Artigos

Conteúdo (article):

Analysis of stroke-related hospitalizations and deaths across different regions of Brazil before and during the COVID-19 pandemic.

Análise das internações e óbitos por Acidente Vascular Cerebral em diferentes regiões do Brasil antes e durante a Pandemia de COVID-19.

Análisis de hospitalizaciones y muertes por accidente cerebrovascular en diferentes regiones de Brasil antes y durante la pandemia de COVID-19.

1- Andreza Maria Luzia Baldo de Souza, Universidade Estadual de Campinas/ UNICAMP, Piracicaba School of Dentistry/FOP, Department of Public Health, Pediatric Dentistry and Orthodontics. andrezamlb@gmail.com, https://orcid.org/0000-0002-6575-2209

2- Antonio Carlos Pereira, Universidade Estadual de Campinas/ UNICAMP, Faculty of Dentistry of Piracicaba Piracicaba School of Dentistry /FOP, Department of Public Health, Pediatric Dentistry and Orthodontics. apereira111@gmail.com, https://orcid.org/0000-0003-1703-8171

3- Marcelo de Castro Meneghim, Universidade Estadual de Campinas/ UNICAMP, Faculty of Dentistry of Piracicaba Piracicaba School of Dentistry/FOP, Department of Public Health, Pediatric Dentistry and Orthodontics. marcelomeneghim@gmail.com, https://orcid.org/0000-0003-2673-3627

Corresponding author: Andreza Maria Luzia Baldo de Souza, Avenida Limeira 901, Bairro Areião, Zip Code 13414903, Piracicaba – SP, Brazil. E-mail: andrezamlb@gmail.com
Authors’ contribution: AMLB Souza contributed to the study conception and design, data analysis and interpretation, writing of the manuscript, and final approval of the published version. MC Meneghim contributed to the study conception and design, data interpretation, critical review of the intellectual content, and final approval of the published version. NMBL Prado contributed with the critical review of the intellectual content and final approval of the published version. AC Pereira contributed with the critical review of the intellectual content and final approval of the published version.

The authors declare no conflicts of interest related to the publication of this article.

Abstract
Stroke, the second leading cause of death globally and a significant source of disability, has been impacted by the COVID-19 pandemic, which may increase the risk of cerebrovascular events. This observational and ecological time-series study aimed to analyze stroke-related hospitalizations and deaths, covering the 2008–2022 period, using data from the Hospital Information System of the Unified Health System. Data were filtered by code, which includes cerebrovascular accidents not specified as hemorrhagic or ischemic. The research resulted in a significant increase in hospitalizations (R2=0.9437, p≤0.0001) and mortality (R2=0.8894, p≤0.0001) over the years. A drop was noted during the peak of the pandemic, followed by a rebound in the indices. The results indicate the urgency of reviewing and adapting public health strategies to prevent and manage stroke in post-pandemic Brazil, highlighting the increase in hospitalizations and deaths.

Keywords: Cerebrovascular Accident, Public Health, Covid-19, Ecological Study, Cerebrovascular.
Resumo
O Acidente Vascular Cerebral, segunda maior causa de morte global e significativa fonte de incapacidade, viu-se impactado pela pandemia de COVID-19, que pode aumentar os riscos de eventos cerebrovasculares. Este estudo observacional e ecológico de série temporal buscou analisar as internações e óbitos por acidente vascular cerebral, cobrindo o período de 2008 a 2022, usando dados do Sistema de Informações Hospitalares do sistema único de saúde. Os dados foram filtrados pelo código, que contempla acidente vascular cerebral não especificados como hemorrágicos ou isquêmicos. A pesquisa resultou em um aumento significativo nas taxas de internação (R2= 0,9437, p=<0,0001) e mortalidade (R2=0,8894, p=<0,0001) ao longo dos anos. Notou-se uma queda durante o pico da pandemia, seguida de uma recuperação nos índices. Os resultados indicam a urgência de revisar e adaptar estratégias de saúde pública para prevenir e tratar o acidente vascular cerebral no Brasil pós-pandemia, destacando o aumento de internações e mortes.

Palavras-chaves: Acidente Vascular Cerebral, Saúde Pública, Covid-19, Estudo ecológico, Cerebrovascular.

Resumen
El accidente cerebrovascular, la segunda causa principal de muerte a nivel mundial y una fuente importante de discapacidad, se ha visto afectado por la pandemia de COVID-19, que puede aumentar los riesgos de eventos cerebrovasculares. Este estudio observacional y ecológico de series temporales buscó analizar las hospitalizaciones y muertes por accidente cerebrovascular, que abarca el período de 2008 a 2022, utilizando datos del Sistema de Información Hospitalaria del sistema único de salud. Los datos fueron filtrados por el código, que incluye accidentes cerebrovasculares no especificados como hemorrágicos o isquémicos. La investigación resultó en un aumento significativo de las tasas de hospitalización (R2= 0,9437, p=<0,0001) y mortalidad (R2=0,8894, p=<0,0001) a lo largo de los años. Se observó una caída durante el pico de la pandemia, seguida de una recuperación en los índices. Los resultados indican la urgencia de revisar y adaptar las estrategias de salud pública para prevenir y tratar el accidente cerebrovascular en Brasil pospandemia, destacando el aumento de hospitalizaciones y muertes.

Palabras clave: Accidente cerebrovascular, Salud pública, Covid-19, Estudio ecológico, Cerebrovascular.

Introduction
Stroke is recognized as the second leading cause of death worldwide, representing a major public health challenge due to its high lethality and significant potential for long-term disability1,2,3. In recent years, the COVID-19 pandemic has emerged as an aggravating factor, being associated with severe cerebrovascular complications in infected individuals4,5,6.
The impact of SARS-CoV-2 infection on the cardiovascular and cerebrovascular system has been extensively studied. Evidence suggests that the virus can trigger thromboinflammation, directly affecting the vascular endothelium and increasing the risk of acute myocardial infarction, myocarditis, and stroke7,8. The underlying pathophysiological mechanisms include hypercoagulability, endothelial dysfunction, and exacerbated inflammatory response4,5.
Beyond its direct biological effects, the pandemic also caused substantial systemic disruptions to healthcare services. The reorganization of healthcare networks, the reallocation of resources to address COVID-19, and public fear of seeking medical care contributed to a reduction in hospitalizations for acute conditions, including stroke9,10,11. This scenario may have led to worse clinical outcomes, especially among populations with limited access to specialized care.
In the context of stroke, the existence of a structured stroke care pathway is essential to ensure early diagnosis, timely treatment, and effective rehabilitation12. However, in Brazil, the implementation of this model is hindered by regional inequalities and structural limitations13. The pandemic intensified these vulnerabilities, requiring a coordinated response involving planning, technological innovation, and service integration.
Understanding the intersections between the COVID-19 pandemic, stroke care, and the organization of healthcare systems is essential to develop more resilient strategies to address future health emergencies.
Thus, this study aimed to analyze trends in stroke-related hospitalizations and deaths in Brazil before and during the COVID-19 pandemic, using aggregated data from the Brazilian Unified Health System (SUS). The analysis seeks to identify temporal patterns and reflect on both the direct impacts (related to infection) and indirect impacts (related to the reorganization of the healthcare system) on the indicators examined. A population-based approach was adopted, with the goal of providing evidence to support the planning and improvement of public health policies.
Method
This is an observational, ecological, time-series study based on secondary data obtained from the Hospital Information System of the Unified Health System (SIH/SUS), made available by the Department of Informatics of SUS (DATASUS). The SIH includes data from all Brazilian federative units, based on records of stroke-related hospitalizations identified via the Hospital Admission Authorizations (Autorizações de Internações Hospitalares – AIH).
DATASUS is an open-access public database in Brazil; therefore, submission to and approval by a Research Ethics Committee are not required (Brazilian Ministry of Health resolution No. 510/2016). STROBE guidelines for reporting observational studies in epidemiology were followed.
Data were collected in August 2023 from the SIH/SUS using ICD-10 code I64, which represents unspecified stroke. Records with incomplete or inconsistent information were excluded. The time series starting in 2008 was selected to ensure a robust historical dataset for the analysis of long-term trends, while the 2020–2022 period enabled the evaluation of potential impacts of the pandemic.
Data search respected the criteria and step-by-step procedure described as follows: ICD-10 category I64, corresponding to stroke not specified as hemorrhage or infarction, was selected; data covering all federative units were extracted from the Hospital Morbidity section of the SIH/SUS, compiling hospitalizations and in-hospital death records for males and females; data encompassed 2008–2019 (pre-pandemic) and 2020–2022 (during the COVID-19 pandemic).

Methodology of statistical analysis
Data was analyzed using the R statistical software, adopting three main approaches: descriptive statistics, control charts, and regression modeling. Initially, data on stroke-related hospitalizations and deaths from 2008 to 2022 were organized into time series and analyzed using control charts, a statistical tool that enables the identification of patterns and variations over time. For this purpose, three zones were established based on standard deviations from the mean. Zone C, or the central zone, corresponds to values within one standard deviation of the mean and represents the range of variation considered normal. Zone B, or the warning zone, includes values between one and two standard deviations from the mean and indicates potential signs of instability. Lastly, Zone A, or the out-of-control zone, comprises values between two and three standard deviations and is interpreted as indicative of significant changes in data behavior. The criteria adopted for graphical interpretation were based on Arantes (2003)14 and Jones (2020)15, and included: the presence of a single year with a value above or below the upper control limit; six consecutive years of increasing or decreasing values; nine consecutive years with values on the same side of the mean; two out of three consecutive years within Zone A; and four out of five consecutive years within or beyond Zone B. The identification of any of these patterns suggests the presence of systematic trends or atypical behavior, enabling more robust inferences about the observed phenomena. Additionally, modeling was performed using generalized additive models (GAMs), which make it possible to estimate nonlinear trend curves fitted to the data. This approach captures complex variations in temporal patterns of hospitalizations and deaths, going beyond traditional linear models. After model fitting, two parameters were assessed: statistical significance (p-value), with a p<0.05 threshold, and the adjusted coefficient of determination (adjusted R²), which indicates the proportion of data variability explained by the fitted curves. All analytical procedures were conducted by a qualified statistician, ensuring technical rigor and reliability of the results presented.
As this is an ecological study based on aggregated data, it was not possible to distinguish patients with or without COVID-19 infection. The analysis aims to assess population trends rather than individual causal associations between COVID-19 and stroke. This limitation is acknowledged and discussed further.
Results
The data show significant variations in the indicators over time, especially in years coinciding with the pandemic.
Table 1 and Figure 1 show data on stroke-related hospitalizations in Brazil between 2008 and 2022. The curve fitted using GAMs shows an upward trend in the number of hospitalizations nationwide over the period (p<0.05). Hospitalizations increased from 90,808 in 2008 to 163,120 in 2019. In 2020, marking the onset of the pandemic in Brazil, a decline in stroke-related hospitalizations was observed, with 153,714 hospitalizations recorded. In 2021, a return to an increasing trend can be noted.
Table 1
Figure 1

Analysis of the temporal pattern of series using the control chart (Figure 2) confirms that, for Brazil as a whole, there was an upward trend in the number of hospitalizations up to 2019 (six or more consecutive years of increase). The chart also shows a decline in hospitalizations in 2020, the first year of the pandemic, followed by a subsequent return to the growth pattern. Moreover, all data points from 2014 to 2022 lie above the average (nine or more consecutive points above the average), indicating overall growth when considering the entire period.
Figure 2

Table 1 and Figures 3 and 4 also present data on the number of stroke-related deaths. The GAM analysis shows an increase in deaths over the study period, rising from 15,940 in 2008 to 27,410 in 2022 (p<0.05). The control chart shows an increase in the number of deaths nationwide from 2008 to 2016 (six or more consecutive years of increase). From 2016 onward, fluctuations in stroke-related deaths are observed, with no clear trend identified by the control chart.
Figure 3
Figure 4

Although the data reflect significant temporal variations during the pandemic, it is not possible, based on the records used, to establish a direct relationship between COVID-19 infection and the identified stroke cases. These findings should be interpreted within a population-level context rather than an individual clinical framework.
Discussion
This study identified relevant temporal patterns in stroke-related hospitalizations and deaths. However, the lack of individual-level clinical data prevents distinguishing between cases associated with COVID-19 and those that were not. Nevertheless, previous studies have already suggested plausible pathophysiological mechanisms underlying the worsening of cerebrovascular conditions in infected patients4,5.
An upward trend in stroke-related hospitalizations and deaths was observed over the years analyzed, with an inflection in 2020 coinciding with the onset of the pandemic. The abrupt decline during this period may reflect both reduced healthcare-seeking behavior and operational constraints within health systems. The subsequent increase in 2021 and 2022 may be related to the release of pent-up demand and the normalization of reporting. Although the literature indicates possible associations between COVID-19 and cerebrovascular events12,13, caution is warranted when interpreting these population-level data.
Evidence indicates that, during the pandemic, fear of infection and restricted access to healthcare services contributed to delays in the care of patients with stroke16,17,18,19,20. Such delays may have resulted in greater disease severity at the time of hospital admission, increasing the risk of death and permanent disabilities. These indirect factors should be considered potential determinants of the observed increase in more severe outcomes21.
The observed pattern highlights not only the immediate impacts of the pandemic but also exposes structural weaknesses in the stroke care pathway during emergency situations. This reinforces the urgency of investing in telehealth, remote triage, rapid response protocols, and the training of qualified teams across all regions of the country.
The literature demonstrates the effectiveness of well-structured stroke care pathways to reduce stroke-related mortality and disability22,23,24. However, their implementation in Brazil remains limited by regional inequalities, lack of resources, and shortcomings in the organization of healthcare networks²⁵,²⁶. The findings of this study reinforce the importance of strengthening these care pathways, focusing on integrated strategies for prevention, early diagnosis, timely treatment, and rehabilitation27,28,29.
The impact of the pandemic on stroke care can also be understood in light of the Sustainable Development Goals (SDGs), especially SDG 3 (Good Health and Well-Being) and SDG 10 (Reduced Inequalities)22. Promoting a more resilient, equitable, and responsive healthcare system is essential to address future emergencies and reduce disparities in access to neurological care30.
The expansion of telehealth, the decentralization of emergency services, and the use of technologies such as artificial intelligence (AI) and clinical decision support systems can reduce inequalities and improve effectiveness in stroke care31,32,33. These innovations should be incorporated as part of permanent healthcare management strategies.
Furthermore, the consolidation of these strategies also requires strengthening legal and regulatory frameworks that ensure coordinated responses in emergency situations. Flexible legislation, aligned with the protection of patients’ rights and the safe use of digital technologies, is essential to ensure continuity of care even in scenarios of social isolation or collapse of healthcare systems34˒35. Regulatory protocols that clearly define the ethical use of AI, clinical prioritization criteria, and the limits of decision automation should form part of this governance framework.
In the technological domain, the growing application of AI stands out as a tool for remote triage, predictive risk analysis, continuous monitoring, and real-time clinical decision support³³˒³⁵˒³⁶. Such systems can optimize responses in high-demand contexts, reducing inequalities by expanding access to qualified care even in regions with limited availability of specialists.
Other digital technologies, such as big data applied to epidemiological surveillance, interoperable healthcare management platforms, and intelligent clinical decision support systems, enhance the capacity of health systems to act in an agile and informed manner³⁷.
Additionally, post-stroke rehabilitation should be considered a priority within the care pathway, as it directly impacts the quality of life of patients and their families. The use of innovative approaches, such as gamification and telerehabilitation, can facilitate access to therapies and promote a more effective recovery38.
However, the adoption of these technologies requires careful attention to ethical, regulatory, and structural aspects39. The lack of adequate technological infrastructure, professional training, and clear regulations may exacerbate regional inequalities and compromise the effectiveness of these strategies. Regulation must ensure patient safety, data privacy, and equity in access, preventing technological advances from benefiting only already advantaged populations39˒40.
The results presented reinforce the need to strengthen the stroke care pathway in Brazil, with an integrated and territorially sensitive approach. Service reorganization in the post-pandemic context must go beyond expanding hospital capacity, encompassing preventive actions, equity in access, and the incorporation of innovative technologies.
This study has limitations inherent to the use of aggregated secondary data, including the lack of individual-level information (such as comorbidities, COVID-19 infection status, and time to care). Moreover, it was not possible to assess installed capacity or available resources across different regions.
In conclusion, this study demonstrates an increasing trajectory in stroke-related hospitalizations and deaths in Brazil, with a temporary decline during the most critical phase of the pandemic followed by a subsequent return to growth. These findings underscore the urgent need to review stroke care strategies, with an emphasis on health system resilience, regional equity, and coordinated responses to public health crises.
Acknowledgements
We thank the Graduate Program of the Piracicaba School of Dentistry (FOP)/UNICAMP.

Funding
This study was conducted with the support of the Coordination for the Improvement of Higher Education Personnel - Brazil (CAPES) - Financing Code -001

References

1. Feigin VL, Brainin M, Norrving B, et al. World Stroke Organization (WSO): Global Stroke Fact Sheet 2022. Int J Stroke. 2022;17(1):18-29. https://doi.org/10.1177/17474930211065917
2. Saini V, Guada L, Yavagal DR. Global Epidemiology of Stroke and Access to Acute Ischemic Stroke Interventions. Neurology. 2021;97(20 Suppl 2). https://doi.org/10.1212/WNL.0000000000012781
3. Gorelick PB. The global burden of stroke: persistent and disabling. Lancet Neurol. 2019;18(5):417-418. https://doi.org/10.1016/s1474-4422(19)30030-4
4. Marín-Medina DS, Muñoz-Rosero AM, Bernal-Bastidas BL, Gaspar-Toro JM. Infección por SARS-CoV-2 y ataque cerebrovascular isquémico [SARS-CoV-2 infection and ischemic stroke]. Semergen. 2021;47(7):482-487. https://doi.org/10.1016/j.semerg.2020.09.007
5. Ntaios G, Michel P, Georgiopoulos G, et al. Características e resultados em pacientes com COVID-19 e acidente vascular cerebral isquêmico agudo: o registro global de acidente vascular cerebral COVID-19. Stroke. 2020;51(9). https://doi.org/10.1161/STROKEAHA.120.031208
6. Dantas LF, Marchesi JF, Peres IT, Hamacher S, Bozza FA. Public hospitalizations for stroke in Brazil from 2009 to 2016. PLoS ONE. 2019;14(3). https://doi.org/10.1371/journal.pone.0213837
7. Oliveira GMM, Brant LCC, Polanczyk CA, Malta DC, Biolo A, Nascimento BR, et al. Cardiovascular Statistics - Brazil 2023. Arq Bras Cardiol. 2024 Feb;121(2):e20240079. doi: https://doi.org/10.36660/abc.20240079
8. Brant LCC, Pinheiro PC, Passaglia LG, Souza MFM, Malta DC, Banerjee A, et al. Cardiovascular mortality in Brazil during the COVID-19 pandemic: a comparison between underlying and multiple causes of death. Public Health. 2023; 224:131–9. doi: https://doi.org/10.1136/heartjnl-2020-317663.
9. Raisi-Estabragh Z, Mamas MA. Cardiovascular Health Care Implications of the COVID-19 pandemic. Cardiol Clin. 2022;40(3):389-396. https://doi.org/10.1016/j.ccl.2022.03.010
10. Ferraro CF, Findlater L, Morbey R, et al. Descrevendo o impacto indireto do COVID-19 na utilização da saúde usando sistemas de vigilância sindrômica. BMC Public Health. 2021;21(1):1–11. https://doi.org/10.1186/s12889-021-12117-5
11. Diegoli H, Magalhães PSC, Martins SCO, et al. Decrease in Hospital Admissions for Transient Ischemic Attack, Mild, and Moderate Stroke During the COVID-19 Era. Stroke. 2020;51(8):2315-2321. https://doi.org/10.1161/STROKEAHA.120.030481
12. Baptista SCPD, Juliani CMCM, Olbrich SRLR, Braga GP, Bazan R, Spiri WC. Avaliação dos indicadores de óbito e incapacidade dos pacientes atendidos em uma unidade de acidente vascular cerebral. Texto Contexto Enferm. 2018;27. https://doi.org/10.1590/0104-070720180001930016
13. Morelli N, Rota E, Terracciano C, et al. The Baffling Case of Ischemic Stroke Disappearance from the Casualty Department in the COVID-19 Era. Eur Neurol. 2020;83(2):213-215. https://doi.org/10.1159/000507666
14. Arantes A, Carvalho EDS, Medeiros EAS, Farhat CK, Mantese OC. Uso de diagramas de controle na vigilância epidemiológica das infecções hospitalares. Rev Saude Publica. 2003; 37:768-774. https://doi.org/10.1590/S0034-89102003000600012
15. Jones B. Avoiding Data Pitfalls: How to Steer Clear of Common Blunders When Working with Data and Presenting Analysis and Visualizations. Hoboken, New Jersey: John Wiley & Sons, Inc.; 2020.
16. Esenwa C, Parides MK, Labovitz DL. The effect of COVID-19 on stroke hospitalizations in New York City. J Stroke Cerebrovasc Dis. 2020;29(10):105114. https://doi.org/10.1016/j.jstrokecerebrovasdis.2020.105114
17. Nogueira RG, Abdalkader M, Qureshi MM, et al. Global impact of COVID-19 on stroke care. Int J Stroke. 2021;16(5):573–584. https://doi.org/10.1177%2F1747493021991652
18. Uchino K, Kolikonda MK, Brown D, et al. Decline in stroke presentations during the COVID-19 outbreak. Stroke. 2020;51(8):2544–2547. https://doi.org/10.1161/STROKEAHA.120.030481
19. Gu S, Dai Z, Shen H, et al. Delay in stroke treatment during the COVID-19 pandemic in China. Cerebrovasc Dis. 2021;50(6):715-721. https://doi.org/10.1159/000514667
20. Schirmer CM, Ringer AJ, Arthur AS, et al. Late presentation of acute ischemic stroke during the COVID-19 crisis. J Neurointerv Surg. 2020;12(7):639–642. https://doi.org/10.1136/neurintsurg-2020-016299
21. Yafasova A, Fosbøl EL, Johnsen SP, et al. Time to thrombolysis and long-term outcomes in patients with acute ischemic stroke: a national study. Stroke. 2021; 52:1724-1732. https://doi.org/10.1161/STROKEAHA.120.032837
22. Markus HS, Brainin M. COVID-19 and stroke—A global World Stroke Organization perspective. Int J Stroke. 2020;15(4):361-4. https://doi.org/10.1177/1747493020923472
23. Aguiar ÉS, Spinola VA, Farias MTD, et al. Factors that increase the incidence of mortality due to cerebrovascular accident. Res Soc Dev. 2022;11(1). https://doi.org/10.33448/rsd-v11i1.24866
24. Dias CH, De Oliveira Moraes PM, Mendonça XMFD, et al. Managerial tools for organizing the stroke care line: an integrative review. Res Soc Dev. 2021;10(7). https://doi.org/10.33448/rsd-v10i7.16262
25. Rangel DM, Feitosa AKN, Araújo FM, et al. The effects of the health line in a stroke unit: three years of experience from a center in Northeast Brazil. Arq Neuropsiquiatr. 2023;81(8):707–11. https://doi.org/10.1055/s-0043-1770350
26. Brandão PDC, Lanzoni GMDM, Pinto ICDM. Emergency care network: stroke care. Acta Paul Enferm. 2023;36. https://doi.org/10.37689/acta-ape/2023AO000611
27. Barbosa E, et al. A systematic review of the cost-effectiveness of emergency interventions for stroke in low- and middle-income countries. Afr J Emerg Med. 2020;10(17). https://doi.org/10.1001/jama.2017.15927
28. Donkor ES. Stroke in the 21st century: a snapshot of the burden, epidemiology, and quality of life. Stroke Res Treat. 2018. https://doi.org/10.1155%2F2018%2F3238165
29. Lima GDSF, Borges MA, Barreto MHBMM. Risk factors of stroke and the humanization of nursing care. Health Soc. 2023;3(01):36-56. https://doi.org/10.51249/hs.v3i01.1164
30. Sociedade Brasileira de AVC. Números do AVC [Internet]. 2024 Aug 9 [cited 2025 Jan 31]. Available from: https://avc.org.br/numeros-do-avc/
31. Demaerschalk BM, Raman R, Ernstrom K, Meyer BC. Efficacy of telemedicine for stroke: pooled analysis of the Stroke Team Remote Evaluation Using a Digital Observation Camera (STRokE DOC) and STRokE DOC Arizona telestroke trials. Telemed J E Health. 2012 Apr;18(3):230-7. doi: https://doi.org/10.1089/tmj.2011.0116
32. Soliman EM, Silveira ACP da, Leal Neto HS, Burille BC, Rolo MLT, Teló AF, et al. Análise epidemiológica e regional dos óbitos por acidente vascular cerebral isquêmico no Brasil (2014-2023). Contrib Ciênc Soc. 2024;17(12):e12874. doi: https://doi.org/10.55905/revconv.17n.12-262
33. Meyer A, Zverinski D, Pfahringer B, et al. Machine learning for real-time prediction of complications in critical care: a retrospective study. Lancet Respir Med. 2018;6(12):905-914. doi: https://doi.org/10.1016/s2213-2600(18)30300-x
34. Gostin LO, Moon S, Meier BM. Reimagining global health governance in the age of COVID-19. Am J Public Health. 2020 Nov;110(11):1615–1619. doi: https://doi.org/10.2105/AJPH.2020.305933.1
35. Topol EJ. High-performance medicine: the convergence of human and artificial intelligence. Nat Med. 2019;25(1):44–56. doi: https://doi.org/10.1038/s41591-018-0300-7
36. Rajkomar A, Dean J, Kohane I. Machine learning in medicine. N Engl J Med. 2019;380(14):1347–58. doi: https://doi.org/10.1056/NEJMra1814259
37. Jiang F, Jiang Y, Zhi H, Dong Y, Li H, Ma S, et al. Artificial intelligence in healthcare: past, present and future. Stroke Vasc Neurol. 2017;2(4):230–243. doi: https://doi.org/10.1136/svn-2017-000101
38. Almenara FD, Barros FS, Silva JMF, Gondim JA, Alves JN. Gameterapia como ferramenta de reabilitação pós-AVC: uma revisão sistemática. Contrib Ciênc Soc. 2024;17(12):e12915. doi: https://doi.org/10.55905/revconv.17n.12-283
39. Nabha R, Laouiti A, Samhat AE. Internet of Things-Based Healthcare Systems: An Overview of Privacy-Preserving Mechanisms. Applied Sciences. 2025;15(7):3629. doi: https://doi.org/10.3390/app15073629
40. Nebeker C, Torous J, Bartlett Ellis RJ. Building the case for actionable ethics in digital health research supported by artificial intelligence. BMC Med. 2019; 17:137. doi: https://doi.org/10.1186/s12916-019-1377-7