|
1
|
Yagin FH, Colak C, Algarni A, Algarni A, Al-Hashem F, Ardigò LP. Explainable Boosting Machines Identify Key Metabolomic Biomarkers in Rheumatoid Arthritis. MEDICINA (KAUNAS, LITHUANIA) 2025; 61:833. [PMID: 40428791 PMCID: PMC12113160 DOI: 10.3390/medicina61050833] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 03/28/2025] [Revised: 04/16/2025] [Accepted: 04/23/2025] [Indexed: 05/29/2025]
Abstract
Background and Objectives: Rheumatoid arthritis (RA) is a chronic autoimmune disease characterised by joint inflammation and pain. Metabolomics approaches, which are high-throughput profiling of small molecule metabolites in plasma or serum in RA patients, have so far provided biomarker discovery in the literature for clinical subgroups, risk factors, and predictors of treatment response using classical statistical approaches or machine learning models. Despite these recent developments, an explainable artificial intelligence (XAI)-based methodology has not been used to identify RA metabolomic biomarkers and distinguish patients with RA. This study constructed a XAI-based EBM model using global plasma metabolomics profiling to identify metabolites predictive of RA patients and to develop a classification model that can distinguish RA patients from healthy controls. Materials and Methods: Global plasma metabolomics data were analysed from RA patients (49 samples) and healthy individuals (10 samples). SMOTE technique was used for class imbalance in data preprocessing. EBM, LightGBM, and AdaBoost algorithms were applied to generate a discriminatory model between RA and controls. Comprehensive performance metrics were calculated, and the interpretability of the optimal model was assessed using global and local feature descriptions. Results: A total of 59 samples were analysed, 49 from RA patients, and 10 from healthy subjects. The EBM generated better results than LightGBM and AdaBoost by attaining an AUC of 0.901 (95% CI: 0.847-0.955) with 87.8% sensitivity which helps prevent false negative early RA diagnosis. The primary biomarkers EBM-based XAI identified were N-acetyleucine, pyruvic acid, and glycerol-3-phosphate. EBM global explanation analysis indicated that elevated pyruvic acid levels were significantly correlated with RA, whereas N-acetyleucine exhibited a nonlinear relationship, implying possible protective effects at specific concentrations. Conclusions: This study underscores the promise of XAI and evidence-based medicine methodology in developing biomarkers for RA through metabolomics. The discovered metabolites offer significant insights into RA pathophysiology and may function as diagnostic biomarkers or therapeutic targets. Incorporating EBM methodologies integrated with XAI improves model transparency and increases the therapeutic applicability of predictive models for RA diagnosis/management. Furthermore, the transparent structure of the EBM model empowers clinicians to understand and verify the reasoning behind each prediction, thereby fostering trust in AI-assisted decision-making and facilitating the integration of metabolomic insights into routine clinical practice.
Collapse
Affiliation(s)
- Fatma Hilal Yagin
- Department of Biostatistics, Faculty of Medicine, Malatya Turgut Ozal University, 44210 Malatya, Turkey
| | - Cemil Colak
- Department of Biostatistics, and Medical Informatics, Faculty of Medicine, Inonu University, 44280 Malatya, Turkey
| | - Abdulmohsen Algarni
- Department of Computer Science, King Khalid University, Abha 61421, Saudi Arabia
| | - Ali Algarni
- Department of Informatics and Computer Systems, College of Computer Science, King Khalid University, Abha 61421, Saudi Arabia
| | - Fahaid Al-Hashem
- Department of Physiology, College of Medicine, King Khalid University, Abha 61421, Saudi Arabia
| | - Luca Paolo Ardigò
- Department of Teacher Education, NLA University College, Linstows Gate 3, 0166 Oslo, Norway
| |
Collapse
|
|
2
|
Zhao F, Chen Y, Liu H, Jin L, Feng X, Dai B, Chen M, Wang Q, Yao Y, Liao R, Zhao J, Qu B, Song Y, Fu L. The interaction between a leflunomide-response methylation site (cg17330251) and variant (rs705379) on response to leflunomide in patients with rheumatoid arthritis. Front Pharmacol 2025; 16:1499723. [PMID: 40183079 PMCID: PMC11965123 DOI: 10.3389/fphar.2025.1499723] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/21/2024] [Accepted: 03/03/2025] [Indexed: 04/05/2025] Open
Abstract
Objectives This research aims to reveal the mechanisms of the effect of the Paraoxonase 1 (PON1) gene on response to leflunomide (LEF) in rheumatoid arthritis (RA) patients, in terms of single nucleotide polymorphism (SNP), DNA methylation levels. Methods A total of 240 RA patients enrolled were categorized into the good response group and the non-response group according to the difference in DAS28 scores between baseline and 6 months after LEF administration. The identified LEF-response cytosine-phosphate-guanines (CpGs) island (cg17330251) and its internal SNPs (rs705379, etc.) located at the PON1 promoter were detected by Sanger sequencing and methyl target sequencing. Results A total of 12 CpG sites at cg17330251 could be identified in our RA patients. There were significant difference between the responders and non-responders in nine CpG sites: cg17330251_2, cg17330251_3, cg17330251_4, cg17330251_6, cg17330251_7, cg17330251_8, cg17330251_9, cg17330251_10, cg17330251_12, [OR (95CI%) = 0.492 (0.250, 0.969), 0.478 (0.243, 0.940), 0.492 (0.250, 0.969), 0.461 (0.234, 0.907), 0.492 (0.250, 0.969), 0.437 (0.225, 0.849), 0.478 (0.243, 0.941), 0.421 (0.212, 0.836), 0.424 (0.213, 0.843), P < 0.05, respectively]. At all these nine CpG sites, the proportions of low methylation levels in the responders were higher than those in the non-responders (P < 0.05). In a dominant model, there was a significant difference in rs705379 wildtype CC and mutant genotypes (CT + TT) between the responders and non-responders (P < 0.05). The average methylation level of 12 CpG sites was lowest in rs705379-CC (median 0.229, IQR 0.195-0.287), then rs705379-CT (median 0.363, IQR 0.332-0.395), and rs705379-TT (median:0.531, IQR:0.496-0.557). The average methylation levels of 12 CpG sites were significantly negative correlated with ΔDAS28 (r = -0.13, P < 0.05). The Logistic regression indicated that combined effect of rs705379, DNA methylation of the PON1 gene [OR (95CI%) = 1.277 [1.003, 1.626)], systemic inflammation index (SIRI) [OR (95CI%) = 1.079 (1.018, 1.143)] served as protective factors on response to LEF in RA patients. Conclusion The RA patients with SNP-rs705379-CC, the low methylation level of PON1-cg17330251 and more SIRI would be susceptible of response to LEF and more suitable to choose LEF treatment.
Collapse
Affiliation(s)
- Feng Zhao
- Department of Clinical Epidemiology and Evidence-based Medicine, The First Hospital, China Medical University, Shenyang, China
| | - Yulan Chen
- Department of Clinical Epidemiology and Evidence-based Medicine, The First Hospital, China Medical University, Shenyang, China
| | - Haina Liu
- Department of Rheumatology, The First Hospital, China Medical University, Shenyang, China
| | - Lei Jin
- Department of Rheumatology, ShengJing Hospital Affiliated of China Medical University, Shenyang, China
| | - Xin Feng
- Department of Rheumatology, First Affiliated Hospital of Jinzhou Medical University, Jinzhou, China
| | - Bingbing Dai
- Department of Rheumatology and Immunology, Dalian Municipal Central Hospital, Dalian, China
| | - Meng Chen
- Department of Clinical Epidemiology and Evidence-based Medicine, The First Hospital, China Medical University, Shenyang, China
| | - Qiao Wang
- Department of Clinical Epidemiology and Evidence-based Medicine, The First Hospital, China Medical University, Shenyang, China
| | - Yuxin Yao
- Department of Clinical Epidemiology and Evidence-based Medicine, The First Hospital, China Medical University, Shenyang, China
| | - Ruobing Liao
- Department of Clinical Epidemiology and Evidence-based Medicine, The First Hospital, China Medical University, Shenyang, China
| | - Junyi Zhao
- Department of Clinical Epidemiology and Evidence-based Medicine, The First Hospital, China Medical University, Shenyang, China
| | - Bingjia Qu
- Department of Clinical Epidemiology and Evidence-based Medicine, The First Hospital, China Medical University, Shenyang, China
| | - Ying Song
- Department of Clinical Epidemiology and Evidence-based Medicine, The First Hospital, China Medical University, Shenyang, China
| | - Lingyu Fu
- Department of Clinical Epidemiology and Evidence-based Medicine, The First Hospital, China Medical University, Shenyang, China
| |
Collapse
|
|
3
|
Zhang R, Wang J, Zhai X, Guo Y, Zhou L, Hao X, Yang L, Xing R, Hu J, Gao J, Wang F, Yang J, Liu J. Targeted Detection of 76 Carnitine Indicators Combined with a Machine Learning Algorithm Based on HPLC-MS/MS in the Diagnosis of Rheumatoid Arthritis. Metabolites 2025; 15:205. [PMID: 40137169 PMCID: PMC11944147 DOI: 10.3390/metabo15030205] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/25/2025] [Revised: 03/11/2025] [Accepted: 03/12/2025] [Indexed: 03/27/2025] Open
Abstract
BACKGROUND/OBJECTIVES Early diagnosis and treatment of rheumatoid arthritis (RA) are essential to reducing disability. However, the diagnostic criteria remain unclear, relying on clinical symptoms and blood markers. METHODS Using high-performance liquid chromatography-mass spectrometry (HPLC-MS/MS) targeted detection, we evaluated 76 carnitine indicators (55 carnitines and 21 corresponding ratios) in the serum of patients with RA to investigate the role of carnitine in RA. A total of 359 patients (207 patients with RA and 152 healthy controls) were included in the study. Screening involved three methods and integrated 76 carnitine indicators and 128 clinical indicators to identify candidate markers to establish a theoretical basis for RA diagnosis and new therapeutic targets. The diagnostic model derived from the screened markers was validated using three machine learning algorithms. RESULTS The model was refined using eight candidate indicators (C0, C10:1, LYMPH, platelet distribution width, anti-keratin antibody, glucose, urobilinogen, and erythrocyte sedimentation rate (ESR)). The receiver operating characteristic curve, sensitivity, specificity, and accuracy of the V8 model obtained from the training set were >0.948, 79.46%, 92.99%, and 89.18%, whereas those of the test set were >0.925, 78.89%, 89.22%, and 85.87%, respectively. Twenty-four carnitines were identified as risk factors of RA, with three significantly correlating with ESR, four with anti-cyclic citrullinated peptide antibody activity, two with C-reactive protein, five with immunoglobulin-G, eight with immunoglobulin-A levels, and eleven with immunoglobulin-M levels. CONCLUSIONS Carnitine is integral in the progression of RA. The diagnostic model developed shows excellent diagnostic capacity, improving early detection and enabling timely intervention to minimize disability associated with RA.
Collapse
Affiliation(s)
- Rui Zhang
- Department of Clinical Laboratory Medicine, Xijing Hospital, Fourth Military Medical University, 127 Changle West Road, Xi’an 710032, China; (R.Z.); (J.W.); (X.Z.); (Y.G.); (L.Z.); (X.H.); (L.Y.); (R.X.); (J.H.); (J.G.); (F.W.)
| | - Juan Wang
- Department of Clinical Laboratory Medicine, Xijing Hospital, Fourth Military Medical University, 127 Changle West Road, Xi’an 710032, China; (R.Z.); (J.W.); (X.Z.); (Y.G.); (L.Z.); (X.H.); (L.Y.); (R.X.); (J.H.); (J.G.); (F.W.)
| | - Xiaonan Zhai
- Department of Clinical Laboratory Medicine, Xijing Hospital, Fourth Military Medical University, 127 Changle West Road, Xi’an 710032, China; (R.Z.); (J.W.); (X.Z.); (Y.G.); (L.Z.); (X.H.); (L.Y.); (R.X.); (J.H.); (J.G.); (F.W.)
| | - Yuanbing Guo
- Department of Clinical Laboratory Medicine, Xijing Hospital, Fourth Military Medical University, 127 Changle West Road, Xi’an 710032, China; (R.Z.); (J.W.); (X.Z.); (Y.G.); (L.Z.); (X.H.); (L.Y.); (R.X.); (J.H.); (J.G.); (F.W.)
| | - Lei Zhou
- Department of Clinical Laboratory Medicine, Xijing Hospital, Fourth Military Medical University, 127 Changle West Road, Xi’an 710032, China; (R.Z.); (J.W.); (X.Z.); (Y.G.); (L.Z.); (X.H.); (L.Y.); (R.X.); (J.H.); (J.G.); (F.W.)
| | - Xiaoyan Hao
- Department of Clinical Laboratory Medicine, Xijing Hospital, Fourth Military Medical University, 127 Changle West Road, Xi’an 710032, China; (R.Z.); (J.W.); (X.Z.); (Y.G.); (L.Z.); (X.H.); (L.Y.); (R.X.); (J.H.); (J.G.); (F.W.)
| | - Liu Yang
- Department of Clinical Laboratory Medicine, Xijing Hospital, Fourth Military Medical University, 127 Changle West Road, Xi’an 710032, China; (R.Z.); (J.W.); (X.Z.); (Y.G.); (L.Z.); (X.H.); (L.Y.); (R.X.); (J.H.); (J.G.); (F.W.)
| | - Ruiqing Xing
- Department of Clinical Laboratory Medicine, Xijing Hospital, Fourth Military Medical University, 127 Changle West Road, Xi’an 710032, China; (R.Z.); (J.W.); (X.Z.); (Y.G.); (L.Z.); (X.H.); (L.Y.); (R.X.); (J.H.); (J.G.); (F.W.)
| | - Juanjuan Hu
- Department of Clinical Laboratory Medicine, Xijing Hospital, Fourth Military Medical University, 127 Changle West Road, Xi’an 710032, China; (R.Z.); (J.W.); (X.Z.); (Y.G.); (L.Z.); (X.H.); (L.Y.); (R.X.); (J.H.); (J.G.); (F.W.)
| | - Jiawei Gao
- Department of Clinical Laboratory Medicine, Xijing Hospital, Fourth Military Medical University, 127 Changle West Road, Xi’an 710032, China; (R.Z.); (J.W.); (X.Z.); (Y.G.); (L.Z.); (X.H.); (L.Y.); (R.X.); (J.H.); (J.G.); (F.W.)
| | - Fengjuan Wang
- Department of Clinical Laboratory Medicine, Xijing Hospital, Fourth Military Medical University, 127 Changle West Road, Xi’an 710032, China; (R.Z.); (J.W.); (X.Z.); (Y.G.); (L.Z.); (X.H.); (L.Y.); (R.X.); (J.H.); (J.G.); (F.W.)
| | - Jun Yang
- Comprehensive Cancer Center, Department of Entomology and Nematology, University of California, Davis, CA 95616, USA
| | - Jiayun Liu
- Department of Clinical Laboratory Medicine, Xijing Hospital, Fourth Military Medical University, 127 Changle West Road, Xi’an 710032, China; (R.Z.); (J.W.); (X.Z.); (Y.G.); (L.Z.); (X.H.); (L.Y.); (R.X.); (J.H.); (J.G.); (F.W.)
| |
Collapse
|
|
4
|
Wang S, Li J, Ren F, Zhang J, Song W, Ren L. New Dawn in the Treatment of Rheumatoid Arthritis: Advanced Insight into Polymer Hydrogel Research. Gels 2025; 11:136. [PMID: 39996679 PMCID: PMC11855332 DOI: 10.3390/gels11020136] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/07/2025] [Revised: 02/07/2025] [Accepted: 02/13/2025] [Indexed: 02/26/2025] Open
Abstract
As a chronic systemic autoimmune disease, rheumatoid arthritis (RA) not only damages joints and other organs or systems throughout the body but also torments patients' physical and mental health for a long time, seriously affecting their quality of life. According to incomplete statistics at present, the global prevalence of RA is approximately 0.5-1%, and the number of patients is increasing year by year. Currently, drug therapies are usually adopted for the treatment of RA, such as non-steroidal anti-inflammatory drugs (NSAIDs), disease-modifying antirheumatic drugs (DMARDs), glucocorticoids/steroids, and so on. However, traditional drug therapy has problems such as long half-lives, long treatment cycles requiring frequent drug administration, lack of specificity, and other possible adverse reactions (such as gastrointestinal side effects, skin stratum corneum barrier damage, and systemic toxicity), which greatly restrict the treatment of RA. In order to improve the limitations of traditional drug, physical, and surgical treatments for RA, a large number of related studies on the treatment of RA have been carried out. Among them, hydrogels have been widely used in the research on the treatment of RA due to their excellent biocompatibility, mechanical properties, and general adaptability. For example, hydrogels can be injected into the synovial cavity of joints as synovial fluid to reduce wear between joints, lubricate joints, and avoid synovial surface degradation. This article reviews the applications of hydrogels in the treatment of RA under different functions and the situation of hydrogels as carriers in the treatment of RA through different drug delivery routes and confirms the outstanding potential of hydrogels as drug carriers in the treatment of RA, which has great research significance.
Collapse
Affiliation(s)
- Shuai Wang
- Key Laboratory of Bionic Engineering (Ministry of Education), College of Biological and Agricultural Engineering, Jilin University, Changchun 130022, China;
| | - Jinyang Li
- College of Biological and Agricultural Engineering, Jilin University, Changchun 130012, China;
| | - Fazhan Ren
- School of Agricultural Engineering and Food Science, Shandong University of Technology, Zibo 255000, China;
| | - Jiale Zhang
- College of Engineering, Northeast Agricultural University, Harbin 150030, China;
| | - Wei Song
- College of Engineering and Technology, Jilin Agricultural University, Changchun 130118, China;
| | - Lili Ren
- Key Laboratory of Bionic Engineering (Ministry of Education), College of Biological and Agricultural Engineering, Jilin University, Changchun 130022, China;
- National Key Laboratory of Automotive Chassis Integration and Bionics, Jilin University, Changchun 130022, China
| |
Collapse
|
|
5
|
Kiełbowski K, Bakinowska E, Gorący-Rosik A, Figiel K, Judek R, Rosik J, Dec P, Modrzejewski A, Pawlik A. DNA and RNA Methylation in Rheumatoid Arthritis-A Narrative Review. EPIGENOMES 2025; 9:2. [PMID: 39846569 PMCID: PMC11755448 DOI: 10.3390/epigenomes9010002] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/27/2024] [Revised: 12/28/2024] [Accepted: 01/06/2025] [Indexed: 01/24/2025] Open
Abstract
Rheumatoid arthritis (RA) is a progressive autoimmune disease leading to structural and functional joint damage and, eventually, to physical disability. The pathogenesis of the disease is highly complex and involves interactions between fibroblast-like synoviocytes (FLSs) and immune cells, which stimulate the secretion of pro-inflammatory factors, leading to chronic inflammation. In recent years, studies have demonstrated the importance of epigenetics in RA. Specifically, epigenetic alterations have been suggested to serve as diagnostic and treatment biomarkers, while epigenetic mechanisms are thought to be involved in the pathogenesis of RA. Epigenetic regulators coordinate gene expression, and in the case of inflammatory diseases, they regulate the expression of a broad range of inflammatory molecules. In this review, we discuss current evidence on the involvement of DNA and RNA methylation in RA.
Collapse
Affiliation(s)
- Kajetan Kiełbowski
- Department of Physiology, Pomeranian Medical University, 70-111 Szczecin, Poland; (K.K.); (E.B.); (K.F.); (R.J.); (J.R.)
| | - Estera Bakinowska
- Department of Physiology, Pomeranian Medical University, 70-111 Szczecin, Poland; (K.K.); (E.B.); (K.F.); (R.J.); (J.R.)
| | - Anna Gorący-Rosik
- Department of Clinical and Molecular Biochemistry, Pomeranian Medical University, 70-111 Szczecin, Poland;
| | - Karolina Figiel
- Department of Physiology, Pomeranian Medical University, 70-111 Szczecin, Poland; (K.K.); (E.B.); (K.F.); (R.J.); (J.R.)
| | - Roksana Judek
- Department of Physiology, Pomeranian Medical University, 70-111 Szczecin, Poland; (K.K.); (E.B.); (K.F.); (R.J.); (J.R.)
| | - Jakub Rosik
- Department of Physiology, Pomeranian Medical University, 70-111 Szczecin, Poland; (K.K.); (E.B.); (K.F.); (R.J.); (J.R.)
| | - Paweł Dec
- Department of Plastic and Reconstructive Surgery, 109 Military Hospital, 71-422 Szczecin, Poland
| | - Andrzej Modrzejewski
- Clinical Department of General Surgery, Pomeranian Medical University in Szczecin, Piotra Skargi 9-11, 70-965 Szczecin, Poland;
| | - Andrzej Pawlik
- Department of Physiology, Pomeranian Medical University, 70-111 Szczecin, Poland; (K.K.); (E.B.); (K.F.); (R.J.); (J.R.)
| |
Collapse
|