2024
DOI: 10.1016/j.jaci.2023.08.026
|View full text |Cite|
|
Sign up to set email alerts
|

IFN-γ ELISpot-enabled machine learning for culprit drug identification in nonimmediate drug hypersensitivity

Yuda Chongpison,
Sira Sriswasdi,
Supranee Buranapraditkun
et al.
Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1

Citation Types

0
1
0

Year Published

2024
2024
2024
2024

Publication Types

Select...
5

Relationship

0
5

Authors

Journals

citations
Cited by 5 publications
(2 citation statements)
references
References 26 publications
0
1
0
Order By: Relevance
“…As discussed with the patient, the ELISpot assay exhibits the highest sensitivity and specificity in cases of DRESS, with a sensitivity of 61% and specificity of 97% [ 16 ]. However, the sensitivity and specificity of the ELISpot depend on factors such as Naranjo score, drug allergy phenotype, type of suspected drug, and underlying disease, as mentioned in Chongpison et al's [ 31 ] study. The confidence score calculated by machine learning for omeprazole was 0.80 (percentage of positive challenge 68.8), while for meropenem and ceftriaxone, it was 0.15 (percentage of positive challenge around 13.1) (as Figure 3 ).…”
Section: Discussionmentioning
confidence: 99%
“…As discussed with the patient, the ELISpot assay exhibits the highest sensitivity and specificity in cases of DRESS, with a sensitivity of 61% and specificity of 97% [ 16 ]. However, the sensitivity and specificity of the ELISpot depend on factors such as Naranjo score, drug allergy phenotype, type of suspected drug, and underlying disease, as mentioned in Chongpison et al's [ 31 ] study. The confidence score calculated by machine learning for omeprazole was 0.80 (percentage of positive challenge 68.8), while for meropenem and ceftriaxone, it was 0.15 (percentage of positive challenge around 13.1) (as Figure 3 ).…”
Section: Discussionmentioning
confidence: 99%
“…Thus, a DL-based approach has shown its utility in vancomycin treatment monitoring to deal with patients suffering critical illnesses, as demonstrated by its superior performance compared to other population pharmacokinetic models [52 ▪▪ ]. Finally, another ML model has recently achieved the highest precision in predicting NIR using IFN-γ ELISpot and clinical variables [53 ▪▪ ].…”
Section: Predictive Models In Drug Allergymentioning
confidence: 99%