1
|
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. IFN-γ ELISpot-enabled machine learning for culprit drug identification in nonimmediate drug hypersensitivity. J Allergy Clin Immunol 2024; 153:193-202. [PMID: 37678574 DOI: 10.1016/j.jaci.2023.08.026] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/14/2023] [Revised: 08/11/2023] [Accepted: 08/17/2023] [Indexed: 09/09/2023]
Abstract
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.
Collapse
Affiliation(s)
- Yuda Chongpison
- Biostatistics Excellence Centre, Research Affairs, Faculty of Medicine, Chulalongkorn University, Bangkok, Thailand; Skin and Allergy Research Unit, Faculty of Medicine, Chulalongkorn University, Bangkok, Thailand
| | - Sira Sriswasdi
- 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, Chulalongkorn University, Bangkok, Thailand
| | - Supranee Buranapraditkun
- 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, Bangkok, Thailand
| | - Pattarawat Thantiworasit
- 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, Bangkok, Thailand
| | - Pawinee Rerknimitr
- 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
| | - Pungjai Mongkolpathumrat
- 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
| | - Leena Chularojanamontri
- Department of Dermatology, Faculty of Medicine Siriraj Hospital, Mahidol University, Bangkok, Thailand
| | - Yuttana Srinoulprasert
- Department of Immunology, Faculty of Medicine Siriraj Hospital, Mahidol University, Bangkok, Thailand
| | - Ticha Rerkpattanapipat
- Division of Allergy, Immunology and Rheumatology, Department of Medicine, Faculty of Medicine, Ramathibodi Hospital, Mahidol University, Bangkok, Thailand
| | - Kumutnart Chanprapaph
- Division of Dermatology, Department of Medicine, Faculty of Medicine, Ramathibodi Hospital, Mahidol University, Bangkok, Thailand
| | - Wareeporn Disphanurat
- Division of Dermatology, Department of Medicine, Faculty of Medicine, Thammasat University, Pathumthani, Thailand
| | - Panlop Chakkavittumrong
- Division of Dermatology, Department of Medicine, Faculty of Medicine, Thammasat University, Pathumthani, Thailand
| | - Napatra Tovanabutra
- Division of Dermatology, Department of Internal Medicine, Chiang Mai University, Chiang Mai, Thailand
| | - Chutika Srisuttiyakorn
- Division of Dermatology, Department of Medicine, Phramongkutklao Hospital, Phramongkutklao College of Medicine, Bangkok, Thailand
| | - Chonlaphat Sukasem
- Division of Pharmacogenomics and Personalized Medicine, Department of Pathology, Faculty of Medicine, Ramathibodi Hospital, Mahidol University, Bangkok, Thailand; Pharmacogenomics and Precision Medicine Clinic, Bumrungrad Genomic Medicine Institute, Bumrungrad International Hospital, Bangkok, Thailand
| | - Papapit Tuchinda
- Department of Dermatology, Faculty of Medicine Siriraj Hospital, Mahidol University, Bangkok, Thailand
| | - Padcha Pongcharoen
- Division of Dermatology, Department of Medicine, Faculty of Medicine, Thammasat University, Pathumthani, Thailand
| | - Jettanong Klaewsongkram
- 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, Bangkok, Thailand; King Chulalongkorn Memorial Hospital, Thai Red Cross Society, Bangkok, Thailand.
| |
Collapse
|
2
|
Bhujoo Z, Ingen-Housz-Oro S, Gener G, Gaudin O, Fleck M, Verlinde-Carvalho M, Paul M, Chosidow O, Wolkenstein P, Assier H. Patch tests in nonimmediate cutaneous adverse drug reactions: The importance of late readings on day 4. Contact Dermatitis 2021; 86:29-33. [PMID: 34590309 DOI: 10.1111/cod.13981] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/08/2021] [Revised: 09/02/2021] [Accepted: 09/22/2021] [Indexed: 12/17/2022]
Abstract
BACKGROUND Patch tests (PTs) with two readings have been used for decades to identify the culprit drug in nonimmediate cutaneous adverse drug reactions (NICADRs), followed more recently by late reading of intradermal tests (IDTs). Some teams tend to perform PTs with only one reading before IDTs or even directly perform IDTs. OBJECTIVES To evaluate the relevance of a late PT reading on day 4 (D4) in NICADRs. METHODS We retrospectively selected patients who had a PT for an NICADR between July 2014 and March 2020. RESULTS During the study period, 328 patients had a PT with available results. Among the 75 positive-PT patients with available data for the two readings, 41 (54.7%) had positive results on D2 and D4 and 34 (45.3%) had negative results on D2 but positive results on D4. No patient had positive results on D2 and negative results on D4. CONCLUSION This study shows that a D4 reading enhanced the PT-positive results. A positive PT result allows for reducing the number of IDTs, which are more difficult and costly to perform. Our series suggests that a late PT reading at D4 should be performed for exploring NICADRs.
Collapse
Affiliation(s)
- Zoé Bhujoo
- Dermatology Department, APHP, Henri Mondor Hospital, Créteil, France
| | - Saskia Ingen-Housz-Oro
- Dermatology Department, APHP, Henri Mondor Hospital, Créteil, France.,EA7379 EpidermE, Univ Paris Est Créteil EpidermE, Créteil, France.,Reference Center for Toxic Bullous Diseases and Severe Drug Reactions, Créteil, France
| | - Gwendeline Gener
- Dermatology Department, APHP, Henri Mondor Hospital, Créteil, France.,Reference Center for Toxic Bullous Diseases and Severe Drug Reactions, Créteil, France
| | - Olivier Gaudin
- Dermatology Department, APHP, Henri Mondor Hospital, Créteil, France.,Reference Center for Toxic Bullous Diseases and Severe Drug Reactions, Créteil, France
| | - Margaux Fleck
- Dermatology Department, APHP, Henri Mondor Hospital, Créteil, France
| | | | - Muriel Paul
- EA7379 EpidermE, Univ Paris Est Créteil EpidermE, Créteil, France.,Department of Pharmacy, AP-HP, Hôpital Henri-Mondor, Créteil, France
| | - Olivier Chosidow
- Dermatology Department, APHP, Henri Mondor Hospital, Créteil, France.,University Paris Est Créteil Val de Marne UPEC, Créteil, France
| | - Paul Wolkenstein
- Dermatology Department, APHP, Henri Mondor Hospital, Créteil, France.,University Paris Est Créteil Val de Marne UPEC, Créteil, France
| | - Haudrey Assier
- Dermatology Department, APHP, Henri Mondor Hospital, Créteil, France.,Reference Center for Toxic Bullous Diseases and Severe Drug Reactions, Créteil, France
| |
Collapse
|