About

Maju Brunette, PhD, is an Associate Professor at the School of Health and Rehabilitation Sciences and serves as the Global Health Equity Chair on the Council on the Physical Environment (COPE) at the University of Ohio State University. She is also the Director of Mujeres en Salud Global Peru Division of Health Sciences. A Peruvian native, Dr. Brunette champions health equity for historically marginalized communities in the Americas. Drawing on her background as an engineer and systems thinker, she co-designs global public health interventions through a decolonizing and gender equity lens. Her primary areas of interest include health equity, tuberculosis prevention and control, community-based participatory research, decolonizing global health, migration, and health.

Research topics

• Computer Science
• Humanities
• Artificial Intelligence
• Medicine
• Political Science
• Engineering drawing
• Family medicine
• Medical physics
• Art
• Engineering
• Nursing
• Pathology
• Surgery
• Medical emergency
• Operating system
• Data science
• Geography

Selected publications

• Using Machine Learning to Develop a Predictive Model of Infant Hypoglycemia Based on Maternal and Infant Variables in an Electronic Health Record

  UNC Libraries · 2025-03-18

  articleOpen access

  All newborns experience low blood glucose levels when they first initiate carbohydrate metabolism. Some levels remain low, with potential seizures and severe brain injury. Predicting newborns at higher risk is clinically useful because newborns can have their blood sugar raised with breastfeeding, donor milk, formula, or oral dextrose gels. Additionally, informing parents of this higher risk can enhance shared decision-making in the first 48 hours after birth. To address this, we propose three predictive models using binary logistic regression for newborns receiving treatment with oral dextrose gels for hypoglycemia. The first is a parsimonious model, where a high-risk newborn's first blood glucose value is highly predictive of requiring an oral dextrose gel treatment. The second model can be used earlier in the clinical workflow. It is based on the most predictive variables that are also electronically available for all newborns and do not change much in the electronic health record. The third model explores the most predictive variables based on a conceptual model of factors associated with health disparities. These three models are informed from insights gleaned by an exploratory analysis of alternative outcome measures, variables, and threshold cutoffs using a standard heuristic of greedily finding the highest average difference for records on both sides of partitions. We discuss how the dynamics of when data are available during a hospital stay in the postnatal care unit for all patients impact the selection of useful variables for electronically-based decision support. We plan to modify handouts for postnatal care nurses that detail treatment guidance and support shared decision-making. We plan to embed stratified guidance, recommended scripts for high and low-risk cohorts, orientation materials for float and junior nurses, and patient-facing educational materials.

  PublisherDOI

• Afrontando los retos del fragmentado sistema de salud peruano: El papel transformador de los académicos

  Revista Médica Herediana · 2024-03-27 · 1 citations

  articleOpen access
  PublisherOA PDFDOI

• The community as an active part in the implementation of interventions for the prevention and care of tuberculosis: A scoping review

  PLOS Global Public Health · 2023-12-15 · 22 citations

  reviewOpen accessSenior author

  Interventions involving direct community stakeholders include a variety of approaches in which members take an active role in improving their health. We evaluated studies in which the community has actively participated to strengthen tuberculosis prevention and care programs. A literature search was performed in Pubmed, Scopus, ERIC, Global Index Medicus, Scielo, Cochrane Library, LILACS, Google Scholar, speciality journals, and other bibliographic references. The primary question for this review was: ¿what is known about tuberculosis control interventions and programs in which the community has been an active part?. Two reviewers performed the search, screening, and selection of studies independently. In cases of discrepancies over the eligibility of an article, it was resolved by consensus. 130 studies were selected, of which 68.47% (n = 89/130) were published after 2010. The studies were conducted in Africa (44.62%), the Americas (22.31%) and Southeast Asia (19.23%). It was found that 20% (n = 26/130) of the studies evaluated the participation of the community in the detection/active search of cases, 20.77% (n = 27/130) in the promotion/prevention of tuberculosis; 23.07% (n = 30/130) in identifying barriers to treatment, 46.15% (n = 60/130) in supervision during treatment and 3.08% (n = 4/130) in social support for patient. Community participation not only strengthens the capacities of health systems for the prevention and care of tuberculosis, but also allows a better understanding of the disease from the perspective of the patient and the affected community by identifying barriers and difficulties through of the tuberculosis care cascade. Engaging key community stakeholders in co-creating solutions offers a critical pathway for local governments to eradicate TB.

  PublisherOA PDFDOI

• Using Machine Learning to Develop a Predictive Model of Infant Hypoglycemia Based on Maternal and Infant Variables in an Electronic Health Record

  Proceedings of the International Symposium on Human Factors and Ergonomics in Health Care · 2023-03-01 · 2 citations

  article

  All newborns experience low blood glucose levels when they first initiate carbohydrate metabolism. Some levels remain low, with potential seizures and severe brain injury. Predicting newborns at higher risk is clinically useful because newborns can have their blood sugar raised with breastfeeding, donor milk, formula, or oral dextrose gels. Additionally, informing parents of this higher risk can enhance shared decision-making in the first 48 hours after birth. To address this, we propose three predictive models using binary logistic regression for newborns receiving treatment with oral dextrose gels for hypoglycemia. The first is a parsimonious model, where a high-risk newborn's first blood glucose value is highly predictive of requiring an oral dextrose gel treatment. The second model can be used earlier in the clinical workflow. It is based on the most predictive variables that are also electronically available for all newborns and do not change much in the electronic health record. The third model explores the most predictive variables based on a conceptual model of factors associated with health disparities. These three models are informed from insights gleaned by an exploratory analysis of alternative outcome measures, variables, and threshold cutoffs using a standard heuristic of greedily finding the highest average difference for records on both sides of partitions. We discuss how the dynamics of when data are available during a hospital stay in the postnatal care unit for all patients impact the selection of useful variables for electronically-based decision support. We plan to modify handouts for postnatal care nurses that detail treatment guidance and support shared decision-making. We plan to embed stratified guidance, recommended scripts for high and low-risk cohorts, orientation materials for float and junior nurses, and patient-facing educational materials.

  PublisherDOI

• The community as an active part in the implementation of interventions for the prevention and control of tuberculosis: a scoping review

  medRxiv · 2023-01-11 · 4 citations

  reviewOpen accessSenior author

  Interventions involving direct community stakeholders include a variety of approaches in which members take an active role in improving their health. We evaluated studies in which the community has actively participated to strengthen tuberculosis prevention and control programs. A literature search was performed in Pubmed, Scopus, ERIC, Global Index Medicus, Scielo, Cochrane Library, LILACS, Google Scholar, speciality journals, and other bibliographic references. The primary question for this review was: what is known about tuberculosis control interventions and programs in which the community has been an active part?. Two reviewers performed the search, screening and selection of studies independently. In cases of discrepancies over the eligibility of an article, it was resolved by consensus. 130 studies were selected, of which 68.47% (n=89/130) were published after 2010. The studies were conducted in Africa (44.62%), the Americas (22.31%) and Southeast Asia (19.23%). It was found that 20% (n=26/130) of the studies evaluated the participation of the community in the detection/active search of cases, 20.77% (n=27/130) in the promotion/prevention of tuberculosis; 23.07% (n=30/130) in identifying barriers to treatment, 46.15% (n=60/130) in supervision during treatment and 3.08% (n=4/130) in social support for patient. Community participation not only strengthens the capacities of health systems for the prevention and control of tuberculosis, but also allows a better understanding of the disease from the perspective of the patient and the affected community by identifying barriers and difficulties through of the tuberculosis care cascade. Engaging key community stakeholders in co-creating solutions offers a critical pathway for local governments to eradicate TB.

  PublisherOA PDFDOI

• eRxNet: A Pipeline of Convolutional Neural Networks for Tuberculosis Screening

  International Journal of Semantic Computing · 2022-03-01 · 1 citations

  article

  Tuberculosis (TB) is a contagious disease affecting millions of people annually worldwide. Treatment of this disease and reduction in local epidemics can be improved markedly by increasing the speed and efficiency of screening and diagnosis. eRxNet is a pipeline of convolutional neural networks designed to provide healthcare professionals with detailed and accurate analysis of chest X-rays (CXRs) for TB screening. The pipeline combines whole image classification, object detection (bounding boxes), and instance segmentation (polygonal masks) to provide data analysis at varying levels of detail. In order to construct a high performing system, a comparison of different CNN architectures applied to these tasks is presented. Images from two large TB datasets, UML-Peru and TBX11K, were used for training and evaluation of the models. Combining the two datasets required the development of a preprocessing stage which includes lung segmentation and image enhancement. We show that the resulting four-stage pipeline of CNNs, using a combination of DenseNet, Faster R-CNN, and Mask R-CNN, has sufficiently strong performance to be a useful tool for TB screening.

  PublisherDOI

• eRxNet: A Pipeline of Convolutional Neural Networks for Tuberculosis Screening

  2021-09-01 · 3 citations

  article

  Tuberculosis (TB) is a contagious disease affecting millions of people annually worldwide. Treatment of this disease and reduction in local epidemics can be improved markedly by increasing the speed and efficiency of screening and diagnosis. eRxNet is a pipeline of convolutional neural networks designed to provide healthcare professionals with detailed and accurate analysis of chest X-rays (CXRs) for TB screening. The pipeline combines whole image classification, object detection (bounding boxes), and instance segmentation (polygonal masks) to provide data analysis at varying levels of detail. In order to construct a high performing system, a comparison of different CNN architectures applied to these tasks is presented. Images from two large TB datasets, UML-Peru and TBX11K, were used for training and evaluation of the models. Combining the two datasets required the development of a preprocessing stage which includes lung segmentation and image enhancement. We show that the resulting four stage pipeline of CNNs, using a combination of DenseNet, Faster R-CNN, and Mask R-CNN, has sufficiently strong performance to be a useful tool for TB screening.

  PublisherDOI

• Object Detection and Instance Segmentation in Chest X-rays for Tuberculosis Screening

  International Journal of Transdisciplinary Artificial Intelligence · 2021-03-01

  articleOpen access

  Tuberculosis (TB) is a highly contagious disease leading to the deaths of approximately 2 million people annually. TB primarily affects the lungs and is spread through the air when people cough, sneeze, or spit. Providing healthcare professionals with better information, at a faster pace, is essential for combating this disease, especially in Low and Middle Income Countries (LMICs) with resource-constrained health systems. In this paper we describe how using convolution neural networks (CNNs) with an object level annotated dataset of chest X-rays (CXRs) allows us to identify the location of pulmonary issues indicative of TB. We compare the performance of Faster R-nobreakdash-CNN, Mask R-nobreakdash-CNN, Cascade versions of each, and SOLOv2, demonstrating reasonable results with a small dataset. We present a method to reduce the false positive rate by comparing the location of a detected object with the known location of areas where the detected class is likely to occur in the lung. Our results show that object detection and instance segmentation of CXRs can be achieved with a dataset of high-quality, object level annotations, and could be used as part of an automated TB screening process. This work has the potential to improve the speed of TB diagnosis in LMICs, if properly integrated into the healthcare system and adapted to existing clinical workflows and local regulations.

  PublisherOA PDFDOI

• Moving the needle on global health equity: a look back from 2030

  Archives of Environmental & Occupational Health · 2021-04-03 · 3 citations

  articleOpen access1st authorCorresponding

  The timing cannot be better for us to critically reflect about how our scholarly efforts can impact the world we want to see in 2030. It is only by taking the time to pause that we may begin to be ...

  PublisherOA PDFDOI

• eRx – A technological advance to speed-up TB diagnostics

  Smart Health · 2020 · 11 citations

  Senior authorCorresponding
  • Computer Science
  • Artificial Intelligence
  • Medicine
  PublisherDOI

Recent grants

• SCH: INT A.Soclotechnilcal Systems Systems Approach for Improving Tuberculosis Diagnostics Using Mobile Health Technologies

  NIH · $1.3M · 2015–2021

Frequent coauthors

• Benyuan Liu

  Air Force Medical University

  11 shared

• César Ugarte‐Gil

  The University of Texas Medical Branch at Galveston

  8 shared

• Yu Cao

  University of Massachusetts Lowell

  8 shared

• Walter H. Curioso

  Universidad Continental

  6 shared

• Lesly Chávez-Rimache

  Universidad San Ignacio de Loyola

  6 shared

• Terence Griffin

  University of Massachusetts Lowell

  5 shared

• Tonya L. Smith‐Jackson

  North Carolina Agricultural and Technical State University

  4 shared

• Chang Liu

  4 shared

Education

• Ph.D., Industrial & Systems Engineering

  University of Wisconsin–Madison

  2002

Awards & honors

• 2024 Global Health Symposium Keynote address: “On my journey…
• MSc in Global Healthcare Leadership Scholarship for Women (2…
• United Nations Global Compact for Migration – Side technical…
• University of Massachusetts Lowell Office of the Chancellor…
• University of Wisconsin-Madison Industrial Engineering Depar…