(1) Background: Diabetes mellitus (DM) is a chronic, metabolic disease characterized by elevated levels of blood glucose. Recently, some studies approached the diabetes care domain through the analysis of the modifications of cardiovascular system parameters. In fact, cardiovascular diseases are the first leading cause of death in diabetic subjects. Thanks to their cost effectiveness and their ease of use, electrocardiographic (ECG) and photoplethysmographic (PPG) signals have recently been used in diabetes detection, blood glucose estimation and diabetes-related complication detection. This review’s aim is to provide a detailed overview of all the published methods, from the traditional (non machine learning) to the deep learning approaches, to detect and manage diabetes using PPG and ECG signals. This review will allow researchers to compare and understand the differences, in terms of results, amount of data and complexity that each type of approach provides and requires. (2) Method: We performed a systematic review based on articles that focus on the use of ECG and PPG signals in diabetes care. The search was focused on keywords related to the topic, such as “Diabetes”, “ECG”, “PPG”, “Machine Learning”, etc. This was performed using databases, such as PubMed, Google Scholar, Semantic Scholar and IEEE Xplore. This review’s aim is to provide a detailed overview of all the published methods, from the traditional (non machine learning) to the deep learning approaches, to detect and manage diabetes using PPG and ECG signals. This review will allow researchers to compare and understand the differences, in terms of results, amount of data and complexity that each type of approach provides and requires. (3) Results: A total of 78 studies were included. The majority of the selected studies focused on blood glucose estimation (41) and diabetes detection (31). Only 7 studies focused on diabetes complications detection. We present these studies by approach: traditional, machine learning and deep learning approaches. (4) Conclusions: ECG and PPG analysis in diabetes care showed to be very promising. Clinical validation and data processing standardization need to be improved in order to employ these techniques in a clinical environment.

Photopletysmography (PPG) is a non-invasive and well known technology that enables the recording of the digital volume pulse (DVP). Although PPG is largely employed in research, several aspects remain unknown. One of these is represented by the lack of information about how many waveform classes best express the variability in shape. In the literature, it is common to classify DVPs into four classes based on the dicrotic notch position. However, when working with real data, labelling waveforms with one of these four classes is no longer straightforward and may be challenging. The correct identification of the DVP shape could enhance the precision and the reliability of the extracted bio markers. In this work we proposed unsupervised machine learning and deep learning approaches to overcome the data labelling limitations. Concretely we performed a K-medoids based clustering that takes as input 1) DVP handcrafted features, 2) similarity matrix computed with the Derivative Dynamic Time Warping and 3) DVP features extracted from a CNN AutoEncoder. All the cited methods have been tested first by imposing four medoids representative of the Dawber classes, and after by automatically searching four clusters. We then searched the optimal number of clusters for each method using silhouette score, the prediction strength and inertia. To validate the proposed approaches we analyse the dissimilarities in the clinical data related to obtained clusters.

Objective: Screening for Peripheral Artery Disease (PAD) remains a challenge in the prevention and care of patients with arteriosclerosis. The Ankle Brachial Index (ABI) is currently the gold standard. However, ABI is time consuming and requires some expertise to perform which is a limiting factor for global screening. The measurement of the Systolic Rise Time (SRT) of the pulse wave of the lower limb may provide an easier alternative to detect PAD. In a retrospective pilot study, we analyzed the possibility of detecting PAD using the SRT of the toe waveform using the Photo-PlethysmoGraphic signal (PPG). Design and method: We measured 79 subjects (41 patients diagnosed with different stages of PAD and 38 healthy volunteers without known PAD). In each subject, at least one lower limb was assessed with classical ABI. All subjects underwent a PPG assessment on the finger and the toe simultaneously using popmètreâ (Axelife – France). In-house software (JAVA) was used to calculate the SRT of all recorded signals. Results: 146 lower limbs were analyzed including 72 healthy and 74 subjects with PAD. The mean age of the population was 69 ± 12 years with 75% men, 28% diabetics, 47% hypertensive, 49% without clinical PAD defined as stage 0 in this study; 16% in stage 1; 32% in stage 2; 2% in stage 3 and 1% in stage 4 according to the Leriche classification. The SRT cut-off value of 160 ms identifies PAD according to Leriche starting at stage 1 with a sensitivity of 78% vs 73% for ABI < 0.9 and a specificity of 86% vs 87%; a positive predictive value (PPV) of 85% vs 86% and a negative predictive value (NPV) of 79% vs 75%. In addition, the ratio between toe-SRT and finger-SRT cut-off value of 1 identifies PAD with a sensitivity of 76% and a specificity of 74%. Conclusions: SRT measured using a PPG pulse signal of the toe is promising as a facile non-invasive method to diagnose PAD (duration < 14 seconds) and determine PAD stages 1 to 4 with similar specificity and sensitivity as the reference method.