Machine Learning-Based Anomaly Detection Algorithms to Alert Patients Using Sensor Augmented Pump of Infusion Site Failures

Abstract

Background: Personal insulin pumps have shown to be effective in improving the quality of therapy for people with type 1 diabetes (T1D). However, the safety of this technology is limited by the possible infusion site failures, which are linked with hyperglycemia and ketoacidosis. Thanks to the large availability of collected data provided by modern therapeutic technologies, machine learning algorithms have the potential to provide new way to identify failures early and avert adverse events. Methods: A clinical dataset ( N = 20) is used to evaluate a novel method for detecting real-time infusion site failures using unsupervised anomaly detection algorithms, previously proposed and developed on in-silico data. An adapted feature engineering procedure is introduced to make the method able to operate in the absence of a closed-loop (CL) system and meal announcements. Results: In the optimal configuration, we obtained a performance of 0.75 Sensitivity (15 out of 20 total failures detected) and 0.08 FP/day, outperforming previously proposed literature algorithms. The algorithm was able to anticipate the replacement of the malfunctioning infusion sets by ~2 h on average. Conclusions: On the considered dataset, the proposed algorithm showed the potential to improve the safety of patients treated with sensor-augmented pump systems.

Artificial Intelligence and Machine Learning for Improving Glycemic Control in Diabetes: Best Practices, Pitfalls, and Opportunities

“…Insulin pumps can also fail during usage as caused by infusion set actuation problems [89]. Machine learning approaches have been applied to detecting these anomalies and alerting patients to these failures [90]. Data scientists must decide how to handle missing CGM and insulin data in the training, validation, and test sets.…”

Performance of a Continuous Subcutaneous Insulin Infusion (CSII) Pump with Acoustic Volume and Flow Sensing in Simulated HighConsequence Situations_supp1-3408092.docx

“…Based upon review of the peer-reviewed literature, ongoing research and innovation to address and to mitigate SIND is focused on: a) exploration of algorithms that track trends in continuous glucose monitor (CGM) measurements suggestive of insulin non-delivery, b) development of improved infusion sets and protocols less prone to cannula obstruction, c) development of continuous ketone monitors, and d) investigation of the mechanisms by which subcutaneous delivery engenders gradual increases in resistance to insulin flow [11][12][13][14].…”