IFN-γ ELISpot-enabled machine learning for culprit drug identification in nonimmediate drug hypersensitivity
Journal of Allergy and Clinical Immunology · 2024
DOI: 10.1016/j.jaci.2023.08.026 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Allergy and Clinical Immunology, 2024. Verfasst von Yuda Chongpison und 17 weiteren Autor:innen. Beteiligte Einrichtung: Biostatistics Excellence Centre, Research Affairs, Faculty of Medicine, Chulalongkorn University, Bangkok, Thailand; Skin and Allergy Research Unit, …. Hauptthemen laut MEDLINE: Drug Hypersensitivity. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 27 Literaturangaben. Gefördert von: Chulalongkorn University.
Abstract (Originalsprache)
BACKGROUND: Diagnosing drug-induced allergy, especially nonimmediate phenotypes, is challenging. Incorrect classifications have unwanted consequences. OBJECTIVE: We sought to evaluate the diagnostic utility of IFN-γ ELISpot and clinical parameters in predicting drug-induced nonimmediate hypersensitivity using machine learning. METHODS: The study recruited 393 patients. A positive patch test or drug provocation test (DPT) was used to define positive drug hypersensitivity. Various clinical factors were considered in developing random forest (RF) and logistic regression (LR) models. Performances were compared against the IFN-γ ELISpot-only model. RESULTS: Among the 102 patients who had 164 DPTs, most patients had severe cutaneous adverse reactions (35/102, 34.3%) and maculopapular exanthems (33/102, 32.4%). Common suspected drugs were antituberculosis drugs (46/164, 28.1%) and β-lactams (42/164, 25.6%). Mean (SD) age of patients with DPT was 52.7 (20.8) years. IFN-γ ELISpot, fixed drug eruption, Naranjo categories, and nonsteroidal anti-inflammatory drugs were the most important features in all developed models. The RF and LR models had higher discriminating abilities. An IFN-γ ELISpot cutoff value of 16.0 spot-forming cells/106 PBMCs achieved 94.8% specificity and 57.1% sensitivity. Depending on clinical needs, optimal cutoff values for RF and LR models can be chosen to achieve either high specificity (0.41 for 96.1% specificity and 0.52 for 97.4% specificity, respectively) or high sensitivity (0.26 for 78.6% sensitivity and 0.37 for 71.4% sensitivity, respectively). CONCLUSIONS: IFN-γ ELISpot assay was valuable in identifying culprit drugs, whether used individually or incorporated in a prediction model. Performances of RF and LR models were comparable. Additional test datasets with DPT would be helpful to validate the model further.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Biostatistics Excellence Centre, Research Affairs, Faculty of Medicine, Chulalongkorn University, Bangkok, Thailand; Skin and Allergy Research Unit, Faculty of Medicine, Chulalongkorn University, Bangkok, Thailand.
- Center of Excellence in Computational Molecular Biology, Faculty of Medicine, Chulalongkorn University, Bangkok, Thailand; Center for Artificial Intelligence in Medicine, Research Affairs, Faculty of Medicine, Chulalong…
- Skin and Allergy Research Unit, Faculty of Medicine, Chulalongkorn University, Bangkok, Thailand; Division of Allergy and Clinical Immunology, Department of Medicine, Faculty of Medicine, Chulalongkorn University, Bangk…
- Skin and Allergy Research Unit, Faculty of Medicine, Chulalongkorn University, Bangkok, Thailand; Division of Dermatology, Department of Medicine, Faculty of Medicine, Chulalongkorn University, Bangkok, Thailand.
- Division of Allergy and Clinical Immunology, Department of Medicine, Faculty of Medicine, Chulalongkorn University, Bangkok, Thailand; King Chulalongkorn Memorial Hospital, Thai Red Cross Society, Bangkok, Thailand.
- Department of Dermatology, Faculty of Medicine Siriraj Hospital, Mahidol University, Bangkok, Thailand.
Förderung
- Chulalongkorn University
Zitieren
APA
Chongpison, Y., Sriswasdi, S., Buranapraditkun, S., Thantiworasit, P., Rerknimitr, P., Mongkolpathumrat, P., Chularojanamontri, L., Srinoulprasert, Y., Rerkpattanapipat, T., Chanprapaph, K., Disphanurat, W., Chakkavittumrong, P., Tovanabutra, N., Srisuttiyakorn, C., Sukasem, C., Tuchinda, P., Pongcharoen, P., & Klaewsongkram, J. (2024). IFN-γ ELISpot-enabled machine learning for culprit drug identification in nonimmediate drug hypersensitivity. Journal of Allergy and Clinical Immunology. https://doi.org/10.1016/j.jaci.2023.08.026
Vancouver
Chongpison Y, Sriswasdi S, Buranapraditkun S, Thantiworasit P, Rerknimitr P, Mongkolpathumrat P, et al. IFN-γ ELISpot-enabled machine learning for culprit drug identification in nonimmediate drug hypersensitivity. Journal of Allergy and Clinical Immunology. 2024. doi:10.1016/j.jaci.2023.08.026
BibTeX
@article{Chongpison2024,
author = {Chongpison, Yuda and Sriswasdi, Sira and Buranapraditkun, Supranee and Thantiworasit, Pattarawat and Rerknimitr, Pawinee and Mongkolpathumrat, Pungjai and Chularojanamontri, Leena and Srinoulprasert, Yuttana and Rerkpattanapipat, Ticha and Chanprapaph, Kumutnart and Disphanurat, Wareeporn and Chakkavittumrong, Panlop and Tovanabutra, Napatra and Srisuttiyakorn, Chutika and Sukasem, Chonlaphat and Tuchinda, Papapit and Pongcharoen, Padcha and Klaewsongkram, Jettanong},
title = {IFN-γ ELISpot-enabled machine learning for culprit drug identification in nonimmediate drug hypersensitivity},
journal = {Journal of Allergy and Clinical Immunology},
year = {2024},
doi = {10.1016/j.jaci.2023.08.026}
}
EUVIMED