Applicability of machine learning algorithm to predict the therapeutic intervention success in Brazilian smokers.

Smoking cessation is an important public health policy worldwide. However, as far as we know, there is a lack of screening of variables related to the success of therapeutic intervention (STI) in Brazilian smokers by machine learning (ML) algorithms. To address this gap in the literature, we evaluated the ability of eight ML algorithms to correctly predict the STI in Brazilian smokers who were treated at a smoking cessation program in Brazil between 2006 and 2017. The dataset was composed of 12 variables and the efficacies of the algorithms were measured by accuracy, sensitivity, specificity, positive predictive value (PPV) and area under the receiver operating characteristic curve. We plotted a decision tree flowchart and also measured the odds ratio (OR) between each independent variable and the outcome, and the importance of the variable for the best model based on PPV. The mean global values for the metrics described above were, respectively, 0.675±0.028, 0.803±0.078, 0.485±0.146, 0.705±0.035 and 0.680±0.033. Supporting vector machines performed the best algorithm with a PPV of 0.726±0.031. Smoking cessation drug use was the roof of decision tree with OR of 4.42 and importance of variable of 100.00. Increase in the number of relapses also promoted a positive outcome, while higher consumption of cigarettes resulted in the opposite. In summary, the best model predicted 72.6% of positive outcomes correctly. Smoking cessation drug use and higher number of relapses contributed to quit smoking, while higher consumption of cigarettes showed the opposite effect. There are important strategies to reduce the number of smokers and increase STI by increasing services and drug treatment for smokers.

Correction: Applicability of machine learning technique in the screening of patients with mild traumatic brain injury.

[This corrects the article DOI: 10.1371/journal.pone.0290721.].

Applicability of machine learning technique in the screening of patients with mild traumatic brain injury.

Even though the demand of head computed tomography (CT) in patients with mild traumatic brain injury (TBI) has progressively increased worldwide, only a small number of individuals have intracranial lesions that require neurosurgical intervention. As such, this study aims to evaluate the applicability of a machine learning (ML) technique in the screening of patients with mild TBI in the Regional University Hospital of Maringá, Paraná state, Brazil. This is an observational, descriptive, cross-sectional, and retrospective study using ML technique to develop a protocol that predicts which patients with an initial diagnosis of mild TBI should be recommended for a head CT. Among the tested models, he linear extreme gradient boosting was the best algorithm, with the highest sensitivity (0.70 ± 0.06). Our predictive model can assist in the screening of mild TBI patients, assisting health professionals to manage the resource utilization, and improve the quality and safety of patient care.

Built environment influence on the incidence of elderly pedestrian collisions in a medium-large city in southern Brazil: a spatial analysis.

Trauma disproportionately affects vulnerable road users, especially the elderly. We analyzed the spatial distribution of elderly pedestrians struck by vehicles in the urban area of Maringa city, from 2014 to 2018. Hotspots were obtained by kernel density estimation and wavelet analysis. The relationship between spatial relative risks (RR) of elderly run-overs and the built environment was assessed through Qualitative Comparative Analysis (QCA). Incidents were more frequent in the central and southeast regions of the city, where the RR was up to 2.58 times higher. The QCA test found a significant association between elderly pedestrian victims and the presence of traffic lights, medical centers/hospitals, roundabouts and schools. There is an association between higher risk of elderly pedestrians collisions and specific elements of built environments in Maringa, providing fundamental data to help guide public policies to improve urban mobility aimed at protecting vulnerable road users and planning an age-friendly city.

Air Medical Transportation Provided by Norte Novo Regional Urgency Mobile Service: What Is the Current Scenario?

OBJECTIVE: The aim of this study was to investigate, describe, and analyze the Norte Novo regional air medical service provided by the Brazilian Emergency Medical Rescue Service. METHODS: This was a retrospective and descriptive study with a quantitative approach of the incidents registered from November 2016 to December 2019. For general patient classification, descriptive statistics of the following variables were performed: sex, age/age group, type of diagnosis, city where the incident took place, city of destination, length of patient care, ventilatory support, use of sedation, and use of vasoactive drugs. All analyses were performed using the XLSTAT program (Version 19.4; Addinsoft, New York, NY), considering a significance level of 5%. RESULTS: There were 1,677 responses divided into clinical (60.8%), traumatic (37.8%), organ transport (1.2%), and interhospital transference (0.2%). The most frequent diagnoses were acute myocardial infarction and stroke (clinical care) and polytrauma (trauma care). The average waiting time until the helicopter arrived at the scene was 25 minutes. CONCLUSION: This study shows the importance and relevance of this air medical service for the area it covers. Further research is needed to address the profile of this service in our country, which will allow us to elucidate scenarios and develop strategies to assist the population and, thus, design training and simulation exercises for emergency service teams based on local realities.

Emergency Care Gap in Brazil: Geographical Accessibility as a Proxy of Response Capacity to Tackle COVID-19.

Background: The new coronavirus disease (COVID-19) has claimed thousands of lives worldwide and disrupted the health system in many countries. As the national emergency care capacity is a crucial part of the COVID-19 response, we evaluated the Brazilian Health Care System response preparedness against the COVID-19 pandemic. Methods: A retrospective and ecological study was performed with data retrieved from the Brazilian Information Technology Department of the Public Health Care System. The numbers of intensive care (ICU) and hospital beds, general or intensivist physicians, nurses, nursing technicians, physiotherapists, and ventilators from each health region were extracted. Beds per health professionals and ventilators per population rates were assessed. A health service accessibility index was created using a two-step floating catchment area (2SFCA). A spatial analysis using Getis-Ord Gi* was performed to identify areas lacking access to high-complexity centers (HCC). Results: As of February 2020, Brazil had 35,682 ICU beds, 426,388 hospital beds, and 65,411 ventilators. In addition, 17,240 new ICU beds were created in June 2020. The South and Southeast regions have the highest rates of professionals and infrastructure to attend patients with COVID-19 compared with the northern region. The north region has the lowest accessibility to ICUs. Conclusions: The Brazilian Health Care System is unevenly distributed across the country. The inequitable distribution of health facilities, equipment, and human resources led to inadequate preparedness to manage the COVID-19 pandemic. In addition, the ineffectiveness of public measures of the municipal and federal administrations aggravated the pandemic in Brazil.

Helicopter Transportation of Brazilian Trauma Patients: A Comparison of Times to Care.

OBJECTIVE: The purpose of this study was to analyze helicopter emergency medical service (HEMS) transport with secondary land ambulance transfer, comparing landings performed inside and outside the hospital complex to the emergency department. METHODS: This was a cross-sectional observational study of HEMS transports of trauma patients between 2016 and 2018 in southern Brazil. Patients were attended by the HEMS team at the trauma site or stabilized in hospitals nearby and subsequently referred to trauma centers. In this region, no trauma centers have their own helipads so helicopters land in remote areas close to the hospital, which may be inside or outside the hospital complex. Both landings require ground emergency medical service transport, with off-site landings necessitating ground emergency medical service transport via public access roads to reach the hospital. Data were analyzed using descriptive statistics, and on-site and off-site transport times were compared using a t-test for independent samples. RESULTS: Of 176 transports, 28.5% resulted in on-site landings, whereas 71.5% occurred off-site. The ground transport time when the landing zone was off-site was 5 minutes longer than on-site (P < .001). CONCLUSION: Off-site landings result in longer transports to the emergency room. The construction of helipads in trauma centers can reduce transport time, in addition to reducing the costs and sequelae of trauma.

The Impact of Socioeconomic Factors, Coverage and Access to Health on Heart Ischemic Disease Mortality in a Brazilian Southern State: A Geospatial Analysis.

Background: No other disease has killed more than ischemic heart disease (IHD) for the past few years globally. Despite the advances in cardiology, the response time for starting treatment still leads patients to death because of the lack of healthcare coverage and access to referral centers. Objectives: To analyze the spatial disparities related to IHD mortality in the Parana state, Brazil. Methods: An ecological study using secondary data from Brazilian Health Informatics Department between 2013-2017 was performed to verify the IHD mortality. An spatial analysis was performed using the Global Moran and Local Indicators of Spatial Association (LISA) to verify the spatial dependency of IHD mortality. Lastly, multivariate spatial regression models were also developed using Ordinary Least Squares and Geographically Weighted Regression (GWR) to identify socioeconomic indicators (aging, income, and illiteracy rates), exam coverage (catheterization, angioplasty, and revascularization rates), and access to health (access index to cardiologists and chemical reperfusion centers) significantly correlated with IHD mortality. The chosen model was based on p < 0.05, highest adjusted R2 and lowest Akaike Information Criterion. Results: A total of 22,920 individuals died from IHD between 2013-2017. The spatial analysis confirmed a positive spatial autocorrelation global between IDH mortality rates (Moran's I: 0.633, p < 0.01). The LISA analysis identified six high-high pattern clusters composed by 66 municipalities (16.5%). GWR presented the best model (Adjusted R2: 0.72) showing that accessibility to cardiologists and chemical reperfusion centers, and revascularization and angioplasty rates differentially affect the IHD mortality rates geographically. Aging and illiteracy rate presented positive correlation with IHD mortality rate, while income ratio presented negative correlation (p < 0.05). Conclusion: Regions of vulnerability were unveiled by the spatial analysis where sociodemographic, exam coverage and accessibility to health variables impacted differently the IHD mortality rates in Paraná state, Brazil. Highlights: The increase in ischemic heart disease mortality rates is related to geographical disparities.The IHD mortality is differentially associated to socioeconomic factors, exam coverage, and access to health.Higher accessibility to chemical reperfusion centers did not necessarily improve patient outcomes in some regions of the state.Clusters of high mortality rate are placed in regions with low amount of cardiologists, income and schooling.

Emergency Care Sensitive Conditions in Brazil: A Geographic Information System Approach to Timely Hospital Access.

Background: The benefits of treatment for many conditions are time dependent. The burden of these emergency care sensitive conditions (ECSCs) is especially high in low- and middle-income countries. Our objective was to analyze geospatial trends in ECSCs and characterize regional disparities in access to emergency care in Brazil. Methods: From publicly available datasets, we extracted data on patients assigned an ECSC-related ICD-10 code and on the country's emergency facilities from 2015-2019. Using ArcGIS, OpenStreetMap, and WorldPop, we created catchment areas corresponding to 180 minutes of driving distance from each hospital. We then used ArcGIS to characterize space-time trends in ECSC admissions and to complete an Origin-Destination analysis to determine the path from household to closest hospital. Findings: There were 1362 municipalities flagged as "hot spots," areas with a high volume of ECSCs. Of those, 69.7% were more than 180 minutes (171 km) from the closest emergency facility. These municipalities were primarily located in the states of Minas Gerais, Bahia, Espiríto Santo, Tocantins, and Amapá. In the North region, only 69.1% of the population resided within 180 minutes of an emergency hospital. Interpretations: Significant geographical barriers to accessing emergency care exist in certain areas of Brazil, especially in peri-urban areas and the North region. One limitation of this approach is that geolocation was not possible in some areas and thus we are likely underestimating the burden of inadequate access. Subsequent work should evaluate ECSC mortality data. Funding: This study was funded by the Duke Global Health Institute Artificial Intelligence Pilot Project.

Spatial inequalities of major lower limb amputation rates in Paraná state, Brazil.

OBJECTIVE: The aim of this observational cross-sectional study was to analyse the spatial distribution of major lower limb amputation (MLLA) rates and associate them to socioeconomic, demographic and public healthcare access-related variables in the State of Paraná, Brazil, from 2012 to 2017. METHOD: Data on MLLA, revascularisation surgeries, diagnostic exams and healthcare coverage were obtained from the Brazilian Public Hospital Information System. Socioeconomic data were obtained from the Brazilian Institute of Geography and Statistics. Spatial autocorrelation of the MLLA rates was tested using Moran's I method. Multivariate spatial regression models using ordinary least squares regression (OLS) and geographically weighted regression (GWR) were used to identify the variables significantly correlated with MLLA. RESULTS: A total of 5270 MLLA were included in the analysis. Mean MLLA rates were 24.32 (±18.22)/100 000 inhabitants, showing a positive global spatial autocorrelation (Moran's I=0.66; p<0.001). Queen contiguity matrix demonstrates that MLLA rates ranged from 7.6 to 46.6/100 000 with five large clusters of high MLLA rates. OLS showed that four of the nine studied variables presented significant spatial correlation with MLLA rates. Colour Doppler ultrasound showed a negative association (p<0.001), while revascularisation surgeries and illiteracy showed a positive correlation (p<0.01). GWR presented the best model (adjusted R2=0.77) showing that the predictors differentially affect the MLLA rates geographically. CONCLUSION: The high MLLA rates in some regions of the state are influenced by the high rate of illiteracy and low utilisation rate of colour Doppler, indicating a social problem and difficulty in accessing health. On the other hand, the high rates of revascularisation surgeries are related to higher MLLA rates, possibly due to delayed access to specialised hospitals. This indicates that attention must be given to population access to public healthcare in the State of Paraná in order to ensure proper and timely medical attention.

Mapping risk of ischemic heart disease using machine learning in a Brazilian state.

Cardiovascular diseases are the leading cause of deaths globally. Machine learning studies predicting mortality rates for ischemic heart disease (IHD) at the municipal level are very limited. The goal of this paper was to create and validate a Heart Health Care Index (HHCI) to predict risk of IHD based on location and risk factors. Secondary data, geographical information system (GIS) and machine learning were used to validate the HHCI and stratify the IHD municipality risk in the state of Paraná. A positive spatial autocorrelation was found (Moran's I = 0.6472, p-value = 0.001), showing clusters of high IHD mortality. The Support Vector Machine, which had an RMSE of 0.789 and error proportion close to one (0.867), was the best for prediction among eight machine learning algorithms after validation. In the north and northwest regions of the state, HHCI was low and mortality clusters patterns were high. By creating an HHCI through ML, we can predict IHD mortality rate at municipal level, identifying predictive characteristics that impact health conditions of these localities' guided health management decisions for improvements for IHD within the emergency care network in the state of Paraná.

Diminuição no uso de bebidas alcoólicas e a violência pelo parceiro íntimo / Decreased use of alcoholic beverages and intimate partner violence / Disminución del uso de bebidas alcohólicas y violencia de pareja

Introdução: A violência praticada por parceiro íntimo refere-se ao comportamento de parceiros ou ex-parceiros íntimos que resulta em dano físico, sexual ou psicológico, incluindo agressão física, coerção sexual, abuso psicológico e comportamento controlador. Sabe-se que o etilismo está associado ao aumento de tal violência. Objetivo: Analisar se a acompanhante do paciente em abstinência alcoólica referia menor índice de violência nesse período em relação ao tempo em que o mesmo fazia abuso de álcool. Métodos: Estudo observacional transversal no qual foram selecionados homens ex-etilistas atendidos no CAPSad de Maringá e suas parceiras. Foi utilizado um questionário para violência contra parceiro (HITS) composto de 4 perguntas objetivas, cuja pontuação varia de 4 até 20. Valores iguais ou superiores a 10 indicam violência. Resultados: Foram entrevistadas 53 mulheres de diversas faixas etárias e escolaridades. Desse total, 84,9% das participantes apresentaram pontuações menores no teste com o parceiro em abstinência em relação ao período em que o mesmo estava em uso/abuso de álcool. Das mulheres 15,1% não notaram diferença no nível de violência do acompanhante, estivesse ele em uso ou em abstinência alcoólica. Conclusões: Demonstrou-se claramente que o fato de cessar o consumo de bebidas alcoólicas reduziu o índice de violência infligida pelo parceiro.

Introduction: Intimate partner violence refers to the behavior of intimate partners or ex-partners resulting in physical, sexual, or psychological harm, including physical aggression, sexual coercion, psychological abuse, and controlling behavior. It is known that alcoholism is associated with increase of this type of violence. Objective: The aim of this study was to analyze whether the partner of the patient in alcohol withdrawal reported a lower rate of violence in this period compared with the period of alcohol abuse. Methods: cross-sectional study in which we selected male former drinkers attended at the CAPSad of Maringá, and their partners. A questionnaire regarding partner violence (HITS), consisting of 4 objective questions with scores ranging from 4 to 20, was used. Values equal to or greater than 10 indicate violence. Results: We interviewed 53 women of different ages and schooling. Of this total, 84.9% of the participants had scores in the test with the partner in withdrawal lower than in the period in which he was in use/abuse of alcohol. 15.1% of the women did not notice a difference in the level of violence of their partners, whether he was in use or withdrawal. Conclusions: It was clearly demonstrated that the cessation of alcohol consumption reduced the rate of violence inflicted by the partner.

Introducción: La violencia practicada por un compañero íntimo se refiere al comportamiento de parejas o ex compañeros íntimos que resultan en daño físico, sexual o psicológico, incluyendo agresión física, coerción sexual, abuso psicológico y comportamiento controlador. Se sabe que el etilismo está asociado al aumento de tal violencia. Objetivo: analizar si la compañera del paciente en abstinencia alcohólica refería menor índice de violencia en ese período en relación al tiempo en que el mismo hacía abuso de alcohol. Método: estudio tranversal en el que se seleccionaron hombres ex etilistas del CAPSad de Maringá y sus parejas. Se utilizó un cuestionario para violencia contra parejas (HITS) compuesto de 4 preguntas objetivas cuya puntuación varía de 4 a 20. Valores igual ou superiores a 10 indican violencia. Resultados: Se entrevistaron a 53 mujeres de diversas edades y escolaridades. De ese total, el 84,9% de las participantes presentó puntuaciones menores en la prueba con el compañero en abstinencia en relación al período en que el mismo estaba en uso / abuso de alcohol. El 15,1% de las mujeres no notaron diferencia en el nivel de violencia del acompañante, esté en uso o abstinencia alcohólica. Conclusión: Se demostró claramente que el hecho de cesar el consumo de bebidas alcohólicas redujo el índice de violencia infligido por el compañero.

Comparative Analysis between the Gail, Tyrer-Cuzick and BRCAPRO Models for Breast Cancer Screening in Brazilian Population.

OBJECTIVE: To analyze the diagnostic accuracy of predictive models of breast cancer risk for the Brazilian population. METHOD: A cross-sectional, study was conducted in a sample of 382 women aged 35-69 years who were users of the Unified Health System (SUS) residing in a municipality in southern Brazil. RESULTS: The results showed that the Tyrer-Cuzick model had the highest mean risk values and estimates (proportion) for predicting the 5-year risk of breast cancer, reaching a maximum risk of ±1.63% in the 60-64 year age group. For the 90-year risk, a maximum risk of ±12.8% was predicted for the 50-54 year age group using this model. The 5-year risk calculated by the three tools increased progressively with increasing age, where the mean risk was ±0.8% in women aged 35-39 and reached ±1.50% in women aged 65-69. The 90-year risk declined with increasing age only in the Tyrer-Cuzick model, from ±10.8% to ±9%. The BRCAPRO model presented a greater sensitivity compared to the Gail and Tyrer-Cuzick models. And, the model that presented greater specificity was Gail. CONCLUSION: The Tyrer-Cuzick model presented the highest risk estimates for 5 years and 90 years in the studied population, however, this data is not enough to validate this tool, since when analyzing the sensitivity and specificity the BRCAPRO and Gail have the highest values respectively.