Erno Harzheim

This study aims to evaluate the viability of the NPS as a parsimonious predictor of the Primary Care Assessment Tool (PCAT). The data used in this study were obtained from a cross-sectional survey conducted in Rio de Janeiro in 2024, including adults and children in separate samples. Both datasets were divided into training (70%) and test (30%) sets. The main predictor was the NPS. Additional predictors consisted of 44 variables for adults and 39 for pediatric populations. Six machine learning algorithms were assessed. After evaluating all variables, six variables were selected for adult sample without showing a decrease in the model performance: 1) NPS, 2) age, 3) years of education; 4) the same doctor was seen consistently, 5) the number of times the service was used, and 6) the number of children. Four similar variables were selected for the children sample: 1) NPS, 2) age (respondent), 3) years of education, 4) the same doctor was seen consistently. We observed a superior performance of predictive models in the children population (AUC=0.82) compared to adults (AUC=0.76). The transfer learning approach achieved robust performance in adapting the adult-derived model to children’s data. This study demonstrated that a predictive model based on NPS and a minimal set of additional variables can effectively estimate PCAT scores.

This study aimed to evaluate the predictive performance of machine learning algorithms in estimating PCATool, leveraging two datasets spanning 10 years. Participants were adults (≥18y) and children (≤12y) surveyed in 2014 and 2024 in Rio de Janeiro. The outcomes were the PCATool i) general and ii) essential scores (Low [≤6.6] and High [>6.6]). Data from 2014 was divided (80:20) into: i) training and ii) test set. Data from 2024 was used for external validation. A total of 4,417 adults and 4,072 children were included. Random Forest Classifier (RFC) demonstrated the best overall performance for the general score in adults, achieving an AUC=0.68 (95%CI [0.64-0.72]) in the test set and 0.66 (95%CI [0.62-0.69]) in the validation set. For the essential score in adults, RFC also outperformed other models, with an AUC=0.68 (95%CI [0.63-0.72]) in the test set and 0.65 (95%CI [0.62-0.69]) in the validation set. In children, Extreme Gradient Boosting exhibited the best overall performance for the general score, achieving an AUC=0.65 (95%CI [0.60-0.69]) in the test set and 0.63 (95%CI [0.59-0.66]) in the validation set. Shapley value analysis identified continuity of care with the same doctor as the most influential predictor across models. These findings highlight the potential of machine learning to predict PCATool scores.

TelessaúdeRS was created 18 years ago to improve people’s health. This article presents its main results. This study aims to summarize and present the main outcomes of TelessaúdeRS. Program actions, publications, and databases from the past 18 years were reviewed to numerically express the program’s production and impact. Linked to UFRGS and HCPA, the project started with asynchronous text-based teleconsultations and evolved to synchronous and phone consultations, increasing access and efficiency. Additionally, it supported the regulation of referrals to specialized care in Rio Grande do Sul, with more than 500,000 discussions. The project also developed remote diagnostic services in spirometry, ophthalmology, dermatology, and stomatology, performing 700,000 telediagnostics and improving healthcare access. Furthermore, it supports the judiciary by applying evidence-based medicine to legal claims. Over 18 years, TelessaúdeRS has achieved its initial goals, expanded its scope, filled care gaps, supported primary care, and improved the healthcare system’s efficiency.

Resumo O TelessaúdeRS foi criado há 18 anos para melhorar a saúde das pessoas. Este artigo apresenta seus principais resultados. O objetivo deste estudo é resumir e apresentar os resultados do TelessaúdeRS. Estudo descritivo. Foram revisadas as ações, publicações e compilados os dados do programa ao longo dos últimos 18 anos para expressar numericamente sua produção e impacto. Vinculado à UFRGS e ao HCPA, o projeto começou com teleconsultorias assíncronas e evoluiu para consultorias síncronas e telefônicas, ampliando o acesso e a agilidade. Associadamente, iniciou-se o suporte à regulação de encaminhamentos para atenção especializada no RS. Essas iniciativas somaram mais de meio milhão de discussões de caso clínico. O projeto também criou serviços de diagnóstico remoto em espirometria, oftalmologia, dermatologia e estomatologia, realizando 700 mil telediagnósticos, ampliando o acesso à saúde. Além disso, oferece apoio ao poder judiciário, aplicando medicina baseada em evidências nos pleitos judiciais relacionados à saúde. Em 18 anos, o TelessaúdeRS alcançou seus objetivos iniciais, ampliando sua atuação para preencher lacunas assistenciais, apoiar a atenção primária e melhorar a eficiência do sistema de saúde.

Objective: Primary health care (PHC) professionals must care for patients with oral problems while performing gatekeeping for specialized care. We explored the effect of a strategy combining referral protocols and teleconsultations on a waiting list. Study design: This retrospective cohort study analyzed data from PHC to specialized oral medicine care from May/2014 to May/2016. The program started in May/2015, and referrals were divided into control and exposed groups. The median waiting time for in-person consultation and the proportion of referrals managed in PHC were analyzed for general and priority cases. Results: There were 1464 referrals. The median waiting time for specialized consultation was reduced from 212 days (95%CI 196-227) to 131 days (I95%CI 95-166). For priority referrals, the control group had 37 days (95%CI 0 - 89) of median waiting time, and the exposed group had 12 days (95%CI 6 - 17). Conclusions: Structured referral protocol and professional-to-professional consultations for oral disease improve referral waiting times. This benefit seems related to improving PHC efficacy.

This study investigated the influence of patient- and doctor-related factors on the quality of this relationship, measured by the Patient-Doctor Relationship Questionnaire (PDRQ-9), within the primary care setting of Brazil’s SUS (Unified Health System). Data were collected from 5,971 adult patients and 494 doctors from Family Health Units (USF) across all regions of Brazil. Multivariate analysis indicated that only patient characteristics were significantly associated with the quality of the doctor-patient relationship. These included living in urban areas, being male, having ten or more years of education, obtaining a same-day consultation, having more than three consultations per year with the same doctor, and being seen at a USF with high-quality primary care. The findings highlight inequalities in the doctor-patient relationship, showing that patients who share common characteristics with their doctors (urban background and higher education) or consult in higher-quality primary care settings report more satisfactory relationships. This underscores the importance of developing doctors’ cultural competence and the impact of service organization on relationship quality.

Resumen Este estudio investigó la influencia de los factores asociados a pacientes y médicos en la calidad de esta relación, medida por el Cuestionario de Relación Paciente-Médico (PDRQ-9), en la atención primaria del SUS, con datos de 5.971 pacientes adultos y 494 médicos de Unidades de Salud de la Familia (USF) de todas las regiones de Brasil. El análisis multivariante indicó que únicamente las características de los pacientes se asociaban significativamente con la calidad de la relación médico-paciente, entre ellas: vivir en una zona urbana, ser hombre, tener diez años o más de estudios, obtener cita el mismo día en que solicitaron atención, tener más de tres citas al año con el mismo médico y ser atendidos en una USF con atención primaria de alta calidad. Estos resultados apuntan a desigualdades en la relación médico-paciente, ya que los pacientes que comparten características comunes con sus médicos (origen urbano y mayor escolaridad), o que consultan en USF con atención primaria de mayor calidad, tienen relaciones más satisfactorias. Esto revela la importancia de desarrollar la competencia cultural de los médicos y el impacto de la organización de los servicios en la calidad de las relaciones.

The present study aimed to assess the degree of orientation for PHC from the perspective of adult and child users in the city of Rio de Janeiro. The design was a cross-sectional observational study and included independent samples of child and adult users leaving medical appointments at different health units in Rio de Janeiro (RJ). The study outcome was the essential and general scores of the PCATool Brazil, categorized as High Score above 6.6 and Low Score below 6.6. Socioeconomic, health-related, service use, and general characteristic variables were also collected. A total of 889 adults and 956 children answered the questionnaire and were analyzed. The core and overall PCATool scores were slightly higher in children than in the adult sample. The overall score was 6.72, 95%CI (6.63-6.81) and 6.40, 95%CI (6.30-6.50) in adults. In the adjusted models, individuals with five or more consultations in the last year: children - (OR=1.33, 95%CI [1.01-1.75])/adults - (OR=2.63, 95%CI [1.68-4.11]) and consultation with the same doctor: children - (OR=2.34, 95%CI [1.77-3.08])/adults - (OR=3.42, 95%CI [2.19-5.32]) were associated with a higher overall score.

Resumo O estudo investigou a influência de fatores associados a pacientes e médicos na qualidade dessa relação, medida pelo Patient-Doctor Relationship Questionnaire (PDRQ-9), na atenção primária do SUS, com dados de 5.971 pacientes adultos e 494 médicos de Unidades de Saúde da Família (USF) de todas as regiões do Brasil. A análise multivariada indicou que apenas características dos pacientes foram significativamente associadas à qualidade da relação médico-paciente, incluindo: residir em área urbana, sexo masculino, ter dez anos ou mais de estudo, conseguir consulta no mesmo dia em que buscou atendimento, ter mais de três consultas anuais com o mesmo médico e ser atendido em USF com alta qualidade na atenção primária. Tais resultados apontam para iniquidades na relação médico-paciente, com pacientes que compartilham características comuns com seus médicos (origem urbana e maior escolaridade) ou que consultam em USF com atenção primária de maior qualidade, tendo relacionamentos mais satisfatórios. Isso revela a importância do desenvolvimento da competência cultural dos médicos e o impacto da organização dos serviços na qualidade dos relacionamentos.

Resumo O estudo tem como objetivo avaliar o grau de orientação à APS na perspectiva dos usuários adultos e crianças no município do Rio de Janeiro. O desenho foi observacional transversal e incluiu amostras independentes de usuários infantis e adultos que saíam de consulta médica em diferentes unidades de saúde do Rio de Janeiro (RJ). O desfecho do estudo foram os escores essencial e geral do PCATool Brasil categorizados em Alto Escore acima de 6,6 e Baixo Escore abaixo de 6,6. Variáveis socioeconômicas, relacionadas à saúde, uso de serviços e características gerais foram também coletadas. Um total de 889 adultos e 956 para crianças responderam ao questionário e foram analisadas. As pontuações essenciais e gerais do PCATool foram ligeiramente maiores em crianças do que na amostra de adultos. O escore geral foi de 6,72, IC95% (6,63-6,81) e 6,40, IC95% (6,30-6,50) em adultos. Nos modelos ajustados, indivíduos com cinco ou mais consultas no último ano: crianças - (OR=1,33, IC95% [1,01-1,75])/adultos - (OR=2,63, IC95% [1,68-4,11]) e consulta com o mesmo médico: crianças - (OR=2,34, IC95% [1,77-3,08])/adultos - (OR=3,42, IC95% [2,19-5,32]) foram associados a maior escore geral.