Classifying patients with psoriatic arthritis according to their disease activity status using serum metabolites and machine learning
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
INTRODUCTION: Psoriatic arthritis (PsA) is a heterogeneous inflammatory arthritis, affecting approximately a quarter of patients with psoriasis. Accurate assessment of disease activity is difficult. There are currently no clinically validated biomarkers to stratify PsA patients based on their disease activity, which is important for improving clinical management. OBJECTIVES: To identify metabolites capable of classifying patients with PsA according to their disease activity. METHODS: An in-house solid-phase microextraction (SPME)-liquid chromatography-high resolution mass spectrometry (LC-HRMS) method for lipid analysis was used to analyze serum samples obtained from patients classified as having low (n = 134), moderate (n = 134) or high (n = 104) disease activity, based on psoriatic arthritis disease activity scores (PASDAS). Metabolite data were analyzed using eight machine learning methods to predict disease activity levels. Top performing methods were selected based on area under the curve (AUC) and significance. RESULTS: The best model for predicting high disease activity from low disease activity achieved AUC 0.818. The best model for predicting high disease activity from moderate disease activity achieved AUC 0.74. The best model for classifying low disease activity from moderate and high disease activity achieved AUC 0.765. Compounds confirmed by MS/MS validation included metabolites from diverse compound classes such as sphingolipids, phosphatidylcholines and carboxylic acids. CONCLUSION: Several lipids and other metabolites when combined in classifying models predict high disease activity from both low and moderate disease activity. Lipids of key interest included lysophosphatidylcholine and sphingomyelin. Quantitative MS assays based on selected reaction monitoring, are required to quantify the candidate biomarkers identified.
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.
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 | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| 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) | 0.000 | 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 it