aceClustering of rheumatoid arthritis patients: an unsupervised machine learning approach for characterizing the TNFi response
Abstract: This study aimed to identifydistinct profiles of response to Tumor Necrosis Factor inhibitors (TNFi) in rheumatoid arthritis (RA) patients using unsupervised machine learning to integrate clinical, demographic, and genetic data. A cohort of 294 RA patients was analyzed using hierarchical clustering techniques. Data collected included body mass index (BMI), adherence to physical activity, prevalence of comorbidities, seropositivity, Health Assessment Questionnaire (HAQ) scores, and genetic polymorphisms in TNF pa…
"MIHANOVICEVA 3 - rheumatology and physiotherapy" by Miroslav Vajdić is licensed under CC BY-SA 2.0. To view a copy of this license, visit https://creativecommons.org/licenses/by-sa/2.0/.
Researchers applied unsupervised hierarchical clustering to 294 rheumatoid arthritis patients to integrate clinical, demographic, and genetic data related to Tumor Necrosis Factor inhibitor response. By publication date 2026-08-17 they reported distinct responder characteristics and identified three subgroups ranging from 73.5% response to 82.9% therapeutic failure.
The clustering approach moves beyond single-variable predictors by combining BMI, physical activity adherence, comorbidities, HAQ functionality, and TNF pathway variants like rs767455 to stratify patients. This supports more personalized TNFi use in RA, though the findings are observational from a single cohort and require external validation before clinical deployment.
- Study analyzed 294 RA patients using hierarchical clustering of clinical, demographic, and genetic data.
- Responders showed lower BMI 25.6 vs 27.0, higher physical activity adherence 56.6% vs 33.3%, lower comorbidity prevalence 69.8% vs 82.4%, and better HAQ 0.8 vs 1.7.
- C allele of rs767455 was more frequent among responders at 74.4% vs 62.4%.
Unsupervised hierarchical clustering integrated BMI, activity, comorbidities, HAQ and TNF pathway genetics to identify three RA subgroups with differing TNFi response rates, including a better-prognosis cluster with 73.5% response.
The rundown
The analysis used hierarchical clustering on 294 RA patients, incorporating BMI, adherence to physical activity, prevalence of comorbidities, seropositivity, HAQ scores, and polymorphisms in TNF pathway. Responders versus non-responders differed on multiple variables, and the C allele of rs767455 was enriched in responders.
Three clusters emerged: a better prognosis group with 73.5% response rate, minimal use of combination therapies, high adherence to physical activity, and male predominance; a poorer response group with 82.9% therapeutic failure, intensive medication use, and low exercise adherence; and an intermediate group. Authors conclude response is multifactorial.
Sources
- Peer-reviewedImmunologic Research2026-08-17
How should this claim be treated?
The debate