Advancing Breast Cancer Diagnosis through Breast Mass Images, Machine Learning, and Regression Models.

Breast cancer results from a disruption of certain cells in breast tissue that undergo uncontrolled growth and cell division. These cells most often accumulate and form a lump called a tumor, which may be benign (non-cancerous) or malignant (cancerous). Malignant tumors can spread quickly throughout the body, forming tumors in other areas, which is called metastasis. Standard screening techniques are insufficient in the case of metastasis; therefore, new and advanced techniques based on artificial intelligence (AI), machine learning, and regression models have been introduced, the primary aim of which is to automatically diagnose breast cancer through the use of advanced techniques, classifiers, and real images. Real fine-needle aspiration (FNA) images were collected from Wisconsin, and four classifiers were used, including three machine learning models and one regression model: the support vector machine (SVM), naive Bayes (NB), k-nearest neighbors (k-NN), and decision tree (DT)-C4.5. According to the accuracy, sensitivity, and specificity results, the SVM algorithm had the best performance; it was the most powerful computational classifier with a 97.13% accuracy and 97.5% specificity. It also had around a 96% sensitivity for the diagnosis of breast cancer, unlike the models used for comparison, thereby providing an exact diagnosis on the one hand and a clear classification between benign and malignant tumors on the other hand. As a future research prospect, more algorithms and combinations of features can be considered for the precise, rapid, and effective classification and diagnosis of breast cancer images for imperative decisions.

BMIVPOT, a Fully Automated Version of the Intravenous Pole: Simulation, Design, and Evaluation.

Robotic intravenous poles are automated supportive instrument that needs to be triggered by patients to hold medications and needed supplies. Healthcare engineering of robotic intravenous poles is advancing in order to improve the quality of health services to patients worldwide. Existing intravenous poles in the market were supportive to patients, yet they constrained their movement, consumed the time of both the patient and the nurse, and they were expensive in regard to what they offer. Although robotic poles overcame some of the movement limitations of the commercial/market poles, they were partially automated and did not offer additional technological features. The aim of our work was to develop a fully automated Biomedical Intravenous Pole Robot (BMIVPOT) to resolve the aforementioned limitations and to offer new technological features to intravenous poles, thereby promoting the health services. Several sensors and build-up materials were empirically chosen to be cost-effective and fulfill our needs. The new prototype was divided into three steps: simulated prototype, real implementation of the prototype, and testing and evaluation. Simulation results showed the best qualitative way to fit all the specifications in the robotic system, such as the shape, sensors, and connections in order to provide the proper functionality of the system. Experimental and real results provided the manufactured parts, implemented sensors, and the final robot. Testing the tracking and the flow sensor performances were provided. Evaluation of our Biomedical Intravenous Pole Robot with alternatives showed that our robot outperforms the other poles in many aspects including the features it offers, the percentage of interventions it comprised, the reliability, and cost-effectiveness. The overall percentage of features offered by our Biomedical Intravenous Pole Robot was 60% higher than that offered by peer research poles and 80% higher than that of the market poles. In addition, the average percentage of integration of interventions (architecture, sensor, wireless, tracking, and mechanical) in the Biomedical Intravenous Pole Robot was at least 56% higher than that of the alternative poles. According to the results, Biomedical Intravenous Pole Robot offers a cost-effective price as compared to the others. As a future prospect, we intend to add more features to this prototype in order to enhance it, such as vital signs detection, and improve the tracking system.

A Handy Preterm Infant Incubator for Providing Intensive Care: Simulation, 3D Printed Prototype, and Evaluation.

Preterm infants encounter an abrupt delivery before their complete maturity during the third trimester of pregnancy. Polls anticipate an increase in the rates of preterm infants for 2025, especially in middle- and low-income countries. Despite the abundance of intensive care methods for preterm infants, such as, but not limited to, commercial, transport, embrace warmer, radiant warmer, and Kangaroo Mother Care methods, they are either expensive, lack the most essential requirements or specifications, or lack the maternal-preterm bond. This drove us to carry this original research and innovative idea of developing a new 3D printed prototype of a Handy preterm infant incubator. We aim to provide the most indispensable intensive care with the lowest cost, to bestow low-income countries with the Handy incubator's care, preserve the maternal -preterm's bond, and diminish the rate of mortality. Biomedical features, electronics, and biocompatible materials were utilized. The design was simulated, the prototype was 3D printed, and the outcomes were tested and evaluated. Simulation results showed the best fit for the Handy incubator's components. Experimental results showed the 3D-printed prototype and the time elapsed to obtain it. Evaluation results revealed that the overall performance of Kangaroo Mother Care and the embrace warmer was 75 ± 1.4% and 66.7 ± 1.5%, respectively, while the overall performance of our Handy incubator was 91.7 ± 1.6%, thereby our cost-effective Handy incubator surpassed existing intensive care methods. The future step is associating the Handy incubator with more specifications and advancements.

n-Order and maximum fuzzy similarity entropy for discrimination of signals of different complexity: Application to fetal heart rate signals.

This paper presents two new concepts for discrimination of signals of different complexity. The first focused initially on solving the problem of setting entropy descriptors by varying the pattern size instead of the tolerance. This led to the search for the optimal pattern size that maximized the similarity entropy. The second paradigm was based on the n-order similarity entropy that encompasses the 1-order similarity entropy. To improve the statistical stability, n-order fuzzy similarity entropy was proposed. Fractional Brownian motion was simulated to validate the different methods proposed, and fetal heart rate signals were used to discriminate normal from abnormal fetuses. In all cases, it was found that it was possible to discriminate time series of different complexity such as fractional Brownian motion and fetal heart rate signals. The best levels of performance in terms of sensitivity (90%) and specificity (90%) were obtained with the n-order fuzzy similarity entropy. However, it was shown that the optimal pattern size and the maximum similarity measurement were related to intrinsic features of the time series.

Reducing sojourn points from recurrence plots to improve transition detection: Application to fetal heart rate transitions.

The analysis of biomedical signals demonstrating complexity through recurrence plots is challenging. Quantification of recurrences is often biased by sojourn points that hide dynamic transitions. To overcome this problem, time series have previously been embedded at high dimensions. However, no one has quantified the elimination of sojourn points and rate of detection, nor the enhancement of transition detection has been investigated. This paper reports our on-going efforts to improve the detection of dynamic transitions from logistic maps and fetal hearts by reducing sojourn points. Three signal-based recurrence plots were developed, i.e. embedded with specific settings, derivative-based and m-time pattern. Determinism, cross-determinism and percentage of reduced sojourn points were computed to detect transitions. For logistic maps, an increase of 50% and 34.3% in sensitivity of detection over alternatives was achieved by m-time pattern and embedded recurrence plots with specific settings, respectively, and with a 100% specificity. For fetal heart rates, embedded recurrence plots with specific settings provided the best performance, followed by derivative-based recurrence plot, then unembedded recurrence plot using the determinism parameter. The relative errors between healthy and distressed fetuses were 153%, 95% and 91%. More than 50% of sojourn points were eliminated, allowing better detection of heart transitions triggered by gaseous exchange factors. This could be significant in improving the diagnosis of fetal state.

Coarse-grained multifractality analysis based on structure function measurements to discriminate healthy from distressed foetuses.

This paper proposes a combined coarse-grained multifractal method to discriminate between distressed and normal foetuses. The coarse-graining operation was performed by means of a coarse-grained procedure and the multifractal operation was based on a structure function. The proposed method was evaluated by one hundred recordings including eighty normal foetuses and twenty distressed foetuses. We found that it was possible to discriminate between distressed and normal foetuses using the Hurst exponent, singularity, and Holder spectra.