Determining Treatment Dosage for Hypothyroidism Using Machine Learning
Bibliographic record
Abstract
Hypothyroidism, a prevalent chronic health condition, can lead to serious complications if untreated. Management typically involves synthetic thyroid hormone replacement, with dosage being crucial for effective treatment. However, factors like stress and weight fluctuations impact thyroid hormone levels, posing challenges in dosage determination. This study introduces an innovative approach using machine learning for precise dosage prediction. We developed a synthetic thyroid disease dataset, encompassing parameters such as age, gender, TSH, T3, and T4, to train and evaluate various machine learning models. The study aimed to surpass the current state-of-the-art in dosage prediction, which is Poisson Regression with a 64.8% accuracy. Our findings reveal that Ridge Regression and Lasso Regression achieved an accuracy of 82%, while Support Vector Regression Machines attained 83%. Notably, k-Nearest Neighbour (k-NN) algorithm demonstrated the highest accuracy of 86%, marking a significant improvement of over 21% from the existing standard. This enhancement in prediction accuracy holds potential for optimizing treatment efficacy and patient outcomes in hypothyroidism management.
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 | 0.007 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| 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".