Cardiovascular Risk Prediction in Ankylosing Spondylitis: From Traditional Scores to Machine Learning Assessment

Rheumatology and Therapy

Giacomo Di Benedetto¹  Raffaele Scarpa²  Ennio Lubrano³  Fabio Perrotta³  Lorenzo Delfino⁴  Claudio Lunardi⁴  Michela Sperti⁵  Marco A. Deriu⁵  Addolorata Corrado⁶  Francesco Paolo Cantatore⁶  Viktoriya Pavlych⁷  Piero Ruscitti⁷  Francesco Caso⁸  Luisa Costa⁸  Marco Tasso⁸  Roberto Giacomelli⁸  Antonella Afeltra⁹  Luca Navarini⁹  Damiano Currado⁹  Liliana Stola⁹  Massimo Ciccozzi^1,10  Alice Laudisio^1,11 

[1] 7HC;;Academic Rheumatology Unit, Dipartimento di Medicina e Scienze della Salute “Vincenzo Tiberio”, Università degli Studi del Molise;Department of Medicine, University of Verona;PolitoBIOMed Lab, Department of Mechanical and Aerospace Engineering, Politecnico di Torino;Rheumatology Clinic, Department of Medical and Surgical Sciences, University of Foggia;Rheumatology Unit, Department of Biotechnological and Applied Clinical Sciences, University of L’Aquila;Rheumatology Unit, Department of Clinical Medicine and Surgery, School of Medicine, University Federico II of Naples;Unit of Allergology, Immunology, Rheumatology, Department of Medicine, Università Campus Bio-Medico di Roma;Unit of Clinical Laboratory Science, Department of Medicine, Università Campus Bio-Medico di Roma;Unit of Geriatrics, Department of Medicine, Università Campus Bio-Medico di Roma;

关键词: Ankylosing spondylitis;    Cardiovascular risk;    C-reactive protein;    Machine learning;   

DOI  :  10.1007/s40744-020-00233-4

来源: DOAJ

【 摘 要 】

Abstract Introduction The performance of seven cardiovascular (CV) risk algorithms is evaluated in a multicentric cohort of ankylosing spondylitis (AS) patients. Performance and calibration of traditional CV predictors have been compared with the novel paradigm of machine learning (ML). Methods A retrospective analysis of prospectively collected data from an AS cohort has been performed. The primary outcome was the first CV event. The discriminatory ability of the algorithms was evaluated using the area under the receiver operating characteristic (ROC) curve (AUC), which is like the concordance-statistic (c-statistic). Three ML techniques were considered to calculate the CV risk: support vector machine (SVM), random forest (RF), and k-nearest neighbor (KNN). Results Of 133 AS patients enrolled, 18 had a CV event. c-statistic scores of 0.71, 0.61, 0.66, 0.68, 0.66, 0.72, and 0.67 were found, respectively, for SCORE, CUORE, FRS, QRISK2, QRISK3, RRS, and ASSIGN. AUC values for the ML algorithms were: 0.70 for SVM, 0.73 for RF, and 0.64 for KNN. Feature analysis showed that C-reactive protein (CRP) has the highest importance, while SBP and hypertension treatment have lower importance. Conclusions All of the evaluated CV risk algorithms exhibit a poor discriminative ability, except for RRS and SCORE, which showed a fair performance. For the first time, we demonstrated that AS patients do not show the traditional ones used by CV scores and that the most important variable is CRP. The present study contributes to a deeper understanding of CV risk in AS, allowing the development of innovative CV risk patient-specific models.

【 授权许可】

Unknown