Computational methods applied to syphilis: where are we, and where are we going?

Syphilis is an infectious disease that can be diagnosed and treated cheaply. Despite being a curable condition, the syphilis rate is increasing worldwide. In this sense, computational methods can analyze data and assist managers in formulating new public policies for preventing and controlling sexually transmitted infections (STIs). Computational techniques can integrate knowledge from experiences and, through an inference mechanism, apply conditions to a database that seeks to explain data behavior. This systematic review analyzed studies that use computational methods to establish or improve syphilis-related aspects. Our review shows the usefulness of computational tools to promote the overall understanding of syphilis, a global problem, to guide public policy and practice, to target better public health interventions such as surveillance and prevention, health service delivery, and the optimal use of diagnostic tools. The review was conducted according to PRISMA 2020 Statement and used several quality criteria to include studies. The publications chosen to compose this review were gathered from Science Direct, Web of Science, Springer, Scopus, ACM Digital Library, and PubMed databases. Then, studies published between 2015 and 2022 were selected. The review identified 1,991 studies. After applying inclusion, exclusion, and study quality assessment criteria, 26 primary studies were included in the final analysis. The results show different computational approaches, including countless Machine Learning algorithmic models, and three sub-areas of application in the context of syphilis: surveillance (61.54%), diagnosis (34.62%), and health policy evaluation (3.85%). These computational approaches are promising and capable of being tools to support syphilis control and surveillance actions.

Osteoporosis screening using machine learning and electromagnetic waves.

Osteoporosis is a disease characterized by impairment of bone microarchitecture that causes high socioeconomic impacts in the world because of fractures and hospitalizations. Although dual-energy X-ray absorptiometry (DXA) is the gold standard for diagnosing the disease, access to DXA in developing countries is still limited due to its high cost, being present only in specialized hospitals. In this paper, we analyze the performance of Osseus, a low-cost portable device based on electromagnetic waves that measures the attenuation of the signal that crosses the medial phalanx of a patient's middle finger and was developed for osteoporosis screening. The analysis is carried out by predicting changes in bone mineral density using Osseus measurements and additional common risk factors used as input features to a set of supervised classification models, while the results from DXA are taken as target (real) values during the training of the machine learning algorithms. The dataset consisted of 505 patients who underwent osteoporosis screening with both devices (DXA and Osseus), of whom 21.8% were healthy and 78.2% had low bone mineral density or osteoporosis. A cross-validation with k-fold = 5 was considered in model training, while 20% of the whole dataset was used for testing. The obtained performance of the best model (Random Forest) presented a sensitivity of 0.853, a specificity of 0.879, and an F1 of 0.859. Since the Random Forest (RF) algorithm allows some interpretability of its results (through the impurity check), we were able to identify the most important variables in the classification of osteoporosis. The results showed that the most important variables were age, body mass index, and the signal attenuation provided by Osseus. The RF model, when used together with Osseus measurements, is effective in screening patients and facilitates the early diagnosis of osteoporosis. The main advantages of such early screening are the reduction of costs associated with exams, surgeries, treatments, and hospitalizations, as well as improved quality of life for patients.

Interventions of Brazil's more doctors program through continuing education for Primary Health Care.

Introduction: Brazil's More Doctors Program, in its training axis, aims to improve medical training for Primary Health Care through interventions related to the reality of the territory. The research presented here analyzed the interventions implemented by Brazil's More Doctors Program physicians, members of the Family Health Continuing Education Program, and the relationship with Primary Health Care programmatic actions. Methodology: The research conducted made use of Text and Data Mining and content analysis. In total, 2,159 reports of interventions from 942 final papers were analyzed. The analysis process was composed of the formation of the corpus; exploration of the materials through text mining; and analysis of the results by inference and interpretation. Results: It was observed that 57% of the physicians worked in the Northeast Region, which was also the region with the most interventions (66.8%). From the analysis of the bigrams, trigrams, and quadrigrams, four constructs were formed: "women's health," "child health," "chronic non-communicable diseases," and "mental health." Terms related to improving access, quality of care, teamwork, and reception were also present among the N-grams. Discussion: The interventions carried out are under the programmatic actions recommended by the Brazilian Ministry of Health for Primary Health Care, also addressing cross-cutting aspects such as Reception, Teamwork, Access Improvement, and Quality of Care, which suggests that the training experience in the Family Health Continuing Education Program reflects on the way these professionals act.

The Text Mining Technique Applied to the Analysis of Health Interventions to Combat Congenital Syphilis in Brazil: The Case of the "Syphilis No!" Project.

Congenital syphilis (CS) remains a threat to public health worldwide, especially in developing countries. To mitigate the impacts of the CS epidemic, the Brazilian government has developed a national intervention project called "Syphilis No." Thus, among its range of actions is the production of thousands of writings featuring the experiences of research and intervention supporters (RIS) of the project, called field researchers. In addition, this large volume of base data was subjected to analysis through data mining, which may contribute to better strategies for combating syphilis. Natural language processing is a form of knowledge extraction. First, the database extracted from the "LUES Platform" with 4,874 documents between 2018 and 2020 was employed. This was followed by text preprocessing, selecting texts referring to the field researchers' reports for analysis. Finally, for analyzing the documents, N-grams extraction (N = 2,3,4) was performed. The combination of the TF-IDF metric with the BoW algorithm was applied to assess terms' importance and frequency and text clustering. In total, 1019 field activity reports were mined. Word extraction from the text mining method set out the following guiding axioms from the bigrams: "confronting syphilis in primary health care;" "investigation committee for congenital syphilis in the territory;" "municipal plan for monitoring and investigating syphilis cases through health surveillance;" "women's healthcare networks for syphilis in pregnant;" "diagnosis and treatment with a focus on rapid testing." Text mining may serve public health research subjects when used in parallel with the conventional content analysis method. The computational method extracted intervention activities from field researchers, also providing inferences on how the strategies of the "Syphilis No" Project influenced the decrease in congenital syphilis cases in the territory.

Brazilian Older People Hospitalized by COVID-19: Characteristics and Prognostic Factors in a Retrospective Cohort Study.

OBJECTIVE: Analyzing the survival of older people hospitalized due to COVID-19 in Brazil and identifying its main predictive factors for death. METHOD: This is a retrospective, multicenter cohort study, based on 20,831 records of hospitalizations of older people due to SARS-CoV-2 in Brazil. The observation period was from February 28 to May 18, 2020. RESULTS: There was a reduced overall survival time of 47.70% (95% confidence interval [CI] = [46.72%, 48.67%]) in 10 days. The variables age, race, education, intensive care unit (ICU), region, day of hospitalization, time elapsed between the first symptom and hospitalization, and the municipality that provided assistance showed increased risk of death using the multiple Cox proportional-hazards model. CONCLUSION: These results emphasize the relevance of inequality and access to health services as determinants for the death of older people with COVID-19.

Prevalence of urinary incontinence and associated factors in nursing home residents.

AIMS: To determine the prevalence of urinary incontinence (UI) and associated factors in the institutionalized elderly. METHODS: A cross-sectional study is presented herein, conducted between October and December 2013, in 10 nursing homes in the city of Natal (Northeast Brazil). Individuals over the age of 60, who reside in institutions, were included. Hospitalized individuals and those at end of life were excluded. Data collection included sociodemographic information, UI characterization, as well as variables related to the institution itself and to health conditions (comorbidities, medication, pelvic floor surgery, Barthel Index for functional capacity, and Pfeiffer test for cognitive status). UI was verified through the Minimum Data Set (MDS) version 3.0, which was also used to assess urinary devices and UI toileting programs. The Chi-square test (or Fisher's exact test), the linear Chi-square test, and logistic regression were utilized to model associations. RESULTS: The final sample consisted of 321 elderly, mostly females, with a mean age of 81.5 years. The prevalence of UI was 58.88% (CI 95%: 53.42-64.13) and the final model revealed a statistically significant association between UI and white race, physical inactivity, stroke, mobility impairment, and cognitive decline. The most frequent UI type was functional UI and toileting programs (prompted voiding) were only applied to approximately 8% of residents. CONCLUSIONS: It is concluded that UI is a health issue that affects more than half of the institutionalized elderly, and is associated with white race, physical inactivity, stroke, and other geriatric syndromes such as immobility and cognitive disability.