Risk Assessment of COVID-19 Cases in Emergency Departments and Clinics With the Use of Real-World Data and Artificial Intelligence: Observational Study
Bibliographic record
Abstract
BACKGROUND: The recent COVID-19 pandemic has highlighted the weaknesses of health care systems around the world. In the effort to improve the monitoring of cases admitted to emergency departments, it has become increasingly necessary to adopt new innovative technological solutions in clinical practice. Currently, the continuous monitoring of vital signs is only performed in patients admitted to the intensive care unit. OBJECTIVE: The study aimed to develop a smart system that will dynamically prioritize patients through the continuous monitoring of vital signs using a wearable biosensor device and recording of meaningful clinical records and estimate the likelihood of deterioration of each case using artificial intelligence models. METHODS: The data for the study were collected from the emergency department and COVID-19 inpatient unit of the Hippokration General Hospital of Thessaloniki. The study was carried out in the framework of the COVID-X H2020 project, which was funded by the European Union. For the training of the neural network, data collection was performed from COVID-19 cases hospitalized in the respective unit. A wearable biosensor device was placed on the wrist of each patient, which recorded the primary characteristics of the visual signal related to breathing assessment. RESULTS: A total of 157 adult patients diagnosed with COVID-19 were recruited. Lasso penalty function was used for selecting 18 out of 48 predictors and 2 random forest-based models were implemented for comparison. The high overall performance was maintained, if not improved, by feature selection, with random forest achieving accuracies of 80.9% and 82.1% when trained using all predictors and a subset of them, respectively. Preliminary results, although affected by pandemic limitations and restrictions, were promising regarding breathing pattern recognition. CONCLUSIONS: This study represents a novel approach that involves the use of machine learning methods and Edge artificial intelligence to assist the prioritization and continuous monitoring procedures of patients with COVID-19 in health departments. Although initial results appear to be promising, further studies are required to examine its actual effectiveness.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.005 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".