RESUMO
Background: In recent decades, the use of artificial intelligence has been widely explored in health care. Similarly, the amount of data generated in the most varied medical processes has practically doubled every year, requiring new methods of analysis and treatment of these data. Mainly aimed at aiding in the diagnosis and prevention of diseases, this precision medicine has shown great potential in different medical disciplines. Laboratory tests, for example, almost always present their results separately as individual values. However, physicians need to analyze a set of results to propose a supposed diagnosis, which leads us to think that sets of laboratory tests may contain more information than those presented separately for each result. In this way, the processes of medical laboratories can be strongly affected by these techniques. Objective: In this sense, we sought to identify scientific research that used laboratory tests and machine learning techniques to predict hidden information and diagnose diseases. Methods: The methodology adopted used the population, intervention, comparison, and outcomes principle, searching the main engineering and health sciences databases. The search terms were defined based on the list of terms used in the Medical Subject Heading database. Data from this study were presented descriptively and followed the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses; 2020) statement flow diagram and the National Institutes of Health tool for quality assessment of articles. During the analysis, the inclusion and exclusion criteria were independently applied by 2 authors, with a third author being consulted in cases of disagreement. Results: Following the defined requirements, 40 studies presenting good quality in the analysis process were selected and evaluated. We found that, in recent years, there has been a significant increase in the number of works that have used this methodology, mainly because of COVID-19. In general, the studies used machine learning classification models to predict new information, and the most used parameters were data from routine laboratory tests such as the complete blood count. Conclusions: Finally, we conclude that laboratory tests, together with machine learning techniques, can predict new tests, thus helping the search for new diagnoses. This process has proved to be advantageous and innovative for medical laboratories. It is making it possible to discover hidden information and propose additional tests, reducing the number of false negatives and helping in the early discovery of unknown diseases.
RESUMO
Workers' intensive use of hand tool cutting in the meat packing industry is a risk factor for occupational health, mainly by mechanical compression of tissues in the upper limbs, which can cause Work-Related Musculoskeletal Disorders (WMSDs). This systematic review aimed to identify the characteristics and measured variables of instrumented knives and determine how they should be designed. The review process and article extractions occurred through an analysis of the (article) titles, keywords and abstracts, followed by reading the full texts by two reviewers independently. Searches were conducted in Medline, Web of Science, Science Direct, Scopus, Ebsco and Engineering Village for articles published in peer-reviewed journals from January 2000 to March 2019, in the English language. The result of (the) search included 1289 potentially eligible studies, with 894 duplicated/triplicated/quadruplicated articles that were excluded, resulting in 404 remaining articles of which 33 were considered eligible, with 36 additional articles, totaling 69 evaluated full texts. After the review, none of the 14 analyzed studies, were rated as having good methodological quality. In addition, four types of instrumented knives were used. Data acquisition was performed in both laboratory and meat processing plants. It is noteworthy that only one knife was submitted to a validation process and that the articles did not provide complete technical information about the knives. The result demonstrated that the cutting force varies within and between subjects, tasks, plants and blade finishings. All knives used some type of electrical connection via cable or wires. Of the articles found, none considered the influences that the workers are subject to when they do not use the same tool daily for data acquisition. Therefore, the development of different types of instrumented knives, with wireless data transmission and more rigorous studies are necessary to expand the knowledge of the cutting force and development of WMSD in slaughterhouse workers who perform meat cutting.
RESUMO
Brazil is the leader in poultry meat exports, in which most products are in the form of cuts. This study analyzed the exertion perception of poultry slaughterhouses workers when performing cutting tasks, as well as the influence of knife sharpness on the risk of developing musculoskeletal disorders by Occupational Repetitive Action (OCRA) method. Participants (n = 101) from three slaughterhouses were asked to rate their perceived exertion on the Borg scale during the cutting task when the knife was well and poorly sharpened. The OCRA results showed that the score for cutting with a dull knife was greater (43.57 ± 13.51) than with a sharp knife (23.79 ± 3.10) (p < 0.001). Consequently, there was a significant increase in the risk level of acquiring upper-limb work-related musculoskeletal disorders (UL-WMSD) by using a "poorly sharpened" knife (29%; p < 0.001; Borg scale 2-8). Thus, maintaining well-sharpened knives for optimal performance of the cutting task (fewer technical actions) is suggested, as well as including knife sharpening in the standard operating procedure to reduce musculoskeletal disorders.