Machine Learning Models Towards Prediction of COVID and Non-COVID 19 Patients in the Hospital’s Intensive Care Units (ICU)
Bibliographic record
Abstract
The global proliferation of COVID-19 prompted research towards the virus's detection and eventual eradication.One important area of research is the use of machine learning (ML) to realize and battle COVID-19.The goal of this study is to use machine learning to monitor COVID and non-COVID-19 patients and decide whether or not to transfer them to the intensive care unit (ICU).The precise disease diagnosis was essential due to the lack of oxygen supplementation in the majority of hospitals around the world.It will improve the effectiveness of the ICU facilities and lessen the load on the medical personnel and the ICU facilities by accurately forecasting how patients will be treated.If stable patients are recognized among all patients, home treatment could be established for stable patients.In this research, three machine learning algorithms were chosen as the method used, which are K-Nearest Neighbor (KNN), Support Vector Machine (SVM), and Extra Tree Classifier.These algorithms were chosen for their simplicity and robustness and based on the conducted literature review.A dataset containing 100 ICU and 131 stable patients of Covid and non-Covid samples from 24 th Moscow City State Hospital was used.By using SMOTE technique with 10-fold cross-validation and feature selection on the dataset, KNN achieved an accuracy of 94.65%, SVM with an accuracy of 94.65%, and an accuracy of 96.18% for the Extra Tree Classifier.The outcomes of this research on the selected dataset prove how accurate these algorithms were able to predict the classes.
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 machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.006 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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 source (direct Gemma or distilled Codex), 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".