A5050419600- Machine Learning in Healthcare
- Artificial Intelligence in Healthcare
- AI in cancer detection
- Phonocardiography and Auscultation Techniques
- Forecasting Techniques and Applications
- Artificial Intelligence in Healthcare and Education
- Cutaneous Melanoma Detection and Management
- COVID-19 diagnosis using AI
- Maternal Mental Health During Pregnancy and Postpartum
- Time Series Analysis and Forecasting
- Forensic Anthropology and Bioarchaeology Studies
- Insurance, Mortality, Demography, Risk Management
- Maternal and Neonatal Healthcare
- Traditional Chinese Medicine Studies
- Autopsy Techniques and Outcomes
- Grief, Bereavement, and Mental Health
- Human-Automation Interaction and Safety
- Digital Imaging for Blood Diseases
- Prenatal Substance Exposure Effects
- Maternal and Perinatal Health Interventions
- Chronic Disease Management Strategies
- Advanced Data Compression Techniques
- Health disparities and outcomes
Universidade Federal de Mato Grosso
2014-2025
Universidade Federal de Goiás
2013-2018
Purpose The Radiological Society of North America (RSNA) Pediatric Bone Age Machine Learning Challenge was created to show an application machine learning (ML) and artificial intelligence (AI) in medical imaging, promote collaboration catalyze AI model creation, identify innovators imaging. Materials Methods goal this challenge solicit individuals teams create algorithm or using ML techniques that would accurately determine skeletal age a curated data set pediatric hand radiographs. primary...
This work extends PneumoCAD, a Computer-Aided Diagnosis system for detecting pneumonia in infants using radiographic images [1], with the aim of improving system's accuracy and robustness. We implement compare three contemporary machine learning classifiers, namely: Näıve Bayes, K-Nearest Neighbor (KNN), Support Vector Machines (SVM). Results our experiments demonstrate that SVM classifier produces best overall results.
This work extends PneumoCAD, a Computer-Aided Diagnosis system for detecting pneumonia in infants using radiographic images, with the aim of improving system's accuracy and robustness. We implement compare five con-temporary machine learning classifiers, namely: Naïve Bayes, K-Nearest Neighbor (KNN), Support Vector Machines (SVM), Multi-Layer Perceptron (MLP) Decision Tree, combined three dimensionality reduction algorithms: Sequential Forward Selection (SFS), Principal Component Analysis...
This paper describes the participation of Araguaia Medical Vision Lab at International Skin Imaging Collaboration 2017 Lesion Challenge. We describe use deep convolutional neural networks in attempt to classify images Melanoma and Seborrheic Keratosis lesions. With finetuned GoogleNet AlexNet we attained results 0.950 0.846 AUC on respectively.
This paper aims to do time series forecasting of live births in Brazil with modern tree-based machine learning models. These models are popular choices for due their ability model non-linear relationships, so they were applied birth multiple covariates. The study uses data from the Brazilian Ministry Health train and evaluate models, following guidelines Ministry's expectations needs using forecasts public policy planning. all 450 micro-regions records between years 2000 2020. objective is a...
The use of forecasting models is becoming even more common in healthcare and administration applications because it can be a reliable decision support tool. Live birth rate health index that directly linked with maternal newborn its prediction assist managers to anticipate resources destined for obstetric pediatric services. Thus, the objective this work forecast number live births state Golás (Brazil) 24-month horizon, providing useful information planning implementation public policies....
<title>Abstract</title> <bold>Background:</bold> Pregnancy is a period characterized by mystique and societal expectations surrounding women. However, it can also be challenging time for The mental well-being of pregnant woman influenced, in part, her obstetric history the psychosocial context. Detecting stress, anxiety, depression women crucial reducing health problems, particularly issues. <bold>Results:</bold> A project named Digital - <italic>Grávida Digital</italic> Portuguese currently...
Major Depressive Disorder and anxiety disorders affect millions globally, contributing significantly to the burden of mental health issues. Early screening is crucial for effective intervention, as timely identification issues can improve treatment outcomes. Artificial intelligence (AI) be valuable improving disorders, enabling early intervention better AI-driven leverage analysis multiple data sources, including facial features in digital images. However, existing methods often rely on...
Managing patients with chronic diseases is a major and growing healthcare challenge in several countries. A condition, such as diabetes, an illness that lasts long time does not go away, often leads to the patient's health gradually getting worse. While recent works involve raw electronic record (EHR) from hospitals, this work uses only financial records plan providers (medical claims) predict diabetes disease evolution self-attentive recurrent neural network. The use of data due possibility...
Supervised learning with irregularly sampled time series have been a challenge to Machine Learning methods due the obstacle of dealing irregular intervals. Some papers introduced recently recurrent neural network models that deals irregularity, but most them rely on complex mechanisms achieve better performance. This work propose novel method represent timestamps (hours or dates) as dense vectors using sinusoidal functions, called Time Embeddings. As data input it and can be applied machine...