Blood-Based Immune Profiling Combined with Machine Learning Discriminates Psoriatic Arthritis from Psoriasis Patients

Abstract

Psoriasis (Pso) is a chronic inflammatory skin disease, and up to 30% of Pso patients develop psoriatic arthritis (PsA), which can lead to irreversible joint damage. Early detection of PsA in Pso patients is crucial for timely treatment but difficult for dermatologists to implement. We, therefore, aimed to find disease-specific immune profiles, discriminating Pso from PsA patients, possibly facilitating the correct identification of Pso patients in need of referral to a rheumatology clinic. The phenotypes of peripheral blood immune cells of consecutive Pso and PsA patients were analyzed, and disease-specific immune profiles were identified via a machine learning approach. This approach resulted in a random forest classification model capable of distinguishing PsA from Pso (mean AUC = 0.95). Key PsA-classifying cell subsets selected included increased proportions of differentiated CD4+CD196+CD183-CD194+ and CD4+CD196-CD183-CD194+ T-cells and reduced proportions of CD196+ and CD197+ monocytes, memory CD4+ and CD8+ T-cell subsets and CD4+ regulatory T-cells. Within PsA, joint scores showed an association with memory CD8+CD45RA-CD197- effector T-cells and CD197+ monocytes. To conclude, through the integration of in-depth flow cytometry and machine learning, we identified an immune cell profile discriminating PsA from Pso. This immune profile may aid in timely diagnosing PsA in Pso.

Harnessing Big Data, Smart and Digital Technologies and Artificial Intelligence for Preventing, Early Intercepting, Managing, and Treating Psoriatic Arthritis: Insights From a Systematic Review of the Literature

“…Mulder et al. ( 30 ) aimed to detect disease-specific immune profiles from the phenotype of peripheral blood immune cells, which were effectively able to differentiate between psoriasis and psoriatic arthritis patients. Authors utilized a random forest-based algorithm coupled with in-depth flow cytometry and with an excellent AUC of 0.95 and found that psoriatic arthritis patients exhibited upregulated differentiated CD4+CD196+CD183-CD194+ and CD4+CD196-CD183-CD194+ T-cells, whereas CD196+ and CD197+ monocytes, memory CD4+ and CD8+ T-cell subsets and CD4+ regulatory T-cells were downregulated.…”

Blood immune cell profiling in adults with longstanding type 1 diabetes is associated with macrovascular complications

“…We and others have shown that blood immune cell profiling approaches are a powerful tool for detailed characterization of immune cell subsets in peripheral blood of healthy individuals and patients ( 18 , 22 – 24 ). The association of peripheral immune cell changes and disease progression of type 1 diabetes has been shown in several studies, especially in newly diagnosed diabetes patients ( 6 , 7 , 23 – 26 ).…”

Artificial intelligence in psoriasis: Where we are and where we are going

“…The NLP and genetic data were adopted in electronic medical records to identify 31 PsA‐related predictors and assess the risk of PsA 104,105 . Besides, other studies built ML models based on blood immune profiling and serum proteomics to discriminate between PsA and psoriatic patients 106,107 . Based on these models, a minimal disease activity (a clinical state characterized by low levels of disease activity) predictive model was developed, with the variables of global pain, impact of the disease (PsAID), patient global assessment of disease, and physical function (HAQ‐Disability Index) having the greatest predictive ability 108 .…”

“…104,105 Besides, other studies built ML models based on blood immune profiling and serum proteomics to discriminate between PsA and psoriatic patients. 106,107 Based on these models, a minimal disease activity (a clinical state characterized by low levels of disease activity) predictive model was developed, with the variables of global pain, impact of the disease (PsAID), patient global assessment of disease, and physical function (HAQ-Disability Index) having the greatest predictive ability. 108 Besides PsA, patient records were detected to identify the top predictors of noncalcified coronary plaque burden in psoriasis, which included obesity, dyslipidemia, and inflammation factors.…”