Explainable Boosting Machines Identify Key Metabolomic Biomarkers in Rheumatoid Arthritis
<i>Background and Objectives</i>: 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 bio...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-04-01
|
| Series: | Medicina |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1648-9144/61/5/833 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850257275626717184 |
|---|---|
| author | Fatma Hilal Yagin Cemil Colak Abdulmohsen Algarni Ali Algarni Fahaid Al-Hashem Luca Paolo Ardigò |
| author_facet | Fatma Hilal Yagin Cemil Colak Abdulmohsen Algarni Ali Algarni Fahaid Al-Hashem Luca Paolo Ardigò |
| author_sort | Fatma Hilal Yagin |
| collection | DOAJ |
| description | <i>Background and Objectives</i>: 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. <i>Materials and Methods</i>: 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. <i>Results</i>: 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 <i>N</i>-acetyleucine, pyruvic acid, and glycerol-3-phosphate. EBM global explanation analysis indicated that elevated pyruvic acid levels were significantly correlated with RA, whereas <i>N</i>-acetyleucine exhibited a nonlinear relationship, implying possible protective effects at specific concentrations. <i>Conclusions</i>: 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. |
| format | Article |
| id | doaj-art-9931a4ac8fe4460cb72b3bd3637450e5 |
| institution | OA Journals |
| issn | 1010-660X 1648-9144 |
| language | English |
| publishDate | 2025-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Medicina |
| spelling | doaj-art-9931a4ac8fe4460cb72b3bd3637450e52025-08-20T01:56:28ZengMDPI AGMedicina1010-660X1648-91442025-04-0161583310.3390/medicina61050833Explainable Boosting Machines Identify Key Metabolomic Biomarkers in Rheumatoid ArthritisFatma Hilal Yagin0Cemil Colak1Abdulmohsen Algarni2Ali Algarni3Fahaid Al-Hashem4Luca Paolo Ardigò5Department of Biostatistics, Faculty of Medicine, Malatya Turgut Ozal University, 44210 Malatya, TurkeyDepartment of Biostatistics, and Medical Informatics, Faculty of Medicine, Inonu University, 44280 Malatya, TurkeyDepartment of Computer Science, King Khalid University, Abha 61421, Saudi ArabiaDepartment of Informatics and Computer Systems, College of Computer Science, King Khalid University, Abha 61421, Saudi ArabiaDepartment of Physiology, College of Medicine, King Khalid University, Abha 61421, Saudi ArabiaDepartment of Teacher Education, NLA University College, Linstows Gate 3, 0166 Oslo, Norway<i>Background and Objectives</i>: 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. <i>Materials and Methods</i>: 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. <i>Results</i>: 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 <i>N</i>-acetyleucine, pyruvic acid, and glycerol-3-phosphate. EBM global explanation analysis indicated that elevated pyruvic acid levels were significantly correlated with RA, whereas <i>N</i>-acetyleucine exhibited a nonlinear relationship, implying possible protective effects at specific concentrations. <i>Conclusions</i>: 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.https://www.mdpi.com/1648-9144/61/5/833rheumatoid arthritismetabolomicsbiomarkermachine learningexplainable artificial intelligenceexplainable boosting machines |
| spellingShingle | Fatma Hilal Yagin Cemil Colak Abdulmohsen Algarni Ali Algarni Fahaid Al-Hashem Luca Paolo Ardigò Explainable Boosting Machines Identify Key Metabolomic Biomarkers in Rheumatoid Arthritis Medicina rheumatoid arthritis metabolomics biomarker machine learning explainable artificial intelligence explainable boosting machines |
| title | Explainable Boosting Machines Identify Key Metabolomic Biomarkers in Rheumatoid Arthritis |
| title_full | Explainable Boosting Machines Identify Key Metabolomic Biomarkers in Rheumatoid Arthritis |
| title_fullStr | Explainable Boosting Machines Identify Key Metabolomic Biomarkers in Rheumatoid Arthritis |
| title_full_unstemmed | Explainable Boosting Machines Identify Key Metabolomic Biomarkers in Rheumatoid Arthritis |
| title_short | Explainable Boosting Machines Identify Key Metabolomic Biomarkers in Rheumatoid Arthritis |
| title_sort | explainable boosting machines identify key metabolomic biomarkers in rheumatoid arthritis |
| topic | rheumatoid arthritis metabolomics biomarker machine learning explainable artificial intelligence explainable boosting machines |
| url | https://www.mdpi.com/1648-9144/61/5/833 |
| work_keys_str_mv | AT fatmahilalyagin explainableboostingmachinesidentifykeymetabolomicbiomarkersinrheumatoidarthritis AT cemilcolak explainableboostingmachinesidentifykeymetabolomicbiomarkersinrheumatoidarthritis AT abdulmohsenalgarni explainableboostingmachinesidentifykeymetabolomicbiomarkersinrheumatoidarthritis AT alialgarni explainableboostingmachinesidentifykeymetabolomicbiomarkersinrheumatoidarthritis AT fahaidalhashem explainableboostingmachinesidentifykeymetabolomicbiomarkersinrheumatoidarthritis AT lucapaoloardigo explainableboostingmachinesidentifykeymetabolomicbiomarkersinrheumatoidarthritis |