Naila Camila da Rocha
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Naila Camila da Rocha has a total of 28 co-authors. Here are the top co-authors by number of shared publications:
- Abner Mácola Pacheco Barbosa
Department of Internal Medicine - UNESP, University Estadual Paulista, Botucatu, Brazil
9 shared publications - Luis Gustavo Modelli de Andrade
Sao Paulo State University
8 shared publications - Daniela Ferreira Salomão Pontes
Department of Internal Medicine - UNESP, University Estadual Paulista, Botucatu, Brazil
3 shared publications - Gustavo Fernandes Ferreira
Renal Transplant Program, Santa Casa de Misericordia de Juiz de Fora, Juiz de Fora, Brazil
3 shared publications - Juliana Machado-Rugolo
Universidade Estadual Paulista Júlio de Mesquita Filho, Brazil
3 shared publications - Allan B. Massie
Department of Surgery, New York University Langone Transplant Institute, New York, USA
2 shared publications
Latest Publications
- Open Access
- 6 October 2026
- Published by Springer Nature in BMC Nephrology
A data-driven approach to predict waiting times in kidney transplantation using machine learning
- 6 October 2026
- Published by Springer Nature in BMC Nephrology
Open AccessA data-driven approach to predict waiting times in kidney transplantation using machine learning
- Open Access
- 5 September 2025
- Published by Springer Nature in Journal of Imaging Informatics in Medicine
- Vol. 39 (3) , 2188-2198
Enhancing Breast Density Assessment in Mammograms Through Artificial Intelligence
Breast cancer is the leading cause of cancer-related deaths among women worldwide. Early detection through mammography significantly improves outcomes, with breast density acting as both a risk factor and a key interpretive feature. Although the Breast Imaging Reporting and Data System (BI-RADS) provides standardized density categories, assessments are often subjective and variable. While automated tools exist, most are proprietary and resource-intensive, limiting their use in underserved settings. There is a critical need for accessible, low-cost AI solutions that provide consistent breast density classification. This study aims to develop and evaluate an open-source, computer vision-based approach using deep learning techniques for objective breast density assessment in mammography images, with a focus on accessibility, consistency, and applicability in resource-limited healthcare environments. Our approach integrates a custom-designed convolutional neural network (CD-CNN) with an extreme learning machine (ELM) layer for image-based breast density classification. The retrospective dataset includes 10,371 full-field digital mammography images, previously categorized by radiologists into one of four BI-RADS breast density categories (A–D). The proposed model achieved a testing accuracy of 95.4%, with a specificity of 98.0% and a sensitivity of 92.5%. Agreement between the automated breast density classification and the specialists’ consensus was strong, with a weighted kappa of 0.90 (95% CI: 0.82–0.98). On the external and independent mini-MIAS dataset, the model achieved an accuracy of 73.9%, a precision of 81.1%, a specificity of 87.3%, and a sensitivity of 75.1%, which is comparable to the performance reported in previous studies using this dataset. The proposed approach advances breast density assessment in mammograms, enhancing accuracy and consistency to support early breast cancer detection.
- 5 September 2025
- Published by Springer Nature in Journal of Imaging Informatics in Medicine
- Vol. 39 (3) , 2188-2198
Open AccessEnhancing Breast Density Assessment in Mammograms Through Artificial Intelligence
Breast cancer is the leading cause of cancer-related deaths among women worldwide. Early detection through mammography significantly improves outcomes, with breast density acting as both a risk factor and a key interpretive feature. Although the Breast Imaging Reporting and Data System (BI-RADS) provides standardized density categories, assessments are often subjective and variable. While automated tools exist, most are proprietary and resource-intensive, limiting their use in underserved settings. There is a critical need for accessible, low-cost AI solutions that provide consistent breast density classification. This study aims to develop and evaluate an open-source, computer vision-based approach using deep learning techniques for objective breast density assessment in mammography images, with a focus on accessibility, consistency, and applicability in resource-limited healthcare environments. Our approach integrates a custom-designed convolutional neural network (CD-CNN) with an extreme learning machine (ELM) layer for image-based breast density classification. The retrospective dataset includes 10,371 full-field digital mammography images, previously categorized by radiologists into one of four BI-RADS breast density categories (A–D). The proposed model achieved a testing accuracy of 95.4%, with a specificity of 98.0% and a sensitivity of 92.5%. Agreement between the automated breast density classification and the specialists’ consensus was strong, with a weighted kappa of 0.90 (95% CI: 0.82–0.98). On the external and independent mini-MIAS dataset, the model achieved an accuracy of 73.9%, a precision of 81.1%, a specificity of 87.3%, and a sensitivity of 75.1%, which is comparable to the performance reported in previous studies using this dataset. The proposed approach advances breast density assessment in mammograms, enhancing accuracy and consistency to support early breast cancer detection.
- 25 October 2024
- Published by Oxford University Press (OUP) in Journal Of Nephrology
- Vol. 37 (9) , 2601-2608
Geographic inequities in hemodialysis access: a call to reassess dialysis facility locations in Brazil
Background: Patients who travel more than 60 min to undergo hemodialysis may experience higher mortality and lower quality of life. The primary aim of this study was to calculate the travel distance between patient city areas and dialysis facility care locations in Brazil, to highlight barriers and need to optimize access to chronic dialysis. Methods: We conducted a retrospective cohort study using claims data from the Brazilian Public Health System's database, focusing on kidney replacement therapy (KRT) by hemodialysis. Our study population comprised all patients undergoing hemodialysis in Brazil between January 2023 and December 2023. For patients from different city areas, we calculated the Haversine distance between the patient city area and the dialysis facility. Results: We evaluated 154,788 patients who received hemodialysis funded by the Brazilian Public Health System. Fifty-nine percent of the patients underwent dialysis in the same city area. Overall, patients traveled a median (IQR) distance of 35.9 [19.5 – 64.2] kilometers to the facilities, 48% traveled more than 40 km, with a maximum traveling distance of 353 km. Notably, the median distance traveled was shortest in the Southeast (27.6 km) and longest in the North (84.3 km). The number of patients that traveled more than 40 km was lower in the Southeast (32%) and higher in the North region (77%). Conclusion: The travel distance to the dialysis facility is an important inequity to KRT access in Brazil. In the South and Southeast, where there is a higher dialysis unit density, patients have greater regional availability of dialysis centers, and shorter traveling distances than in the North, Midwest, and Northeast regions. Graphical
- 25 October 2024
- Published by Oxford University Press (OUP) in Journal Of Nephrology
- Vol. 37 (9) , 2601-2608
Geographic inequities in hemodialysis access: a call to reassess dialysis facility locations in Brazil
Background: Patients who travel more than 60 min to undergo hemodialysis may experience higher mortality and lower quality of life. The primary aim of this study was to calculate the travel distance between patient city areas and dialysis facility care locations in Brazil, to highlight barriers and need to optimize access to chronic dialysis. Methods: We conducted a retrospective cohort study using claims data from the Brazilian Public Health System's database, focusing on kidney replacement therapy (KRT) by hemodialysis. Our study population comprised all patients undergoing hemodialysis in Brazil between January 2023 and December 2023. For patients from different city areas, we calculated the Haversine distance between the patient city area and the dialysis facility. Results: We evaluated 154,788 patients who received hemodialysis funded by the Brazilian Public Health System. Fifty-nine percent of the patients underwent dialysis in the same city area. Overall, patients traveled a median (IQR) distance of 35.9 [19.5 – 64.2] kilometers to the facilities, 48% traveled more than 40 km, with a maximum traveling distance of 353 km. Notably, the median distance traveled was shortest in the Southeast (27.6 km) and longest in the North (84.3 km). The number of patients that traveled more than 40 km was lower in the Southeast (32%) and higher in the North region (77%). Conclusion: The travel distance to the dialysis facility is an important inequity to KRT access in Brazil. In the South and Southeast, where there is a higher dialysis unit density, patients have greater regional availability of dialysis centers, and shorter traveling distances than in the North, Midwest, and Northeast regions. Graphical
- 30 August 2024
- Published by Wiley in Clinical Transplantation
- Vol. 38 (9) , e15446
Regional Disparities in Kidney Transplant Allocation in Brazil: A Retrospective Cohort Study
Background: Brazil has a large public transplant program, but it remains unclear if the kidney waitlist criteria effectively allocate organs. This study aimed to investigate whether gender, ethnicity, clinical characteristics, and Brazilian regions affect the chance of deceased donor kidney transplant (DDKT).Methods: We conducted a retrospective cohort study using the National Transplant System/Brazil database, which included all patients on the kidney transplant waitlist from January 2012 to December 2022, followed until May 2023. The primary outcome assessed was the chance of DDKT, measured using subdistribution hazard and cause‐specific hazard models (subdistribution hazard ratio [sHR]).Results: We analyzed 118 617 waitlisted patients over a 10‐year study period. Male patients had an sHR of 1.07 ([95% CI: 1.05–1.10],p < 0.001), indicating a higher chance of DDTK. Patients of mixed race and Yellow/Indigenous ethnicity had lower rates of receiving a transplant compared to Caucasian patients, with sHR of 0.97 (95% CI: 0.95–1) and 0.89 (95% CI: 0.95–1), respectively. Patients from the South region had the highest chance of DDKT, followed by those from the Midwest and Northeast, compared to patients from the Southeast, with sHR of 2.53 (95% CI: 2.47–2.61), 1.21 (95% CI: 1.16–1.27), and 1.10 (95% CI: 1.07–1.13), respectively. The North region had the lowest chance of DDTK, sHR of 0.29 (95% CI: 0.27–0.31).Conclusion: We found that women and racial minorities faced disadvantages in kidney transplantation. Additionally, we observed regional disparities, with the North region having the lowest chance of DDKT and longer times on dialysis before being waitlisted. In contrast, patients in the South regions had a chance of DDKT and shorter times on dialysis before being waitlisted. It is urgent to implement approaches to enhance transplant capacity in the North region and address race and gender disparities in transplantation.
- 30 August 2024
- Published by Wiley in Clinical Transplantation
- Vol. 38 (9) , e15446
Regional Disparities in Kidney Transplant Allocation in Brazil: A Retrospective Cohort Study
Background: Brazil has a large public transplant program, but it remains unclear if the kidney waitlist criteria effectively allocate organs. This study aimed to investigate whether gender, ethnicity, clinical characteristics, and Brazilian regions affect the chance of deceased donor kidney transplant (DDKT).Methods: We conducted a retrospective cohort study using the National Transplant System/Brazil database, which included all patients on the kidney transplant waitlist from January 2012 to December 2022, followed until May 2023. The primary outcome assessed was the chance of DDKT, measured using subdistribution hazard and cause‐specific hazard models (subdistribution hazard ratio [sHR]).Results: We analyzed 118 617 waitlisted patients over a 10‐year study period. Male patients had an sHR of 1.07 ([95% CI: 1.05–1.10],p < 0.001), indicating a higher chance of DDTK. Patients of mixed race and Yellow/Indigenous ethnicity had lower rates of receiving a transplant compared to Caucasian patients, with sHR of 0.97 (95% CI: 0.95–1) and 0.89 (95% CI: 0.95–1), respectively. Patients from the South region had the highest chance of DDKT, followed by those from the Midwest and Northeast, compared to patients from the Southeast, with sHR of 2.53 (95% CI: 2.47–2.61), 1.21 (95% CI: 1.16–1.27), and 1.10 (95% CI: 1.07–1.13), respectively. The North region had the lowest chance of DDTK, sHR of 0.29 (95% CI: 0.27–0.31).Conclusion: We found that women and racial minorities faced disadvantages in kidney transplantation. Additionally, we observed regional disparities, with the North region having the lowest chance of DDKT and longer times on dialysis before being waitlisted. In contrast, patients in the South regions had a chance of DDKT and shorter times on dialysis before being waitlisted. It is urgent to implement approaches to enhance transplant capacity in the North region and address race and gender disparities in transplantation.
- Open Access
- 6 August 2024
- Published by Wolters Kluwer Health in Kidney360
- Vol. 5 (10) , 1477-1489
KRT in Brazil: A Retrospective Cohort Study Based on Analysis of the Brazilian Public Health System
Key Points: A large comprehensive analysis of patients undergoing KRT within Brazil's Public Health System from 2015 to 2023. We reported an increase in the age at which dialysis began and a decline in the adoption of peritoneal dialysis over the years. We showed better hemodialysis adequacy as measured by single-pool Kt/V. Background: Brazil has the largest public health system providing universal coverage for chronic dialysis. The objective was to describe the number, sociodemographic, and clinical characteristics of patients undergoing KRT by dialysis within the public health system in Brazil. Methods: We carried out a retrospective cohort study analyzing the database from the Brazilian Public Health System, focusing on procedures related to KRT. The study encompassed both prevalent and incident patients who underwent KRT in Brazil between 2015 and 2023. Results: We observed an increase in the number and prevalence rate of dialysis patients from 2015 to 2023. We also noticed an increase in the age at dialysis initiation and in the prevalence of mixed-race patients and a reduction in the proportion of those undergoing peritoneal dialysis and with arteriovenous fistula. We identified an upward trajectory in the values of single-pool Kt/V over the years, contrasting with a decline in hemoglobin levels. The overall estimated prevalence rate of dialysis patients increased from 654 per million population (pmp) to 792 pmp over the years. The survival rates of incident patients undergoing KRT at 12 and 96 months were 81% and 60%, respectively. Conclusions: We reported an increase in the age at which dialysis began and a decline in the adoption of peritoneal dialysis over the years. Although there have been some improvements over the years resulting in better adequacy of hemodialysis as measured by Kt/V, controlling certain parameters, such as hemoglobin levels, has remained challenging.
- 6 August 2024
- Published by Wolters Kluwer Health in Kidney360
- Vol. 5 (10) , 1477-1489
Open AccessKRT in Brazil: A Retrospective Cohort Study Based on Analysis of the Brazilian Public Health System
Key Points: A large comprehensive analysis of patients undergoing KRT within Brazil's Public Health System from 2015 to 2023. We reported an increase in the age at which dialysis began and a decline in the adoption of peritoneal dialysis over the years. We showed better hemodialysis adequacy as measured by single-pool Kt/V. Background: Brazil has the largest public health system providing universal coverage for chronic dialysis. The objective was to describe the number, sociodemographic, and clinical characteristics of patients undergoing KRT by dialysis within the public health system in Brazil. Methods: We carried out a retrospective cohort study analyzing the database from the Brazilian Public Health System, focusing on procedures related to KRT. The study encompassed both prevalent and incident patients who underwent KRT in Brazil between 2015 and 2023. Results: We observed an increase in the number and prevalence rate of dialysis patients from 2015 to 2023. We also noticed an increase in the age at dialysis initiation and in the prevalence of mixed-race patients and a reduction in the proportion of those undergoing peritoneal dialysis and with arteriovenous fistula. We identified an upward trajectory in the values of single-pool Kt/V over the years, contrasting with a decline in hemoglobin levels. The overall estimated prevalence rate of dialysis patients increased from 654 per million population (pmp) to 792 pmp over the years. The survival rates of incident patients undergoing KRT at 12 and 96 months were 81% and 60%, respectively. Conclusions: We reported an increase in the age at which dialysis began and a decline in the adoption of peritoneal dialysis over the years. Although there have been some improvements over the years resulting in better adequacy of hemodialysis as measured by Kt/V, controlling certain parameters, such as hemoglobin levels, has remained challenging.
- Open Access
- 22 November 2023
- Published by Springer Nature in Thrombosis Journal
- Vol. 21 (1) , 1-12
A comprehensive model for assessing and classifying patients with thrombotic microangiopathy: the TMA-INSIGHT score
Background: Thrombotic Microangiopathy (TMA) is a syndrome characterized by the presence of anemia, thrombocytopenia and organ damage and has multiple etiologies. The primary aim is to develop an algorithm to classify TMA (TMA-INSIGHT score). Methods: This was a single-center retrospective cohort study including hospitalized patients with TMA at a single center. We included all consecutive patients diagnosed with TMA between 2012 and 2021. TMA was defined based on the presence of anemia (hemoglobin level < 10 g/dL) and thrombocytopenia (platelet count < 150,000/µL), signs of hemolysis, and organ damage. We classified patients in eight categories: infections; Malignant Hypertension; Transplant; Malignancy; Pregnancy; Thrombotic Thrombocytopenic Purpura (TTP); Shiga toxin-mediated hemolytic uremic syndrome (STEC-SHU) and Complement Mediated TMA (aHUS). We fitted a model to classify patients using clinical characteristics, biochemical exams, and mean arterial pressure at presentation. Results: We retrospectively retrieved TMA phenotypes using automatic strategies in electronic health records in almost 10 years (n = 2407). Secondary TMA was found in 97.5% of the patients. Primary TMA was found in 2.47% of the patients (TTP and aHUS). The best model was LightGBM with accuracy of 0.979, and multiclass ROC-AUC of 0.966. The predictions had higher accuracy in most TMA classes, although the confidence was lower in aHUS and STEC-HUS cases. Conclusion: Secondary conditions were the most common etiologies of TMA. We retrieved comorbidities, associated conditions, and mean arterial pressure to fit a model to predict TMA and define TMA phenotypic characteristics. This is the first multiclass model to predict TMA including primary and secondary conditions.
- 22 November 2023
- Published by Springer Nature in Thrombosis Journal
- Vol. 21 (1) , 1-12
Open AccessA comprehensive model for assessing and classifying patients with thrombotic microangiopathy: the TMA-INSIGHT score
Background: Thrombotic Microangiopathy (TMA) is a syndrome characterized by the presence of anemia, thrombocytopenia and organ damage and has multiple etiologies. The primary aim is to develop an algorithm to classify TMA (TMA-INSIGHT score). Methods: This was a single-center retrospective cohort study including hospitalized patients with TMA at a single center. We included all consecutive patients diagnosed with TMA between 2012 and 2021. TMA was defined based on the presence of anemia (hemoglobin level < 10 g/dL) and thrombocytopenia (platelet count < 150,000/µL), signs of hemolysis, and organ damage. We classified patients in eight categories: infections; Malignant Hypertension; Transplant; Malignancy; Pregnancy; Thrombotic Thrombocytopenic Purpura (TTP); Shiga toxin-mediated hemolytic uremic syndrome (STEC-SHU) and Complement Mediated TMA (aHUS). We fitted a model to classify patients using clinical characteristics, biochemical exams, and mean arterial pressure at presentation. Results: We retrospectively retrieved TMA phenotypes using automatic strategies in electronic health records in almost 10 years (n = 2407). Secondary TMA was found in 97.5% of the patients. Primary TMA was found in 2.47% of the patients (TTP and aHUS). The best model was LightGBM with accuracy of 0.979, and multiclass ROC-AUC of 0.966. The predictions had higher accuracy in most TMA classes, although the confidence was lower in aHUS and STEC-HUS cases. Conclusion: Secondary conditions were the most common etiologies of TMA. We retrieved comorbidities, associated conditions, and mean arterial pressure to fit a model to predict TMA and define TMA phenotypic characteristics. This is the first multiclass model to predict TMA including primary and secondary conditions.
- Open Access
Natural Language Processing to Extract Information from Portuguese-Language Medical Records
Studies that use medical records are often impeded due to the information presented in narrative fields. However, recent studies have used artificial intelligence to extract and process secondary health data from electronic medical records. The aim of this study was to develop a neural network that uses data from unstructured medical records to capture information regarding symptoms, diagnoses, medications, conditions, exams, and treatment. Data from 30,000 medical records of patients hospitalized in the Clinical Hospital of the Botucatu Medical School (HCFMB), São Paulo, Brazil, were obtained, creating a corpus with 1200 clinical texts. A natural language algorithm for text extraction and convolutional neural networks for pattern recognition were used to evaluate the model with goodness-of-fit indices. The results showed good accuracy, considering the complexity of the model, with an F-score of 63.9% and a precision of 72.7%. The patient condition class reached a precision of 90.3% and the medication class reached 87.5%. The proposed neural network will facilitate the detection of relationships between diseases and symptoms and prevalence and incidence, in addition to detecting the identification of clinical conditions, disease evolution, and the effects of prescribed medications.
Open AccessNatural Language Processing to Extract Information from Portuguese-Language Medical Records
Studies that use medical records are often impeded due to the information presented in narrative fields. However, recent studies have used artificial intelligence to extract and process secondary health data from electronic medical records. The aim of this study was to develop a neural network that uses data from unstructured medical records to capture information regarding symptoms, diagnoses, medications, conditions, exams, and treatment. Data from 30,000 medical records of patients hospitalized in the Clinical Hospital of the Botucatu Medical School (HCFMB), São Paulo, Brazil, were obtained, creating a corpus with 1200 clinical texts. A natural language algorithm for text extraction and convolutional neural networks for pattern recognition were used to evaluate the model with goodness-of-fit indices. The results showed good accuracy, considering the complexity of the model, with an F-score of 63.9% and a precision of 72.7%. The patient condition class reached a precision of 90.3% and the medication class reached 87.5%. The proposed neural network will facilitate the detection of relationships between diseases and symptoms and prevalence and incidence, in addition to detecting the identification of clinical conditions, disease evolution, and the effects of prescribed medications.
- Open Access
- 6 November 2022
- Published by MDPI AG in Journal of Clinical Medicine
- Vol. 11 (21) , 6581
Impact of the COVID-19 Pandemic on Solid Organ Transplant and Rejection Episodes in Brazil’s Unified Healthcare System
Background: Brazil has the world’s largest public organ transplant program, which was severely affected by the COVID-19 pandemic. The primary aim of the study was to evaluate differences in solid organ transplants and rejection episodes during the COVID-19 pandemic compared to the five years before the pandemic in the country. Methods: A seven-year database was built by downloading data from the DATASUS server. The pandemic period was defined as March 2020 to December 2021. The pre-pandemic period was from January 2015 to March 2020. Results: During the pandemic, the number of solid organ transplants decreased by 19.3% in 2020 and 22.6% in 2021 compared to 2019. We found a decrease for each evaluated organ, which was more pronounced for lung, pancreas, and kidney transplants. The seasonal plot of rejection data indicated a high rejection rate between 2018 and 2021. There was also an 18% (IRR 1.18 (95% CI 1.01 to 1.37), p = 0.04) increase in the rejection rate during the COVID-19 pandemic. Conclusions: The total number of organ transplants performed in 2021 represents a setback of six years. Transplant procedures were concentrated in the Southeast region of the country, and a higher proportion of rejections occurred during the pandemic. Together, these findings could have an impact on transplant procedures and outcomes in Brazil.
- 6 November 2022
- Published by MDPI AG in Journal of Clinical Medicine
- Vol. 11 (21) , 6581
Open AccessImpact of the COVID-19 Pandemic on Solid Organ Transplant and Rejection Episodes in Brazil’s Unified Healthcare System
Background: Brazil has the world’s largest public organ transplant program, which was severely affected by the COVID-19 pandemic. The primary aim of the study was to evaluate differences in solid organ transplants and rejection episodes during the COVID-19 pandemic compared to the five years before the pandemic in the country. Methods: A seven-year database was built by downloading data from the DATASUS server. The pandemic period was defined as March 2020 to December 2021. The pre-pandemic period was from January 2015 to March 2020. Results: During the pandemic, the number of solid organ transplants decreased by 19.3% in 2020 and 22.6% in 2021 compared to 2019. We found a decrease for each evaluated organ, which was more pronounced for lung, pancreas, and kidney transplants. The seasonal plot of rejection data indicated a high rejection rate between 2018 and 2021. There was also an 18% (IRR 1.18 (95% CI 1.01 to 1.37), p = 0.04) increase in the rejection rate during the COVID-19 pandemic. Conclusions: The total number of organ transplants performed in 2021 represents a setback of six years. Transplant procedures were concentrated in the Southeast region of the country, and a higher proportion of rejections occurred during the pandemic. Together, these findings could have an impact on transplant procedures and outcomes in Brazil.