Universitätspublikationen
Refine
Document Type
- Article (2)
Language
- English (2) (remove)
Has Fulltext
- yes (2)
Is part of the Bibliography
- no (2)
Keywords
- Advanced stage (1)
- COVID-19 (1)
- Complicated stage (1)
- Human genetics (1)
- LEOSS (1)
- Machine learning (1)
- Predictive model (1)
- e-Learning (1)
- evaluation (1)
- multimedia (1)
Institute
- Medizin (2) (remove)
Introduction: This study presents our online-teaching material within the k-MED project (Knowledge in Medical Education) at the university of Marburg. It is currently organized in five e-learning modules: cytogenetics, chromosomal aberrations, formal genetics, fundamentals of molecular diagnostics, and congenital abnormalities and syndromes. These are basic courses intended to do the educational groundwork, which will enable academic teachers to concentrate on more sophisticated topics during their lectures. Methods: The e-learning modules have been offered to a large group of about 3300 students during four years at the Faculty of Medicine in Marburg. The group consists of science students (human biology) and medical students in the preclinical or the clinical period, respectively. Participants were surveyed on acceptance by evaluating user-tracking data and questionnaires. Results and Conclusion: Analysis of the evaluation data proofs the broad acceptance of the e-learning modules during eight semesters. The courses are in stable or even increasing use from winter term 2005/06 until spring term 2009. Conclusion: Our e-learning-model is broadly accepted among students with different levels of knowledge at the Faculty of Medicine in Marburg. If the e-learning courses are maintained thoroughly, minor adaptations can increase acceptance and usage even furthermore. Their use should be extended to the medical education of technical assistances and nurses, who work in the field of human genetics. Keywords: Human genetics, e-Learning, evaluation, multimedia
Purpose: While more advanced COVID-19 necessitates medical interventions and hospitalization, patients with mild COVID-19 do not require this. Identifying patients at risk of progressing to advanced COVID-19 might guide treatment decisions, particularly for better prioritizing patients in need for hospitalization.
Methods: We developed a machine learning-based predictor for deriving a clinical score identifying patients with asymptomatic/mild COVID-19 at risk of progressing to advanced COVID-19. Clinical data from SARS-CoV-2 positive patients from the multicenter Lean European Open Survey on SARS-CoV-2 Infected Patients (LEOSS) were used for discovery (2020-03-16 to 2020-07-14) and validation (data from 2020-07-15 to 2021-02-16).
Results: The LEOSS dataset contains 473 baseline patient parameters measured at the first patient contact. After training the predictor model on a training dataset comprising 1233 patients, 20 of the 473 parameters were selected for the predictor model. From the predictor model, we delineated a composite predictive score (SACOV-19, Score for the prediction of an Advanced stage of COVID-19) with eleven variables. In the validation cohort (n = 2264 patients), we observed good prediction performance with an area under the curve (AUC) of 0.73 ± 0.01. Besides temperature, age, body mass index and smoking habit, variables indicating pulmonary involvement (respiration rate, oxygen saturation, dyspnea), inflammation (CRP, LDH, lymphocyte counts), and acute kidney injury at diagnosis were identified. For better interpretability, the predictor was translated into a web interface.
Conclusion: We present a machine learning-based predictor model and a clinical score for identifying patients at risk of developing advanced COVID-19.