Craif and a physician at Tokyo Metropolitan Tama Medical Center presented the joint work at the 13th AACR-JCA Joint Conference. Urine samples from 182 gastric cancer patients and 181 healthy controls; more than half of the cases were early stage (Stage 0/I).
TOKYO, March 11, 2025 - Craif Inc., a bio-AI company developing a urine analysis platform for early detection of cancer and other diseases, presented joint research on the early detection of gastric cancer using urinary microRNA at the 13th AACR-JCA Joint Conference, organized by the American Association for Cancer Research (AACR) and the Japanese Cancer Association (JCA) and held in Hawaii from February 1 to 5, 2025.
The presentation, "Development and Validation of a Urinary MicroRNA Test for Early Detection of Gastric Cancer," was given jointly with Tatsuro Murano, a physician at Tokyo Metropolitan Tama Medical Center, and colleagues.
Craif is a venture company founded in 2018 out of Nagoya University. Its core technology, NANO IP (NANO Intelligence Platform), detects disease-related biological substances, including microRNA, with high accuracy in easy-to-collect body fluids such as urine.
What the study found
- Researchers used urinary microRNA to detect early gastric cancer. The team focused on microRNA in urine, aiming to develop a painless, highly accurate method for detecting gastric cancer early. The researchers extracted exosome-derived microRNA from urine samples from 182 gastric cancer patients and 181 healthy controls and analyzed them comprehensively by next-generation sequencing. Of the 325 microRNAs detected, the team focused on 20 whose expression levels differed between the gastric cancer patients and the healthy controls.
- A machine learning model reached an AUC of 0.830 in blinded validation. The team built a machine learning model to predict gastric cancer. Evaluated in a blinded validation cohort in which clinical information was withheld, the model achieved an AUC of 0.830, which the team describes as showing reliability for use in actual clinical practice.
- Sensitivity held up in early-stage cases. More than half of the cases in the model were early stage (Stage 0/I), and the model showed consistently high sensitivity from the early stages. The team views this as suggesting that early gastric cancer, which has been hard to find with existing test methods, may be detectable.
Why gastric cancer
Gastric cancer is one of the top five cancers in both incidence and mortality. Its high mortality is mainly a consequence of diagnosis at an advanced stage and of few early symptoms. Existing test methods impose burdens on patients or make early detection difficult. This study developed a new urine-based microRNA test to detect gastric cancer early.
The miSignal series is not a medical device. It determines risk by statistically analyzing the data. It does not replace a medical diagnosis of whether a person has cancer, and a result of low risk does not mean that cancer is absent or that the person will not develop cancer in the future.
About the 13th AACR-JCA Joint Conference
- Dates: February 1 to 5, 2025
- Location: Hawaii, United States
- Official website: https://www.aacr.org/meeting/13th-aacr-jca-joint-conference-from-cancer-discovery-science-to-therapeutic-innovation/
The American Association for Cancer Research (AACR) and the Japanese Cancer Association (JCA) jointly host the meeting.
About Craif
Craif is a bio-AI company founded in 2018 that develops non-invasive tests for the early detection of cancer. Its platform combines proprietary biomarker detection from urine and other bodily fluids with AI to assess disease risk. Building on one of the world's largest urine datasets, Craif aims to create a urine analysis platform that detects a wide range of diseases early, with cancer as the first step. The company is based in Tokyo and operates a wholly owned laboratory in San Diego, opened in 2026. Learn more at craif.com.