Background: Drug reaction with eosinophilia and systemic symptoms (DRESS) and morbilliform drug eruption (MDE) are 2 distinct drug eruptions that can appear clinically similar at presentation. Given the significant morbidity of DRESS, there is a need for objective markers that can aid in early recognition.
Objective: The purpose of this study is to explore the diagnostic potential of routine hematological data on or near the date of rash onset.
Methods: We use machine learning as an exploratory method to identify any early hematological patterns capable of differentiating DRESS from MDE.
Results: We found that lymphocyte count, pan-immune inflammation value, neutrophil-to-lymphocyte ratio, and platelet levels were strong discriminators of DRESS from MDE at initial presentation.
Conclusions: These findings highlight the potential of hematologic profiles to enhance early diagnostic accuracy.
Get full access to this article
View all access options for this article.
References
1.
CalleAM, AguirreN, ArdilaJC, et al.DRESS syndrome: A literature review and treatment algorithm. World Allergy Organ J. 2023;16(3):100673; doi: 10.1016/j.waojou.2022.100673
2.
HamaN, AbeR, GibsonA, et al.Drug-induced hypersensitivity syndrome (DIHS)/drug reaction with eosinophilia and systemic symptoms (DRESS): Clinical features and pathogenesis. J Allergy Clin Immunol Pract. 2022;10(5):1155–1167.e5; doi: 10.1016/j.jaip.2022.02.004
3.
KardaunSH, SidoroffA, Valeyrie-AllanoreL, et al.Variability in the clinical pattern of cutaneous side-effects of drugs with systemic symptoms: Does a DRESS syndrome really exist? Br J Dermatol. 2007;156(3):609–611; doi: 10.1111/j.1365-2133.2006.07704.x
4.
HusainZ, ReddyBY, SchwartzRA. DRESS syndrome: Part I. Clinical perspectives. J Am Acad Dermatol. 2013;68(5):693.e1-708; doi: 10.1016/j.jaad.2013.01.033
5.
BanerjeeM, ReynoldsE, AnderssonHB, et al.Tree-based analysis. Circ Cardiovasc Qual Outcomes. 2019;12(5):e004879; doi: 10.1161/CIRCOUTCOMES.118.004879
6.
LeeYW, ChoiJW, ShinEH. Machine learning model for predicting malaria using clinical information. Comput Biol Med. 2021;129:104151; doi: 10.1016/j.compbiomed.2020.104151
