Applying Machine Learning for Intelligent Assessment of Wheelchair Cushions from Pressure Mapping Images.

Pressure ulcers are skin and underlying tissue injuries caused by the cells' lack of oxygen and nutrition due to blood flow obstruction from constant pressure on the skin. It is prevalent in people with motion disabilities, such as wheelchair users. For both prevention and healing, wheelchair users should occasionally change their sitting posture, use cushions that evenly distribute the pressure, or relieve pressure from the sensitive areas. Occupational therapists (OTs) often use pressure mapping systems (PMS) to assess their clients and recommend them a cushion. A cushion with more uniform pressure distribution and fewer pressure concentration points is ranked the highest. This paper offers a novel approach to enhance the objectivity of PMS readings and rankings for OTs. Our method relies on image segmentation techniques to generate quantifiable measures for cushions assessment. We implemented a sequential process to generate a score representing a cushion's suitability for an individual, which begins with PMS image segmentation using machine learning, followed by a deep learning algorithm for identifying high-risk pressure points. We introduced a Cushion Index for quantifying and ranking the cushions. Clinical Relevance- By selecting proper cushions for wheelchair users, the risk of developing PUs is reduced.

Comparison of risk assessment tools for cardiovascular diseases: results of an Iranian cohort study.

OBJECTIVES: Several popular cardiovascular risk assessment tools have been developed in Western countries; however, the predictive abilities of these tools have not been evaluated in Middle Eastern countries. The present study aimed to determine the abilities of cardiovascular risk assessment tools in a population-based study in Northern Iran. STUDY DESIGN: Population-based cohort study in Northern Iran. METHODS: In total, 2883 individuals (1629 men and 1254 women), aged 40-74 years, were included in the study. We determined the predictive abilities of the American College of Cardiology/American Heart Association (ACC/AHA) risk prediction tool, the Framingham general cardiovascular risk profile in primary care settings, and the Systematic Coronary Risk Evaluation (SCORE) equations for low- and high-risk European countries. Receiver operating characteristic (ROC) analysis was used to determine the predictive abilities of these four risk assessment tools. RESULTS: Based on areas under curve (AUC) values and related 95% confidence intervals (95% CIs), the discriminative abilities of the ACC/AHA tool, the Framingham approach, and the SCORE for low- and high-risk European countries to estimate non-fatal cardiovascular disease (CVD) events were 0.6625, 0.6517, 0.6476 and 0.6458, respectively, in men, and 0.7722, 0.7525, 0.7330 and 0.7331, respectively, in women. Moreover, the abilities of these four tools to estimate fatal CVD events were found to be 0.8614, 0.8329, 0.7996 and 0.7988 in men, and 0.8779, 0.8372, 0.8535 and 0.8518 in women, respectively. CONCLUSIONS: The cardiovascular risk assessment tools investigated in this study showed acceptable predictive abilities in women. The ACC/AHA approach showed slightly better performance compared with the SCORE tool; however, the SCORE tool benefited from the lowest cost compared with all the other tools.

Soil nitrogen accumulation, denitrification potential, and carbon source tracing in bioretention basins.

Bioretention basins are one of the most commonly used green stormwater features, with the potential to accumulate significant levels of nitrogen (N) in their soil and to permanently remove it through denitrification. Many studies have investigated the N removal potential of bioretention basins through the assessment of inflow and outflow concentrations. However, their long-term N removal through soil accumulation and denitrification potential is less known. This study investigated the temporal variation of total N (TN) accumulation and denitrification potential in soils of 25 bioretention basins within a 13-year soil chronosequence, in a subtropical climate in Australia. The denitrification potential of a subset of seven bioretention basins was investigated in accompaniment with nutrient and soil characteristics. Additionally, stable isotopes (δ13C and δ15N) were used to assess temporal changes in the soil composition as well as to identify the sources of carbon (C) into these basins. Over 13 years of operation, TN accumulated faster in the top 5 cm of soil than deeper soils. Soil TN density was highest in the top 5 cm with an average of 1.4 kg N m-3, which was about two times higher than deeper soils. Site age and soil texture were the best predictors of soil TN density and denitrification (1 to 9.7 mg N m-2 h-1). The isotope values were variable among basins. Low δ15N values in young basins (-1.02‰) suggested fixation as the main source of N, while older basins had higher δ15N, indicating higher denitrification. Bioretention plants were the primary source of soil C; although the occurrence of soil amendment also contributed to the C pool. To improve the performance of these bioretention basins, we recommend increasing vegetation at initial years after construction, and enhancing more frequent anaerobic conditions in the high soil profile. These two conditions can improve denitrification potential, and thus the performance of these basins for improving water quality.