Publications by authors named "M I Guimaraes"
In 2019, COVID-19 began one of the greatest public health challenges in history, reaching pandemic status the following year. Systems capable of predicting individuals at higher risk of progressing to severe forms of the disease could optimize the allocation and direction of resources. In this work, we evaluated the performance of different Machine Learning algorithms when predicting clinical outcomes of patients hospitalized with COVID-19, using clinical data from hospital admission alone.
View Article and Find Full Text PDFMachine learning models are widely applied across diverse fields, including nearly all segments of human activity. In healthcare, artificial intelligence techniques have revolutionized disease diagnosis, particularly in image classification. Although these models have achieved significant results, their lack of explainability has limited widespread adoption in clinical practice.
View Article and Find Full Text PDFArticle Synopsis
- RF titers are significant in the pathophysiology of rheumatoid arthritis (RA) and vary in their clinical impact, with high RF titers linked to poorer health outcomes.
- A study with 1,097 RA adults found a substantial portion had positive RF, with high titers prevalent, and identified associations of high RF with factors such as tobacco use and higher body mass index.
- High RF levels correlated with increased disease activity, reduced functional capacity, and greater use of corticosteroids and biological drugs, indicating a need for careful monitoring in RA patients.
This pipeline presents a refined approach for deriving personalized neurobiological insights from iPSC-derived neurospheres. By employing Tandem Mass Tag (TMT) labeling, we optimized sample pooling and multiplexing for robust comparative analysis across experimental conditions, maximizing data yield per sample. Through single-patient-derived neurospheres-composed of neural progenitor cells, early neurons, and radial glia-this study explores proteomic profiling to mirror the cellular complexity of neurodevelopment more accurately than traditional 2D cultures.
View Article and Find Full Text PDFArticle Synopsis
- Obesity adversely affects kidney health, but the specific kidney dysfunction markers in bariatric surgery candidates are not well understood, prompting a study comparing these biomarkers to those of living kidney donors.
- The study involved matching 200 bariatric candidates with 200 living kidney donors based on sex and age, using a 24-hour urine collection to assess protein levels and kidney function.
- Findings indicated that patients with obesity had higher creatinine clearance and proteinuria than kidney donors, underscoring the need to reconsider how kidney function is evaluated in obese individuals considering bariatric surgery, particularly regarding body surface area adjustments.