: 36013211 PMCID: PMC9409948 DOI: 10.3390/jpm12081262] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/21/2022] [Revised: 07/29/2022] [Accepted: 07/29/2022] [Indexed: 11/16/2022] Open
Abstract
Nocturnal hypoglycemia (NH) is a dangerous complication of insulin therapy that often goes undetected. In this study, we aimed to generate machine learning (ML)-based models for short-term NH prediction in hospitalized patients with type 1 diabetes (T1D). The models were trained on continuous glucose monitoring (CGM) data obtained from 406 adult patients admitted to a tertiary referral hospital. Eight CGM-derived metrics of glycemic control and glucose variability were included in the models. Combinations of CGM and clinical data (23 parameters) were also assessed. Random Forest (RF), Logistic Linear Regression with Lasso regularization, and Artificial Neuron Networks algorithms were applied. In our models, RF provided the best prediction accuracy with 15 min and 30 min prediction horizons. The addition of clinical parameters slightly improved the prediction accuracy of most models, whereas oversampling and undersampling procedures did not have significant effects. The areas under the curve of the best models based on CGM and clinical data with 15 min and 30 min prediction horizons were 0.97 and 0.942, respectively. Basal insulin dose, diabetes duration, proteinuria, and HbA1c were the most important clinical predictors of NH assessed by RF. In conclusion, ML is a promising approach to personalized prediction of NH in hospitalized patients with T1D.
Collapse
Affiliation(s)
- Vladimir B. Berikov
- Laboratory of Endocrinology, Research Institute of Clinical and Experimental Lymphology—Branch of the Institute of Cytology and Genetics, Siberian Branch of Russian Academy of Sciences (RICEL—Branch of IC&G SB RAS), 630060 Novosibirsk, Russia; (V.B.B.); (J.F.S.)
- Laboratory of Data Analysis, Sobolev Institute of Mathematics, Siberian Branch of Russian Academy of Sciences, 630090 Novosibirsk, Russia;
| | - Olga A. Kutnenko
- Laboratory of Data Analysis, Sobolev Institute of Mathematics, Siberian Branch of Russian Academy of Sciences, 630090 Novosibirsk, Russia;
| | - Julia F. Semenova
- Laboratory of Endocrinology, Research Institute of Clinical and Experimental Lymphology—Branch of the Institute of Cytology and Genetics, Siberian Branch of Russian Academy of Sciences (RICEL—Branch of IC&G SB RAS), 630060 Novosibirsk, Russia; (V.B.B.); (J.F.S.)
| | - Vadim V. Klimontov
- Laboratory of Endocrinology, Research Institute of Clinical and Experimental Lymphology—Branch of the Institute of Cytology and Genetics, Siberian Branch of Russian Academy of Sciences (RICEL—Branch of IC&G SB RAS), 630060 Novosibirsk, Russia; (V.B.B.); (J.F.S.)
- Correspondence: ; Tel.: +7-913-956-82-99
| |
Collapse
|
14
|
Parcerisas A, Contreras I, Delecourt A, Bertachi A, Beneyto A, Conget I, Viñals C, Giménez M, Vehi J. A Machine Learning Approach to Minimize Nocturnal Hypoglycemic Events in Type 1 Diabetic Patients under Multiple Doses of Insulin. SENSORS 2022; 22:s22041665. [PMID: 35214566 PMCID: PMC8876195 DOI: 10.3390/s22041665] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 01/14/2022] [Revised: 02/10/2022] [Accepted: 02/19/2022] [Indexed: 11/16/2022]
Abstract
Nocturnal hypoglycemia (NH) is one of the most challenging events for multiple dose insulin therapy (MDI) in people with type 1 diabetes (T1D). The goal of this study is to design a method to reduce the incidence of NH in people with T1D under MDI therapy, providing a decision-support system and improving confidence toward self-management of the disease considering the dataset used by Bertachi et al. Different machine learning (ML) algorithms, data sources, optimization metrics and mitigation measures to predict and avoid NH events have been studied. In addition, we have designed population and personalized models and studied the generalizability of the models and the influence of physical activity (PA) on them. Obtaining 30 g of rescue carbohydrates (CHO) is the optimal value for preventing NH, so it can be asserted that this is the value with which the time under 70 mg/dL decreases the most, with almost a 35% reduction, while increasing the time in the target range by 1.3%. This study supports the feasibility of using ML techniques to address the prediction of NH in patients with T1D under MDI therapy, using continuous glucose monitoring (CGM) and a PA tracker. The results obtained prove that BG predictions can not only be critical in achieving safer diabetes management, but also assist physicians and patients to make better and safer decisions regarding insulin therapy and their day-to-day lives.
Collapse
Affiliation(s)
- Adrià Parcerisas
- Institut d’Informàtica i Aplicacions, Universitat de Girona, 17003 Girona, Spain; (A.P.); (I.C.); (A.D.); (A.B.)
| | - Ivan Contreras
- Institut d’Informàtica i Aplicacions, Universitat de Girona, 17003 Girona, Spain; (A.P.); (I.C.); (A.D.); (A.B.)
| | - Alexia Delecourt
- Institut d’Informàtica i Aplicacions, Universitat de Girona, 17003 Girona, Spain; (A.P.); (I.C.); (A.D.); (A.B.)
| | - Arthur Bertachi
- Campus Guarapuava, Federal University of Technology—Paraná (UTFPR), Guarapuava 85053-525, Brazil;
| | - Aleix Beneyto
- Institut d’Informàtica i Aplicacions, Universitat de Girona, 17003 Girona, Spain; (A.P.); (I.C.); (A.D.); (A.B.)
| | - Ignacio Conget
- Endocrinology and Diabetes Unit, Hospital Clínic, 08036 Barcelona, Spain; (I.C.); (C.V.); (M.G.)
- Centro de Investigación Biomédica en Red de Diabetes y Enfermedades Metabólicas Asociadas (CIBERDEM), 28029 Madrid, Spain
- Institut d’Investigacions Biomèdiques August Pi i Sunyer, 08036 Barcelona, Spain
| | - Clara Viñals
- Endocrinology and Diabetes Unit, Hospital Clínic, 08036 Barcelona, Spain; (I.C.); (C.V.); (M.G.)
| | - Marga Giménez
- Endocrinology and Diabetes Unit, Hospital Clínic, 08036 Barcelona, Spain; (I.C.); (C.V.); (M.G.)
- Centro de Investigación Biomédica en Red de Diabetes y Enfermedades Metabólicas Asociadas (CIBERDEM), 28029 Madrid, Spain
- Institut d’Investigacions Biomèdiques August Pi i Sunyer, 08036 Barcelona, Spain
| | - Josep Vehi
- Institut d’Informàtica i Aplicacions, Universitat de Girona, 17003 Girona, Spain; (A.P.); (I.C.); (A.D.); (A.B.)
- Centro de Investigación Biomédica en Red de Diabetes y Enfermedades Metabólicas Asociadas (CIBERDEM), 28029 Madrid, Spain
- Correspondence:
| |
Collapse
|
15
|
Diouri O, Cigler M, Vettoretti M, Mader JK, Choudhary P, Renard E. Hypoglycaemia detection and prediction techniques: A systematic review on the latest developments. Diabetes Metab Res Rev 2021; 37:e3449. [PMID: 33763974 PMCID: PMC8519027 DOI: 10.1002/dmrr.3449] [Citation(s) in RCA: 16] [Impact Index Per Article: 5.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 06/08/2020] [Revised: 12/08/2020] [Accepted: 01/28/2021] [Indexed: 02/06/2023]
Abstract
The main objective of diabetes control is to correct hyperglycaemia while avoiding hypoglycaemia, especially in insulin-treated patients. Fear of hypoglycaemia is a hurdle to effective correction of hyperglycaemia because it promotes under-dosing of insulin. Strategies to minimise hypoglycaemia include education and training for improved hypoglycaemia awareness and the development of technologies to allow their early detection and thus minimise their occurrence. Patients with impaired hypoglycaemia awareness would benefit the most from these technologies. The purpose of this systematic review is to review currently available or in-development technologies that support detection of hypoglycaemia or hypoglycaemia risk, and identify gaps in the research. Nanomaterial use in sensors is a promising strategy to increase the accuracy of continuous glucose monitoring devices for low glucose values. Hypoglycaemia is associated with changes on vital signs, so electrocardiogram and encephalogram could also be used to detect hypoglycaemia. Accuracy improvements through multivariable measures can make already marketed galvanic skin response devices a good noninvasive alternative. Breath volatile organic compounds can be detected by dogs and devices and alert patients at hypoglycaemia onset, while near-infrared spectroscopy can also be used as a hypoglycaemia alarms. Finally, one of the main directions of research are deep learning algorithms to analyse continuous glucose monitoring data and provide earlier and more accurate prediction of hypoglycaemia. Current developments for early identification of hypoglycaemia risk combine improvements of available 'needle-type' enzymatic glucose sensors and noninvasive alternatives. Patient usability will be essential to demonstrate to allow their implementation for daily use in diabetes management.
Collapse
Affiliation(s)
- Omar Diouri
- Department of Endocrinology, Diabetes, NutritionMontpellier University HospitalMontpellierFrance
- Department of PhysiologyInstitute of Functional Genomics, CNRS, INSERMUniversity of MontpellierMontpellierFrance
| | - Monika Cigler
- Division of Endocrinology and DiabetologyDepartment of Internal MedicineMedical University of GrazGrazAustria
| | | | - Julia K. Mader
- Division of Endocrinology and DiabetologyDepartment of Internal MedicineMedical University of GrazGrazAustria
| | - Pratik Choudhary
- Department of Diabetes and Nutritional SciencesKing's College LondonLondonUK
- Diabetes Research CentreUniversity of LeicesterLeicesterUK
| | - Eric Renard
- Department of Endocrinology, Diabetes, NutritionMontpellier University HospitalMontpellierFrance
- Department of PhysiologyInstitute of Functional Genomics, CNRS, INSERMUniversity of MontpellierMontpellierFrance
| | | |
Collapse
|
16
|
Felizardo V, Garcia NM, Pombo N, Megdiche I. Data-based algorithms and models using diabetics real data for blood glucose and hypoglycaemia prediction - A systematic literature review. Artif Intell Med 2021; 118:102120. [PMID: 34412843 DOI: 10.1016/j.artmed.2021.102120] [Citation(s) in RCA: 18] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/11/2020] [Revised: 05/24/2021] [Accepted: 05/25/2021] [Indexed: 10/21/2022]
Abstract
BACKGROUND AND AIM Hypoglycaemia prediction play an important role in diabetes management being able to reduce the number of dangerous situations. Thus, it is relevant to present a systematic review on the currently available prediction algorithms and models for hypoglycaemia (or hypoglycemia in US English) prediction. METHODS This study aims to systematically review the literature on data-based algorithms and models using diabetics real data for hypoglycaemia prediction. Five electronic databases were screened for studies published from January 2014 to June 2020: ScienceDirect, IEEE Xplore, ACM Digital Library, SCOPUS, and PubMed. RESULTS Sixty-three eligible studies were retrieved that met the inclusion criteria. The review identifies the current trend in this topic: most of the studies perform short-term predictions (82.5%). Also, the review pinpoints the inputs and shows that information fusion is relevant for hypoglycaemia prediction. Regarding data-based models (80.9%) and hybrid models (19.1%) different predictive techniques are used: Artificial neural network (22.2%), ensemble learning (27.0%), supervised learning (20.6%), statistic/probabilistic (7.9%), autoregressive (7.9%), evolutionary (6.4%), deep learning (4.8%) and adaptative filter (3.2%). Artificial Neural networks and hybrid models show better results. CONCLUSIONS The data-based models for blood glucose and hypoglycaemia prediction should be able to provide a good balance between the applicability and performance, integrating complementary data from different sources or from different models. This review identifies trends and possible opportunities for research in this topic.
Collapse
Affiliation(s)
- Virginie Felizardo
- Instituto de Telecomunicações, Covilhã, Portugal; Universidade da Beira Interior, Covilhã, Portugal.
| | - Nuno M Garcia
- Instituto de Telecomunicações, Covilhã, Portugal; Universidade da Beira Interior, Covilhã, Portugal.
| | - Nuno Pombo
- Instituto de Telecomunicações, Covilhã, Portugal; Universidade da Beira Interior, Covilhã, Portugal.
| | - Imen Megdiche
- IRIT, Institut de Recherche en Informatique de Toulouse, Toulouse University, France.
| |
Collapse
|
17
|
Dave D, DeSalvo DJ, Haridas B, McKay S, Shenoy A, Koh CJ, Lawley M, Erraguntla M. Feature-Based Machine Learning Model for Real-Time Hypoglycemia Prediction. J Diabetes Sci Technol 2021; 15:842-855. [PMID: 32476492 PMCID: PMC8258517 DOI: 10.1177/1932296820922622] [Citation(s) in RCA: 40] [Impact Index Per Article: 13.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 12/14/2022]
Abstract
BACKGROUND Hypoglycemia is a serious health concern in youth with type 1 diabetes (T1D). Real-time data from continuous glucose monitoring (CGM) can be used to predict hypoglycemic risk, allowing patients to take timely intervention measures. METHODS A machine learning model is developed for probabilistic prediction of hypoglycemia (<70 mg/dL) in 30- and 60-minute time horizons based on CGM datasets obtained from 112 patients over a range of 90 days consisting of over 1.6 million CGM values under normal living conditions. A comprehensive set of features relevant for hypoglycemia are developed and a parsimonious subset with most influence on predicting hypoglycemic risk is identified. Model performance is evaluated both with and without contextual information on insulin and carbohydrate intake. RESULTS The model predicted hypoglycemia with >91% sensitivity for 30- and 60-minute prediction horizons while maintaining specificity >90%. Inclusion of insulin and carbohydrate data yielded performance improvement for 60-minute but not for 30-minute predictions. Model performance was highest for nocturnal hypoglycemia (~95% sensitivity). Shortterm (less than one hour) and medium-term (one to four hours) features for good prediction performance are identified. CONCLUSIONS Innovative feature identification facilitated high performance for hypoglycemia risk prediction in pediatric youth with T1D. Timely alerts of impending hypoglycemia may enable proactive measures to avoid severe hypoglycemia and achieve optimal glycemic control. The model will be deployed on a patient-facing smartphone application in an upcoming pilot study.
Collapse
Affiliation(s)
- Darpit Dave
- Department of Industrial and Systems Engineering, Texas A&M University, College Station, TX, USA
| | - Daniel J. DeSalvo
- Baylor College of Medicine, Houston, TX, USA
- Texas Children’s Hospital, Houston, TX, USA
| | - Balakrishna Haridas
- Department of Biomedical Engineering, Texas A&M University, College Station, TX, USA
| | - Siripoom McKay
- Baylor College of Medicine, Houston, TX, USA
- Texas Children’s Hospital, Houston, TX, USA
| | | | - Chester J. Koh
- Baylor College of Medicine, Houston, TX, USA
- Texas Children’s Hospital, Houston, TX, USA
| | - Mark Lawley
- Department of Industrial and Systems Engineering, Texas A&M University, College Station, TX, USA
| | - Madhav Erraguntla
- Department of Industrial and Systems Engineering, Texas A&M University, College Station, TX, USA
- Madhav Erraguntla, PhD, Department of Industrial and Systems Engineering, Texas A&M University, 4021 Emerging Technology Building, College Station, TX 77843, USA.
| |
Collapse
|
18
|
Witkowski P, Philipson LH, Kaufman DB, Ratner LE, Abouljoud MS, Bellin MD, Buse JB, Kandeel F, Stock PG, Mulligan DC, Markmann JF, Kozlowski T, Andreoni KA, Alejandro R, Baidal DA, Hardy MA, Wickrema A, Mirmira RG, Fung J, Becker YT, Josephson MA, Bachul PJ, Pyda JS, Charlton M, Millis JM, Gaglia JL, Stratta RJ, Fridell JA, Niederhaus SV, Forbes RC, Jayant K, Robertson RP, Odorico JS, Levy MF, Harland RC, Abrams PL, Olaitan OK, Kandaswamy R, Wellen JR, Japour AJ, Desai CS, Naziruddin B, Balamurugan AN, Barth RN, Ricordi C. The demise of islet allotransplantation in the United States: A call for an urgent regulatory update. Am J Transplant 2021; 21:1365-1375. [PMID: 33251712 PMCID: PMC8016716 DOI: 10.1111/ajt.16397] [Citation(s) in RCA: 26] [Impact Index Per Article: 8.7] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/17/2020] [Revised: 10/14/2020] [Accepted: 11/02/2020] [Indexed: 02/06/2023]
Abstract
Islet allotransplantation in the United States (US) is facing an imminent demise. Despite nearly three decades of progress in the field, an archaic regulatory framework has stymied US clinical practice. Current regulations do not reflect the state-of-the-art in clinical or technical practices. In the US, islets are considered biologic drugs and "more than minimally manipulated" human cell and tissue products (HCT/Ps). In contrast, across the world, human islets are appropriately defined as "minimally manipulated tissue" and not regulated as a drug, which has led to islet allotransplantation (allo-ITx) becoming a standard-of-care procedure for selected patients with type 1 diabetes mellitus. This regulatory distinction impedes patient access to islets for transplantation in the US. As a result only 11 patients underwent allo-ITx in the US between 2016 and 2019, and all as investigational procedures in the settings of a clinical trials. Herein, we describe the current regulations pertaining to islet transplantation in the United States. We explore the progress which has been made in the field and demonstrate why the regulatory framework must be updated to both better reflect our current clinical practice and to deal with upcoming challenges. We propose specific updates to current regulations which are required for the renaissance of ethical, safe, effective, and affordable allo-ITx in the United States.
Collapse
Affiliation(s)
- Piotr Witkowski
- Department of Surgery, Transplantation Institute, University of Chicago, Chicago, Illinois, USA
| | | | - Dixon B. Kaufman
- Division of Transplantation, Department of Surgery, University of Wisconsin, School of Medicine and Public Health, Madison, Wisconsin, USA
| | - Lloyd E. Ratner
- Department of Surgery, Columbia University College of Physicians and Surgeons, New York, New York, USA
| | - Marwan S. Abouljoud
- Transplant and Hepatobiliary Surgery, Henry Ford Hospital, Detroit, Michigan, USA
| | - Melena D. Bellin
- Schulze Diabetes Institute, Department of Surgery, University of Minnesota, Minneapolis, Minnesota, USA
| | - John B. Buse
- Division of Endocrinology, Department of Medicine, University of North Carolina School of Medicine, Chapel Hill, North Carolina, USA
| | - Fouad Kandeel
- Department of Translational Research and Cellular Therapeutics, Diabetes and Metabolism Research Institute, Beckman Research Institute of City of Hope, Duarte, California, USA
| | - Peter G. Stock
- Division of Transplant Surgery, Department of Surgery, University of California, San Francisco, California, USA
| | - David C. Mulligan
- Department of Surgery, Transplantation and Immunology, Yale University, New Haven, Connecticut, USA
| | - James F. Markmann
- Division of Transplantation, Department of Surgery, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts, USA
| | - Tomasz Kozlowski
- Division of Transplantation, Department of Surgery, The University of Oklahoma College of Medicine, Oklahoma City, Oklahoma, USA
| | - Kenneth A. Andreoni
- Department of Surgery, University of Florida, College of Medicine, Gainesville, Florida, USA
| | - Rodolfo Alejandro
- Diabetes Research Institute and Cell Transplant Center, University of Miami, Miami, Florida, USA
| | - David A. Baidal
- Diabetes Research Institute and Cell Transplant Center, University of Miami, Miami, Florida, USA
| | - Mark A. Hardy
- Department of Surgery, Columbia University College of Physicians and Surgeons, New York, New York, USA
| | - Amittha Wickrema
- Department of Medicine, Section of Hematology and Oncology, University of Chicago, Chicago, Illinois, USA
| | - Raghavendra G. Mirmira
- Department of Medicine, Translational Research Center, University of Chicago, Chicago, Illinois, USA
| | - John Fung
- Department of Surgery, Transplantation Institute, University of Chicago, Chicago, Illinois, USA
| | - Yolanda T. Becker
- Department of Surgery, Transplantation Institute, University of Chicago, Chicago, Illinois, USA
| | - Michelle A. Josephson
- Department of Surgery, Transplantation Institute, University of Chicago, Chicago, Illinois, USA
| | - Piotr J. Bachul
- Department of Surgery, Transplantation Institute, University of Chicago, Chicago, Illinois, USA
| | - Jordan S. Pyda
- Department of Surgery, Beth Israel Deaconess Medical Center, Harvard Medical School, Boston, Massachusetts, USA
| | - Michael Charlton
- Department of Surgery, Transplantation Institute, University of Chicago, Chicago, Illinois, USA
| | - J. Michael Millis
- Department of Surgery, Transplantation Institute, University of Chicago, Chicago, Illinois, USA
| | - Jason L. Gaglia
- Joslin Diabetes Center, Harvard Medical School, Boston, Massachusetts, USA
| | - Robert J. Stratta
- Department of Surgery, Section of Transplantation, Wake Forest School of Medicine, Winston-Salem, North Carolina, USA
| | - Jonathan A. Fridell
- Department of Surgery, Indiana University School of Medicine, Indianapolis, Indiana, USA
| | - Silke V. Niederhaus
- Department of Surgery, University of Maryland Medical Center, Baltimore, Maryland, USA
| | - Rachael C. Forbes
- Division of Kidney and Pancreas Transplantation, Department of Surgery, Vanderbilt University Medical Center, Nashville, Tennessee, USA
| | - Kumar Jayant
- Department of Surgery, Transplantation Institute, University of Chicago, Chicago, Illinois, USA
| | - R. Paul Robertson
- Division of Endocrinology and Metabolism, Department of Internal Medicine, University of Washington, Seattle, Washington, USA
| | - Jon S. Odorico
- Division of Transplantation, Department of Surgery, University of Wisconsin, School of Medicine and Public Health, Madison, Wisconsin, USA
| | - Marlon F. Levy
- Division of Transplantation, Hume-Lee Transplant Center, Virginia Commonwealth University School of Medicine, Richmond, Virginia, USA
| | | | - Peter L. Abrams
- MedStar Georgetown Transplant Institute, Washington, District of Columbia, USA
| | | | - Raja Kandaswamy
- Department of Surgery, University of Minnesota, Minneapolis, Minnesota, USA
| | - Jason R. Wellen
- Department of Surgery, Washington University, St Louis, Missouri, USA
| | - Anthony J. Japour
- Anthony Japour and Associates, Medical and Scientific Consulting Inc, Miami, FL, USA
| | - Chirag S. Desai
- Department of Surgery, Section of Transplantation, University of North Carolina at Chapel Hill, Chapel Hill, North Carolina, USA
| | - Bashoo Naziruddin
- Transplantation Institute, Baylor University Medical Center, Dallas, Texas, USA
| | - Appakalai N. Balamurugan
- Division of Pediatric General and Thoracic Surgery, Department of Surgery, Cincinnati Children’s Hospital Medical Center, University of Cincinnati, Cincinnati, Ohio, USA
| | - Rolf N. Barth
- Department of Surgery, Transplantation Institute, University of Chicago, Chicago, Illinois, USA
| | - Camillo Ricordi
- Diabetes Research Institute and Cell Transplant Center, University of Miami, Miami, Florida, USA
| | | |
Collapse
|
19
|
Kodama S, Fujihara K, Shiozaki H, Horikawa C, Yamada MH, Sato T, Yaguchi Y, Yamamoto M, Kitazawa M, Iwanaga M, Matsubayashi Y, Sone H. Ability of Current Machine Learning Algorithms to Predict and Detect Hypoglycemia in Patients With Diabetes Mellitus: Meta-analysis. JMIR Diabetes 2021; 6:e22458. [PMID: 33512324 PMCID: PMC7880810 DOI: 10.2196/22458] [Citation(s) in RCA: 13] [Impact Index Per Article: 4.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/13/2020] [Revised: 11/09/2020] [Accepted: 12/07/2020] [Indexed: 12/12/2022] Open
Abstract
Background Machine learning (ML) algorithms have been widely introduced to diabetes research including those for the identification of hypoglycemia. Objective The objective of this meta-analysis is to assess the current ability of ML algorithms to detect hypoglycemia (ie, alert to hypoglycemia coinciding with its symptoms) or predict hypoglycemia (ie, alert to hypoglycemia before its symptoms have occurred). Methods Electronic literature searches (from January 1, 1950, to September 14, 2020) were conducted using the Dialog platform that covers 96 databases of peer-reviewed literature. Included studies had to train the ML algorithm in order to build a model to detect or predict hypoglycemia and test its performance. The set of 2 × 2 data (ie, number of true positives, false positives, true negatives, and false negatives) was pooled with a hierarchical summary receiver operating characteristic model. Results A total of 33 studies (14 studies for detecting hypoglycemia and 19 studies for predicting hypoglycemia) were eligible. For detection of hypoglycemia, pooled estimates (95% CI) of sensitivity, specificity, positive likelihood ratio (PLR), and negative likelihood ratio (NLR) were 0.79 (0.75-0.83), 0.80 (0.64-0.91), 8.05 (4.79-13.51), and 0.18 (0.12-0.27), respectively. For prediction of hypoglycemia, pooled estimates (95% CI) were 0.80 (0.72-0.86) for sensitivity, 0.92 (0.87-0.96) for specificity, 10.42 (5.82-18.65) for PLR, and 0.22 (0.15-0.31) for NLR. Conclusions Current ML algorithms have insufficient ability to detect ongoing hypoglycemia and considerate ability to predict impeding hypoglycemia in patients with diabetes mellitus using hypoglycemic drugs with regard to diagnostic tests in accordance with the Users’ Guide to Medical Literature (PLR should be ≥5 and NLR should be ≤0.2 for moderate reliability). However, it should be emphasized that the clinical applicability of these ML algorithms should be evaluated according to patients’ risk profiles such as for hypoglycemia and its associated complications (eg, arrhythmia, neuroglycopenia) as well as the average ability of the ML algorithms. Continued research is required to develop more accurate ML algorithms than those that currently exist and to enhance the feasibility of applying ML in clinical settings. Trial Registration PROSPERO International Prospective Register of Systematic Reviews CRD42020163682; http://www.crd.york.ac.uk/PROSPERO/display_record.php?ID=CRD42020163682
Collapse
Affiliation(s)
- Satoru Kodama
- Department of Prevention of Noncommunicable Diseases and Promotion of Health Checkup, Niigata University Graduate School of Medical and Dental Sciences, Niigata, Japan
| | - Kazuya Fujihara
- Department of Hematology, Endocrinology and Metabolism, Niigata University Graduate School of Medical and Dental Sciences, Niigata, Japan
| | - Haruka Shiozaki
- Department of Hematology, Endocrinology and Metabolism, Niigata University Graduate School of Medical and Dental Sciences, Niigata, Japan
| | - Chika Horikawa
- Department of Health and Nutrition, Faculty of Human Life Studies, University of Niigata Prefecture, Niigata, Japan
| | - Mayuko Harada Yamada
- Department of Hematology, Endocrinology and Metabolism, Niigata University Graduate School of Medical and Dental Sciences, Niigata, Japan
| | - Takaaki Sato
- Department of Hematology, Endocrinology and Metabolism, Niigata University Graduate School of Medical and Dental Sciences, Niigata, Japan
| | - Yuta Yaguchi
- Department of Hematology, Endocrinology and Metabolism, Niigata University Graduate School of Medical and Dental Sciences, Niigata, Japan
| | - Masahiko Yamamoto
- Department of Hematology, Endocrinology and Metabolism, Niigata University Graduate School of Medical and Dental Sciences, Niigata, Japan
| | - Masaru Kitazawa
- Department of Hematology, Endocrinology and Metabolism, Niigata University Graduate School of Medical and Dental Sciences, Niigata, Japan
| | - Midori Iwanaga
- Department of Hematology, Endocrinology and Metabolism, Niigata University Graduate School of Medical and Dental Sciences, Niigata, Japan
| | - Yasuhiro Matsubayashi
- Department of Hematology, Endocrinology and Metabolism, Niigata University Graduate School of Medical and Dental Sciences, Niigata, Japan
| | - Hirohito Sone
- Department of Hematology, Endocrinology and Metabolism, Niigata University Graduate School of Medical and Dental Sciences, Niigata, Japan
| |
Collapse
|
20
|
Mujahid O, Contreras I, Vehi J. Machine Learning Techniques for Hypoglycemia Prediction: Trends and Challenges. SENSORS (BASEL, SWITZERLAND) 2021; 21:E546. [PMID: 33466659 PMCID: PMC7828835 DOI: 10.3390/s21020546] [Citation(s) in RCA: 23] [Impact Index Per Article: 7.7] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 12/17/2020] [Revised: 01/08/2021] [Accepted: 01/12/2021] [Indexed: 12/11/2022]
Abstract
(1) Background: the use of machine learning techniques for the purpose of anticipating hypoglycemia has increased considerably in the past few years. Hypoglycemia is the drop in blood glucose below critical levels in diabetic patients. This may cause loss of cognitive ability, seizures, and in extreme cases, death. In almost half of all the severe cases, hypoglycemia arrives unannounced and is essentially asymptomatic. The inability of a diabetic patient to anticipate and intervene the occurrence of a hypoglycemic event often results in crisis. Hence, the prediction of hypoglycemia is a vital step in improving the life quality of a diabetic patient. The objective of this paper is to review work performed in the domain of hypoglycemia prediction by using machine learning and also to explore the latest trends and challenges that the researchers face in this area; (2) Methods: literature obtained from PubMed and Google Scholar was reviewed. Manuscripts from the last five years were searched for this purpose. A total of 903 papers were initially selected of which 57 papers were eventually shortlisted for detailed review; (3) Results: a thorough dissection of the shortlisted manuscripts provided an interesting split between the works based on two categories: hypoglycemia prediction and hypoglycemia detection. The entire review was carried out keeping this categorical distinction in perspective while providing a thorough overview of the machine learning approaches used to anticipate hypoglycemia, the type of training data, and the prediction horizon.
Collapse
Affiliation(s)
- Omer Mujahid
- Model Identification and Control Laboratory, Institut d’Informatica i Applicacions, Universitat de Girona, 17003 Girona, Spain; (O.M.); (I.C.)
| | - Ivan Contreras
- Model Identification and Control Laboratory, Institut d’Informatica i Applicacions, Universitat de Girona, 17003 Girona, Spain; (O.M.); (I.C.)
| | - Josep Vehi
- Model Identification and Control Laboratory, Institut d’Informatica i Applicacions, Universitat de Girona, 17003 Girona, Spain; (O.M.); (I.C.)
- Centro de Investigación Biomédica en Red de Diabetes y Enfermedades Metabólicas Asociadas (CIBERDEM), 17003 Girona, Spain
| |
Collapse
|
21
|
Mosquera-Lopez C, Dodier R, Tyler NS, Wilson LM, El Youssef J, Castle JR, Jacobs PG. Predicting and Preventing Nocturnal Hypoglycemia in Type 1 Diabetes Using Big Data Analytics and Decision Theoretic Analysis. Diabetes Technol Ther 2020; 22:801-811. [PMID: 32297795 PMCID: PMC7698985 DOI: 10.1089/dia.2019.0458] [Citation(s) in RCA: 14] [Impact Index Per Article: 3.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 01/07/2023]
Abstract
Background: Despite new glucose sensing technologies, nocturnal hypoglycemia is still a problem for people with type 1 diabetes (T1D) as symptoms and sensor alarms may not be detected while sleeping. Accurately predicting nocturnal hypoglycemia before sleep may help minimize nighttime hypoglycemia. Methods: A support vector regression (SVR) model was trained to predict, before bedtime, the overnight minimum glucose and overnight nocturnal hypoglycemia for people with T1D. The algorithm was trained on continuous glucose measurements and insulin data collected from 124 people (22,804 valid nights of data) with T1D. The minimum glucose threshold for announcing nocturnal hypoglycemia risk was derived by applying a decision theoretic criterion to maximize expected net benefit. Accuracy was evaluated on a validation set from 10 people with T1D during a 4-week trial under free-living sensor-augmented insulin-pump therapy. The primary outcome measures were sensitivity and specificity of prediction, the correlation between predicted and actual minimum nocturnal glucose, and root-mean-square error. The impact of using the algorithm to prevent nocturnal hypoglycemia is shown in-silico. Results: The algorithm predicted 94.1% of nocturnal hypoglycemia events (<3.9 mmol/L, 95% confidence interval [CI], 71.3-99.9) with an area under the receiver operating characteristic curve of 0.86 (95% CI, 0.75-0.98). Correlation between actual and predicted minimum glucose was high (R = 0.71, P < 0.001). In-silico simulations showed that the algorithm could reduce nocturnal hypoglycemia by 77.0% (P = 0.006) without impacting time in target range (3.9-10 mmol/L). Conclusion: An SVR model trained on a big data set and optimized using decision theoretic criterion can accurately predict at bedtime if overnight nocturnal hypoglycemia will occur and may help reduce nocturnal hypoglycemia.
Collapse
Affiliation(s)
- Clara Mosquera-Lopez
- Artificial Intelligence for Medical Systems (AIMS) Lab, Department of Biomedical Engineering, Oregon Health & Science University, Portland, Oregon, USA
- Harold Schnitzer Diabetes Health Center, Oregon Health and Science University, Portland, Oregon, USA
- Clara Mosquera-Lopez, PhD, Artificial Intelligence for Medical Systems (AIMS) Lab, Department of Biomedical Engineering, Oregon Health & Science University, 3303 SW Bond Avenue, Portland, OR 97239, USA
| | - Robert Dodier
- Artificial Intelligence for Medical Systems (AIMS) Lab, Department of Biomedical Engineering, Oregon Health & Science University, Portland, Oregon, USA
- Harold Schnitzer Diabetes Health Center, Oregon Health and Science University, Portland, Oregon, USA
| | - Nichole S. Tyler
- Artificial Intelligence for Medical Systems (AIMS) Lab, Department of Biomedical Engineering, Oregon Health & Science University, Portland, Oregon, USA
- Harold Schnitzer Diabetes Health Center, Oregon Health and Science University, Portland, Oregon, USA
| | - Leah M. Wilson
- Artificial Intelligence for Medical Systems (AIMS) Lab, Department of Biomedical Engineering, Oregon Health & Science University, Portland, Oregon, USA
- Harold Schnitzer Diabetes Health Center, Oregon Health and Science University, Portland, Oregon, USA
| | - Joseph El Youssef
- Artificial Intelligence for Medical Systems (AIMS) Lab, Department of Biomedical Engineering, Oregon Health & Science University, Portland, Oregon, USA
- Harold Schnitzer Diabetes Health Center, Oregon Health and Science University, Portland, Oregon, USA
| | - Jessica R. Castle
- Artificial Intelligence for Medical Systems (AIMS) Lab, Department of Biomedical Engineering, Oregon Health & Science University, Portland, Oregon, USA
- Harold Schnitzer Diabetes Health Center, Oregon Health and Science University, Portland, Oregon, USA
| | - Peter G. Jacobs
- Artificial Intelligence for Medical Systems (AIMS) Lab, Department of Biomedical Engineering, Oregon Health & Science University, Portland, Oregon, USA
- Harold Schnitzer Diabetes Health Center, Oregon Health and Science University, Portland, Oregon, USA
- Address correspondence to: Peter G. Jacobs, PhD, Artificial Intelligence for Medical Systems (AIMS) Lab, Department of Biomedical Engineering, Oregon Health & Science University, 3303 SW Bond Avenue, Portland, OR 97239, USA
| |
Collapse
|
22
|
Worth C, Dunne M, Ghosh A, Harper S, Banerjee I. Continuous glucose monitoring for hypoglycaemia in children: Perspectives in 2020. Pediatr Diabetes 2020; 21:697-706. [PMID: 32315515 DOI: 10.1111/pedi.13029] [Citation(s) in RCA: 19] [Impact Index Per Article: 4.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 03/16/2020] [Revised: 04/08/2020] [Accepted: 04/10/2020] [Indexed: 12/20/2022] Open
Abstract
Hypoglycaemia in children is a major risk factor for adverse neurodevelopment with rates as high as 50% in hyperinsulinaemic hypoglycaemia (HH). A key part of management relies upon timely identification and treatment of hypoglycaemia. The current standard of care for glucose monitoring is by infrequent fingerprick plasma glucose testing but this carries a high risk of missed hypoglycaemia identification. High-frequency Continuous Glucose Monitoring (CGM) offers an attractive alternative for glucose trend monitoring and glycaemic phenotyping but its utility remains largely unestablished in disorders of hypoglycaemia. Attempts to determine accuracy through correlation with plasma glucose measurements using conventional methods such as Mean Absolute Relative Difference (MARD) overestimate accuracy at hypoglycaemia. The inaccuracy of CGM in true hypoglycaemia is amplified by calibration algorithms that prioritize hyperglycaemia over hypoglycaemia with minimal objective evidence of efficacy in HH. Conversely, alternative algorithm design has significant potential for predicting hypoglycaemia to prevent neuroglycopaenia and consequent brain dysfunction in childhood disorders. Delays in the detection of hypoglycaemia, alarm fatigue, device calibration and current high cost are all barriers to the wider adoption of CGM in disorders of hypoglycaemia. However, machine learning, artificial intelligence and other computer-generated algorithms now offer significant potential for further improvement in CGM device technology and widespread application in childhood hypoglycaemia.
Collapse
Affiliation(s)
- Chris Worth
- Department of Paediatric Endocrinology, Royal Manchester Children's Hospital, Manchester, UK
| | - Mark Dunne
- Faculty of Biology, Medicine and Health, University of Manchester, Manchester, UK
| | - Arunabha Ghosh
- Department of Inherited Metabolic Disease, St Mary's Hospital, Manchester, UK
| | - Simon Harper
- Faculty of Computer Engineering, University of Manchester, Manchester, UK
| | - Indraneel Banerjee
- Department of Paediatric Endocrinology, Royal Manchester Children's Hospital, Manchester, UK
| |
Collapse
|
23
|
Bertachi A, Viñals C, Biagi L, Contreras I, Vehí J, Conget I, Giménez M. Prediction of Nocturnal Hypoglycemia in Adults with Type 1 Diabetes under Multiple Daily Injections Using Continuous Glucose Monitoring and Physical Activity Monitor. SENSORS (BASEL, SWITZERLAND) 2020; 20:E1705. [PMID: 32204318 PMCID: PMC7147466 DOI: 10.3390/s20061705] [Citation(s) in RCA: 29] [Impact Index Per Article: 7.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 02/25/2020] [Revised: 03/10/2020] [Accepted: 03/17/2020] [Indexed: 12/16/2022]
Abstract
(1) Background: nocturnal hypoglycemia (NH) is one of the most challenging side effects of multiple doses of insulin (MDI) therapy in type 1 diabetes (T1D). This work aimed to investigate the feasibility of a machine-learning-based prediction model to anticipate NH in T1D patients on MDI. (2) Methods: ten T1D adults were studied during 12 weeks. Information regarding T1D management, continuous glucose monitoring (CGM), and from a physical activity tracker were obtained under free-living conditions at home. Supervised machine-learning algorithms were applied to the data, and prediction models were created to forecast the occurrence of NH. Individualized prediction models were generated using multilayer perceptron (MLP) and a support vector machine (SVM). (3) Results: population outcomes indicated that more than 70% of the NH may be avoided with the proposed methodology. The predictions performed by the SVM achieved the best population outcomes, with a sensitivity and specificity of 78.75% and 82.15%, respectively. (4) Conclusions: our study supports the feasibility of using ML techniques to address the prediction of nocturnal hypoglycemia in the daily life of patients with T1D on MDI, using CGM and a physical activity tracker.
Collapse
Affiliation(s)
- Arthur Bertachi
- Institute of Informatics and Applications, University of Girona, 17003 Girona, Spain; (A.B.); (L.B.); (I.C.)
- Federal University of Technology—Paraná (UTFPR), Guarapuava 85053-525, Brazil
| | - Clara Viñals
- Diabetes Unit, Endocrinology and Nutrition Dpt. Hospital Clínic de Barcelona, 08036 Barcelona, Spain; (C.V.); (I.C.); (M.G.)
| | - Lyvia Biagi
- Institute of Informatics and Applications, University of Girona, 17003 Girona, Spain; (A.B.); (L.B.); (I.C.)
- Federal University of Technology—Paraná (UTFPR), Guarapuava 85053-525, Brazil
| | - Ivan Contreras
- Institute of Informatics and Applications, University of Girona, 17003 Girona, Spain; (A.B.); (L.B.); (I.C.)
| | - Josep Vehí
- Institute of Informatics and Applications, University of Girona, 17003 Girona, Spain; (A.B.); (L.B.); (I.C.)
- Centro de Investigación Biomédica en Red de Diabetes y Enfermedades Metabólicas Asociadas (CIBERDEM), 08036 Barcelona, Spain
| | - Ignacio Conget
- Diabetes Unit, Endocrinology and Nutrition Dpt. Hospital Clínic de Barcelona, 08036 Barcelona, Spain; (C.V.); (I.C.); (M.G.)
- Centro de Investigación Biomédica en Red de Diabetes y Enfermedades Metabólicas Asociadas (CIBERDEM), 08036 Barcelona, Spain
| | - Marga Giménez
- Diabetes Unit, Endocrinology and Nutrition Dpt. Hospital Clínic de Barcelona, 08036 Barcelona, Spain; (C.V.); (I.C.); (M.G.)
- Centro de Investigación Biomédica en Red de Diabetes y Enfermedades Metabólicas Asociadas (CIBERDEM), 08036 Barcelona, Spain
| |
Collapse
|