Closing the Loop

A Hybrid Dynamic Wavelet-Based Modeling Method for Blood Glucose Concentration Prediction in Type 1 Diabetes

Background:

Diabetes mellitus (DM) is a chronic disease that affects public health. The prediction of blood glucose concentration (BGC) is essential to improve the therapy of type 1 DM (T1DM).

Methods:

Having considered the risk of hyper- and hypo-glycemia, we provide a new hybrid modeling approach for BGC prediction based on a dynamic wavelet neural network (WNN) model, including a heuristic input selection. The proposed models include a hybrid dynamic WNN (HDWNN) and a hybrid dynamic fuzzy WNN (HDFWNN). These wavelet-based networks are designed based on dominant wavelets selected by the genetic algorithm-orthogonal least square method. Furthermore, the HDFWNN model structure is improved using fuzzy rule induction, an important innovation in the fuzzy wavelet modeling. The proposed networks are tested on real data from 12 T1DM patients and also simulated data from 33 virtual patients with an UVa/ Padova simulator, an approved simulator by the US Food and Drug Administration.

Results:

A comparison study is performed in terms of new glucose-based assessment metrics, such as gFIT, glucose-weighted form of ESOD_n (gESOD_n), and glucose-weighted R² (gR²). For real patients’ data, the values of the mentioned indices are accomplished as gFIT = 0.97 ± 0.01, gESOD_n = 1.18 ± 0.38, and gR² = 0.88 ± 0.07. HDFWNN, HDWNN and jump NN method showed the prediction error (root mean square error [RMSE]) of 11.23 ± 2.77 mg/dl, 10.79 ± 3.86 mg/dl and 16.45 ± 4.33 mg/dl, respectively.

Conclusion:

Furthermore, the generalized estimating equation and post hoc tests show that proposed models perform better compared with other proposed methods.

Wearable Electrochemical Sensors for the Monitoring and Screening of Drugs

Wearable electrochemical sensors capable of noninvasive monitoring of chemical markers represent a rapidly emerging digital-health technology. Recent advances toward wearable continuous glucose monitoring (CGM) systems have ignited tremendous interest in expanding such sensor technology to other important fields. This article reviews for the first time wearable electrochemical sensors for monitoring therapeutic drugs and drugs of abuse. This rapidly emerging class of drug-sensing wearable devices addresses the growing demand for personalized medicine, toward improved therapeutic outcomes while minimizing the side effects of drugs and the related medical expenses. Continuous, noninvasive monitoring of therapeutic drugs within bodily fluids empowers clinicians and patients to correlate the pharmacokinetic properties with optimal outcomes by realizing patient-specific dose regulation and tracking dynamic changes in pharmacokinetics behavior while assuring the medication adherence of patients. Furthermore, wearable electrochemical drug monitoring devices can also serve as powerful screening tools in the hands of law enforcement agents to combat drug trafficking and support on-site forensic investigations. The review covers various wearable form factors developed for noninvasive monitoring of therapeutic drugs in different body fluids and toward on-site screening of drugs of abuse. The future prospects of such wearable drug monitoring devices are presented with the ultimate goals of introducing accurate real-time drug monitoring protocols and autonomous closed-loop platforms toward precise dose regulation and optimal therapeutic outcomes. Finally, current unmet challenges and existing gaps are discussed for motivating future technological innovations regarding personalized therapy. The current pace of developments and the tremendous market opportunities for such wearable drug monitoring platforms are expected to drive intense future research and commercialization efforts.