Nov18: As drug-related crime rises rapidly worldwide, the need for fast, reliable technologies that can identify illicit drug use at the point of testing is becoming increasingly urgent.
Laboratory testing can provide accurate results, but it requires multiple sample preparation steps and specialized analytical equipment. In contrast, rapid on-site test kits offer faster results, yet their accuracy was limited by factors such as insufficient volume and cross-reactivity with structrually similar drugs.
A research team led by Dr. Eun-Kyung Lim at the Bionanotechnology Research Center of the Korea Research Institute of Bioscience and Biotechnology has developed a platform that combines nanotechnology and artificial intelligence to screen urine for illicit drug use within five minutes, without chemical pretreatment. The study was conducted in collaboration with Professor Tae Hwan Kim at Daegu Catholic University, Professor Joon Hee Lee at Seoul National University Bundang Hospital, and the AI Research Center at StoneLab.
The researchers developed a nanostructured substrate that amplifies the faint light signals produced by drug molecules by millions of times or more. They formed densely packed, grass-like nanopillars on a thin gold surface and roughened their surfaces by selective etching. When drug molecules settle on the substrate, their characteristic vibrational light signals become much stronger, allowing even trace amounts to be clearly identified.
The team also used an artificial intelligence model called LightGBM to distinguish the unique signal fingerprints of illicit drugs from the complex background signals in urine. This approach addresses a longstanding challenge: identifying drug-specific signals in samples containing a wide range of metabolic waste products and medication metabolites.
In tests using real urine specimens, the AI-assisted platform identified drug-positive samples with approximately 80% accuracy, even among urine samples from patients taking non-narcotic analgesics or multiple medications. In experiments with rats, the researchers further demonstrated that drug components could be analyzed in urine collected within six hours after administration.
The findings establish a core technology for rapid, precise on-site drug screening using a single drop of urine without sample pretreatment. The approach brings together advantages of large laboratory instruments and rapid test kits.
With further development into a compact, portable measurement device, the platform could be used in medical and forensic settings, including on-site drug screening by law enforcement agencies and rapid assessment of drug intoxication in hospital emergency departments.
"This study demonstrates that combining nanoengineering with explainable AI algorithms can enable rapid, precise classification of illicit drugs even in complex bodily fluids," said Dr. Eun-Kyung Lim, who led the study. "By further developing the platform into a portable diagnostic device for on-site use, we hope to transform drug screening and emergency diagnostics."
The study was published in September 2026 in ACS Measurement Science Au (Impact Factor: 14.7), an international scientific journal.
The article is titled "Interpretable Screening of Illicit Drugs in Raw Urine via LightGBM-Assisted SERS" (2026). The corresponding authors are Dr. Eun-Kyung Lim of KRIBB, Professor Tae Hwan Kim of Daegu Catholic University, and Professor Joon Hee Lee of Seoul National University Bundang Hospital. Dr. Jinyoung Kim of KRIBB is a first author.
This research was supported by the Institute of Information & Communications Technology Planning & Evaluation (IITP), the Korea Planning & Evaluation Institute of Industrial Technology (KEIT), the Korea Health Industry Development Institute (KHIDI), the Korea Medical Device Development Fund (KMDF), the National Research Council of Science & Technology (NST), the Korea Institute of Planning and Evaluation for Technology in Food, Agriculture and Forestry (IPET), the National Research Foundation of Korea (NRF), and the Major Research Programs of KRIBB.
