Predicting anti-TNF treatment response in rheumatoid arthritis: An artificial intelligence-driven model using cytokine profile and routine clinical practice parameters
Introduction: Rheumatoid arthritis (RA) is a heterogeneous disease in which therapeutic strategies used have evolved dramatically. Despite significant progress in treatment strategies such as the development of anti-TNF drugs, it is still not possible to differentiate those patients who will respond...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-01-01
|
| Series: | Heliyon |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2405844023101332 |
| _version_ | 1797337075718029312 |
|---|---|
| author | Juan Luis Valdivieso Shephard Enrique Josue Alvarez Robles Carmen Cámara Hijón Borja Hernandez Breijo Marta Novella-Navarro Patricia Bogas Schay Ricardo Cuesta de la Cámara Alejandro Balsa Criado Eduardo López Granados Chamaida Plasencia Rodríguez |
| author_facet | Juan Luis Valdivieso Shephard Enrique Josue Alvarez Robles Carmen Cámara Hijón Borja Hernandez Breijo Marta Novella-Navarro Patricia Bogas Schay Ricardo Cuesta de la Cámara Alejandro Balsa Criado Eduardo López Granados Chamaida Plasencia Rodríguez |
| author_sort | Juan Luis Valdivieso Shephard |
| collection | DOAJ |
| description | Introduction: Rheumatoid arthritis (RA) is a heterogeneous disease in which therapeutic strategies used have evolved dramatically. Despite significant progress in treatment strategies such as the development of anti-TNF drugs, it is still not possible to differentiate those patients who will respond from who will not. This can lead to effective-treatment delays and unnecessary costs. The aim of this study was to utilize a profile of the patient's characteristics, clinical parameters, immune status (cytokine profile) and artificial intelligence to assess the feasibility of developing a tool that could allow us to predict which patients will respond to treatment with anti-TNF drugs. Methods: This study included 38 patients with RA from the RA-Paz cohort. Clinical activity was measured at baseline and after 6 months of treatment. The cytokines measured before the start of anti-TNF treatment were IL-1, IL-12, IL-10, IL-2, IL-4, IFNg, TNFa, and IL-6. Statistical analyses were performed using the Wilcoxon-Rank-Sum Test and the Benjamini-Hochberg method. The predictive model viability was explored using the 5-fold cross-validation scheme in order to train the logistic regression models. Results: Statistically significant differences were found in parameters such as IL-6, IL-2, CRP and DAS-ESR. The predictive model performed to an acceptable level in correctly classifying patients (ROC-AUC 0.804167 to 0.891667), suggesting that it would be possible to develop a clinical classification tool. Conclusions: Using a combination of parameters such as IL-6, IL-2, CRP and DAS-ESR, it was possible to develop a predictive model that can acceptably discriminate between remitters and non-remitters. However, this model needs to be replicated in a larger cohort to confirm these findings. |
| first_indexed | 2024-03-08T09:04:10Z |
| format | Article |
| id | doaj.art-1f0b1ae5ecc5435e88634c56b64ad22e |
| institution | Directory Open Access Journal |
| issn | 2405-8440 |
| language | English |
| last_indexed | 2024-03-08T09:04:10Z |
| publishDate | 2024-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Heliyon |
| spelling | doaj.art-1f0b1ae5ecc5435e88634c56b64ad22e2024-02-01T06:30:25ZengElsevierHeliyon2405-84402024-01-01101e22925Predicting anti-TNF treatment response in rheumatoid arthritis: An artificial intelligence-driven model using cytokine profile and routine clinical practice parametersJuan Luis Valdivieso Shephard0Enrique Josue Alvarez Robles1Carmen Cámara Hijón2Borja Hernandez Breijo3Marta Novella-Navarro4Patricia Bogas Schay5Ricardo Cuesta de la Cámara6Alejandro Balsa Criado7Eduardo López Granados8Chamaida Plasencia Rodríguez9Immunology Unit, Hospital Universitario La Paz-Idipaz, 28046, Madrid, Spain; Corresponding author.Spaik Technologies, S.L. Madrid, SpainImmunology Unit, Hospital Universitario La Paz-Idipaz, Madrid, SpainImmunology-Rheumatology Research Group, Hospital Universitario La Paz-Idipaz, Madrid, SpainRheumatology Service, Hospital Universitario La Paz-Idipaz, Madrid, SpainRheumatology Service, Hospital Universitario La Paz-Idipaz, Madrid, SpainImmunology Unit, Hospital Universitario La Paz-Idipaz, Madrid, SpainRheumatology Service, Hospital Universitario La Paz-Idipaz, Madrid, SpainImmunology Unit, Hospital Universitario La Paz-Idipaz, Madrid, SpainRheumatology Service, Hospital Universitario La Paz-Idipaz, Madrid, SpainIntroduction: Rheumatoid arthritis (RA) is a heterogeneous disease in which therapeutic strategies used have evolved dramatically. Despite significant progress in treatment strategies such as the development of anti-TNF drugs, it is still not possible to differentiate those patients who will respond from who will not. This can lead to effective-treatment delays and unnecessary costs. The aim of this study was to utilize a profile of the patient's characteristics, clinical parameters, immune status (cytokine profile) and artificial intelligence to assess the feasibility of developing a tool that could allow us to predict which patients will respond to treatment with anti-TNF drugs. Methods: This study included 38 patients with RA from the RA-Paz cohort. Clinical activity was measured at baseline and after 6 months of treatment. The cytokines measured before the start of anti-TNF treatment were IL-1, IL-12, IL-10, IL-2, IL-4, IFNg, TNFa, and IL-6. Statistical analyses were performed using the Wilcoxon-Rank-Sum Test and the Benjamini-Hochberg method. The predictive model viability was explored using the 5-fold cross-validation scheme in order to train the logistic regression models. Results: Statistically significant differences were found in parameters such as IL-6, IL-2, CRP and DAS-ESR. The predictive model performed to an acceptable level in correctly classifying patients (ROC-AUC 0.804167 to 0.891667), suggesting that it would be possible to develop a clinical classification tool. Conclusions: Using a combination of parameters such as IL-6, IL-2, CRP and DAS-ESR, it was possible to develop a predictive model that can acceptably discriminate between remitters and non-remitters. However, this model needs to be replicated in a larger cohort to confirm these findings.http://www.sciencedirect.com/science/article/pii/S2405844023101332Rheumatoid arthritisCytokinesArtificial intelligenceAnti-TNF response predictionInterleukin 2Interleukin 6 |
| spellingShingle | Juan Luis Valdivieso Shephard Enrique Josue Alvarez Robles Carmen Cámara Hijón Borja Hernandez Breijo Marta Novella-Navarro Patricia Bogas Schay Ricardo Cuesta de la Cámara Alejandro Balsa Criado Eduardo López Granados Chamaida Plasencia Rodríguez Predicting anti-TNF treatment response in rheumatoid arthritis: An artificial intelligence-driven model using cytokine profile and routine clinical practice parameters Heliyon Rheumatoid arthritis Cytokines Artificial intelligence Anti-TNF response prediction Interleukin 2 Interleukin 6 |
| title | Predicting anti-TNF treatment response in rheumatoid arthritis: An artificial intelligence-driven model using cytokine profile and routine clinical practice parameters |
| title_full | Predicting anti-TNF treatment response in rheumatoid arthritis: An artificial intelligence-driven model using cytokine profile and routine clinical practice parameters |
| title_fullStr | Predicting anti-TNF treatment response in rheumatoid arthritis: An artificial intelligence-driven model using cytokine profile and routine clinical practice parameters |
| title_full_unstemmed | Predicting anti-TNF treatment response in rheumatoid arthritis: An artificial intelligence-driven model using cytokine profile and routine clinical practice parameters |
| title_short | Predicting anti-TNF treatment response in rheumatoid arthritis: An artificial intelligence-driven model using cytokine profile and routine clinical practice parameters |
| title_sort | predicting anti tnf treatment response in rheumatoid arthritis an artificial intelligence driven model using cytokine profile and routine clinical practice parameters |
| topic | Rheumatoid arthritis Cytokines Artificial intelligence Anti-TNF response prediction Interleukin 2 Interleukin 6 |
| url | http://www.sciencedirect.com/science/article/pii/S2405844023101332 |
| work_keys_str_mv | AT juanluisvaldiviesoshephard predictingantitnftreatmentresponseinrheumatoidarthritisanartificialintelligencedrivenmodelusingcytokineprofileandroutineclinicalpracticeparameters AT enriquejosuealvarezrobles predictingantitnftreatmentresponseinrheumatoidarthritisanartificialintelligencedrivenmodelusingcytokineprofileandroutineclinicalpracticeparameters AT carmencamarahijon predictingantitnftreatmentresponseinrheumatoidarthritisanartificialintelligencedrivenmodelusingcytokineprofileandroutineclinicalpracticeparameters AT borjahernandezbreijo predictingantitnftreatmentresponseinrheumatoidarthritisanartificialintelligencedrivenmodelusingcytokineprofileandroutineclinicalpracticeparameters AT martanovellanavarro predictingantitnftreatmentresponseinrheumatoidarthritisanartificialintelligencedrivenmodelusingcytokineprofileandroutineclinicalpracticeparameters AT patriciabogasschay predictingantitnftreatmentresponseinrheumatoidarthritisanartificialintelligencedrivenmodelusingcytokineprofileandroutineclinicalpracticeparameters AT ricardocuestadelacamara predictingantitnftreatmentresponseinrheumatoidarthritisanartificialintelligencedrivenmodelusingcytokineprofileandroutineclinicalpracticeparameters AT alejandrobalsacriado predictingantitnftreatmentresponseinrheumatoidarthritisanartificialintelligencedrivenmodelusingcytokineprofileandroutineclinicalpracticeparameters AT eduardolopezgranados predictingantitnftreatmentresponseinrheumatoidarthritisanartificialintelligencedrivenmodelusingcytokineprofileandroutineclinicalpracticeparameters AT chamaidaplasenciarodriguez predictingantitnftreatmentresponseinrheumatoidarthritisanartificialintelligencedrivenmodelusingcytokineprofileandroutineclinicalpracticeparameters |