Diabetes Detection and Management through Photoplethysmographic and Electrocardiographic Signals Analysis: A Systematic Review.

(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.

Risk assessment of diabetic retinopathy with machine and deep learning models with PPG signals and PWV.

Retinopathy is one of the most common micro vascular impairments in diabetic subjects. Elevated blood glucose leads to capillary occlusion, provoking the uncontrolled increase in local growth of new vessels in the retina. When left untreated, it can lead to blindness. Traditional approaches for retinopathy detection require expensive devices and high specialized personnel. Being a microvascular complication, the retinopathy could be detected using the photoplethysmography (PPG) technology. In this paper we investigate the predictive value of the pulse wave velocity and PPG signal analysis with machine and deep learning approaches to detect retinopathy in diabetic subjects. PPG signals and pulse wave velocity (PWV) showed promising results in assessing the diabetic retinopathy. The best performances were scored by a LightGBM based model trained over a subset of the available dataset obtaining 80% of specificity and sensitivity.Clinical relevance- PPG based retinopathy detection could make the retinopathy detection more accessible since it does not need neither expensive devices for signal acquisition nor highly specialized personnel to be interpreted.

Clustered photoplethysmogram pulse wave shapes and their associations with clinical data.

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.

Adversarial multi-source transfer learning in healthcare: Application to glucose prediction for diabetic people.

BACKGROUND AND OBJECTIVES: Deep learning has yet to revolutionize general practices in healthcare, despite promising results for some specific tasks. This is partly due to data being in insufficient quantities hurting the training of the models. To address this issue, data from multiple health actors or patients could be combined by capitalizing on their heterogeneity through the use of transfer learning. METHODS: To improve the quality of the transfer between multiple sources of data, we propose a multi-source adversarial transfer learning framework that enables the learning of a feature representation that is similar across the sources, and thus more general and more easily transferable. We apply this idea to glucose forecasting for diabetic people using a fully convolutional neural network. The evaluation is done by exploring various transfer scenarios with three datasets characterized by their high inter and intra variability. RESULTS: While transferring knowledge is beneficial in general, we show that the statistical and clinical accuracies can be further improved by using of the adversarial training methodology, surpassing the current state-of-the-art results. In particular, it shines when using data from different datasets, or when there is too little data in an intra-dataset situation. To understand the behavior of the models, we analyze the learnt feature representations and propose a new metric in this regard. Contrary to a standard transfer, the adversarial transfer does not discriminate the patients and datasets, helping the learning of a more general feature representation. CONCLUSION: The adversarial training framework improves the learning of a general feature representation in a multi-source environment, enhancing the knowledge transfer to an unseen target. The proposed method can help improve the efficiency of data shared by different health actors in the training of deep models.

Transfer learning of CNN-based signal quality assessment from clinical to non-clinical PPG signals.

Photoplethysmography (PPG) is a non-invasive and cost-efficient optical technique used to assess blood volume variation inside the micro-circulation. PPG technology is widely used in a variety of clinical and non-clinical devices in order to investigate the cardiovascular system. One example of clinical PPG device is the pulse oxymeter, while non-clinical PPG devices include smartphones and smartwatches. Such a wide diffusion of PPG devices generates plenty of different PPG signals that differ from each other. In fact, intrinsic device characteristics strongly influence PPG waveform. In this paper we investigate transfer learning approaches on a Covolutional Neural Network based quality assessment method in order to generalize our model across different PPG devices. Our results show that our model is able to classify accurately signal quality over different PPG datasets while requiring a small amount of data for fine-tuning.Clinical relevance- A precise detection and extraction of high quality PPG segments could enhance significantly the reliability of the medical analysis based on the signal.

Age-Related Evolution Patterns in Online Handwriting.

Characterizing age from handwriting (HW) has important applications, as it is key to distinguishing normal HW evolution with age from abnormal HW change, potentially triggered by neurodegenerative decline. We propose, in this work, an original approach for online HW style characterization based on a two-level clustering scheme. The first level generates writer-independent word clusters from raw spatial-dynamic HW information. At the second level, each writer's words are converted into a Bag of Prototype Words that is augmented by an interword stability measure. This two-level HW style representation is input to an unsupervised learning technique, aiming at uncovering HW style categories and their correlation with age. To assess the effectiveness of our approach, we propose information theoretic measures to quantify the gain on age information from each clustering layer. We have carried out extensive experiments on a large public online HW database, augmented by HW samples acquired at Broca Hospital in Paris from people mostly between 60 and 85 years old. Unlike previous works claiming that there is only one pattern of HW change with age, our study reveals three major aging HW styles, one specific to aged people and the two others shared by other age groups.