A5084658628- Artificial Intelligence in Healthcare
- Ethics in Clinical Research
- Data-Driven Disease Surveillance
- Artificial Intelligence in Healthcare and Education
- Antibiotic Use and Resistance
- SARS-CoV-2 and COVID-19 Research
- COVID-19 diagnosis using AI
- Nursing Diagnosis and Documentation
- Vaccine Coverage and Hesitancy
- COVID-19 Impact on Reproduction
- Scientific Computing and Data Management
- COVID-19 Pandemic Impacts
- Pregnancy and Medication Impact
- Essential Oils and Antimicrobial Activity
- Anomaly Detection Techniques and Applications
- Stress and Burnout Research
- Surgical site infection prevention
- Antioxidant Activity and Oxidative Stress
- Quality and Safety in Healthcare
- Cardiac Structural Anomalies and Repair
- Nursing care and research
- Digital and Cyber Forensics
- Patient Satisfaction in Healthcare
- Infection Control in Healthcare
- Data Quality and Management
University Medical Center Utrecht
2023-2024
Utrecht University
2024
Hospital de Clínicas de Porto Alegre
2016-2020
Sport Lisboa e Benfica
2018
University of Lisbon
2013
Objective: to describe the development of a predictive nursing workload classifier model, using artificial intelligence. Method: retrospective observational study, secondary sources electronic patient records, machine learning. The convenience sample consisted 43,871 assessments carried out by clinical nurses Perroca Patient Classification System, which served as gold standard, and data from medical records 11,774 patients, constituted variables. In order organize carry analysis, Dataiku®...
Surveillance of hospital-acquired infections (HAIs) is the foundation infection control. Machine learning (ML) has been demonstrated to be a valuable tool for HAI surveillance. We compared manual surveillance with supervised, semiautomated, ML method, and we explored types features importance depicted by model.
The aim of this study was two-fold: (i) to analyze the variations in internal load and well-being professional handball players between normal congested weeks (ii) training days within weeks. Twenty male (26.5 ± 4.9 yo) were monitored during a full season. MD-1 (match day −1) revealed larger decreases muscle soreness (−17.3%, [−26.6;−6.9]) fatigue (−16.6%, [−24.8;−7.4]) Regarding MD-2, DOMS (−19.9%, [−30.5;−7.6]), (−19.7%, [−30.0;−7.9] Hooper index (−16.7%, [−25.6;−6.7]) found results reveal...
Healthcare-associated infections (HAIs) are among the most common adverse events in hospitals. We used artificial intelligence (AI) algorithms for infection surveillance a cohort study. The model correctly detected 67 out of 73 patients with HAIs. final multilayer perceptron neural network achieving an area under receiver operating curve (AUROC) 90.27%; specificity 78.86%; sensitivity 88.57%. Respiratory had best results (AUROC ≥93.47%). AI algorithm could identify is feasible method HAI...
Abstract Purpose The COVID-19 pandemic has impacted medication needs and prescribing practices, including those affecting pregnant women. Our goal was to investigate patterns of use among women with COVID-19, focusing on variations by trimester infection location. Methods We conducted an observational study using six electronic healthcare databases from European regions (Aragon/Spain; France; Norway; Tuscany, Italy; Valencia/Spain; Wales/UK). prevalence primary care or dispensing compared in...
Using 4 data-sources (Spain, Italy, United Kingdom) data and a 1:1 matched cohort study, we aimed to estimate vaccine effectiveness (VE) in preventing SARS-CoV-2 infections with hospitalisations (±30 days) death (±56 general population clinical subgroups homologous/heterologous booster schedules (Comirnaty-BNT Spikevax-MOD original COVID-19 vaccines) by comparison unboosted individuals, during Delta beginning of Omicron variants. Hazard Ratio (HR, Cox models) VE ([1-HR]*100) were calculated...
Objetivo: describir el desarrollo de un modelo clasificador predictivo la carga trabajo enfermería, utilizando inteligencia artificial. Método: estudio observacional retrospectivo, en fuentes secundarias registros electrónicos pacientes, con uso aprendizaje automático. La muestra por conveniencia se constituyó 43.871 evaluaciones realizadas enfermeras asistenciales Sistema Clasificación Pacientes Perroca, que sirvieron como patrón oro, y datos clínicos del expediente electrónico 11.774...
Lycopene is a very attractive antioxidant associated with cancer prevention in humans. Therefore, it important to develop new analytical methods that allow for differentiation of food production streams contain various concentrations. The lycopene content tomato juice, an intermediate between raw tomatoes and the final paste product, was monitored on-line 46 days at plant novel, patented double-channel Raman setup. setup comprises mini spectrometer placed fixed optical setup, each...
Abstract Failure to adjust doses may contribute adverse events. We evaluated the effectiveness of providing estimated glomerular filtration rate on appropriateness dosing for antimicrobials. The approach increased from 33.9% 41.4% ( P < .001). Nudging prescription behavior can boost strategies adequate antimicrobial prescription.
Abstract Objective Methods Several statistical analysis plans (SAP) from the Vaccine Monitoring Collaboration for Europe (VAC4EU) were analyzed to identify study design sections and specifications programming RWE studies based on multi-databases standardized common data models. We envisioned a metadata schema that transforms epidemiologist’s knowledge into machine-readable format. This must also contain different sections, code lists, time anchoring specified in SAPs. Further desired...
Objetivo: descrever o desenvolvimento de um modelo classificador preditivo da carga trabalho enfermagem, utilizando inteligência artificial. Método: estudo observacional retrospectivo, em fontes secundárias registros eletrônicos pacientes, com uso aprendizado máquina. A amostra por conveniência constituiu-se 43.871 avaliações realizadas enfermeiras assistenciais Sistema Classificação Pacientes Perroca, as quais serviram como padrão ouro, e os dados clínicos do prontuário eletrônico 11.774...
ABSTRACT Objective To enhance documentation on programming decisions in Real World Evidence (RWE) studies. Materials and Methods We analyzed several statistical analysis plans (SAP) within the Vaccine Monitoring Collaboration for Europe (VAC4EU) to identify study design sections specifications RWE designed a machine‐readable metadata schema containing sections, codelists, time anchoring definitions specified SAPs with adaptability user‐friendliness. Results developed RWE‐BRIDGE, form of...
This article details the creation of a novel domain ontology at intersection epidemiology, medicine, statistics, and computer science. It outlines systematic approach to handling structured data anonymously in preparation for its use Artificial Intelligence (AI) applications healthcare. The development followed 7 steps, including defining scope, selecting knowledge, reviewing important terms, constructing classes that describe designs used epidemiological studies, machine learning paradigms,...
This article details the creation of a novel domain ontology at intersection epidemiology, medicine, statistics, and computer science. Using terminology defined by current legislation, outlines systematic approach to handling hospital data anonymously in preparation for its use Artificial Intelligence (AI) applications healthcare. The development process consisted 7 pragmatic steps, including defining scope, selecting knowledge, reviewing important terms, constructing classes that describe...
SummarySurveillance of health care–associated infection (HAI) is the foundation control and one first steps in prevention. Traditionally, however, surveillance performed by professionals (ICPs) who manually review patients' records, searching for defined criteria. Such an approach leaves room subjective interpretation, resulting low interrater reliability. Moreover, depending on method used — instance, a search based antimicrobial results it may have sensitivity. In Brazil, leaders at...
An abstract is not available for this content. As you have access to content, full HTML content provided on page. A PDF of also in through the 'Save PDF' action button.