Mental health and long COVID status prediction among recovered COVID-19 patients: A comparison of machine learning methods
Bibliographic record
Abstract
The COVID-19 pandemic has led to different health outcomes, including long COVID (LCo) and mental health (MH) disorders, impacting millions globally. To enable early healthcare diagnosis, including the prediction of MH conditions and LCo, various research studies have utilized machine learning (ML) techniques. However, there is still a gap in understanding the mental health of recovered COVID-19 patients with long COVID using ML techniques. This study aims to bridge this gap by developing and evaluating ML models, including support vector machine, multilayer perceptron (MLP), k-nearest neighbor, gradient boosting, voting classifier, and extreme gradient boosting, tailored for mental health and long COVID datasets from recovered COVID-19 patients. Additionally, feature selection methods, e.g., Recursive Feature Elimination (RFE) and Extra Trees (ET), and optimized models with hyper-parameter tuning will be employed. Our experiments utilize the dataset of recovered COVID-19 patients. Among these ML models, the MLP with ET-based features achieved the highest accuracy and AUC scores in this dataset, with 1.00 and 0.97 ± 0.02, respectively. The research reveals the high prevalence and risk factors of mental health disorders and long COVID from the dataset. These findings will contribute to personalized healthcare strategies for individuals navigating the complexities of post-COVID-19 recovery, integrating machine learning insights into mental health and long COVID support.
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 | 0.006 | 0.013 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.002 | 0.002 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
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".