Supervised Machine Learning-Based Models for Predicting Raised Blood Sugar.

Raised blood sugar (hyperglycemia) is considered a strong indicator of prediabetes or diabetes mellitus. Diabetes mellitus is one of the most common non-communicable diseases (NCDs) affecting the adult population. Recently, the prevalence of diabetes has been increasing at a faster rate, especially in developing countries. The primary concern associated with diabetes is the potential for serious health complications to occur if it is not diagnosed early. Therefore, timely detection and screening of diabetes is considered a crucial factor in treating and controlling the disease. Population screening for raised blood sugar aims to identify individuals at risk before symptoms appear, enabling timely intervention and potentially improved health outcomes. However, implementing large-scale screening programs can be expensive, requiring testing, follow-up, and management resources, potentially straining healthcare systems. Given the above facts, this paper presents supervised machine-learning models to detect and predict raised blood sugar. The proposed raised blood sugar models utilize diabetes-related risk factors including age, body mass index (BMI), eating habits, physical activity, prevalence of other diseases, and fasting blood sugar obtained from the dataset of the STEPwise approach to NCD risk factor study collected from adults in the Palestinian community. The diabetes risk factor obtained from the STEPS dataset was used as input for building the prediction model that was trained using various types of supervised learning classification algorithms including random forest, decision tree, Adaboost, XGBoost, bagging decision trees, and multi-layer perceptron (MLP). Based on the experimental results, the raised blood sugar models demonstrated optimal performance when implemented with a random forest classifier, yielding an accuracy of 98.4%. Followed by the bagging decision trees, XGBoost, MLP, AdaBoost, and decision tree with an accuracy of 97.4%, 96.4%, 96.3%, 95.2%, and 94.8%, respectively.

A New Method for Detecting Dehydration of the Human Body Using Non-Contact Millimeter Wave Radiometry.

Dehydration is a common problem in the aging population. Medical professionals can detect dehydration using either blood or urine tests. This requires experimental tests in the lab as well as urine and blood samples to be obtained from the patients. This paper proposed 100 GHz millimeter wave radiometry for early detection of dehydration. Reflectance measurements were performed on healthy and dehydrated patients of both genders (120 males and 80 females) in the aging population. Based on the cause of dehydration, the patient groups were divided into three categories: (1) patients dehydrated due to less thirst sensation, (2) patients dehydrated due to illnesses (vomiting and diarrhea), and (3) patients dehydrated due to diabetes. Reflectance measurements were performed on eight locations: (1) the palm, (2) the back of the hand, (3) the fingers, (4) the inner wrist, (5) the outer wrist, (6) the volar side of the arm, (7) the dorsal surface of the arm, and (8) the elbow. Skin dehydrated due to vomiting and diarrhea was found to have lower reflectance at all the measurement locations compared with healthy and other types of dehydrated skin. The elbow region showed the highest difference in reflectance between healthy and dehydrated skin. This indicates that radiometric sensitivity is sufficient to detect dehydration in a few seconds. This will reduce the patient's waiting time and the healthcare professional's intervention time as well as allow early treatment of dehydration, thus avoiding admission to hospitals.

Systematic Review for Risks of Pressure Injury and Prediction Models Using Machine Learning Algorithms.

Pressure injuries are increasing worldwide, and there has been no significant improvement in preventing them. This study is aimed at reviewing and evaluating the studies related to the prediction model to identify the risks of pressure injuries in adult hospitalized patients using machine learning algorithms. In addition, it provides evidence that the prediction models identified the risks of pressure injuries earlier. The systematic review has been utilized to review the articles that discussed constructing a prediction model of pressure injuries using machine learning in hospitalized adult patients. The search was conducted in the databases Cumulative Index to Nursing and Allied Health Literature (CINAHIL), PubMed, Science Direct, the Institute of Electrical and Electronics Engineers (IEEE), Cochrane, and Google Scholar. The inclusion criteria included studies constructing a prediction model for adult hospitalized patients. Twenty-seven articles were included in the study. The defects in the current method of identifying risks of pressure injury led health scientists and nursing leaders to look for a new methodology that helps identify all risk factors and predict pressure injury earlier, before the skin changes or harms the patients. The paper critically analyzes the current prediction models and guides future directions and motivations.

Early Detection of Skin Disorders and Diseases Using Radiometry.

Skin diseases and disorders have a significant impact on people's health and quality of life. Current medical practice suggests different methodologies for detecting and diagnosing skin diseases and conditions. Most of these require medical tests, laboratory analyses, images, and healthcare professionals to assess the results. This consumes time, money, and effort, and the waiting time is stressful for the patient. Therefore, it is an essential requirement to develop a new automatic method for the non-invasive diagnosis of skin diseases and disorders without the need for healthcare professionals or being in a medical clinic. This research proposes millimeter-wave (MMW) radiometry as a non-contact sensor for the non-invasive diagnosis of skin diseases and conditions. Reflectance measurements performed using 90 GHz radiometry were conducted on two samples of participants; sample 1 consisted of 60 participants (30 males and 30 females) with healthy skin, and sample 2 contained 60 participants (30 males and 30 females) suffering from skin diseases and conditions, which were: basal cell carcinoma (BCC), squamous cell carcinoma (SCC), burn wounds, and eczema. Radiometric measurements show substantial differences in reflectance in the range of 0.02-0.27 between healthy and unhealthy regions of the skin on the same person. These results indicate that radiometry, as a non-contact sensor, can identify and distinguish between healthy and diseased regions of the skin. This indicates the potential of using radiometry as a non-invasive technique for the early detection of skin diseases and disorders.

Passive Millimeter-Wave Imaging for Burns Diagnostics under Dressing Materials.

This paper presents a feasibility study of using a passive millimeter-wave imaging (PMMWI) system to assess burn wounds and the potential for monitoring the healing process under dressing materials, without their painful removal. Experimental images obtained from ex vivo porcine skin samples indicate that a ThruVision passive imager operating over the band 232-268 GHz can be used for diagnosing burns and for potentially monitoring the healing under dressing materials. Experimental images show that single and multiple burns are observed throughout dressing materials. As the interaction of millimeter-wave (MMW) radiation with the human body is almost exclusively with the skin, the major outcomes of the research are that PMMWI is capable of discriminating burn-damaged skin from unburned skin, and these measurements can be made through bandages without the imager making any physical contact with the skin or the bandage. This highlights the opportunity that the healing of burn wounds can be assessed and monitored without the removal of dressing materials. The key innovation in this work is in detecting single and multiple burns under dressing materials in noncontact with the skin and without exposing the skin to any type of manmade radiation (i.e., passive sensing technology). These images represent the first demonstration of burns wound under dressing materials using a passive sensing imager.

The Reflectance of Human Skin in the Millimeter-Wave Band.

The millimeter-wave band is an ideal part of the electromagnetic radiation to diagnose human skin conditions because this radiation interacts only with tissue down to a depth of a millimetre or less over the band range from 30 GHz to 300 GHz. In this paper, radiometry is used as a non-contact sensor for measuring the human skin reflectance under normal and wet skin conditions. The mean reflectance of the skin of a sample of 50 healthy participants over the (80-100) GHz band was found to be ~0.615 with a standard deviation of ~0.088, and an experimental measurement uncertainty of ±0.005. The thinner skin regions of the back of the hand, the volar forearms and the inner wrist had reflectances 0.068, 0.068 and 0.062 higher than the thicker skin regions of the palm of the hand, the dorsal forearm and the outer wrist skin. Experimental measurements of human skin reflectance in a normal and a wet state on the back of the hand and the palm of the hand regions indicated that the mean differences in the reflectance before and after the application of water were ~0.078 and ~0.152, respectively. These differences were found to be statistically significant as assessed using t-tests (34 paired t-tests and six independent t-tests were performed to assess the significance level of the mean differences in the reflectance of the skin). Radiometric measurements in this paper show the quantitative variations in the skin reflectance between locations, sexes, and individuals. The study reveals that these variations are related to the skin thickness and water content, a capability that has the potential to allow radiometry to be used as a non-contact sensor to detect and monitor skin conditions such as eczema, psoriasis, malignancy, and burn wounds.

Synthetic Aperture Radar Imaging for Burn Wounds Diagnostics.

The need for technologies to monitor the wound healing under dressing materials has led us to investigate the feasibility of using microwave and millimetre wave radiations due to their sensitivity to water, non- ionising nature, and transparency to dressing materials and clothing. This paper presents synthetic aperture radar (SAR) images obtained from an active microwave and millimetre wave scanner operating over the band 15-40 GHz. Experimental images obtained from porcine skin samples with the presence of dressing materials and after the application of localised heat treatments reveal that SAR images can be used for diagnosing burns and for potentially monitoring the healing under dressing materials. The experimental images were extracted separately from the amplitude and phase measurements of the input reflection coefficient (S11). The acquired images indicate that skin and burns can be detected and observed through dressing materials as well as features of the skin such as edges, irregularities, bends, burns, and variation in the reflectance of the skin. These unique findings enable a microwave and millimetre-wave scanner to be used for evaluating the wound healing progress under dressing materials without their often-painful removal: a capability that will reduce the cost of healthcare, distress caused by long waiting hours, and the healthcare interventional time.

Assessment of Bandaged Burn Wounds Using Porcine Skin and Millimetric Radiometry.

This paper describes the experimental setup and measurements of the emissivity of porcine skin samples over the band of 80-100 GHz. Measurements were conducted on samples with and without dressing materials and before and after the application of localized heat treatments. Experimental measurements indicate that the differences in the mean emissivity values between unburned skin and burned damaged skin was up to ~0.28, with an experimental measurement uncertainty of ±0.005. Measured differences in the mean emissivity values between unburned and burn damaged skin increases with the depth of the burn, indicating a possible non-contact technique for assessing the degree of a burn. The mean emissivity of the dressed burned skin was found to be slightly higher than the undressed burned skin, typically ~0.01 to ~0.02 higher. This indicates that the signature of the burn caused by the application of localized heat treatments is observable through dressing materials. These findings reveal that radiometry, as a non-contact method, is capable of distinguishing between normal and burn-damaged skin under dressing materials without their often-painful removal. This indicates the potential of using millimeter wave (MMW) radiometry as a new type of medical diagnostic to monitor burn wounds.

Millimeter-wave emissivity as a metric for the non-contact diagnosis of human skin conditions.

A half-space electromagnetic model of human skin over the band 30-300 GHz was constructed and used to model radiometric emissivity. The model showed that the radiometric emissivity rose from 0.4 to 0.8 over this band, with emission being localized to a layer approximately one millimeter deep in the skin. Simulations of skin with differing water contents associated with psoriasis, eczema, malignancy, and thermal burn wounds indicated radiometry could be used as a non-contact technique to detect and monitor these conditions. The skin emissivity of a sample of 30 healthy volunteers, measured using a 95 GHz radiometer, was found to range from 0.2 to 0.7, and the experimental measurement uncertainty was ±0.002. Men on average were found to have an emissivity 0.046 higher than those of women, a measurement consistent with men having thicker skin than women. The regions of outer wrist and dorsal forearm, where skin is thicker, had emissivities 0.06-0.08 higher than the inner wrist and volar forearms where skin is generally thinner. Recommendations are made to develop a more sophisticated model of the skin and to collect larger data sets to obtain a deeper understanding of the signatures of human skin in the millimeter wave band. Bioelectromagnetics. 38:559-569, 2017. © 2017 The Authors. Bioelectromagnetics published by Wiley Periodicals, Inc.