Designing Adaptive Mechanism for COVID-19 and Exacerbation in Cases of COPD Patients Using Machine Learning Approaches
Bibliographic record
Abstract
The technology of machine learning has been widely applied in several domains and complex medical problems, specifically in chronic obstructive pulmonary disease (COPD). Researchers in the field of respiratory diseases confirm that people who suffer from COPD have high risks when exposed to COVID-19. The most common oncoming COPD exacerbations and COPD symptoms of COVID-19 are congruent. The distinction between COPD exacerbations and COVID-19 with COPD is nearly impossible without testing. This paper proposes a new powerful model for classifying COPD patients with exacerbations and those with COVID-19 using machine learning and deep learning algorithms. The major contribution of this research is the dynamic classification process based on the patient context that can help detect exacerbations or COVID-19 per period. Indeed, Five Machine Learning algorithms are trained, tested and a performant classification model is identified. This prediction model is then associated with a dynamic COPD patient context for monitoring the patient's health status. This model based on the dynamic adaptation mechanism combined with a classification contributes to identifying dynamically COPD exacerbations and COVID-19 symptoms for COPD patients. Indeed, periodically, data on a new patient is injected into the prediction model. At the output of the model, the patient is either classified in the exacerbation category, or classified in the COVID-19 category, or no category. By period. A dynamic dashboard of classified patients is available to help medical staff take appropriate decisions. This approach helps to follow the evolution of COPD patient comorbidities (exacerbation, COVID-19). Finally, classification would allow healthcare stakeholders to provide healthcare service according to the patient’s status. The methodology of research consists of designing and implementing a dynamic model for classifying COPD patients. Since early intervention is associated with improved prognosis, with our solution, healthcare staff can identify COPD patients who are most at risk of developing exacerbation or COVID-19. Consequently, upon admission, this will ensure that these patients receive appropriate care as soon as possible.
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 | 0.002 | 0.004 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| 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".