While image-difference metrics show good prediction performance on visual data, they often yield artifact-contaminated results if used as objective functions for optimizing complex image-processing tasks. We investigate in this regard the recently proposed color-image-difference (CID) metric particularly developed for predicting gamut-mapping distortions. We present an algorithm for optimizing gamut mapping employing the CID metric as the objective function. Resulting images contain various visual artifacts, which are addressed by multiple modifications yielding the improved color-image-difference (iCID) metric. The iCID-based optimizations are free from artifacts and retain contrast, structure, and color of the original image to a great extent. Furthermore, the prediction performance on visual data is improved by the modifications.

No abstract

No abstract

No abstract

The Virtual Learning Environment of the Brazilian Health System (AVASUS) is a free and open distance education platform of the Ministry of Health (MS). AVASUS is a scalable virtual learning environment that has surpassed 800,000 users, 2 million enrollments, and 310 courses in its catalog. The objective of this paper was to assess the impacts of the educational offerings on health services and AVASUS course participants' professional practice. This study analyzed data from AVASUS, the Brazilian National Registry of Health Care Facilities (CNES), the Brazilian Occupational Classification (CBO), and a questionnaire applied to 720-course participants from five regions of Brazil. After acquiring and extracting data, computational methods were used for the evaluation process. Only the responses of 462 participants were considered for data analysis, as they had a formal link to CNES. The results showed that respondents recommended 76.2% of AVASUS courses to peers. Accordingly, the quality of educational offerings motivated 81.3% of such recommendations. In addition, 75.6% of course participants who answered the questionnaire also indicated that AVASUS course contents contribute to enhancing existing health services in the health facilities where they work. Finally, 24.6% of all responses mentioned that courses available in AVASUS were essential in offering new health services in such facilities.

Introduction The use of machine learning (ML) techniques in healthcare encompasses an emerging concept that envisages vast contributions to the tackling of rare diseases. In this scenario, amyotrophic lateral sclerosis (ALS) involves complexities that are yet not demystified. In ALS, the biomedical signals present themselves as potential biomarkers that, when used in tandem with smart algorithms, can be useful to applications within the context of the disease. Methods This Systematic Literature Review (SLR) consists of searching for and investigating primary studies that use ML techniques and biomedical signals related to ALS. Following the definition and execution of the SLR protocol, 18 articles met the inclusion, exclusion, and quality assessment criteria, and answered the SLR research questions. Discussions Based on the results, we identified three classes of ML applications combined with biomedical signals in the context of ALS: diagnosis (72.22%), communication (22.22%), and survival prediction (5.56%). Conclusions Distinct algorithmic models and biomedical signals have been reported and present promising approaches, regardless of their classes. In summary, this SLR provides an overview of the primary studies analyzed as well as directions for the construction and evolution of technology-based research within the scope of ALS.

No abstract

IntroductionBrazil has one of the largest prison populations globally, with over 682,000 imprisoned people. Prison health is a public health emergency as it presents increasingly aggravating disease rates, mainly sexually transmitted infections (STI). And this problem already affects both developed and developing nations. Therefore, when thinking about intervention strategies to improve this scenario in Brazil, the course “Health Care for People Deprived of Freedom” (ASPPL), aimed at prison health, was developed. This course was implemented in the Virtual Learning Environment of the Brazilian Health System (AVASUS). Given this context, this study analyzed the aspects associated with massive training through technological mediation and its impacts on prison health.MethodsThis cross-sectional study analyzed data from 8,118 ASPPL course participants. The data analyzed were collected from six sources, namely: (i) AVASUS, (ii) National Registry of Health Care Facilities (CNES), (iii) Brazilian Occupational Classification (CBO), (iv) National Prison Department (DEPEN); (v) Brazilian Institute of Geography and Statistics (IBGE); and the (iv) Brazilian Ministry of Health (MoH), through the Outpatient Information System of the Brazilian National Health System (SIA/SUS). A data processing pipeline was conducted using Python 3.8.9.ResultsThe ASPPL course had 8,118 participants distributed across the five Brazilian regions. The analysis of course evaluation by participants who completed it shows that 5,190 (63.93%) reported a significant level of satisfaction (arithmetic mean = 4.9, median = 5, and standard deviation = 0.35). The analysis revealed that 3,272 participants (40.31%) are health workers operating in distinct levels of care. The prison system epidemiological data shows an increase in syphilis diagnosis in correctional facilities.ConclusionsThe course enabled the development of a massive training model for various health professionals at all care levels and regions of Brazil. This is particularly important in a country with a continental size and a large health workforce like Brazil. As a result, social and prison health impacts were observed.