The automated classification of heart sounds plays a significant role in the diagnosis of cardiovascular diseases (CVDs). With the recent introduction of medical big data and artificial intelligence technology, there has been an increased focus on the development of deep learning approaches for heart sound classification. However, despite significant achievements in this field, there are still limitations due to insufficient data, inefficient training, and the unavailability of effective models. With the aim of improving the accuracy of heart sounds classification, an in-depth systematic review and an analysis of existing deep learning methods were performed in the present study, with an emphasis on the convolutional neural network (CNN) and recurrent neural network (RNN) methods developed over the last five years. This paper also discusses the challenges and expected future trends in the application of deep learning to heart sounds classification with the objective of providing an essential reference for further study.

https://www.mdpi.com/1099-4300/23/6/667/pdf

Deep Learning Methods for Heart Sounds Classification: A Systematic Review

The measurement of glucose concentration finds interesting potential applications in both industry and biomedical contexts. Among the proposed solutions, the use of microwave planar resonant sensors has led to remarkable scientific activity during the last years. These sensors rely on the changes in the dielectric properties of the medium due to variations in the glucose concentration. These devices show electrical responses dependent on the surrounding dielectric properties, and therefore the changes in their response can be related to variations in the glucose content. This work shows an up-to-date review of this sensing approach after more than one decade of research and development. The attempts involved are sorted by the sensing parameter, and the computation of a common relative sensitivity to glucose is proposed as general comparison tool. The manuscript also discusses the key points of each sensor category and the possible future lines and challenges of the sensing approach.

Microwave Planar Resonant Solutions for Glucose Concentration Sensing: A Systematic Review

Collaborative Drought Monitoring and Analysis: Examples from the NOAA National Centers for Environmental Information

Diabetes is a chronic and, according to the state of the art, an incurable disease. Therefore, to treat diabetes, regular blood glucose monitoring is crucial since it is mandatory to mitigate the risk and incidence of hyperglycemia and hypoglycemia. Nowadays, it is common to use blood glucose meters or continuous glucose monitoring via stinging the skin, which is classified as invasive monitoring. In recent decades, non-invasive monitoring has been regarded as a dominant research field. In this paper, electrochemical and electromagnetic non-invasive blood glucose monitoring approaches will be discussed. Thereby, scientific sensor systems are compared to commercial devices by validating the sensor principle and investigating their performance utilizing the Clarke error grid. Additionally, the opportunities to enhance the overall accuracy and stability of non-invasive glucose sensing and even predict blood glucose development to avoid hyperglycemia and hypoglycemia using post-processing and sensor fusion are presented. Overall, the scientific approaches show a comparable accuracy in the Clarke error grid to that of the commercial ones. However, they are in different stages of development and, therefore, need improvement regarding parameter optimization, temperature dependency, or testing with blood under real conditions. Moreover, the size of scientific sensing solutions must be further reduced for a wearable monitoring system.

/pdf/commercial-and-scientific-solutions-for-blood-glucose-2l33ztg2.pdf

Commercial and Scientific Solutions for Blood Glucose Monitoring—A Review

Biosensors have potentially revolutionized the biomedical field. Their portability, cost-effectiveness, and ease of operation have made the market for these biosensors to grow rapidly. Diabetes mellitus is the condition of having high glucose content in the body, and it has become one of the very common conditions that is leading to deaths worldwide. Although it still has no cure or prevention, if monitored and treated with appropriate medication, the complications can be hindered and mitigated. Glucose content in the body can be detected using various biological fluids, namely blood, sweat, urine, interstitial fluids, tears, breath, and saliva. In the past decade, there has been an influx of potential biosensor technologies for continuous glucose level estimation. This literature review provides a comprehensive update on the recent advances in the field of biofluid-based sensors for glucose level detection in terms of methods, methodology and materials used.

/pdf/recent-advancement-in-biofluid-based-glucose-sensors-using-2xfgcp8e.pdf

Recent Advancement in Biofluid-Based Glucose Sensors Using Invasive, Minimally Invasive, and Non-Invasive Technologies: A Review

This paper proposes a robust and real-time capable algorithm for classification of the firstand second heart sounds. The classification algorithm is based on the evaluation of the envelope curveof the phonocardiogram. For the evaluation, in contrast to other studies, measurements on twelveprobands were conducted in different physiological conditions. Moreover, for each measurement theauscultation point, posture and physical stress were varied. The proposed envelope-based algorithmis tested with two different methods for envelope curve extraction: the Hilbert transform andthe short-time Fourier transform. The performance of the classification of the first heart soundsis evaluated by using a reference electrocardiogram. Overall, by using the Hilbert transform,the algorithm has a better performance regarding the F1-score and computational effort. Theproposed algorithm achieves for the S1 classification an F1-score up to 95.7% and in average 90.5 %.The algorithm is robust against the age, BMI, posture, heart rate and auscultation point (exceptmeasurements on the back) of the subjects. The ECG and PCG records are available from the authors.

https://www.mdpi.com/1424-8220/20/4/972/pdf

A Robust and Real-Time Capable Envelope-Based Algorithm for Heart Sound Classification: Validation under Different Physiological Conditions.

Abstract In this paper, the impact of interference due to the geomagnetic field on a static magnetic localization setup for capsule endoscopy, which is suitable for a wearable application, was investigated. For this purpose, a study was carried out in which the average abdomen size of 15 subjects was evaluated. With the determined geometry values, a setup consisting of three elliptical sensor rings was modeled. Simulations were performed, where the magnetic flux density was evaluated at the sensors by using different-sized magnets. The measured values were compared with each other and the geomagnetic flux density. The results revealed that the measured values were for all evaluated magnet sizes of the order of the geomagnetic flux density, which is problematic since the calibration of sensors is no longer valid if the orientation of the wearable sensor array is changed. However, it is suggested that a differential measurement is suitable for the proposed system and could reduce static interference caused by the geomagnetic field.

/pdf/evaluation-of-the-impact-of-static-interference-on-an-15edr5buu8.pdf

Evaluation of the Impact of Static Interference on an Empirical Data Based Static Magnetic Localization Setup for Capsule Endoscopy

Magnetic localization is an excellent candidate for localization of capsule endoscopes. A small magnet is embedded into the capsule, and its magnetic field is measured at a sensor array around the patient’s abdomen. However, relative movement between the abdomen and the array causes high localization errors. In this study, an innovative movement compensation method is proposed. A rigid array comprising 12 sensors was used to localize a permanent magnet. Furthermore, two orthogonal reference coils fed with a low-frequency signal were assumed to be fixed at the abdomen. The coils were alternately switched on and off, and thus, all three magnetic objects were separately localized since their magnetic fields can be distinguished in the time and frequency domains. A reference coordinate system was set up with the coils, in which the magnet was localized. The proposed compensation method was evaluated for relative rotations and displacements between the sensors and the three magnetic objects. Moreover, the compensation method was evaluated for two reference magnets and compared with the coil-based approach. The mean position error was reduced by approximately a factor of 10 from 41.5 ± 15.5 to 3.8 ± 1.1 mm, respectively, and the orientation error did not exceed 3° for the coil-based compensation method. In contrast, with two reference magnets, the mean position and orientation errors were higher than 30 mm and 20°, respectively. Consequently, it was shown that the coil-based method is the next step toward a wearable magnetic localization system to compensate for relative movement.

A Compensation Method for Relative Movement Between a Sensor Array and the Abdomen for Magnetic Localization of Capsule Endoscopes

Wireless capsule endoscopy is a promising medical application and a potential alternative to conventional endoscopy. A small capsule with an integrated camera for recording a video is swallowed by a patient allowing gastrointestinal diagnosis. It is of particular interest for doctors that a certain video frame is correlated to the precise location of the capsule within the gastrointestinal tract. Static magnetic localization is well-established for that purpose and the localization method is based on the magnetic dipole model. Generally, the dipole model is only valid for sufficiently large distances from the magnet. In this paper, simulations in which the magnetic flux density generated by different-sized permanent magnets and different sized computational domains was compared to the magnetic dipole model by simulations in COMSOL Multiphysics ®. The computational domain dimensions, as well as the ratio of the length and diameter of the magnet, were optimized to fit the magnetic flux density generated by the magnet with the dipole mode. The distance from the magnet, for which the dipole model is sufficiently accurate, was determined. Subsequently, the standard static magnetic localization method was applied to the proposed empirical data-based localization setup with different parameters. The results revealed, that the localization performance was significantly improved by applying the optimized parameters.

/pdf/performance-optimization-of-a-differential-method-for-o4fjepaoul.pdf

Samuel Zeising

Papers

Commercial and Scientific Solutions for Blood Glucose Monitoring—A Review

A Robust and Real-Time Capable Envelope-Based Algorithm for Heart Sound Classification: Validation under Different Physiological Conditions.

Evaluation of the Impact of Static Interference on an Empirical Data Based Static Magnetic Localization Setup for Capsule Endoscopy

A Compensation Method for Relative Movement Between a Sensor Array and the Abdomen for Magnetic Localization of Capsule Endoscopes

Performance Optimization of a Differential Method for Localization of Capsule Endoscopes