http://hdl.handle.net/10183/135562 Sun, 15 Nov 2026 07:34:32 GMT 2026-11-15T07:34:32Z http://hdl.handle.net/10183/301630 Telemedicine gatekeeping over 15,000 patients from specialist consultation waiting lists : a cost-minimization study Pfeil, Juliana Nunes; Roman, Rudi; Rados, Dimitris Rucks Varvaki; Umpierre, Roberto Nunes; Oliveira, Matheus Grassi de; Etges, Ana Paula Beck da Silva; Silva, Rodolfo Souza da; Katz, Natan; Mattiello, Rita; Harzheim, Erno Objective: This study assesses the cost-minimization of the RegulaSUS telemedicine program, reducing the necessity for face-to-face specialist consultations. Methods: A cost analysis study, utilizing a retrospective cohort design, was conducted from January 2017 to December 2019. The gatekeeping process for waiting lists for specialized consultations was performed by two groups: the RegulaSUS program through telemedicine intervention and those regulated by the usual procedures of the Ambulatory Regulation Center of the State of Rio Grande do Sul (the contemporaneous controls group). The primary outcome was to evaluate the financial impact of the RegulaSUS program on the health system costs using the Time-Driven Activity-Based Costing (TDABC) method. Results: The RegulaSUS program substantially reduced health care and societal expenditures, with gatekeeping by telemedicine costing $85.02 versus $214.45 for usual procedures—a 60% reduction. This intervention resulted in societal savings of R$7,833,882.56 over 36 months by successfully managing 15,064 patients within primary care settings, rather than referring them to specialists. Conclusions: The RegulaSUS program demonstrates a remarkable economic impact by integrating evidencebased gatekeeping protocols with telemedicine infrastructure, effectively decreasing specialist demand. This intervention provides compelling evidence for the potential of telemedicine to optimize health care resource allocation, enhance care coordination, and improve system efficiency. The outcomes present a scalable, financially sustainable model for health system strengthening that merits consideration for broader implementation across Brazil’s public health network and adaptation to comparable global health care contexts facing similar resource constraints. Wed, 01 Jan 2025 00:00:00 GMT http://hdl.handle.net/10183/301630 2025-01-01T00:00:00Z http://hdl.handle.net/10183/295784 Accuracy of artificial intelligence for gatekeeping in referrals to specialized care Vergara, Piter Oliveira; Oliveira, Jerônimo de Conto; Mattiello, Rita; Montelongo, Alfredo; Roman, Rudi; Katz, Natan; Wives, Leandro Krug; Rados, Dimitris Rucks Varvaki IMPORTANCE Integrating artificial intelligence (AI) technologies into gatekeeping holds significant potential, as it efficiently handles repetitive tasks and can process large amounts of information quickly. OBJECTIVE To develop and assess the accuracy of an AI model that enhances the gatekeeping process for referrals to specialized care. DESIGN, SETTING, AND PARTICIPANTS This diagnostic study comprised referrals from primary care to endocrinology, gastroenterology, proctology, rheumatology, and urology from a retrospective administrative database of patients in Brazil between June 2016 and April 2019. Analysis was performed between December 2022 and July 2024. MAIN OUTCOMES AND MEASURES The algorithm’s development and testing comprised 2 stages. Multiple AI models were initially evaluated to train and test the algorithm for categorizing referrals as authorizing or requiring additional information. Subsequently, the model’s performance was assessed against an independent set of referrals. Additionally, the current (human) evaluations of gatekeepers were evaluated against the standard. The reference standard was the consensus of 2 physicians with extensive experience. Accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC-ROC) were assessed. RESULTS The electronic system retrieved 45 039 eligible referrals for the development stage (mean [SD] patient age, 51.9 [15.8] years; 25 458 women [56.5%]). An algorithm utilizing word embeddings and a neural network proved the most effective. In the second phase, 1750 referrals (350 for each specialty) showed a 32% authorization rate according to the reference standard. The AI model achieved an overall accuracy of 0.716 (95% IC, 0.694-0.737), with a sensitivity of 0.542 (95% CI, 0.501 to 0.582) and specificity of 0.801 (95% CI, 0.777 to 0.822). Regarding individual specialties, rheumatology exhibited the highest accuracy (0.811; 95% IC, 0.767-0.849), while proctology had the lowest (0.649; 95% IC, 0.597-0.697). The overall AUC-ROC was 0.765 (95% IC, 0.742-0.788). When compared against the consensus standard, the AI model had higher accuracy and specificity and lower sensitivity than the current approach. CONCLUSIONS AND RELEVANCE In this diagnostic study of referral data, a novel AI model effectively distinguished between referrals that warranted immediate authorization and those that required further information with moderate accuracy; it had higher specificity and lower sensitivity than gatekeepers decisions. Implementing this AI model in the gatekeeping process should combine human judgment and AI support to optimize the referral process. Wed, 01 Jan 2025 00:00:00 GMT http://hdl.handle.net/10183/295784 2025-01-01T00:00:00Z http://hdl.handle.net/10183/295652 Educação em saúde por meio do YouTube® : a experiência de um núcleo de telessaúde no Sul do Brasil Silva, Filipe Ribeiro da; Martins, Letícia Felipak dos Passos; Cunha, Natássia Scortegagna da; D'Avila, Otávio Pereira; Umpierre, Roberto Nunes Objetivos: Este artigo tem como objetivo analisar a abrangência e visibilidade de vídeos educativos postados no site YouTube® por um núcleo de Telessaúde de uma universidade brasileira. Materiais e métodos: O estudo envolve pesquisa exploratória com abordagem quantitativa. Resultados: A busca realizada no Canal do TelessaúdeRS no YouTube® resultou na identificação de 265 vídeos, sendo 218 com assuntos diretamente ligados à Atenção Primária à Saúde que registraram 421.064 visualizações no período abarcado pela pesquisa, com uma média de 17.544 visualizações por mês. Conclusão: Os resultados da pesquisa – em especial no que se refere aos temas dos vídeos mais acessados – poderão ser usados para aperfeiçoamento das ações das Equipes de comunicação e teleducação do núcleo de Telessaúde e abrir caminho para novas investigações sobre receptividade dos conteúdos educativos.; Aims: This article aims to analyze the comprehensiveness and visibility of educational videos posted on YouTube® by a Telehealth hub of a Brazilian university. Materials and methods: The study involves exploratory research with a quantitative approach. Results: The search on the TelesaudeRS Channel on YouTube® resulted in the identification of 265 videos, of which 218 were directly related to Primary Health Care, which recorded 421,064 views in the period covered by the survey, with an average of 17,544 views per month. Conclusion: The results of the research - especially with regard to the themes of the most accessed videos - could be used to improve the actions of the communication and tele-education teams of the Telehealth nucleus and pave the way for new research into the receptivity of educational content. Mon, 01 Jan 2018 00:00:00 GMT http://hdl.handle.net/10183/295652 2018-01-01T00:00:00Z http://hdl.handle.net/10183/274103 Avaliação da regulação de consultas médicas especializadas pelo projeto RegulaSUS Pfeil, Juliana Nunes Introdução. Em contextos onde longas filas para consultas médicas especializadas comprometem a eficiência do Sistema Único de Saúde (SUS) - um desafio não exclusivo do Brasil - este estudo objetiva avaliar o RegulaSUS, uma iniciativa do TelessaúdeRS, financiado pela Secretaria de Saúde do Rio Grande do Sul. O objetivo deste estudo é aferir a eficácia desta estratégia na otimização da regulação das consultas especializadas, mensurar seu impacto na redução dos tempos de espera e apurar sua relação custo-minimização. Métodos. Inicialmente conduziu-se uma coorte retrospectiva com controle contemporâneo entre Janeiro de 2017 e Dezembro de 2019. Especialidades reguladas por telemedicina foram comparadas com especialidades reguladas de forma usual pela Central de Regulação Ambulatorial do Rio Grande do Sul (RS). A regulação por telemedicina incluiu elaboração de protocolos, classificação de risco da fila de espera e teleconsultorias. Para avaliar a associação entre o projeto RegulaSUS e o manejo dos pacientes na Atenção Primária à Saúde (APS) utilizou-se a proporção de encaminhamentos removidos da fila de espera para consulta médica especializada após atuação do RegulaSUS como desfecho primário. O desfecho secundário foi definido como tempo em fila dos pacientes durante o período do estudo. Na segunda etapa foi conduzida uma análise de custo-minimização do projeto RegulaSUS nos 36 meses de observação. O custo do projeto foi calculado através da metodologia de custeio baseado em atividade e tempo (TDABC) - usando o tempo para direcionar os custos dos recursos diretamente ao produto, neste caso, regulações realizadas pelo RegulaSUS. Para o cálculo de custo-minimização utilizou-se o número de encaminhamentos para consulta médica especializada que foram removidos da fila de espera após atuação do RegulaSUS. Resultados: Ao final do período de observação, 142.117 encaminhamentos foram regulados pelo RegulaSUS e 103.526 encaminhamentos foram regulados pela regulação usual. Dos encaminhamentos regulados pelo RegulaSUS, 17.604 (12,3% das solicitações reguladas pelo RegulaSUS) estavam em fila de espera, 44.879 (31,57%) resultaram em consulta médica especializada e 79.634 (56%) foram removidas da fila. Das solicitações reguladas pela regulação do Estado, 10.354 (10%) permaneceram na fila de espera, 46.117 (44,5%) resultaram em consulta médica especializada e 47.055 (45%) foram removidas da fila. Aproximadamente 10,6% dos encaminhamentos regulados pelo RegulaSUS foram removidos da fila após teleconsultoria e mantido seu manejo na APS. O tempo médio em fila de espera para encaminhamentos regulados pelo RegulaSUS foi de 964,6 dias e para encaminhamentos regulados pela regulação usual foi de 1.128,7 dias. O custo individual da remoção de um encaminhamento da fila de espera para manejo na APS foi de R$239,22, enquanto o custo individual de um encaminhamento que resulta em consulta médica especializada foi de R$759,26. A custo-minimização do projeto nos 36 meses de observação do estudo foi de R$7.833.882,56 Discussão. As filas de espera para cuidados médicos eletivos são uma preocupação global. A regulação de consultas médicas especializadas através de protocolos e teleconsultorias mostrou-se como uma opção viável para fortalecimento da APS e evitação de encaminhamentos de pessoas que poderiam ser manejadas na unidade de saúde para consulta médica especializada. Além disso, o RegulaSUS demonstrou eficiência da regulação por telemedicina para redução de tempo em fila dos encaminhamentos e para diminuição de custos para a sociedade em relação à regulação padrão. Estes achados possuem importância para discussão sobre alocação eficiente de recursos no sistema de saúde, especialmente na vigência de recursos limitados.; Introduction. In a context where long queues for specialized medical appointments compromise the efficiency of the Unified Health System (SUS), a challenge not limited to Brazil, this study aims to evaluate RegulaSUS, an initiative of TelessaúdeRS and the Health Department of Rio Grande do Sul. The objective of this study is to evaluate the effectiveness of this strategy in optimizing the regulation of specialized consultations, to measure its impact on reducing waiting times, and to determine its cost-minimization. Methods. First, a retrospective cohort with contemporary control was conducted between January 2017 and December 2019. Specialties regulated by telemedicine were compared with specialties regulated in a standard way by the Appointment and Exam Appointment Department (CMCE) of Porto Alegre. Telemedicine regulation included protocol development, waiting list risk classification, and teleconsultation. The proportion of PHC management of referrals regulated by the RegulaSUS project was defined as the primary outcome. The secondary outcome was defined as patient waiting time during the study period. In the second stage, a cost-minimization analysis of the RegulaSUS project was performed over the 36 months of observation. The project costs were calculated using the Time Activity Based Costing (TDABC) methodology - using time to assign resource costs directly to the product, in this case the regulations performed by RegulaSUS. To calculate cost minimization, the number of referrals for specialized medical consultation that were removed from the waiting list after RegulaSUS acted was used. The secondary outcome was the cost-effectiveness analysis using the TDABC and the number of patients treated in PHC after the RegulaSUS action. Results: At the end of the observation period, 142,117 referrals were regulated by RegulaSUS and 103,526 referrals were regulated by the usual regulation. Among the referrals regulated by RegulaSUS, 17,604 (12.3% of the total requests regulated by RegulaSUS) were on the waiting list, 44,879 (31.57%) resulted in a specialized medical consultation and 79,634 (56%) were removed from the queue. Of the requests regulated by the usual regulations, 10,354 (10%) remained on the waiting list, 46,117 (44.5%) resulted in a specialized medical consultation and 47,055 (45%) were removed from the queue. Approximately 10.6% of referrals regulated by RegulaSUS were removed from the queue after teleconsultation and continued to be managed in the PHC. The average waiting time was 964.6 days for referrals regulated by RegulaSUS and 1,128.7 days for referrals regulated by the usual regulation. The individual cost of removing a referral from the waiting list for PHC management was R$239.22, while the individual cost of a referral resulting in a specialized medical consultation was R$759,26. The cost minimization of the project during the 36 months of the study was R$ 7.833.882,56. Discussion. Waiting lists for elective medical care are a global problem. Regulating specialist consultations through protocols and teleconsultations proved to be a viable option for strengthening PHC and avoiding referrals of people who could be managed in the health unit for specialist consultations. In addition, RegulaSUS demonstrated its efficiency in reducing the waiting time for referrals and reducing costs to society. These results are important for the discussion of efficient resource allocation in the health system, especially in the face of limited resources. Mon, 01 Jan 2024 00:00:00 GMT http://hdl.handle.net/10183/274103 2024-01-01T00:00:00Z