Academia Sinica and National Taiwan University (NTU) Hospital have jointly developed PanMETAI, an AI metabolomics platform to detect the early stages of pancreatic cancer.
The tabular AI model detects molecular traces of cancer by leveraging a standardised nuclear magnetic resonance (NMR) analysis platform.
Go deeper with GlobalData
Discover B2B Marketing That Performs
Combine business intelligence and editorial excellence to reach engaged professionals across 36 leading media platforms.
Pancreatic cancer is often diagnosed at advanced stages due to a lack of early symptoms and has a five-year survival rate of only 13%. The new AI metabolomics platform aims to improve precision screening and patient outcomes by facilitating earlier diagnosis.
PanMETAI analyses up to 260,000 molecular signals per individual using a standardised NMR approach.
Unlike conventional diagnostics relying on single biomarkers, it captures comprehensive metabolic profiles from pre-cancerous changes to early lesions. This capability addresses critical gaps in risk assessment.
The model underwent validation through independent blind testing in Taiwan and additional evaluation with a European cohort in Lithuania.
US Tariffs are shifting - will you react or anticipate?
Don’t let policy changes catch you off guard. Stay proactive with real-time data and expert analysis.
By GlobalDataResults showed an area under the curve (AUC) of 0.99 with 93% sensitivity and 94% specificity in Taiwan. It also achieved a high AUC of 93% in the Lithuanian cohort.
PanMETAI development integrates more than two decades of clinical experience from NTU Hospital with Academia Sinica’s research in metabolomics, fundamental science and theoretical computational science.
The research team envisions the model as a useful screening tool for individuals at high risk. In the future, this AI system could potentially evolve into a “Multi-Cancer Early Prediction Platform”, contributing to advancements in precision medicine.
The first author of the study is postdoctoral fellow Dan-Ni Wu from the Genomics Research Center, Academia Sinica.
The corresponding authors are NTU Hospital’s professor Yu-Ting Chang, distinguished research fellow Chao-Ping Hsu (Institute of Chemistry, Academia Sinica), and assistant research fellow Chun-Mei Hu (Genomics Research Center, Academia Sinica).
