Everton Jose Santana

All Publications

• Improving Reporting of Exercise Capacity Across Age Ranges Using Novel Workload Reference Equations. The American journal of cardiology Santana, E. J., Christle, J. W., Cauwenberghs, N., Peterman, J. E., Busque, V., Gomes, B., Bagherzadeh, S. P., Moneghetti, K., Kuznetsova, T., Wheeler, M., Ashley, E., Harber, M. P., Arena, R., Kaminsky, L. A., Myers, J., Haddad, F. 2024

  Abstract

  Exercise capacity (EC) is an important predictor of survival in the general population as well as in individuals with cardiopulmonary disease. Despite its relevance, considering percent-predicted workload (%pWL) given by current equations may overestimate EC in older adults. Therefore, to improve the reporting of EC in clinical practice, our main objective was to develop workload reference equations (pWL) that better reflect the relation between workload and age. Using the Fitness Registry and the Importance of Exercise National Database (FRIEND), we analyzed a reference group of 6,966 apparently healthy participants and 1,060 participants with HF who underwent graded treadmill cardiopulmonary exercise testing. For the first group, the mean age was 44 years [18-79]; 56.5% of individuals were male and 15.4% had obesity. Peak VO2 was 11.6 ± 3.0 METs in males and 8.5±2.4 METs in females. After partition analysis, we first developed sex-specific pWL equations to allow comparisons to a healthy weight reference. For males, pWL (METs) = 14.1 - 0.9 × 10-3 × age2 and for female 11.5 - 0.87 × 10-3 × age2. We used those equations as denominators of %pWL and, based on their distribution, we determined thresholds for EC classification, with average EC defined by the range corresponding to 85-115%pWL. Compared to %pWL using current equations, the new equations yielded better-calibrated %pWL across different age ranges. We also derived body mass index-adjusted pWL equations that better assessed EC in individuals with HF. In conclusion, the novel pWL equations have the potential to impact the report of EC in practice.

  View details for DOI 10.1016/j.amjcard.2024.01.022

  View details for PubMedID 38301753

• Right Ventricular Dysfunction Patterns Among Patients with COVID-19 in the Intensive Care Unit - a Retrospective Cohort Analysis. Annals of the American Thoracic Society Sanchez, P. A., O'Donnell, C. T., Francisco, N., Santana, E. J., Moore, A. R., Pacheco-Navarro, A., Roque, J., Lebold, K. M., Parmer, C. M., Pienkos, S. M., Celestin, B. E., Levitt, J. E., Collins, W. J., Lanspa, M. J., Ashley, E. A., Wilson, J. G., Haddad, F., Rogers, A. J. 2023

  Abstract

  Right ventricular (RV) dysfunction is common among patients hospitalized with COVID-19; however, its epidemiology may depend on the echocardiographic parameters used to define it.To evaluate the prevalence of abnormalities in three common echocardiographic parameters of RV function among COVID-19 patients admitted to the intensive care unit, as well as the effect of RV dilatation on differential parameter abnormality and the association of RV dysfunction with 60-day mortality.Retrospective cohort study of COVID-19 ICU patients between March 4th,2020 to March 4th, 2021, who received a transthoracic echocardiogram within 48 hours before to at most 7 days after ICU admission. RV dysfunction and dilatation respectively defined by guideline thresholds for tricuspid annular plane systolic excursion (TAPSE), RV fractional area change (RVFAC), RV free wall longitudinal strain (RVFWS), and RV basal dimension or RV end-diastolic area. Association of RV dysfunction with 60-day mortality assessed through logistic regression adjusting for age, prior history of congestive heart failure, invasive ventilation at time of TTE and APACHE II score.116 patients were included, of which 69% had RV dysfunction by > 1 parameter and 36.3% of these had RV dilatation. The three most common patterns of RV dysfunction included: Presence of 3 abnormalities, the combination of abnormal RVFWS and TAPSE, and isolated TAPSE abnormality. Patients with RV dilatation had worse RVFAC (24% vs 36%, p = 0.001), worse RVFWS (16.3% vs 19.1%, p = 0.005), higher RVSP (45mmHg vs 31mmHg, p = 0.001) but similar TAPSE (13mm vs 13mm, p = 0.30) compared to those with normal RV size. After multivariable adjustment, 60-day mortality was significantly associated with RV dysfunction (OR 2.91, 95% CI 1.01 - 9.44), as was the presence of at least 2 parameter abnormalities.ICU patients with COVID-19 had significant heterogeneity in RV function abnormalities present with different patterns associated with RV dilatation. RV dysfunction by any parameter was associated with increased mortality. Therefore, a multiparameter evaluation may be critical in recognizing RV dysfunction in COVID-19.

  View details for DOI 10.1513/AnnalsATS.202303-235OC

  View details for PubMedID 37478340

• Multiple voice disorders in the same individual: Investigating handcrafted features, multi-label classification algorithms, and base-learners SPEECH COMMUNICATION Barbon Junior, S., Guido, R., Aguiar, G., Santana, E., Proenca Junior, M., Patil, H. A. 2023; 152

  View details for DOI 10.1016/j.specom.2023.102952

  View details for Web of Science ID 001036871600001

• Novel left ventricular mechanical index in pulmonary arterial hypertension. Pulmonary circulation Ichimura, K., Santana, E. J., Kuznetsova, T., Cauwenberghs, N., Sabovčik, F., Chun, L., Francisco, N. L., Kheyfets, V. O., Salerno, M., Zamanian, R. T., Spiekerkoetter, E., Haddad, F. 2023; 13 (2): e12216

  Abstract

  Ventricular interdependence plays an important role in pulmonary arterial hypertension (PAH). It can decrease left ventricular (LV) longitudinal strain (LVLS) and lead to a leftward displacement ("transverse shortening") of the interventricular septum (sTS). For this study, we hypothesized the ratio of LVLS/sTS would be a sensitive marker of systolic ventricular interactions in PAH. In a cross-sectional cohort of patients with PAH (n = 57) and matched controls (n = 57), we quantified LVLS and septal TS in the amplitude and time domain. We then characterized LV phenotypes using upset plots, ventricular interactions using network analysis, and longitudinal analysis in a representative cohort of 45 patients. We also measured LV metrics in mice subjected to pulmonary arterial banding (PAB) using a 7 T magnetic resonance imaging at baseline, Week 1, and Week 7 post-PAB (N = 9). Patients with PAH had significantly reduced absolute LVLS (15.4 ± 3.4 vs. 20.1 ± 2.3%, p < 0.0001), higher sTS (53.0 ± 12.2 vs. 28.0 ± 6.2%, p < 0.0001) and lower LVLS/sTS (0.30 ± 0.09 vs. 0.75 ± 0.16, p < 0.0001) compared to controls. Reduced LVLS/sTS was observed in 89.5% of patients, while diastolic dysfunction, impaired LVLS (<16%), and LV atrophy were observed in 73.7%, 52.6%, and 15.8%, respectively. In the longitudinal cohort, changes in LVLS/sTS were closely associated with changes in N-terminal pro B-type natriuretic peptide (r = 0.73, p < 0.0001) as well as survival. Mice subjected to PAB showed significant RV systolic dysfunction and decreased LVLS/sTS compared to sham animals. We conclude that in PAH, LVLV/sTS is a simple ratio that can reflect ventricular systolic interactions.

  View details for DOI 10.1002/pul2.12216

  View details for PubMedID 37063750

  View details for PubMedCentralID PMC10103585

• Challenging obesity and sex based differences in resting energy expenditure using allometric modeling, a sub-study of the DIETFITS clinical trial. Clinical nutrition ESPEN Haddad, F., Li, X., Perelman, D., Santana, E. J., Kuznetsova, T., Cauwenberghs, N., Busque, V., Contrepois, K., Snyder, M. P., Leonard, M. B., Gardner, C. 2023; 53: 43-52

  Abstract

  BACKGROUND & AIMS: Resting energy expenditure (REE) is a major component of energy balance. While REE is usually indexed to total body weight (BW), this may introduce biases when assessing REE in obesity or during weight loss intervention. The main objective of the study was to quantify the bias introduced by ratiometric scaling of REE using BW both at baseline and following weight loss intervention.DESIGN: Participants in the DIETFITS Study (Diet Intervention Examining The Factors Interacting with Treatment Success) who completed indirect calorimetry and dual-energy X-ray absorptiometry (DXA) were included in the study. Data were available in 438 participants at baseline, 340at 6 months and 323at 12 months. We used multiplicative allometric modeling based on lean body mass (LBM) and fat mass (FM) to derive body size independent scaling of REE. Longitudinal changes in indexed REE were then assessed following weight loss intervention.RESULTS: A multiplicative model including LBM, FM, age, Black race and the double product (DP) of systolic blood pressure and heart rate explained 79% of variance in REE. REE indexed to [LBM0.66*FM0.066] was body size and sex independent (p=0.91 and p=0.73, respectively) in contrast to BW based indexing which showed a significant inverse relationship to BW (r=-0.47 for female and r=-0.44 for male, both p<0.001). When indexed to BW, significant baseline differences in REE were observed between male and female (p<0.001) and between individuals who are overweight and obese (p<0.001) while no significant differences were observed when indexed to REE/[LBM0.66*FM0.066], p>0.05). Percentage predicted REE adjusted for LBM, FM and DP remained stable following weight loss intervention (p=0.614).CONCLUSION: Allometric scaling of REE based on LBM and FM removes body composition-associated biases and should be considered in obesity and weight-based intervention studies.

  View details for DOI 10.1016/j.clnesp.2022.11.015

  View details for PubMedID 36657929

• Feature-based clustering of the left ventricular strain curve for cardiovascular risk stratification in the general population. Frontiers in cardiovascular medicine Ntalianis, E., Cauwenberghs, N., Sabovcik, F., Santana, E., Haddad, F., Claus, P., Kuznetsova, T. 2023; 10: 1263301

  Abstract

  Objective: Identifying individuals with subclinical cardiovascular (CV) disease could improve monitoring and risk stratification. While peak left ventricular (LV) systolic strain has emerged as a strong prognostic factor, few studies have analyzed the whole temporal profiles of the deformation curves during the complete cardiac cycle. Therefore, in this longitudinal study, we applied an unsupervised machine learning approach based on time-series-derived features from the LV strain curve to identify distinct strain phenogroups that might be related to the risk of adverse cardiovascular events in the general population.Method: We prospectively studied 1,185 community-dwelling individuals (mean age, 53.2 years; 51.3% women), in whom we acquired clinical and echocardiographic data including LV strain traces at baseline and collected adverse events on average 9.1 years later. A Gaussian Mixture Model (GMM) was applied to features derived from LV strain curves, including the slopes during systole, early and late diastole, peak strain, and the duration and height of diastasis. We evaluated the performance of the model using the clinical characteristics of the participants and the incidence of adverse events in the training dataset. To ascertain the validity of the trained model, we used an additional community-based cohort (n=545) as external validation cohort.Results: The most appropriate number of clusters to separate the LV strain curves was four. In clusters 1 and 2, we observed differences in age and heart rate distributions, but they had similarly low prevalence of CV risk factors. Cluster 4 had the worst combination of CV risk factors, and a higher prevalence of LV hypertrophy and diastolic dysfunction than in other clusters. In cluster 3, the reported values were in between those of strain clusters 2 and 4. Adjusting for traditional covariables, we observed that clusters 3 and 4 had a significantly higher risk for CV (28% and 20%, P≤0.038) and cardiac (57% and 43%, P≤0.024) adverse events. Using SHAP values we observed that the features that incorporate temporal information, such as the slope during systole and early diastole, had a higher impact on the model's decision than peak LV systolic strain.Conclusion: Employing a GMM on features derived from the raw LV strain curves, we extracted clinically significant phenogroups which could provide additive prognostic information over the peak LV strain.

  View details for DOI 10.3389/fcvm.2023.1263301

  View details for PubMedID 38099222

• Using meta-learning for multi-target regression INFORMATION SCIENCES Aguiar, G. J., Santana, E. J., de Carvalho, A. L., Barbon Junior, S. 2022; 584: 665-684

  View details for DOI 10.1016/j.ins.2021.11.003

  View details for Web of Science ID 000727774200005

• Detecting and Mitigating Adversarial Examples in Regression Tasks: A Photovoltaic Power Generation Forecasting Case Study INFORMATION Santana, E., Silva, R., Zarpelao, B., Barbon Junior, S. 2021; 12 (10)

  View details for DOI 10.3390/info12100394

  View details for Web of Science ID 000712846100001

• Improved prediction of soil properties with multi-target stacked generalisation on EDXRF spectra CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS Santana, E., dos Santos, F., Mastelini, S., Melquiades, F., Barbon Jr, S. 2021; 209

  View details for DOI 10.1016/j.chemolab.2020.104231

  View details for Web of Science ID 000618009800007

• Evaluating the Four-Way Performance Trade-Off for Data Stream Classification in Edge Computing IEEE TRANSACTIONS ON NETWORK AND SERVICE MANAGEMENT Lopes, J., Santana, E., Turrisi da Costa, V. G., Zarpelao, B., Barbon Junior, S. 2020; 17 (2): 1013-1025

  View details for DOI 10.1109/TNSM.2020.2983921

  View details for Web of Science ID 000542964800027

• DSTARS: A multi-target deep structure for tracking asynchronous regressor stacking APPLIED SOFT COMPUTING Mastelini, S., Santana, E., Cerri, R., Barbon Jr, S. 2020; 91

  View details for DOI 10.1016/j.asoc.2020.106215

  View details for Web of Science ID 000535478600003

• Photovoltaic Generation Forecast: Model Training and Adversarial Attack Aspects Santana, E. J., Silva, R. P., Zarpelão, B. B., Barbon Jr., S. 2020: 634-649

  View details for DOI 10.1007/978-3-030-61380-8_43

• Advantages of Multi-Target Modelling for Spectral Regression Spectroscopic Techniques & Artificial Intelligence for Food and Beverage Analysis Barbon Jr., S., Santana, E. J., Badaró, A. T., Borrás, N. A., Barbin, D. F. edited by Shukla, A. K. Springer Singapore. 2020: 95-121

  View details for DOI 10.1007/978-981-15-6495-6_5

• Multi-Output Tree Chaining: An Interpretative Modelling and Lightweight Multi-Target Approach JOURNAL OF SIGNAL PROCESSING SYSTEMS FOR SIGNAL IMAGE AND VIDEO TECHNOLOGY Mastelini, S., Turrisi da Costa, V., Santana, E., Nakano, F., Guido, R., Cerri, R., Barbon, S. 2019; 91 (2): 191-215

  View details for DOI 10.1007/s11265-018-1376-5

  View details for Web of Science ID 000456065100007

• Towards Meta-Learning for Multi-Target Regression Problems Aguiar, G. J., Santana, E. J., Mastelini, S. M., Mantovani, R. G., Barbon Jr., S. 2019: 337-382

  View details for DOI 10.1109/BRACIS.2019.00073

• Evaluating the Four-Way Performance Trade-Off for Stream Classification Turrisi da Costa, V. G., Santana, E., Lopes, J. F., Barbon, S., Miani, R., Camargos, L., Zarpelao, B., Rosas, E., Pasquini, R. SPRINGER INTERNATIONAL PUBLISHING AG. 2019: 3-17

  View details for DOI 10.1007/978-3-030-19223-5_1

  View details for Web of Science ID 000493300600001

• Predicting poultry meat characteristics using an enhanced multi-target regression method BIOSYSTEMS ENGINEERING Santana, E. J., Geronimo, B. C., Mastelini, S. M., Carvalho, R. H., Barbin, D. F., Ida, E. I., Barbon, S. 2018; 171: 193-204

  View details for DOI 10.1016/j.biosystemseng.2018.04.023

  View details for Web of Science ID 000437080100015

• Benchmarking multi-target regression methods Mastelini, S., Santana, E., Turrisi da Costa, V. G., Barbon, S., IEEE IEEE. 2018: 396-401

  View details for DOI 10.1109/BRACIS.2018.00075

  View details for Web of Science ID 000457627300067

• Stock Portfolio Prediction by Multi-Target Decision Support Provin Ribeiro da Silva, J., Santana, E., Mastelini, S., Barbon, S., ACM ASSOC COMPUTING MACHINERY. 2018: 262-269

  View details for DOI 10.1145/3229345.3229382

  View details for Web of Science ID 000457908100034

• DSTARS: A Multi-Target Deep Structure for Tracking Asynchronous Regressor Stack Mastelini, S., Santana, E., Cerri, R., Barbon, S., IEEE IEEE COMPUTER SOC. 2017: 19-24

  View details for DOI 10.1109/BRACIS.2017.30

  View details for Web of Science ID 000428685400004