RLRaquel Lutkmeier

Raquel Lutkmeier

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Raquel Lutkmeier has a total of 108 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Potential and limitations of machine meta-learning (ensemble) methods for predicting COVID-19 mortality in a large inhospital Brazilian dataset

    by Bruno Barbosa Miranda de Paiva, Polianna Delfino Pereira, Claudio Moisés Valiense de Andrade, Virginia Mara Reis Gomes, Maira Viana Rego Souza-Silva, Karina Paula Medeiros Prado Martins, Thaís Lorenna Souza Sales, Rafael Lima Rodrigues de Carvalho, Magda Carvalho Pires, Lucas Emanuel Ferreira Ramos, et al.

    The majority of early prediction scores and methods to predict COVID-19 mortality are bound by methodological flaws and technological limitations (e.g., the use of a single prediction model). Our aim is to provide a thorough comparative study that tackles those methodological issues, considering multiple techniques to build mortality prediction models, including modern machine learning (neural) algorithms and traditional statistical techniques, as well as meta-learning (ensemble) approaches. This study used a dataset from a multicenter cohort of 10,897 adult Brazilian COVID-19 patients, admitted from March/2020 to November/2021, including patients [median age 60 (interquartile range 48–71), 46% women]. We also proposed new original population-based meta-features that have not been devised in the literature. Stacking has shown to achieve the best results reported in the literature for the death prediction task, improving over previous state-of-the-art by more than 46% in Recall for predicting death, with AUROC 0.826 and MacroF1 of 65.4%. The newly proposed meta-features were highly discriminative of death, but fell short in producing large improvements in final prediction performance, demonstrating that we are possibly on the limits of the prediction capabilities that can be achieved with the current set of ML techniques and (meta-)features. Finally, we investigated how the trained models perform on different hospitals, showing that there are indeed large differences in classifier performance between different hospitals, further making the case that errors are produced by factors that cannot be modeled with the current predictors.


  • Open Access

    Factors associated with mortality in critically ill patients with COVID-19

    by Rafaela dos Santos Charão de Almeida, André Klafke, Andresa Fontoura Garbini, Daniela dos Reis Carazai, Fernanda Costa dos Santos, Raquel Lutkmeier, Veridiana Baldon

    Background and objectives: COVID-19 is a life-threatening disease. Recognizing the main characteristics of the disease and its main complications will help future interventions, care, and management of health services since territorial and population diversities directly influence health outcomes. Our main objective is to describe the clinical characteristics, outcomes, and factors associated with mortality of patients with COVID-19 admitted to the intensive care unit of a public and tertiary hospital. Methods: Cohort study, conducted from March 1 to September 30, 2020. Poisson regression was performed to investigate the variables of hospital treatment as potential risk factors for in-hospital mortality. Results: Of the 283 eligible patients in this study, the hospital mortality rate was of 41.7% (n=118). The most common outcomes were acute respiratory distress syndrome, nosocomial infection, and septic shock. Factors independently associated with increased risk of death were age greater than 51 years old (RR=1.7, 95%CI=1.0-2.8), especially over 70 years old (RR=2.9, 95%CI=1.7-2.8), current smoker (RR=1.8, 95%CI=1.1-2.9), requiring the use of inotrope (RR=1.4, 95%CI=1.0-2.0), and presenting potassium greater than 5.0 mEq/l on admission (RR=1.3, 95%CI=1.0-1.7).


  • Open Access

    Adult patients admitted to a tertiary hospital for COVID-19 and risk factors associated with severity: a retrospective cohort study

    by Veridiana Baldon dos Santos, Airton Tetelbom Stein, Sofia Louise Santin Barilli, Andresa Fontoura Garbini, Rafaela Charão de Almeida, Daniela dos Reis Carazai, Fernanda Costa dos Santos, Raquel Lutkmeier, Isadora Helena Greve, André Klafke, et al.

    COVID-19 is a disease whose knowledge is still under construction, high transmissibility, with no consensual treatment available to everyone. Therefore, the identification of patients at higher risk of evolving to the critical form of the disease is fundamental. The study aimed to determine risk factors associated with the severity of COVID-19 in adults patients. This is an observational, retrospective study from a cohort of adult patients with COVID-19 admitted to a public hospital from March to August 2020, whose medical records were evaluated. For the association of possible severity predictors, a Poisson regression was used. The primary outcome was the critical form of the disease (need for admission to the Intensive Care Unit and/or invasive mechanical ventilation). We included 565 patients: mostly men; 55.5% of those who progressed to the critical form of the disease were over sixty years old. Hypertension, diabetes mellitus and obesity were the most frequent comorbidities. There were 39.8% of patients who progressed to the critical form of the disease. The hospital mortality rate was 22.1%, and that of critical patients was 46.7%. The independent factors associated with the severity of the disease were obesity [RR = 1.33 (95% CI 1.07 to 1.66; p = 0.011)], SpO2/FiO2 ratio ≤ 315 [RR = 2.20 (95% CI 1.79 to 2.71; p = 0.000)], C-reactive protein > 100 mg/L [RR = 1.65 (95% CI 1.33 to 2.06; p = 0.000)], and lymphocytes < 1,000/µL [RR = 1.44 (95% CI 1.18 to 1.75; p = 0.000)]. Advanced age and comorbidities were dependent factors strongly associated with the critical form of the disease.