mHealth in Sub-Saharan Africa and Europe: Context of current health, healthcare status, and demographic structure.

Introduction: The advent of digital systems and global mobile phone availability presents an opportunity for better healthcare access and equity. However, the disparity in the usage and availability of mHealth systems between Europe and Sub-Saharan Africa (SSA) has not been explored in relation to current health, healthcare status, and demographics. Objective: This study aimed to compare mHealth system availability and use in SSA and Europe in the above-mentioned context. Methods: The study analyzed health, healthcare status, and demographics in both regions. It assessed mortality, disease burden, and universal health coverage. A systematic narrative review was conducted to thoroughly assess available data on mHealth availability and use, guiding future research in the field. Results: SSA is on the verge of stages 2 and 3 in the demographic transition with a youthful population and high birth rate. Communicable, maternal, neonatal, and nutritional diseases contribute to high mortality and disease burden, including child mortality. Europe is on the verge of stages 4 and 5 in the demographic transition with low birth and death rates. Europe's population is old, and non-communicable diseases (NCDs) pose major health challenges. The mHealth literature adequately covers cardiovascular disease/heart failure, and cancer. However, it lacks approaches for respiratory/enteric infections, malaria, and NCDs. Conclusions: mHealth systems in SSA are underutilized than in Europe, despite alignment with the region's demographics and major health issues. Most initiatives in SSA lack implementation depth, with only pilot tests or small-scale implementations. Europe's reported cases highlight actual implementation and acceptability, indicating a strong implementation depth of mHealth systems.

Cervix Type and Cervical Cancer Classification System Using Deep Learning Techniques.

Purpose: Cervical cancer is the 4th most common cancer among women, worldwide. Incidence and mortality rates are consistently increasing, especially in developing countries, due to the shortage of screening facilities, limited skilled professionals, and lack of awareness. Cervical cancer is screened using visual inspection after application of acetic acid (VIA), papanicolaou (Pap) test, human papillomavirus (HPV) test and histopathology test. Inter- and intra-observer variability may occur during the manual diagnosis procedure, resulting in misdiagnosis. The purpose of this study was to develop an integrated and robust system for automatic cervix type and cervical cancer classification using deep learning techniques. Methods: 4005 colposcopy images and 915 histopathology images were collected from different local health facilities and online public datasets. Different pre-trained models were trained and compared for cervix type classification. Prior to classification, the region of interest (ROI) was extracted from cervix images by training and validating a lightweight MobileNetv2-YOLOv3 model to detect the transformation region. The extracted cervix images were then fed to the EffecientNetb0 model for cervix type classification. For cervical cancer classification, an EffecientNetB0 pre-trained model was trained and validated using histogram matched histopathological images. Results: Mean average precision (mAP) of 99.88% for the region of interest (ROI) extraction, and test accuracies of 96.84% and 94.5% were achieved for the cervix type and cervical cancer classification, respectively. Conclusion: The experimental results demonstrate that the proposed system can be used as a decision support tool in the diagnosis of cervical cancer, especially in low resources settings, where the expertise and the means are limited.

Repeatability and reproducibility of prospective motion- and shim corrected 2D glycoCEST MRI.

BACKGROUND: Repeated glycoCEST MRI measurements on the same subject should produce similar results under the same environmental and experimental conditions. However, fluctuations in the static B0 field, which may occur between and within measurements due to heating of the shim iron or subject motion, may alter results and affect reproducibility. Here we investigate the repeatability and reproducibility of glycoCEST measurements and examine the effectiveness of a real-time shim- and motion navigated chemical exchange saturation transfer (CEST) sequence to improve reproducibility. METHODS: In nine subjects, double volumetric navigated (DvNav)-CEST acquisitions in the calf muscle were repeated five times in each of two sessions-the first without correction, and the second with real-time shim- and motion correction applied. In both sessions a dynamically changing field was introduced by running a 5-minute gradient intensive diffusion sequence. We evaluated the effect of the introduced B0 inhomogeneity on the reproducibility of glycoCEST, where the small chemical shift difference between the hydroxyl and bulk water protons at 3 T makes CEST quantification extremely sensitive to magnetic field inhomogeneities. RESULTS: With real-time shim- and motion correction, glycoCEST results were relatively consistent with mean coefficient of variation (CoV) 2.7%±1.4% across all subjects, whereas without correction the results were less consistent with CoV 84%±71%. CONCLUSIONS: Our results demonstrate that real-time shim- and motion correction can mitigate effects of B0 field fluctuations and improve reproducibility of glycoCEST data. This is important when conducting longitudinal studies or when using glycoCEST MRI to assess treatment or physiological responses over time.