m-Health 2.0: New perspectives on mobile health, machine learning and big data analytics.

Mobile health (m-Health) has been repeatedly called the biggest technological breakthrough of our modern times. Similarly, the concept of big data in the context of healthcare is considered one of the transformative drivers for intelligent healthcare delivery systems. In recent years, big data has become increasingly synonymous with mobile health, however key challenges of 'Big Data and mobile health', remain largely untackled. This is becoming particularly important with the continued deluge of the structured and unstructured data sets generated on daily basis from the proliferation of mobile health applications within different healthcare systems and products globally. The aim of this paper is of twofold. First we present the relevant big data issues from the mobile health (m-Health) perspective. In particular we discuss these issues from the technological areas and building blocks (communications, sensors and computing) of mobile health and the newly defined (m-Health 2.0) concept. The second objective is to present the relevant rapprochement issues of big m-Health data analytics with m-Health. Further, we also present the current and future roles of machine and deep learning within the current smart phone centric m-health model. The critical balance between these two important areas will depend on how different stakeholder from patients, clinicians, healthcare providers, medical and m-health market businesses and regulators will perceive these developments. These new perspectives are essential for better understanding the fine balance between the new insights of how intelligent and connected the future mobile health systems will look like and the inherent risks and clinical complexities associated with the big data sets and analytical tools used in these systems. These topics will be subject for extensive work and investigations in the foreseeable future for the areas of data analytics, computational and artificial intelligence methods applied for mobile health.

The evolution and mapping trends of mobile health (m-Health): a bibliometric analysis (1997-2023).

Background: Mobile health (m-Health) is widely acknowledged as a pivotal domain for improving global healthcare and driving its digital health transformation. Despite the vast amount of literature published in recent years, bibliometric studies on m-Health remain limited in scope and coverage. This study presents a comprehensive review of m-Health literature extracted from Scopus and PubMed databases, spanning the period from 1997 to 2023, including publications during the coronavirus disease 2019 (COVID-19) pandemic. Methods: The combined Scopus and PubMed databases were used in this study. The search formula for the literature retrieval used the most appropriate and relevant keywords to m-Health. The bibliometric data importation, extraction and analysis of authors, titles, publication date, publication place, publisher, volume number, issue number, citation count, document type, author keywords, affiliation were all carried out using the 'Biblioshiny', 'EndNote X9®', 'Microsoft Excel®' and 'Microsoft Access®' software tools. Duplicate records were manually identified and removed. Visualization maps illustrating the recurrent keywords, collaboration patterns, and prolific publishing countries were generated using 'VOSviewer®'. Results: A total of 37,470 (20,703 from Scopus and 16,767 from PubMed) publications were selected for the literature analysis. The results provided the definitive literature evidence on the origin of the concept of m-Health in 2003. Significant increase in the publications followed the global surge of smart phones usage in 2007, and the emergence of m-Health applications (Apps) and their global markets and ecosystems. The number of the publications peaked between 2013 and 2022 with most citations in 2022. There was noticeable spike in m-Health literature during the COVID-19 pandemic. The results also showed that most of the highly cited publications, leading institutions, and most prolific authors were predominantly from the developed countries. The USA has the highest number of publications followed by the UK, Australia, Germany, Canada and China, with most of the prolific authors originating from these countries. Conclusions: In conclusion, while there has been a remarkable increase in global m-Health publications since 2003, most of the impactful literature and publications in this area originated from selected countries in the developed world. The study indicates a significant disparity between the published literature from developed compared to the developing countries. Addressing this disparity, further bibliographical studies are required to address these and other literature gaps.

Mobile Health (m-Health) in Retrospect: The Known Unknowns.

For nearly two decades, mobile health or (m-Health) was hailed as the most innovative and enabling area for the digital transformation of healthcare globally. However, this profound vision became a fleeting view since the inception and domination of smart phones, and the reorientation of the concept towards the exclusivity of global smart phone application markets and services. The global consumerization of m-Health in numerous disciplines of healthcare, fitness and wellness areas is unprecedented. However, this divergence between 'mobile health capitalism' and the 'science of mobile health' led to the creation of the 'm-Health schism'. This schism was sustained by the continued domination of the former on the expense of the latter. This also led to increased global m-Health inequality and divide between the much-perceived health and patient benefits and the markets of m-Health. This divergence was more evident in low and middle income (LMIC) countries compared to the developed world. This powerful yet misguided evolution of the m-Health was driven essentially by complex factors. These are presented in this paper as the 'known unknowns' or 'the obvious but sanctioned facts' of m-Health. These issues had surreptitiously contributed to this reorientation and the widening schism of m-Health. The collateral damage of this process was the increased shift towards understanding 'digital health' as a conjecture term associated with mobile health. However, to date, no clear or scientific views are discussed or analyzed on the actual differences and correlation aspects between digital and mobile health. This particular 'known unknown' is presented in detail in order to provide a rapprochement framework of this correlation and valid presentations between the two areas. The framework correlates digital health with the other standard ICT for the healthcare domains of telemedicine, telehealth and e-health. These are also increasingly used in conjunction with digital health, without clear distinctions between these terms and digital health. These critical issues have become timelier and more important to discuss and present, particularly after the world has been caught off guard by the COVID-19 pandemic. The much hyped and the profiteering digital health solutions developed in response of this pandemic provided a modest impact, and the benefits were mostly inadequate in mitigating the massive health, human, and economic impact of this pandemic. This largely commercial reorientation of mobile health was unable not only to predict the severity of the pandemic, but also unable to provide adequate digital tools or effective pre-emptive digital epidemiological shielding and guarding mechanisms against this devastating pandemic. There are many lessons to be learnt from the COVID-19 pandemic from the mobile and digital health perspectives, and lessons must be learnt from the past and to address the critical aspects discussed in this paper for better understanding of mobile health and effective tackling of future global healthcare challenges.

Design and evaluation of a wireless decision-support system for heart rate variability study in haemodialysis follow-up procedures.

In this paper a new wireless decision-support system for haemodialysis patients using heart rate variability (HRV) is presented. The telemedicine system provides connectivity to three participant sites: the general practitioner or nurse at the point of care in the dialysis unit, the remote information and processing server and the cardiologist. At the clinical point of care, the nurse acquires the electrocardiogram (ECG) by using a tailored mobile telecardiology system as well as other relevant physiological information during the clinical procedure, and sends it to the information server. The received information is stored in a secure file server, linked to the patient database and the ECG signal is automatically analyzed by using advanced signal processing tools in the processing server, where a complete clinical results report is generated. The cardiologist can then be linked by means of a web browser to the information server to analyze these results for further clinical diagnosis support. The system has been applied to study HRV in patients undergoing haemodialysis. The clinical report consisted of trends for time- and frequency-domain HRV indexes and other supplementary information automatically calculated, which show the response of the electrical activity of the heart to the dialysis process and that can be helpful for the follow-up of these patients. The telecardiology framework has been successfully evaluated both by the patients and the hospital personnel showing a high compliance with the system. The design and implementation of the telecardiology system have followed the most recent advances in web technologies, biomedical information and storage standards and signal processing techniques. The presented system can be used as a telemedicine tool for clinical diagnosis support and could also be used in other clinical settings.

Enhanced real-time ECG coder for packetized telecardiology applications.

A new real-time compression method for electrocardiogram (ECG) signals has been developed based on the wavelet transform approach. The method is specifically adaptable for packetized telecardiology applications. The signal is segmented into beats and a beat template is subtracted from them, producing a residual signal. Beat templates and residual signals are coded with a wavelet expansion. Compression is achieved by selecting a subset of wavelet coefficients. The number of selected coefficients depends on a threshold which has different definitions depending on the operational mode of the coder. Compression performance has been tested using a subset of ECG records from MIT-BIH Arrhythmia database. This method has been designed for real-time packetized telecardiology scenarios both in wired and wireless environments.

Comparative evaluation of despeckle filtering in ultrasound imaging of the carotid artery.

It is well-known that speckle is a multiplicative noise that degrades the visual evaluation in ultrasound imaging. The recent advancements in ultrasound instrumentation and portable ultrasound devices necessitate the need of more robust despeckling techniques for enhanced ultrasound medical imaging for both routine clinical practice and teleconsultation. The objective of this work was to carry out a comparative evaluation of despeckle filtering based on texture analysis, image quality evaluation metrics, and visual evaluation by medical experts in the assessment of 440 (220 asymptomatic and 220 symptomatic) ultrasound images of the carotid artery bifurcation. In this paper a total of 10 despeckle filters were evaluated based on local statistics, median filtering, pixel homogeneity, geometric filtering, homomorphic filtering, anisotropic diffusion, nonlinear coherence diffusion, and wavelet filtering. The results of this study suggest that the first order statistics filter lsmv, gave the best performance, followed by the geometric filter gf4d, and the homogeneous mask area filter lsminsc. These filters improved the class separation between the asymptomatic and the symptomatic classes based on the statistics of the extracted texture features, gave only a marginal improvement in the classification success rate, and improved the visual assessment carried out by the two experts. More specifically, filters lsmv or gf4d can be used for despeckling asymptomatic images in which the expert is interested mainly in the plaque composition and texture analysis; and filters lsmv, gf4d, or lsminsc can be used for the despeckling of symptomatic images in which the expert is interested in identifying the degree of stenosis and the plaque borders. The proper selection of a despeckle filter is very important in the enhancement of ultrasonic imaging of the carotid artery. Further work is needed to evaluate at a larger scale and in clinical practice the performance of the proposed despeckle filters in the automated segmentation, texture analysis, and classification of carotid ultrasound imaging.

Clinical trials and evaluation of a mobile, robotic tele-ultrasound system.

We have developed a robotic tele-ultrasound system (OTELO) that allows an expert to examine a distant patient by ultrasound. At the expert station, a sonographer controls a virtual probe. Movements are reproduced at the patient station, which may be several kilometres away, on a real probe held by a lightweight robot, which is positioned on the patient by a paramedic. Two medical teams tested the tele-ultrasound system at two different hospitals on a total of 52 patients. Except for some difficulties caused by particular conditions, the diagnosis obtained with the remote scanning system agreed in at least 80% of the cases with the diagnosis made by conventional scanning. The results demonstrate the feasibility and efficiency of the device.

Microarray image enhancement by denoising using stationary wavelet transform.

Microarray imaging is considered an important tool for large scale analysis of gene expression. The accuracy of the gene expression depends on the experiment itself and further image processing. It's well known that the noises introduced during the experiment will greatly affect the accuracy of the gene expression. How to eliminate the effect of the noise constitutes a challenging problem in microarray analysis. Traditionally, statistical methods are used to estimate the noises while the microarray images are being processed. In this paper, we present a new approach to deal with the noise inherent in the microarray image processing procedure. That is, to denoise the image noises before further image processing using stationary wavelet transform (SWT). The time invariant characteristic of SWT is particularly useful in image denoising. The testing result on sample microarray images has shown an enhanced image quality. The results also show that it has a superior performance than conventional discrete wavelet transform and widely used adaptive Wiener filter in this procedure.

Application of wavelet modulus maxima in microarray spots recognition.

This paper presents a novel approach to recognize the microarray image spots. The approach is based on the detection of wavelet modulus maxima in the microarray images. The detected maxima is actually the contour of the spots and thus the spots are recognized precisely. Then, the intensities within the contour of the spots can be obtained with low error rate. The test results on example image show this is an effective approach, especially for those spots with low intensities.

The potential of m-health systems for diabetes management in post conflict regions a case study from Iraq.

The recent developments of m-health technologies particularly in the developing world are increasing sharply due to the importance and accelerated adoption of these technologies in the developing countries. However, there are few if any studies on the effectiveness of mobile health in post conflict regions especially in the Middle East region. In this paper we describe the design, implementation and clinical outcomes of a feasibility study on mobile diabetes management in Basra, Southern Iraq as an exemplar for the effectiveness of mobile health technologies for improved healthcare delivery in similar post conflict regions. The key clinical outcome of this study indicated the lowering of HbA1C levels in the mobile health group indicating the potential of deploying such technologies in these regions where health resources are limited and challenging.

Cross-layer ultrasound video streaming over mobile WiMAX and HSUPA networks.

It is well known that the evolution of 4G-based mobile multimedia network systems will contribute significantly to future mobile healthcare (m-health) applications that require high bandwidth and fast data rates. Central to the success of such emerging applications is the compatibility of broadband networks, such as mobile Worldwide Interoperability For Microwave Access (WiMAX) and High-Speed Uplink Packet Access (HSUPA), and especially their rate adaption issues combined with the acceptable real-time medical quality of service requirements. In this paper, we address the relevant challenges of cross-layer design requirements for real-time rate adaptation of ultrasound video streaming in mobile WiMAX and HSUPA networks. A comparative performance analysis of such approach is validated in two experimental m-health test bed systems for both mobile WiMAX and HSUPA networks. The experimental results have shown an improved performance of mobile WiMAX compared to the HSUPA using the same cross-layer optimization approach.

Cross layer design for optimised region of interest of ultrasound video data over mobile WiMAX.

The application of advanced error concealment techniques applied as a post-process to conceal lost video information in error-prone channels, such as the wireless channel, demand additional processing at the receiver. This increases the delivery delay and needs more computational power. However, in general, only a small region within medical video is of interest to the physician and thus if only this area is considered, the number of computations can be curtailed. In this paper we present a technique whereby the Region of Interest (ROI) specified by the physician is used to delimit the area where the more complex concealment techniques are applied. A cross layer design approach in mobile WiMAX wireless communication environment is adopted in this paper to provide an optimized Quality of Experience (QoE) in the region that matters most to the mobile physician while relaxing the requirements in the background, ensuring real-time delivery. Results show that a diagnostically acceptable Peak Signal-to-Noise-Ratio (PSNR) of about 36 dB can still be achieved within reasonable decoding time.

Comparative analysis of genomic signal processing for microarray data clustering.

Genomic signal processing is a new area of research that combines advanced digital signal processing methodologies for enhanced genetic data analysis. It has many promising applications in bioinformatics and next generation of healthcare systems, in particular, in the field of microarray data clustering. In this paper we present a comparative performance analysis of enhanced digital spectral analysis methods for robust clustering of gene expression across multiple microarray data samples. Three digital signal processing methods: linear predictive coding, wavelet decomposition, and fractal dimension are studied to provide a comparative evaluation of the clustering performance of these methods on several microarray datasets. The results of this study show that the fractal approach provides the best clustering accuracy compared to other digital signal processing and well known statistical methods.

Mobile telemonitoring for achieving tighter targets of blood pressure control in patients with complicated diabetes: a pilot study.

BACKGROUND: Hypertension is a major risk factor for the long-term complications of diabetes. Mobile, self-measurement of blood pressure is emerging as a method to manage blood pressure in general, but its impact in patients with diabetes is unclear. METHODS: We randomized 137 patients with diabetes and hypertension to either mobile telemonitoring (n = 72) or usual care (n = 65). Clinic blood pressure was recorded at baseline and after 6 months. Patients in the intervention arm transmitted weekly blood pressure readings wirelessly, using adapted sensors via mobile phones to a central server. Clinicians received the data in real-time and using a web-based application provided management advice to the patient and their physicians. RESULTS: Systolic blood pressure fell significantly in the patients in the intervention group (mean [95% confidence interval], -6.5 [-0.8 to -12.2] mm Hg; P = 0.027) and remained unchanged in the control group (2.1 [9.3 to -5.0] mm Hg; P = 0.57). Patients within the intervention arm of African origin seemed to benefit more from the intervention. In addition, those who achieved a systolic blood pressure of <120 mm Hg had lower average blood sugars than those with higher readings (7.8 [SD 1.6] vs. 8.9 [SD 2.2] mmol/L; P = 0.02). CONCLUSIONS: In patients with diabetes, mobile telemonitoring has potential for delivering intensified care to improve blood pressure control, and its use may be associated with reduced exposure to hyperglycemia.

Technical and compliance considerations for mobile health self-monitoring of glucose and blood pressure for patients with diabetes.

Self-monitoring of blood glucose is an integral part of diabetes care which may be extended to other biometrics. Cellular and short range communication technologies will be important for the routine usage of these systems. However, the issues of follow-up and patient compliance with these emerging systems have not been yet studied evaluated but could be critical to the adoption of these technologies. We evaluated the impact of mobile telemonitoring on the intensification of care on blood pressure control and exposure to hyperglycaemia in patients with diabetes. We randomised 137 patients with diabetes to either mobile telemonitoring (n = 72) or usual care patients (n = 65) for 9 months. In this paper we present some of the clinical results with focus on blood pressure control hypertension and highlight some of the technical and compliance issues that were encountered.

UK and Canadian perspectives of the effectiveness of mobile diabetes management systems.

The use of mobile technologies for self-monitoring of blood glucose and blood pressure for diabetes patients is becoming increasingly popular worldwide. This is propelled by the proliferation of the wider usage of mobile phones and other wireless technologies and computing platforms in the healthcare sector. Such technologies can play a pivotal role in chronic disease management and patient self-care. There have been several clinical trials in recent years on mobile diabetes management in UK and Canada. However, no studies to date have addressed and correlated the technological and clinical outcomes concerning the use of mobile chronic disease management systems for diabetes from the UK and Canadian perspectives. In this paper we address some of these correlative issues based on similar clinical trials on mobile type-2 diabetes management systems deployed in these two countries. In particular, the outcomes of these trials supported the use of telemonitoring for effective blood pressure control, but telemonitoring was less effective at managing blood glucose control. Some of the clinical results and challenges are presented together with future work and suggestions that aim to validate a generic platform for mobile diabetes management.