Blood Pressure Estimation From Photoplethysmography by Considering Intra- and Inter-Subject Variabilities: Guidelines for a Fair Assessment

Costa, Tássia R.; Dias, Felipe Meneguitti; Cárdenas, Diego; Toledo, Marcelo; Lima, Daniel Magalhães; Krieger, José Eduardo; Gutierrez, Marco Antônio

doi:10.1109/access.2023.3284458

Cited by 2 publications

(4 citation statements)

References 71 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Gupta et al [2022] also did the same approach, not clearly specifying the dataset division. Previous research has shown that utilizing the same subject for both the training and test sets can yield better outcomes, as data leakage may occur due to the high interdependence among intra-subject heartbeats de Chazal et al [2004], Costa et al [2023]. Reddy.…”

Section: Discussionmentioning

confidence: 99%

“…Each PPG cycle segmented by the FSW served as input for the feature extraction algorithm. We used the same features presented in Costa et al [2023], resulting in 104 features. The features were computed from each signal cycle (heartbeat) and its corresponding first and second derivatives.…”

Section: Feature Extractionmentioning

confidence: 99%

“…The features included a variety of values such as pulse width, area, intervals, peak-to-peak interval, and systolic amplitude. A detailed description of the features used here can be found in Costa et al [2023], Chowdhury et al…”

Section: Feature Extractionmentioning

confidence: 99%

“…This way, features extracted from signals of the same patient are placed in training folds or testing fold, never in both. By allocating each patient in training and testing sets by their IDs, we avoided the classification bias caused by mixing information of the same patient in both training and testing folds in each iterationCosta et al [2023] deChazal et al [2004].…”

mentioning

confidence: 99%

See 3 more Smart Citations

Mortality predictors in a cohort of patients with COVID-19 admitted to a large tertiary hospital in the city of São Paulo, Brazil: a retrospective study

Oliveira¹,

Gorzoni

Rosa

2023

Sao Paulo Med. J.

View full text Add to dashboard Cite

INTRODUCTIONCoronavirus disease (COVID-19) is a potentially fatal infection caused by the new severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) that was first reported in the city of Wuhan, China, in December 2019. Since then, the disease has achieved a pandemic status, assuming dramatic proportions, thus leading to a global public health emergency. [1][2][3] In Brazil, the first case was officially confirmed on February 26, 2020, in the city of São Paulo, which has remained the epicenter of the country's pandemic with the third highest total number of confirmed cases. 4,5 Reports issued by the World Health Organization (WHO) on July 31, 2020, show that there is a significant difference in prognoses across countries, with a case fatality rate of the disease ranging between 3.53% (90,134/2,552,265 cases) in Brazil, 3.42% (150,054/4,388,566 cases) in the United States of America, and 14.21% (35,132/247,158 cases) in Italy. The reasons for such discrepancies remain to be fully elucidated, with population and genetic aspects, epidemiological control, population testing, and local management of the pandemic seeming to contribute to this situation. 6 Moreover, in Brazil, approximately 70% of the population relied solely on the services of its National Healthcare System (known as the "Unified Health System, " or by its acronym in Portuguese: SUS, Sistema Único de Saúde), 7 which rapidly led to hospital overcapacity and, therefore, possible preventable fatalities. In addition, hospitalization is known to have an array of negative impacts on the overall health of patients, such as secondary infections, needless procedures, psychological distress, and economic fallout of the health system that covers most of the nation's population.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Feature Extractionmentioning

confidence: 99%

Section: Feature Extractionmentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations