Detection of Insulin Pump Malfunctioning to Improve Safety in Artificial Pancreas Using Unsupervised Algorithms

Lorenzo Meneghetti, Gian Antonio Susto, Simone Del Favero, Lorenzo Meneghetti, Gian Antonio Susto, Simone Del Favero

Abstract

Background: Recent development of automated closed-loop (CL) insulin delivery systems, the so-called artificial pancreas (AP), improved the quality of type 1 diabetes (T1D) therapy. As new technologies emerge, patients put increasing trust in their therapeutic devices; therefore, it becomes increasingly important to detect malfunctioning affecting such devices. In this work, we explore a new paradigm to detect insulin pump faults (IPFs) that use unsupervised anomaly detection.

Methods: We generated CL data corrupted with IPFs using the latest version of the T1D Padova/UVA simulator. From the data, we extracted several features capable to describe the patient dynamics and making more apparent suspicious data portions. Then, a feature selection is performed to determine the optimal feature set. Finally, the performance of several popular unsupervised anomaly detection algorithms is analyzed and compared on the identified optimal feature set.

Results: Using the identified optimal configuration, the best performance is obtained by the Histogram-Based Outlier Score (HBOS) algorithm, which detected 87% of the IPF with only 0.08 false positives per day on average. Isolation forest is the best algorithm that offers more conservative performances, detection of 85% of the faults but only 0.06 false positives per day on average.

Conclusion: Unsupervised anomaly detection algorithms can be used effectively to detect IPFs and improve the safety of the AP. Future studies will be dedicated to test the presented method inside dedicated clinical trials.

Keywords: anomaly detection; artificial pancreas; fault detection; insulin pump; insulin pump faults; unsupervised anomaly detection.

Conflict of interest statement

Declaration of Conflicting Interests: The author(s) declared the following potential conflicts of interest with respect to the research, authorship, and/or publication of this article: L.M, G.A.S, and S.D.F. hold patent applications related to the proposed method.

Figures

Figure 1.
Figure 1.
Scheme of the insulin pump fault detection method steps (on the left) and the design pipeline (on the right).
Figure 2.
Figure 2.
Example of a comparison of two Precision-Recall curves and their respective average precision.
Figure 3.
Figure 3.
Feature selection on HBOS.
Figure 4.
Figure 4.
Feature selection on IForest.
Figure 5.
Figure 5.
Feature selection on KNN.
Figure 6.
Figure 6.
Feature selection on OCSVM.
Figure 7.
Figure 7.
Analysis of the performance obtained in the Recall-FP/day space for the selection of the optimal threshold.
Figure 8.
Figure 8.
Algorithm comparison in the Precision-Recall space on the test set.
Figure 9.
Figure 9.
Algorithm comparison in the FP/day-Recall space on the test set.

References

    1. Vettoretti M, Cappon G, Acciaroli G, Facchinetti A, Sparacino G. Continuous glucose monitoring: current use in diabetes management and possible future applications. J Diabetes Sci Technol. 2018;12(5):1064-1071.
    1. Cappon G, Acciaroli G, Vettoretti M, Facchinetti A, Sparacino G. Wearable continuous glucose monitoring sensors: a revolution in diabetes treatment. Electronics. 2017;6(3):65.
    1. McAdams B, Rizvi A. An overview of insulin pumps and glucose sensors for the generalist. J Clin Med. 2016;5(1):E5.
    1. Thabit H, Hovorka R. Coming of age: the artificial pancreas for type 1 diabetes. Diabetologia. 2016;59(9):1795-1805.
    1. Acciaroli G, Vettoretti M, Facchinetti A, Sparacino G. Calibration of minimally invasive continuous glucose monitoring sensors: state-of-the-art and current perspectives. Biosensors. 2018;8(1):24.
    1. Schmidt S, Nørgaard K, Neergaard K, Almdal T, Hommel EE. Long-term adherence to automated bolus calculators. J Diabetes Sci Technol. 2017;11(1):174-175.
    1. Herrero P, Pesl P, Reddy M, Oliver N, Georgiou P, Toumazou C. Advanced insulin bolus advisor based on run-to-run control and case-based reasoning. IEEE J Biomed Health. 2015;19(3):1087-1096.
    1. Cappon G, Vettoretti M, Marturano F, Facchinetti A, Sparacino G. A neural-network-based approach to personalize insulin bolus calculation using continuous glucose monitoring. J Diabetes Sci Technol. 2018;12(2):265-272.
    1. Brown D, Aldea A, Harrison R, Martin C, Bayley I. Temporal case-based reasoning for type 1 diabetes mellitus bolus insulin decision support. Artif Intell Med. 2018;85:28-42.
    1. Zisser H, Robinson L, Bevier W, et al. Bolus calculator: a review of four “smart” insulin pumps. Diabetes Technol Ther. 2008;10(6):441-444.
    1. Huckvale K, Adomaviciute S, Prieto JT, Leow MKS, Car J. Smartphone apps for calculating insulin dose: a systematic assessment. BMC Med. 2015;13(1):106.
    1. Anthimopoulos M, Dehais J, Shevchik S, et al. Computer vision-based carbohydrate estimation for type 1 patients with diabetes using smartphones. J Diabetes Sci Technol. 2015;9(3):507-515.
    1. Farrington C. Psychosocial impacts of hybrid closed-loop systems in the management of diabetes: a review. Diabet Med. 2018;35(4):436-449.
    1. Zhang Y, Jones PL, Jetley R. A hazard analysis for a generic insulin infusion pump. J Diabetes Sci Technol. 2010;4(2):263-283.
    1. Kölle K, Fougner AL, Lundteigen MA, Carlsen SM, Ellingsen R, Stavdahl Ø. Risk analysis for the design of a safe artificial pancreas control system. Health Technol. 2019;9(3):311-328.
    1. Guilhem I, Balkau B, Lecordier F, et al. Insulin pump failures are still frequent: a prospective study over 6 years from 2001 to 2007. Diabetologia. 2009;52(12):2662-2664.
    1. Schmid V, Hohberg C, Borchert M, Forst T, Pfuẗzner A. Pilot study for assessment of optimal frequency for changing catheters in insulin pump therapy: trouble starts on day 3. J Diabetes Sci Technol. 2010;4(4):976-982.
    1. van Bon AC, Dragt D, DeVries JH. Significant time until catheter occlusion alerts in currently marketed insulin pumps at two basal rates. Diabetes Technol Ther. 2012;14(5):447-448.
    1. Karlin AW, Ly TT, Pyle L, et al. Duration of infusion set survival in lipohypertrophy versus nonlipohypertrophied tissue in patients with type 1 diabetes. Diabetes Technol Ther. 2016;18(7):429-435.
    1. Deiss D, Adolfsson P, Alkemade-van Zomeren M, et al. Insulin infusion set use: European perspectives and recommendations. Diabetes Technol Ther. 2016;18(9):517-524.
    1. Hanas R, Lindgren F, Lindblad B. A 2-yr national population study of pediatric ketoacidosis in Sweden: predisposing conditions and insulin pump use. Pediatr Diabetes. 2009;10(1):33-37.
    1. Dogan ADA, Jørgensen UL, Gjessing HJ. Diabetic ketoacidosis among patients treated with continuous subcutaneous insulin infusion. J Diabetes Sci Technol. 2017;11(3):631-632.
    1. Realsen J, Goettle H, Chase HP. Morbidity and mortality of diabetic ketoacidosis with and without insulin pump care. Diabetes Technol Ther. 2012;14(12):1149-1154.
    1. Maahs DM, Hermann JM, Holman N, et al. Rates of diabetic ketoacidosis: international comparison with 49,859 pediatric patients with type 1 diabetes from England, Wales, the U.S., Austria, and Germany. Diabetes Care. 2015;38(10):1876-1882.
    1. Facchinetti A, Favero S, Sparacino G, Cobelli C. An online failure detection method of the glucose sensor-insulin pump system: improved overnight safety of type-1 diabetic subjects. IEEE Trans Biomed Eng. 2013;60(2):406-416.
    1. Del Favero S, Monaro M, Facchinetti A, Tagliavini A, Sparacino G, Cobelli C. Real-time detection of glucose sensor and insulin pump faults in an artificial pancreas. IFAC Proc. 2014;47(3):1941-1946.
    1. Gao Z, Cecati C, Ding SX. A survey of fault diagnosis and fault-tolerant techniques-part I: fault diagnosis with model-based and signal-based approaches. IEEE Trans Ind Electron. 2015;62(6):3757-3767.
    1. Kovács L, Kulcsár B, Bokor J, Bcnyó Z. LPV fault detection of glucose-insulin system. 14th Mediterranean Conference on Control and Automation (MED’06); Jun 28, 2006; Ancona, Italy: Electronic Publication; TLA2-TLA4.
    1. Vega-Hernández O, Campos-Cornejo F, Campos-Delgado DU, Espinoza-Trejo DR. Increasing security in an artificial pancreas: diagnosis of actuator faults. 2009 Pan American Health Care Exchanges - PAHCE 2009; Mar 16, 2009; Mexico City, Mexico: IEEE; 137-142.
    1. Herrero P, Calm R, Vehí J, et al. Robust fault detection system for insulin pump therapy using continuous glucose monitoring. J Diabetes Sci Technol. 2012;6(5):1131-1141.
    1. Meneghetti L, Terzi M, Del Favero S, Susto GA, Cobelli C. Data-driven anomaly recognition for unsupervised model-free fault detection in artificial pancreas. IEEE Trans Contr Syst Technol. 2018;1-15. doi:10.1109/TCST.2018.2885963.
    1. Goldstein M, Uchida S. A comparative evaluation of unsupervised anomaly detection algorithms for multivariate data. PLoS One. 2016;11(4):1-31.
    1. Björklund J, Eksvärd K, Schaffer C. A review of unsupervised feature learning and deep learning for time-series modeling. Pattern Recogn Lett. 2014;42:11-24.
    1. Visentin R, Campos-Náñez E, Schiavon M, et al. The UVA/Padova type 1 diabetes simulator goes from single meal to single day. J Diabetes Sci Technol. 2018;12(2):273-281.
    1. Man CD, Micheletto F, Lv D, Breton M, Kovatchev B, Cobelli C. The UVA/PADOVA type 1 diabetes simulator: new features. J Diabetes Sci Technol. 2014;8(1):26-34.
    1. Perriello G, De Feo P, Torlone E, et al. The dawn phenomenon in Type 1 (insulin-dependent) diabetes mellitus: magnitude, frequency, variability, and dependency on glucose counterregulation and insulin sensitivity. Diabetologia. 1991;34(1):21-28.
    1. Steil GM. Algorithms for a closed-loop artificial pancreas: the case for proportional-integral-derivative control. J Diabetes Sci Technol. 2013;7(6):1621-1631.
    1. Brazeau AS, Mircescu H, Desjardins K, et al. Carbohydrate counting accuracy and blood glucose variability in adults with type 1 diabetes. Diabetes Res Clin Pract. 2013;99(1):19-23.
    1. Vettoretti M, Facchinetti A, Sparacino G, Cobelli C. Type-1 diabetes patient decision simulator for in silico testing safety and effectiveness of insulin treatments. IEEE Trans Biomed Eng. 2018;65(6):1281-1290.
    1. van Bon AC, Bode BW, Sert-Langeron C, DeVries JH, Charpentier G. Insulin glulisine compared to insulin aspart and to insulin lispro administered by continuous subcutaneous insulin infusion in patients with type 1 diabetes: a randomized controlled trial. Diabetes Technol Ther. 2011;13(6):607-614.
    1. Saito T, Rehmsmeier M. The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets. PLoS One. 2015;10(3):e0118432.
    1. Ellingsen C, Dassau E, Zisser H, Grosman B, Percival MW. Safety constraints in an artificial pancreatic beta cell: an implementation of model predictive control with insulin on board. J Diabetes Sci Technol. 2009;3(3):536-544.
    1. Schiavon M, Dalla Man C, Kudva YC, Basu A, Cobelli C. Quantitative estimation of insulin sensitivity in type 1 diabetic subjects wearing a sensor-augmented insulin pump. Diabetes Care. 2014;37(5):1216-1223.
    1. Howsmon DP, Cameron F, Baysal N, et al. Continuous glucose monitoring enables the detection of losses in infusion set actuation (LISAs). Sensors. 2017;17(1):161.
    1. Franklin J. The elements of statistical learning: data mining, inference and prediction. Math Intell. 2005;27(2):83-85.
    1. Zhao Y, Nasrullah Z, Li Z. PyOD: a python toolbox for scalable outlier detection. J Mach Learn Res. 2019;20(96):1-7.
    1. Liu FT, Ting KM. Isolation forest. Eighth IEE International Conference on Data Mining; December 15-19 2018; Pisa, Italy: IEEE; 413-422.
    1. Platt JC, Shawe-Taylor J, Smola AJ, Williamson RC, Scholkopf B. Estimating the support of a high-dimensional distribution. Neural Comput. 2001;13(7):1443-1471.
    1. Goldstein M, Dengel A. Histogram-based Outlier Score (HBOS): a fast unsupervised anomaly detection algorithm. In: KI 2012: Advances in Artificial Intelligence; December 4-7, 2012; Sydney, Australia; 5.
    1. Ramaswamy S, Rastogi R, Shim K. Efficient algorithms for mining outliers from large data sets. Proceedings of the 2000 ACM SIGMOD International Conference on Management of Data - SIGMOD ’00; May 15-18, 2000; Dallas, TX, USA; 427-438.
    1. Breunig MM, Kriegel H-P, Ng RT, Sander J. LOF: identifying density-based local outliers. Proceedings of the 2000 ACM SIGMOD International Conference on Management of Data - SIGMOD ’00 May 15-18, 2000; Dallas, TX, USA; 93-104.
    1. He Z, Xu X, Deng S. Discovering cluster-based local outliers. Pattern Recognit Lett. 2003;24(9-10):1641-1650.
    1. Shyu ML, Chen SC, Sarinnapakorn K, Chang L. Principal component-based anomaly detection scheme. Stud Comput Intell. 2006;9:311-329.
    1. Lee YJ, Yeh YR, Wang YCF. Anomaly detection via online oversampling principal component analysis. IEEE Trans Knowl Data Eng. 2013;25(7):1460-1470.
    1. Hardin J, Rocke DM. Outlier detection in the multiple cluster setting using the minimum covariance determinant estimator. Comput Stat Data Anal. 2004;44(4):625-638.
    1. Kriegel H-P, Schubert M, Zimek A. Angle-based outlier detection in high-dimensional data. Proceedings of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining; August 24-27, 2008; Las Vegas, NV, USA: ACM; 444-452.
    1. Rojas R, Garcia-Gabin W, Bequette BW. Multivariate statistical analysis to detect insulin infusion set failure. Proceedings of the 2011 American Control Conference; June 29-July 1, 2011; San Francisco, CA, USA; IEEE; 1952-1957.
    1. Cescon M, Desalvo DJ, Ly TT, et al. Early detection of infusion set failure during insulin pump therapy in type 1 diabetes. J Diabetes Sci Technol. 2016;10(6):1268-1276.
    1. Howsmon DP, Baysal N, Buckingham BA, et al. Real-time detection of infusion site failures in a closed-loop artificial pancreas. J Diabetes Sci Technol. 2018;12(3):599-607.
    1. Zimek A, Schubert E, Kriegel H-P. A survey on unsupervised outlier detection in high-dimensional numerical data. Stat Anal Data Min. 2012;5(5):363-387.
    1. Heinemann L, Fleming GA, Petrie JR, Holl RW, Bergenstal RM, Peters AL. Insulin pump risks and benefits: a clinical appraisal of pump safety standards, adverse event reporting, and research needs: a joint statement of the European Association for the Study of Diabetes and the American Diabetes Association Diabetes Technology Working Group. Diabetes Care. 2015;38(4):716-722.

Source: PubMed

Sponsorit ja yhteistyökumppanit

Sairaudet

Huumeiden interventiot

3
Tilaa