Comparative Analysis of Machine Learning Algorithms Used for Translating Aptamer-Antigen Binding Kinetic Profiles to Diagnostic Decisions
Bibliographic record
Abstract
Current approaches for classifying biosensor data in diagnostics rely on fixed decision thresholds based on receiver operating characteristic (ROC) curves, which can be limited in accuracy for complex and variable signals. To address these limitations, we developed a framework that facilitates the application of machine learning (ML) to diagnostic data for the binary classification of clinical samples, when using real-time electrochemical measurements. The framework was applied to a real-time multimeric aptamer assay (RT-MAp) that captures single-frequency (12.6 Hz) impedance data during the binding of viral protein targets to trimeric aptamers. The impedance data collected from 172 COVID-19 saliva samples were processed through multiple nonlinear regression models to extract nine key features from the transient signals. These features were then used to train three supervised ML algorithms─support vector machine (SVM), artificial neural network (ANN), and random forest (RF)─using a 75:25 training-testing ratio. Traditional ROC-based classification achieved an accuracy of 83.6%, while ML-based models significantly improved performance, with SVM, ANN, and RF achieving accuracies of 86.0%, 100%, and 100%, respectively. The ANN model demonstrated superior performance in handling complex and high-variance biosensor data, providing a robust and scalable solution for improving diagnostic accuracy in point-of-care settings.
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 | 0.009 | 0.024 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.004 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| 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".