Originally published in Liberty Times Health Network
 [Reporter YANG, MIEN-CHIEH / Taipei Report]

A world-first breakthrough! As lung cancer emerges as a major public health concern, timely treatment is critical. A research team from Taipei Medical University has integrated clinical big data with AI to develop a comprehensive system spanning six models, covering diagnosis, treatment, and medication decisions. This system incorporates imaging, clinical data, and other essential factors. After two years of development, the “Lung Cancer Clinical Intelligent Decision Support System” is now available to assist doctors and patients with diagnosis, medication selection, and prognosis evaluation. It has already entered clinical trials.

According to data from the National Health Administration, lung cancer ranks among the top three most common cancers in Taiwan and is the leading cause of cancer-related deaths. The five-year survival rate is approximately 26%, and in many cases, the disease is already at an advanced stage when diagnosed. Lung cancer treatment decisions require consideration of multiple factors, including precise imaging at the time of diagnosis and genetic mutations associated with cancer that influence treatment and medication choices. Utilizing big data and AI can aid in early decision-making, ultimately improving medical efficiency.

A research team led by Taipei Medical University Vice President Cheng-Yu Chen, comprising interdisciplinary experts and supported by the Ministry of Science and Technology, has leveraged AI and big data to enhance clinical applications. By utilizing an innovative AI-powered lung cancer module, the team has developed a pioneering platform—the “Lung Cancer Clinical Decision Support System.” This system assists in interpreting clinical CT scans and digital pathology images while integrating clinical data and genetic information, making it a globally leading innovation.

Cheng-Yu Chen stated that the team has developed a “Fully Automated Low-Dose CT Lung Cancer Gene Mutation Prediction Model,” which can automatically detect tumors from over 300 CT images, perform precise segmentation and calculations, determine tumor types and potential gene mutations, and generate automated recommendations for lung nodule management.

In addition, through collaboration with AetherAI Technology, the team has further developed the “Fully Automated Digital Lung Adenocarcinoma Pathology Gene Mutation Prediction and Drug Selection Model.” This model can rapidly and automatically annotate data, predict the most common mutations in the epidermal growth factor receptor (EGFR) gene, and integrate pathology with clinical data from thousands of patients, aiding in the early and precise selection of targeted therapies.

The team has also developed the “Pathology Report Natural Language Processing (NLP) Automated Drug Recommendation System” and the “Comprehensive Genetic Drug Recommendation Model for Lung Adenocarcinoma.” Utilizing AI-powered NLP technology, these systems can automatically generate recommendations for both insurance-covered and self-paid medications with higher survival rates based on a patient’s pathology report. Additionally, by linking treatment outcomes with survival rates, the system identifies the most optimal drug treatment options for patients with similar conditions and prognoses—essentially functioning as a collective decision-making tool equivalent to dozens of experts who have reviewed hundreds of pathology reports.

For patients with advanced lung cancer who are ineligible for surgery or have experienced metastasis and recurrence, the system automatically matches their condition with global clinical trial databases for new drug testing. This provides patients with the opportunity to enroll in the most suitable clinical trials, offering them access to emerging treatment options.

Cheng-Yu Chen stated that as the project enters its third year, the developed technology models are currently undergoing domestic and international patent applications. Additionally, clinical validation is being conducted in collaboration with various hospitals. Moving forward, the team aims to commercialize these innovations and integrate them into practical medical applications for real-world treatment.