An artificial intelligence decision support system for the management of type 1 diabetes
Nichole S Tyler, Clara M Mosquera-Lopez, Leah M Wilson, Robert H Dodier, Deborah L Branigan, Virginia B Gabo, Florian H Guillot, Wade W Hilts, Joseph El Youssef, Jessica R Castle, Peter G Jacobs, Nichole S Tyler, Clara M Mosquera-Lopez, Leah M Wilson, Robert H Dodier, Deborah L Branigan, Virginia B Gabo, Florian H Guillot, Wade W Hilts, Joseph El Youssef, Jessica R Castle, Peter G Jacobs
Abstract
Type 1 diabetes (T1D) is characterized by pancreatic beta cell dysfunction and insulin depletion. Over 40% of people with T1D manage their glucose through multiple injections of long-acting basal and short-acting bolus insulin, so-called multiple daily injections (MDI)1,2. Errors in dosing can lead to life-threatening hypoglycaemia events (<70 mg dl-1) and hyperglycaemia (>180 mg dl-1), increasing the risk of retinopathy, neuropathy, and nephropathy. Machine learning (artificial intelligence) approaches are being harnessed to incorporate decision support into many medical specialties. Here, we report an algorithm that provides weekly insulin dosage recommendations to adults with T1D using MDI therapy. We employ a unique virtual platform3 to generate over 50,000 glucose observations to train a k-nearest neighbours4 decision support system (KNN-DSS) to identify causes of hyperglycaemia or hypoglycaemia and determine necessary insulin adjustments from a set of 12 potential recommendations. The KNN-DSS algorithm achieves an overall agreement with board-certified endocrinologists of 67.9% when validated on real-world human data, and delivers safe recommendations, per endocrinologist review. A comparison of inter-physician-recommended adjustments to insulin pump therapy indicates full agreement of 41.2% among endocrinologists, which is consistent with previous measures of inter-physician agreement (41-45%)5. In silico3,6 benchmarking using a platform accepted by the United States Food and Drug Administration for evaluation of artificial pancreas technologies indicates substantial improvement in glycaemic outcomes after 12 weeks of KNN-DSS use. Our data indicate that the KNN-DSS allows for early identification of dangerous insulin regimens and may be used to improve glycaemic outcomes and prevent life-threatening complications in people with T1D.
Trial registration: ClinicalTrials.gov NCT03443713.
Figures
References
- Paris CA et al. Predictors of insulin regimens and impact on outcomes in youth with type 1 diabetes: the SEARCH for Diabetes in Youth study. The Journal of pediatrics 155, 183–189.e181, doi:10.1016/j.jpeds.2009.01.063 (2009).
- Miller KM et al. Current state of type 1 diabetes treatment in the U.S.: updated data from the T1D Exchange clinic registry. Diabetes care 38, 971–978, doi:10.2337/dc15-0078 (2015).
- Resalat N, El Youssef J, Tyler N, Castle J & Jacobs PG A statistical virtual patient population for the glucoregulatory system in type 1 diabetes with integrated exercise model. PloS one 14, e0217301, doi:10.1371/journal.pone.0217301 (2019).
- Cover T & Hart P Nearest neighbor pattern classification. IEEE Trans. Inf. Theor. 13, 21–27, doi:10.1109/tit.1967.1053964 (2006).
- Nimri R et al. Adjusting insulin doses in patients with type 1 diabetes who use insulin pump and continuous glucose monitoring: Variations among countries and physicians. Diabetes, Obesity and Metabolism 20, 2458–2466, doi:10.1111/dom.13408 (2018).
- Man CD et al. The UVA/PADOVA Type 1 Diabetes Simulator: New Features. Journal of diabetes science and technology 8, 26–34, doi:10.1177/1932296813514502 (2014).
- Intensive Diabetes Treatment and Cardiovascular Outcomes in Type 1 Diabetes: The DCCT/EDIC Study 30-Year Follow-up. Diabetes care 39, 686–693, doi:10.2337/dc15-1990 (2016).
- Schwartz FL, Guo A, Marling CR & Shubrook JH Analysis of use of an automated bolus calculator reduces fear of hypoglycemia and improves confidence in dosage accuracy in type 1 diabetes mellitus patients treated with multiple daily insulin injections. Journal of diabetes science and technology 6, 150–152, doi:10.1177/193229681200600118 (2012).
- Roze S et al. Cost-effectiveness of continuous subcutaneous insulin infusion versus multiple daily injections of insulin in Type 1 diabetes: a systematic review. Diabetic medicine : a journal of the British Diabetic Association 32, 1415–1424, doi:10.1111/dme.12792 (2015).
- McNally K, Rohan J, Pendley JS, Delamater A & Drotar D Executive Functioning, Treatment Adherence, and Glycemic Control in Children With Type 1 Diabetes. Diabetes care 33, 1159–1162, doi:10.2337/dc09-2116 (2010).
- Sarbacker GB & Urteaga EM Adherence to Insulin Therapy. Diabetes spectrum : a publication of the American Diabetes Association 29, 166–170, doi:10.2337/diaspect.29.3.166 (2016).
- Kirwan M, Vandelanotte C, Fenning A & Duncan JM Diabetes Self-Management Smartphone Application for Adults With Type 1 Diabetes: Randomized Controlled Trial. J Med Internet Res 15, e235, doi:10.2196/jmir.2588 (2013).
- Charpentier G et al. The Diabeo software enabling individualized insulin dose adjustments combined with telemedicine support improves HbA1c in poorly controlled type 1 diabetic patients: a 6-month, randomized, open-label, parallel-group, multicenter trial (TeleDiab 1 Study). Diabetes care 34, 533–539, doi:10.2337/dc10-1259 (2011).
- Wu Y et al. Mobile App-Based Interventions to Support Diabetes Self-Management: A Systematic Review of Randomized Controlled Trials to Identify Functions Associated with Glycemic Efficacy. JMIR mHealth and uHealth 5, e35, doi:10.2196/mhealth.6522 (2017).
- Veazie S et al. Rapid Evidence Review of Mobile Applications for Self-management of Diabetes. Journal of general internal medicine, doi:10.1007/s11606-018-4410-1 (2018).
- Beck RW et al. Effect of Continuous Glucose Monitoring on Glycemic Control in Adults With Type 1 Diabetes Using Insulin Injections: The DIAMOND Randomized Clinical Trial. Jama 317, 371–378, doi:10.1001/jama.2016.19975 (2017).
- Steil GM et al. Use of Automated Clinical Decision Support (CDS) to Effect Glycemic Control in Elderly Patients with T1D. Diabetes 67, 921–P, doi:10.2337/db18-921-P (2018).
- Palerm CC, Zisser H, Jovanovic L & Doyle FJ 3rd. A Run-to-Run Control Strategy to Adjust Basal Insulin Infusion Rates in Type 1 Diabetes. J Process Control 18, 258–265, doi:10.1016/j.jprocont.2007.07.010 (2008).
- Herrero P, Bondia J, Gimenez M, Oliver N & Georgiou P Automatic Adaptation of Basal Insulin Using Sensor-Augmented Pump Therapy. Journal of diabetes science and technology 12, 282–294, doi:10.1177/1932296818761752 (2018).
- Toffanin C, Messori M, Cobelli C & Magni L Automatic adaptation of basal therapy for Type 1 diabetic patients: A Run-to-Run approach. Biomedical Signal Processing and Control 31, 539–549, doi:10.1016/j.bspc.2016.09.002 (2017).
- Zisser H, Palerm CC, Bevier WC, Doyle FJ 3rd & Jovanovic L Clinical update on optimal prandial insulin dosing using a refined run-to-run control algorithm. Journal of diabetes science and technology 3, 487–491, doi:10.1177/193229680900300312 (2009).
- Herrero P et al. Advanced Insulin Bolus Advisor Based on Run-To-Run Control and Case-Based Reasoning. IEEE journal of biomedical and health informatics 19, 1087–1096, doi:10.1109/jbhi.2014.2331896 (2015).
- Perez-Gandia C et al. Decision Support in Diabetes Care: The Challenge of Supporting Patients in Their Daily Living Using a Mobile Glucose Predictor. Journal of diabetes science and technology 12, 243–250, doi:10.1177/1932296818761457 (2018).
- Breton MD et al. Continuous Glucose Monitoring and Insulin Informed Advisory System with Automated Titration and Dosing of Insulin Reduces Glucose Variability in Type 1 Diabetes Mellitus. Diabetes technology & therapeutics 20, 531–540, doi:10.1089/dia.2018.0079 (2018).
- Reddy M et al. Clinical Safety and Feasibility of the Advanced Bolus Calculator for Type 1 Diabetes Based on Case-Based Reasoning: A 6-Week Nonrandomized Single-Arm Pilot Study. Diabetes technology & therapeutics 18, 487–493, doi:10.1089/dia.2015.0413 (2016).
- Resalat N, El Youssef J, Reddy R, Castle J & Jacobs PG Adaptive tuning of basal and bolus insulin to reduce postprandial hypoglycemia in a hybrid artificial pancreas. Journal of Process Control 80, 247–254, doi:10.1016/j.jprocont.2019.05.018 (2019).
- Sørensen TJ A method of establishing groups of equal amplitude in plant sociology based on similarity of species content and its application to analyses of the vegetation on Danish commons. (I kommission hos E. Munksgaard, 1948).
- Davidson MB, Duran P, Davidson SJ & Lee M Comparison of Insulin Dose Adjustments by Primary Care Physicians and Endocrinologists. Clinical Diabetes 36, 39, doi:10.2337/cd17-0021 (2018).
- Bashan E & Hodish I Frequent insulin dosage adjustments based on glucose readings alone are sufficient for a safe and effective therapy. Journal of Diabetes and its Complications 26, 230–236, doi:10.1016/j.jdiacomp.2012.03.012 (2012).
- Reddy R et al. The effect of exercise on sleep in adults with type 1 diabetes. Diabetes, obesity & metabolism 20, 443–447, doi:10.1111/dom.13065 (2018).
- Castle JR et al. Randomized Outpatient Trial of Single- and Dual-Hormone Closed-Loop Systems That Adapt to Exercise Using Wearable Sensors. Diabetes care 41, 1471–1477, doi:10.2337/dc18-0228 (2018).
- Pettus J & Edelman SV Recommendations for Using Real-Time Continuous Glucose Monitoring (rtCGM) Data for Insulin Adjustments in Type 1 Diabetes. Journal of diabetes science and technology 11, 138–147, doi:10.1177/1932296816663747 (2017).
- Whitney AW A Direct Method of Nonparametric Measurement Selection. IEEE Trans. Comput. 20, 1100–1103, doi:10.1109/t-c.1971.223410 (1971).
- Scheiner G Practical CGM: improving patient outcomes through continuous glucose monitoring. (American Diabetes Association, 2015).
- White JW, Rassweiler A, Samhouri JF, Stier AC & White C Ecologists should not use statistical significance tests to interpret simulation model results. Oikos 123, 385–388, doi:10.1111/j.1600-0706.2013.01073.x (2014).
Source: PubMed