1. Noninvasive Precision Screening of Prostate Cancer by Urinary Multimarker Sensor and Artificial Intelligence Analysis
- Author
-
Choung-Soo Kim, Kwan Hyi Lee, Hojun Kim, Sungwook Park, Youngdo Jeong, Sang Hoon Song, and In Gab Jeong
- Subjects
Oncology ,Male ,medicine.medical_specialty ,Urinary system ,Biopsy ,General Physics and Astronomy ,Clinical state ,02 engineering and technology ,010402 general chemistry ,01 natural sciences ,Unmet needs ,Prostate cancer ,Artificial Intelligence ,Internal medicine ,Cancer screening ,medicine ,False positive paradox ,Biomarkers, Tumor ,Humans ,General Materials Science ,Early Detection of Cancer ,business.industry ,General Engineering ,Prostatic Neoplasms ,Prostate-Specific Antigen ,021001 nanoscience & nanotechnology ,Antigen test ,medicine.disease ,0104 chemical sciences ,0210 nano-technology ,business - Abstract
Screening for prostate cancer relies on the serum prostate-specific antigen test, which provides a high rate of false positives (80%). This results in a large number of unnecessary biopsies and subsequent overtreatment. Considering the frequency of the test, there is a critical unmet need of precision screening for prostate cancer. Here, we introduced a urinary multimarker biosensor with a capacity to learn to achieve this goal. The correlation of clinical state with the sensing signals from urinary multimarkers was analyzed by two common machine learning algorithms. As the number of biomarkers was increased, both algorithms provided a monotonic increase in screening performance. Under the best combination of biomarkers, the machine learning algorithms screened prostate cancer patients with more than 99% accuracy using 76 urine specimens. Urinary multimarker biosensor leveraged by machine learning analysis can be an important strategy of precision screening for cancers using a drop of bodily fluid.
- Published
- 2020