Predicting autoimmune thyroiditis in primary Sjogren’s syndrome patients using a random forest classifier: a retrospective study
Bibliographic record
Abstract
BACKGROUND: Primary Sjogren's syndrome (pSS) and autoimmune thyroiditis (AIT) share overlapping genetic and immunological profiles. This retrospective study evaluates the efficacy of machine learning algorithms, with a focus on the Random Forest Classifier, to predict the presence of thyroid-specific autoantibodies (TPOAb and TgAb) in pSS patients. METHODS: A total of 96 patients with pSS were included in the retrospective study. All participants underwent a complete clinical and laboratory evaluation. All participants underwent thyroid function tests, including TPOAb and TgAb, and were accordingly divided into positive and negative thyroid autoantibody groups. Four machine learning algorithms were then used to analyze the risk factors affecting patients with pSS with positive and negative for thyroid autoantibodies. RESULTS: The results indicated that the Random Forest Classifier algorithm (AUC = 0.755) outperformed the other three machine learning algorithms. The random forest classifier indicated Age, IgG, C4 and dry mouth were the main factors influencing the prediction of positive thyroid autoantibodies in pSS patients. It is feasible to predict AIT in pSS using machine learning algorithms. CONCLUSIONS: Analyzing clinical and laboratory data from 96 pSS patients, the Random Forest model demonstrated superior performance (AUC = 0.755), identifying age, IgG levels, complement component 4 (C4), and absence of dry mouth as primary predictors. This approach offers a promising tool for early identification and management of AIT in pSS patients. TRIAL REGISTRATION: This retrospective study was approved and monitored by the Ethics Committee of The Third Affiliated Hospital of Sun Yat-sen University (No.II2023-254-02).
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 | 0.005 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| 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".