EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Explainable artificial intelligence-driven prostate cancer screening using exosomal multi-marker based dual-gate FET biosensor

Jae Yi Choi, Sungwook Park, Ji Sung Shim, Hyung Joon Park, Sung Uk Kuh, Youngdo Jeong, Min Gu Park, Tae Il Noh, Sung Goo Yoon, Yoo Min Park, Seok Jae Lee, Hojun Kim und 2 weitere

Biosensors and Bioelectronics · 2025-01 · 267 · 116773

DOI: 10.1016/j.bios.2024.116773 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Biosensors and Bioelectronics, 2025-01. Verfasst von Jae Yi Choi und 13 weiteren Autor:innen. Beteiligte Einrichtung: Center for Advanced Biomolecular Recognition, Biomedical Research Division, Korea Institute of Science and Technology, Seoul, 02792, Republic of Kore…. Hauptthemen laut MEDLINE: Prostatic Neoplasms, Biosensing Techniques, Biomarkers, Tumor, Artificial Intelligence. Die Arbeit wurde bisher 50-mal zitiert (Crossref) und nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: National NanoFab Center, KU-KIST Graduate School of Converging Science and Technology, Korea Institute of Science and Technology.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Prostate Imaging Reporting and Data System (PI-RADS) score, a reporting system of prostate MRI cases, has become a standard prostate cancer (PCa) screening method due to exceptional diagnosis performance. However, PI-RADS 3 lesions are an unmet medical need because PI-RADS provides diagnosis accuracy of only 30-40% at most, accompanied by a high false-positive rate. Here, we propose an explainable artificial intelligence (XAI) based PCa screening system integrating a highly sensitive dual-gate field-effect transistor (DGFET) based multi-marker biosensor for ambiguous lesions identification. This system produces interpretable results by analyzing sensing patterns of three urinary exosomal biomarkers, providing a possibility of an evidence-based prediction from clinicians. In our results, XAI-based PCa screening system showed a high accuracy with an AUC of 0.93 using 102 blinded samples with the non-invasive method. Remarkably, the PCa diagnosis accuracy of patients with PI-RADS 3 was more than twice that of conventional PI-RADS scoring. Our system also provided a reasonable explanation of its decision that TMEM256 biomarker is the leading factor for screening those with PI-RADS 3. Our study implies that XAI can facilitate informed decisions, guided by insights into the significance of visualized multi-biomarkers and clinical factors. The XAI-based sensor system can assist healthcare professionals in providing practical and evidence-based PCa diagnoses.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Prostatic NeoplasmsBiosensing TechniquesBiomarkers, TumorArtificial IntelligenceExosomesEarly Detection of CancerMaleHumansTransistors, ElectronicMembrane ProteinsProstate-Specific Antigen

Stichwörter der Autor:innen

Cancer screeningDual-gate field-effect-transistor sensorExplainable artificial intelligencePI-RADSProstate cancerUrinary exosome

Substanzen

Biomarkers, TumorMembrane ProteinsProstate-Specific Antigen

Autor:innen und Institutionen

  • Center for Advanced Biomolecular Recognition, Biomedical Research Division, Korea Institute of Science and Technology, Seoul, 02792, Republic of Korea; Department of Medical Device Engineering and Management, College of…
  • Center for Advanced Biomolecular Recognition, Biomedical Research Division, Korea Institute of Science and Technology, Seoul, 02792, Republic of Korea.
  • Department of Urology, College of Medicine, Korea University, Seoul, 02841, Republic of Korea.
  • Center for Advanced Biomolecular Recognition, Biomedical Research Division, Korea Institute of Science and Technology, Seoul, 02792, Republic of Korea; KU-KIST Graduate School of Converging Science and Technology, Korea…
  • Department of Medical Device Engineering and Management, College of Medicine, Yonsei University, Seoul, 06229, Republic of Korea; Department of Neurosurgery, College of Medicine, Yonsei University, Seoul, 03722, Republi…
  • Center for Advanced Biomolecular Recognition, Biomedical Research Division, Korea Institute of Science and Technology, Seoul, 02792, Republic of Korea; Department of HY-KIST Bio-convergence, Hanyang University, Seoul, 0…

Förderung

  • National NanoFab Center
  • KU-KIST Graduate School of Converging Science and Technology
  • Korea Institute of Science and Technology
  • Korea Ministry of Science and ICT

Zitieren

APA

Choi, J. Y., Park, S., Shim, J. S., Park, H. J., Kuh, S. U., Jeong, Y., Park, M. G., Noh, T. I., Yoon, S. G., Park, Y. M., Lee, S. J., Kim, H., Kang, S. H., & Lee, K. H. (2025). Explainable artificial intelligence-driven prostate cancer screening using exosomal multi-marker based dual-gate FET biosensor. Biosensors and Bioelectronics, 267, 116773. https://doi.org/10.1016/j.bios.2024.116773

Vancouver

Choi JY, Park S, Shim JS, Park HJ, Kuh SU, Jeong Y, et al. Explainable artificial intelligence-driven prostate cancer screening using exosomal multi-marker based dual-gate FET biosensor. Biosensors and Bioelectronics. 2025;267:116773. doi:10.1016/j.bios.2024.116773

BibTeX
@article{Choi2025,
  author = {Choi, Jae Yi and Park, Sungwook and Shim, Ji Sung and Park, Hyung Joon and Kuh, Sung Uk and Jeong, Youngdo and Park, Min Gu and Noh, Tae Il and Yoon, Sung Goo and Park, Yoo Min and Lee, Seok Jae and Kim, Hojun and Kang, Seok Ho and Lee, Kwan Hyi},
  title = {Explainable artificial intelligence-driven prostate cancer screening using exosomal multi-marker based dual-gate FET biosensor},
  journal = {Biosensors and Bioelectronics},
  year = {2025},
  volume = {267},
  pages = {116773},
  doi = {10.1016/j.bios.2024.116773}
}
Kostenlos starten →