Toward Detecting Infection Incidence in People With Type 1 Diabetes Using Self-Recorded Data (Part 1): A Novel Framework for a Personalized Digital Infectious Disease Detection System (Preprint)

Abstract

BACKGROUND Type 1 diabetes mellitus is a blood glucose (BG) metabolic disorder, which is caused by deficiencies of insulin secretion from pancreatic cells. People with type 1 diabetes often experience prolonged hyperglycemia episodes upon infection incidences. Despite the fact that patients increasingly gather data about themselves, there are no solid findings to what extent the key parameters of BG dynamics are affected during infection incidences to support the effort towards developing a digital infectious disease detection system. OBJECTIVE The objective of the study is to retrospectively analyze the effect of infection incidences and pinpoint optimal parameters that can effectively be used as input variables for developing an infection detection algorithm. Moreover, to provide a general framework regarding how a digital infectious disease detection system can be designed using self-recorded data from people with type 1 diabetes as a secondary source of information. METHODS We retrospectively analyzed high precision self-recorded data of 10 patient years captured within the longitudinal records of 3 people with type 1 diabetes. Getting such a rich and big dataset from large number of participants are extremely expensive and difficult to acquire, if not impossible. The participants were 2 males and 1 female with an average age of 34  13.2 years. The dataset incorporates BG levels, insulin, carbohydrate and self-reported events of infections. We investigated the temporal evolution and probability distribution of BG levels, injected insulin, carbohydrate intake, and insulin to carbohydrate ratio within a specified timeframe (weekly, daily and hourly). All the experiments were carried out using MATLAB® 2018a (Mathworks, Inc, Natwick, MA). RESULTS Our analysis demonstrated that upon infection incidences, there is a dramatic shift in the operating point of the individual BG dynamics in all the timeframes (weekly, daily and hourly), which clearly violate the usual norm of BG dynamics. During regular/normal situations, BG levels usually lower when there is a significant increase in insulin injection and reduction in carbohydrate consumption. However, in all of the individual’s infection cases as opposed to the regular/normal days, there were prolonged period with elevated BG levels despite injecting higher insulin and consuming less carbohydrate. For instance, in all the infection week on average, BG levels were elevated by 6.1% and 16%, insulin (bolus) were increased by 42% and 39.3%, carbohydrate consumption were reduced by 19% and 28.1%, and insulin to carbohydrate ratio were raised by 108.7% as compared to pre-infection and post-infection week respectively. CONCLUSIONS Despite the fact that patients increasingly gather data about themselves, there are no solid findings to what extent the key parameters of BG dynamics are affected during infection incidences to support the effort towards developing a digital infectious disease detection system. We presented the effect of infection incidences on key parameters of the BG dynamics along with the necessary framework to exploit the information for realizing a digital infectious disease detection system. The result demonstrated that as compared to the regular/normal days, infection incidence substantially alters the norm of BG dynamics, which are quite significant changes that could possibly be detected through a personalized modelling, e.g. prediction models and anomalies detection algorithms. Generally, we foresee that these findings can benefit the efforts towards building the next generation digital infectious disease detection systems and provoke further thoughts in this challenging field.

A Novel Approach for Continuous Health Status Monitoring and Automatic Detection of Infection Incidences in People With Type 1 Diabetes Using Machine Learning Algorithms (Part 2): A Personalized Digital Infectious Disease Detection Mechanism (Preprint)

“…In addition, the unsupervised models were also tested, including the LOF [31,33] and the connectivity-based outlier factor (COF) [33,34]. The input variables, average blood glucose levels and ratio of total insulin (bolus) to total carbohydrate, used in training and testing of the models were selected in accordance with the description provided by Woldaregay et al [19], and the ratio was calculated by dividing the total insulin with the total carbohydrate within a specified time-bin. The data set consists of high-precision self-recorded data collected from 3 real subjects (2 males and 1 female; average age 34 [SD 13.2] years) with type 1 diabetes.…”

“…It incorporates blood glucose levels, insulin, carbohydrate information, and self-reported infections cases of influenza (flu) and, mild and light common cold without fever, as shown in Table 1. Exemplar data depicting the model's input features for 2 specific patient years with and without infection are shown in Figures 1-4, and a more detailed description of the input features for 10-patient years with and without infection incidences can be found in Multimedia Appendix 2 [12,19]. The data were resampled and imputed in accordance with the description provided by Woldaregay et al [19], and the preprocessed data were smoothed using a moving average filter of 2 days' (48 hours) window size to remove short-term and small-scale features [19,40,41].…”

“…Type 1 diabetes, also known as insulin-dependent diabetes, is a chronic disease of blood glucose regulation (hemostasis), and is caused by the lack of insulin secretion from pancreatic cells [17,18]. In people with type 1 diabetes, the incidence of infection often results in hyperglycemia and frequent insulin injection [19][20][21][22][23][24][25][26]. Infection-induced anomalies are characterized by violation of the norm of blood glucose dynamics, where blood glucose remains elevated despite taking a higher amount of insulin injection with less carbohydrate consumption [19].…”

“…In people with type 1 diabetes, the incidence of infection often results in hyperglycemia and frequent insulin injection [19][20][21][22][23][24][25][26]. Infection-induced anomalies are characterized by violation of the norm of blood glucose dynamics, where blood glucose remains elevated despite taking a higher amount of insulin injection with less carbohydrate consumption [19]. Despite these potentials, there have been very few studies that focused on detecting infection incidence in individuals with type 1 diabetes using a dedicated personalized health model.…”

“…For this, a one-class classifier and unsupervised models are proposed. The model is expected to detect any deviations from the norm because of infection incidences considering elevated blood glucose level (hyperglycemia incidences) coupled with unusual changes in the insulin-to-carbohydrate ratio, that is, frequent insulin injections and unusual reduction in the amount of carbohydrate intake [19]. Three groups of one-class classifiers and two unsupervised density-based models were explored.…”