- Asthma and respiratory diseases
- Respiratory and Cough-Related Research
- Allergic Rhinitis and Sensitization
- Pediatric health and respiratory diseases
- Animal health and immunology
- Infrastructure Maintenance and Monitoring
- Asphalt Pavement Performance Evaluation
- Vehicle Dynamics and Control Systems
- Diabetes and associated disorders
- Veterinary Equine Medical Research
- Transport Systems and Technology
- Topic Modeling
- Machine Learning in Healthcare
- Immunodeficiency and Autoimmune Disorders
- Railway Engineering and Dynamics
- Mechanical Engineering and Vibrations Research
- Drug-Induced Adverse Reactions
- Soil Mechanics and Vehicle Dynamics
- Medical research and treatments
- Cell Image Analysis Techniques
- Ethics and bioethics in healthcare
- Reproductive Physiology in Livestock
- Chronic Obstructive Pulmonary Disease (COPD) Research
- Biomedical Text Mining and Ontologies
- Transportation Safety and Impact Analysis
Universidad Católica de Córdoba
2015-2024
Rush University Medical Center
2024
Stanford University
2023-2024
Associação Brasileira de Oncologia Veterinária
2023
Critical Path Institute
2023
Accident Compensation Corporation
2023
Blue Marble Space Institute of Science
2022
Instituto Politécnico Nacional
2021-2022
Blue Marble Space
2022
Consejo Nacional de Investigaciones Científicas y Técnicas
2016-2020
The ability of large language models (LLMs) to follow natural instructions with human-level fluency suggests many opportunities in healthcare reduce administrative burden and improve quality care. However, evaluating LLMs on realistic text generation tasks for remains challenging. Existing question answering datasets electronic health record (EHR) data fail capture the complexity information needs documentation burdens experienced by clinicians. To address these challenges, we introduce...
Aim We analyzed data from 71 patients with chronic granulomatous disease (CGD) a confirmed genetic diagnosis, registered in the online Latin American Society of Primary Immunodeficiencies (LASID) database. Results CGD presented recurrent and severe infections caused by several organisms. The mean age at onset was 23.9 months, diagnosis 52.7 months. Recurrent pneumonia most frequent clinical condition (76.8%), followed lymphadenopathy (59.4%), granulomata (49.3%), skin (42%), diarrhea...
Problem IgG is the only antibody class, that is, actively transferred from mother to fetus across placenta by an active, neonatal Fc receptor (FcRn) mediated process during pregnancy, conferring passive immunity and protection against infections newborn first months of life. Preterm infants may not receive sufficient titers protective antibodies, as most them are after 34th week gestation. Because great importance this process, we investigated in a clinical setting placental transmission...
Cell and organelle shape are driven by diverse genetic environmental factors thus accurate quantification of cellular morphology is essential to experimental cell biology. Autoencoders a popular tool for unsupervised biological image analysis because they learn low-dimensional representation that maps images feature vectors generate semantically meaningful embedding space morphological variation. The learned can also be used clustering, dimensionality reduction, outlier detection, supervised...
Matching patients to clinical trials is a key unsolved challenge in bringing new drugs market. Today, identifying who meet trial's eligibility criteria highly manual, taking up 1 hour per patient. Automated screening challenging, however, as it requires understanding unstructured text. Large language models (LLMs) offer promising solution. In this work, we explore their application trial matching. First, design an LLM-based system which, given patient's medical history text, evaluates...
0. Abstract Background The integration of large language models (LLMs) in healthcare offers immense opportunity to streamline tasks, but also carries risks such as response accuracy and bias perpetration. To address this, we conducted a red-teaming exercise assess LLMs developed dataset clinically relevant scenarios for future teams use. Methods We convened 80 multi-disciplinary experts evaluate the performance popular across multiple medical scenarios. Teams composed clinicians, engineering...
The development of vision-language models (VLMs) is driven by large-scale and diverse multimodal datasets. However, progress toward generalist biomedical VLMs limited the lack annotated, publicly accessible datasets across biology medicine. Existing efforts are restricted to narrow domains, missing full diversity knowledge encoded in scientific literature. To address this gap, we introduce BIOMEDICA, a scalable, open-source framework extract, annotate, serialize entirety PubMed Central Open...
The rapid development of vision language models (VLMs) demands rigorous and reliable evaluation. However, current visual question answering (VQA) benchmarks often depend on open-ended questions, making accurate evaluation difficult due to the variability in natural responses. To address this, we introduce AutoConverter, an agentic framework that automatically converts these questions into multiple-choice format, enabling objective while reducing costly creation process. Our experiments...
Building a virtual cell capable of accurately simulating cellular behaviors in silico has long been dream computational biology. We introduce CellFlow, an image-generative model that simulates morphology changes induced by chemical and genetic perturbations using flow matching. Unlike prior methods, CellFlow models distribution-wise transformations from unperturbed to perturbed states, effectively distinguishing actual perturbation effects experimental artifacts such as batch -- major...
Objectives: Type 1 diabetes is an autoimmune disease characterized by destruction of pancreatic beta cells, requiring these individuals to be completely dependent on exogenous insulin. Intensive insulin therapy highly burdensome for patients and caregivers associated with the risk fatal hypoglycemia. Residual endogenous secretion reduced needs improved outcomes [1]. Our objective was understand predictors use in new-onset T1D patients, defined as less than 100 days from diagnosis. Although...
We present an open-source chemoinformatic workflow to generate and analyze complex abiological chemical networks discover novel compounds autocatalytic processes. demonstrate this pipeline's capabilities against a well-studied model system.
Previous studies have provided conflicting results about how living in a rural or urban environment influences schoolchildren with asthma and allergic diseases different ways. The aim of the present study was to evaluate if recurrent wheezing preschoolers from areas differ asthma, diseases, atopy.A cross-sectional-study Rafaela, Argentina, on 143 settings performed (2010-2012). Diagnosis (by positive predictive index [API]), (rhinitis, dermatitis), atopy skin prick test [SPT], peripheral...
The ability of large language models (LLMs) to follow natural instructions with human-level fluency suggests many opportunities in healthcare reduce administrative burden and improve quality care. However, evaluating LLMs on realistic text generation tasks for remains challenging. Existing question answering datasets electronic health record (EHR) data fail capture the complexity information needs documentation burdens experienced by clinicians. To address these challenges, we introduce...
It is expected that a lot of the new light vehicles in future will be electrical (EV). The storage capacity these EVs has potential to complement renewable energy resources and mitigate its intermittency. However, EV charging may have negative impact on power grid. This paper investigates Danish distribution system when aims reduce cost by at cheapest hours. Results show based price signal only adverse effect also proposes an alternate method where operator (DSO) optimizes while taking...
Two kidney transplant recipients from a single donor became infected with HTLV-1 (human T-lymphotropic virus type 1) in Spain. One developed myelopathy 8 months following surgery despite early prescription of antiretroviral therapy. The allograft was removed the second recipient at month due to rejection and immunosuppressors discontinued. To date, 3 years later, this patient remains but asymptomatic. infection recognized retrospectively donor, native Spaniard who had sex partners endemic...
Allergic rhinitis (AR) is one of the most common chronic diseases in children. However, it remains underdiagnosed and undertreated. Its prevalence has increased recent years varies from 2 to 25 %. Symptoms include sneezing, itching, runny nose, nasal congestion. A correct diagnosis treatment AR its comorbidities such as rhinosinusitis with or without polyposis, conjunctivitis, otitis media, bronchial asthma respiratory tract infections, are important reduce negative impact on quality life...