Interpretable Screening of Illicit Drugs in Raw Urine via LightGBM-Assisted SERS.
8 affiliations
- 1Bionanotechnology Research Center, Korea Research Institute of Bioscience and Biotechnology (KRIBB), 125 Gwahak-ro, Yuseong-gu, Daejeon 34141, Republic of Korea.
- 2College of Pharmacy, Daegu Catholic University, 13-13 Hayang-ro, Hayang-eup, Gyeongsan, Gyeongbuk 38430, Republic of Korea.
- 3StoneLab Inc., 205, Daehak-ro 155-gil 10, Yuseong-gu, Daejeon 34138, Republic of Korea.
- 4Graduate School of Medical Science and Engineering, Korea Advanced Institute of Science and Technology (KAIST), 291, Daehak-ro, Yuseong-gu, Daejeon 34051, Republic of Korea.
- 5Department of Nanobiotechnology, KRIBB School, University of Science and Technology (UST), 125 Gwahak-ro, Yuseong-gu, Daejeon 34113, Republic of Korea.
- 6School of Pharmacy, Sungkyunkwan University, Suwon 16419, Republic of Korea.
- 7Department of Laboratory Medicine, Seoul National University College of Medicine, Seoul 03080, Republic of Korea.
- 8Department of Laboratory Medicine, Seoul National University Bundang Hospital, Seongnam 13620, Republic of Korea.
Abstract
Illicit drug-related offenses are a rapidly escalating global concern, driving an urgent need for rapid and reliable drug screening systems. Although conventional identification methods provide definitive results, they often require prolonged turnaround times and complex procedures, limiting their utility in point-of-care (POC) applications. Here, we report a roughened gold nanograss (RGNG) surface-enhanced Raman scattering (SERS) substrate designed for sensitive and automated narcotics screening. The hierarchical RGNG architecture, optimized through Au-Ag codeposition followed by selective etching, generates high-density plasmonic hotspots and achieves high analytical sensitivity, even in complex biological matrices. In vivo studies using rat models demonstrated successful classification of four illicit drugs in urine for up to 6 h after administration using principal component analysis. Furthermore, integration with an explainable LightGBM machine learning framework enabled differentiation (AUC = 0.80) of illicit drug-positive samples from heavily medicated negative-control samples across 155 clinical urine specimens by distinguishing drug-associated biomarker patterns from systemic metabolic backgrounds. This diagnostic pipeline, which combines advanced plasmonic engineering with interpretable gradient-boosting algorithms, provides a scalable proof-of-concept approach for rapid forensic and medical screening; external validation in an independent cohort will be required before clinical deployment.
Related
- Assessing the use of ASAP‐MS for Screening a UK Pub for Illicit Drug Substances
- A Mixed-Micelle Capillary Electrophoresis Method for Fast Quality Screening of Antimalarial Drugs
- Descriptor-guided thermodynamic screening of H2 adsorption on single-atom-doped anatase TiO2 nanoparticles with interpretable machine learning
- Microscale high-throughput screening-assisted discovery of a photo/copper dual catalytic system for benzylic C(sp2)–C(sp3) Suzuki–Miyaura coupling: data mining and mechanistic insights
- Physics-guided thermodynamic screening of H₂ adsorption on alkaline-earth-modified anatase TiO₂ nanoparticles with LLM-assisted interpretation.
BibTeX
@article{kim2026interpretable,
title = {{Interpretable Screening of Illicit Drugs in Raw Urine via LightGBM-Assisted SERS.}},
author = {Jinyoung Kim and Kang Sik Nam and Seongwon Kim and Woojin Nam and Mingoo Song and Taejoon Kang and Juyeon Jung and Tae Hwan Kim and Joon Hee Lee and Eun-Kyung Lim},
journal = {ACS measurement science au},
year = {2026},
month = sep,
doi = {10.1021/acsmeasuresciau.6c00234},
url = {https://europepmc.org/article/MED/42921410},
note = {CC BY-NC-ND},
}
RIS
TY - JOUR
TI - Interpretable Screening of Illicit Drugs in Raw Urine via LightGBM-Assisted SERS.
AU - Jinyoung Kim
AU - Kang Sik Nam
AU - Seongwon Kim
AU - Woojin Nam
AU - Mingoo Song
AU - Taejoon Kang
AU - Juyeon Jung
AU - Tae Hwan Kim
AU - Joon Hee Lee
AU - Eun-Kyung Lim
PY - 2026
DA - 2026/09/24
JO - ACS measurement science au
DO - 10.1021/acsmeasuresciau.6c00234
UR - https://europepmc.org/article/MED/42921410
AB - Illicit drug-related offenses are a rapidly escalating global concern, driving an urgent need for rapid and reliable drug screening systems. Although conventional identification methods provide definitive results, they often require prolonged turnaround times and complex procedures, limiting their utility in point-of-care (POC) applications. Here, we report a roughened gold nanograss (RGNG) surface-enhanced Raman scattering (SERS) substrate designed for sensitive and automated narcotics screening. The hierarchical RGNG architecture, optimized through Au-Ag codeposition followed by selective etching, generates high-density plasmonic hotspots and achieves high analytical sensitivity, even in complex biological matrices. In vivo studies using rat models demonstrated successful classification of four illicit drugs in urine for up to 6 h after administration using principal component analysis. Furthermore, integration with an explainable LightGBM machine learning framework enabled differentiation (AUC = 0.80) of illicit drug-positive samples from heavily medicated negative-control samples across 155 clinical urine specimens by distinguishing drug-associated biomarker patterns from systemic metabolic backgrounds. This diagnostic pipeline, which combines advanced plasmonic engineering with interpretable gradient-boosting algorithms, provides a scalable proof-of-concept approach for rapid forensic and medical screening; external validation in an independent cohort will be required before clinical deployment.
SN - 2694-250X
ER -