Bruno Aparecido Cazotti Ramalho

Verified @usp.br

School of Pharmaceutical Sciences of Ribeirão Preto, University of São Paulo

Bruno Aparecido Cazotti Ramalho


            Download Compact PDF  
https://researchid.co/brunoramalho

RESEARCH, TEACHING, or OTHER INTERESTS

Artificial Intelligence, Pharmacy
4

Scopus Publications

11

Scholar Citations

2

Scholar h-index

Scopus Publications

  • Potentially inappropriate medications in outpatient palliative care: retrospective longitudinal study of exposure and costs
    Júlia Raso Ferreira De Oliveira, Bruno Aparecido Cazotti Ramalho, Bruno Vieira Felix Da Silva, Nátali Voltolini Marinho, Marília Silveira De Almeida Campos, Nereida Kilza Da Costa Lima, Leonardo Régis Leira Pereira, Maria Olivia Barboza Zanetti, Fabiana Rossi Varallo
    BMJ Supportive and Palliative Care, 2026
    Objective To identify potentially inappropriate medications (PIMs) using deprescribing tools and to evaluate longitudinal changes in the number of PIMs and their associated costs between baseline (T₀) and follow-up (T F ) among patients receiving outpatient palliative care (PC). Methods This retrospective longitudinal study reviewed electronic medical records of adult patients (≥18 years) who initiated follow-up in 2022 at an outpatient PC clinic of a Brazilian teaching hospital. Patients were monitored for up to 12 months. PIMs were identified using the STOPPFrail version 2 (v2) and OncPal criteria at baseline (T₀) and at the last outpatient consultation (T F ). Differences in the number of PIMs and their associated costs between T₀ and T F were analysed using descriptive statistics and paired comparisons with the Wilcoxon signed-rank test. Results Among 42 patients included in the longitudinal analysis, STOPPFrail v2 identified a small but statistically significant increase in PIM exposure over time (median 3 (IQR 3–4) at T₀ vs 4 (IQR 3–5) at T F ; p=0.041). Median PIM-related costs also increased, from US$0.06 (IQR 0.03–0.25) at T₀ to US$0.14 (IQR 0.04–0.26) at T F ; however, this difference was not statistically significant (p=0.165). In contrast, according to the OncPal criteria, PIM exposure remained stable (median 4 (IQR 3–5) at both T₀ and T F ; p=0.591). Likewise, PIM-related costs showed no significant change, increasing from US$0.05 (IQR 0.01–0.10) at T₀ to US$0.08 (IQR 0.04–0.14) at T F (p=0.117). Conclusions PIM exposure remained high over time in outpatient PC, with minimal variation depending on the assessment tool used and no significant reduction in medication-related costs. These findings highlight the complexity of prescribing in this population and the need for new deprescribing strategies.
  • The impact of the orientation of MRI slices on the accuracy of Alzheimer’s disease classification using convolutional neural networks (CNNs)
    Bruno A. C. Ramalho, Lara R. Bortolato, Naomy D. Gomes, Lauro Wichert-Ana, Fernando Eduardo Padovan-Neto, Marco Antonio A. da Silva, Kleython José C. C. de Lacerda
    Journal of Medical Artificial Intelligence, 2024
    Background: Alzheimer’s disease (AD) is the leading cause of major neurocognitive disorders, affecting approximately 50 million people worldwide. Due to its high prevalence, AD significantly impacts patients’ quality of life and poses a substantial challenge to healthcare systems. Diagnosis is intricate, with specificity and sensitivity rates falling below the ideal. Early identification of AD is essential to increase the effectiveness of pharmacotherapeutic treatment and improve quality of life. Consequently, there is a quest for innovative methods, such as machine learning and deep learning, to automate the diagnosis of AD in its early stages. Methods: We developed and validated a convolutional neural network (CNN) algorithm using the Keras Sequential API in Python to investigate the impact of slicing T1-weighted magnetic resonance images on the classification of patients with mild cognitive impairment (MCI) and healthy patients (NC), grouped based on scores on the Mini-Mental State Examination (MMSE). We selected 318 patients (250 healthy and 68 MCI) with a minimum of 16 years of education (equivalent to a completed undergraduate degree). The training, testing, and validation datasets were split in a 70/15/15 ratio for each slice. Results: The CNN achieved high accuracy values in classifying healthy and MCI groups, ranging between 97% and 99% depending on the slice, the number of training epochs, and batch size. In addition to precision, the F1-score, recall, and precision parameters were also evaluated, with values above 91%. Generally, the coronal slice produced the best results, followed by the axial and the sagittal slices, which nevertheless showed high performance, standing out individually in different evaluation parameters. Notably, the choice of batch size and the number of epochs also influenced the network’s classification. Conclusions: Our study findings indicate that utilizing CNN in conjunction with selecting a coronal slice proves to be a promising tool for facilitating the early-stage diagnosis of neurodegenerative diseases, such as AD, through magnetic resonance imaging analysis, enabling more effective treatments and appropriate future planning. Moving forward, we aim to investigate whether these results replicate across other imaging modalities, such as positron emission tomography, and explore additional datasets.
  • Introduction to quantum machine learning, its applications and advantages
    Naomy Duarte Gomes, Togni Togni, Bruno Aparecido Cazotti Ramalho, Kleython José Coriolano Cavalcanti de Lacerda, Paulo Henrique Ferreira
    Revista Brasileira De Ensino De Fisica, 2024
    Neste artigo, abordamos o campo emergente do aprendizado de máquina quântico (AMQ) e suas aplicações inovadoras. Exploramos uma visão geral das bases da mecânica quântica relevantes para o aprendizado de máquina, destacando como os princípios quânticos podem ser utilizados para processar informações de maneira mais eficiente em comparação às abordagens clássicas. Discutimos o passo a passo de um exemplo de algoritmo quântico utilizando Qiskit, comparando-o com seu análogo clássico. Abordamos as vantagens do AMQ, incluindo o potencial de aceleração em problemas de grande escala e a capacidade de lidar com dados altamente dimensionais. Por fim, são discutidos os desafios atuais e as perspectivas futuras do campo, enfatizando seu papel na transformação de diversos setores tecnológicos. Este artigo serve como uma introdução abrangente para aqueles interessados em explorar a interseção entre aprendizado de máquina e mecânica quântica, destacando as promissoras oportunidades que essa combinação oferece.
  • Automating behavioral analysis in neuroscience: Development of an open-source python software for more consistent and reliable results
    A.J.D.O. Cerveira, B.A.C. Ramalho, C.C.B. de Souza, A.P. Spadaro, B.A. Ramos, L. Wichert-Ana, F.E. Padovan-Neto, K.J.C.C. de Lacerda
    Journal of Neuroscience Methods, 2023

RECENT SCHOLAR PUBLICATIONS

  • Potentially inappropriate medications in outpatient palliative care: retrospective longitudinal study of exposure and costs
    JRF De Oliveira, BAC Ramalho, BVF Da Silva, NV Marinho, ...
    BMJ Supportive & Palliative Care , 2026
    2026
  • Detecting Potential Pharmacovigilance Signals in Z-Drugs: A Comparative Study of Inn Stems and Drug Names
    LR Bortolato, BAC Ramalho, MSA Campos, LR Pereira, MOB Zanetti, ...
    PHARMACOEPIDEMIOLOGY AND DRUG SAFETY 35 , 2026
    2026
  • Introduction to quantum machine learning, its applications and advantages
    ND Gomes, T Togni, BAC Ramalho, KJCC Lacerda, PH Ferreira
    Revista Brasileira de Ensino de Física 46, e20240230 , 2024
    2024
    Citations: 1
  • The impact of the orientation of MRI slices on the accuracy of Alzheimer’s disease classification using convolutional neural networks (CNNs)
    BAC Ramalho, LR Bortolato, ND Gomes, L Wichert-Ana, ...
    Journal of Medical Artificial Intelligence 7, 35 , 2024
    2024
    Citations: 6
  • Automating behavioral analysis in neuroscience: Development of an open-source python software for more consistent and reliable results
    AJDO Cerveira, BAC Ramalho, CCB de Souza, AP Spadaro, BA Ramos, ...
    Journal of Neuroscience Methods 398, 109957 , 2023
    2023
    Citations: 4

MOST CITED SCHOLAR PUBLICATIONS

  • The impact of the orientation of MRI slices on the accuracy of Alzheimer’s disease classification using convolutional neural networks (CNNs)
    BAC Ramalho, LR Bortolato, ND Gomes, L Wichert-Ana, ...
    Journal of Medical Artificial Intelligence 7, 35 , 2024
    2024
    Citations: 6
  • Automating behavioral analysis in neuroscience: Development of an open-source python software for more consistent and reliable results
    AJDO Cerveira, BAC Ramalho, CCB de Souza, AP Spadaro, BA Ramos, ...
    Journal of Neuroscience Methods 398, 109957 , 2023
    2023
    Citations: 4
  • Introduction to quantum machine learning, its applications and advantages
    ND Gomes, T Togni, BAC Ramalho, KJCC Lacerda, PH Ferreira
    Revista Brasileira de Ensino de Física 46, e20240230 , 2024
    2024
    Citations: 1
  • Potentially inappropriate medications in outpatient palliative care: retrospective longitudinal study of exposure and costs
    JRF De Oliveira, BAC Ramalho, BVF Da Silva, NV Marinho, ...
    BMJ Supportive & Palliative Care , 2026
    2026
  • Detecting Potential Pharmacovigilance Signals in Z-Drugs: A Comparative Study of Inn Stems and Drug Names
    LR Bortolato, BAC Ramalho, MSA Campos, LR Pereira, MOB Zanetti, ...
    PHARMACOEPIDEMIOLOGY AND DRUG SAFETY 35 , 2026
    2026