Acryl and Samsung Medical Center Publish SCI-Grade Paper on AI Model for Diagnosing Prostate Conditions

PublicationsDec 24, 2024



"Offering Hope to Prostate Patients" – Acryl's AI Research Featured in International Journal


Acryl (CEO Jin Park), a specialist in AI infrastructure and medical solutions, has collaborated with the research team at Samsung Medical Center to develop a non-invasive AI model for diagnosing lower urinary tract symptoms (LUTS). The results of this groundbreaking research were recently published in the International Neurourology Journal, a prestigious international urology journal.


The research introduces an innovative alternative to invasive diagnostic methods. The paper is titled “Machine Learning Models for the Noninvasive Diagnosis of Bladder Outlet Obstruction and Detrusor Underactivity in Men With Lower Urinary Tract Symptoms.”


LUTS are common urinary symptoms experienced by middle-aged and older men, often caused by bladder outlet obstruction (BOO) or detrusor underactivity (DU). These symptoms are closely associated with benign prostatic hyperplasia (BPH), where an enlarged prostate compresses the urethra, leading to difficulties in urination. LUTS encompasses a range of symptoms, including frequent urination, delayed urination, and weak urinary stream, significantly affecting patients’ quality of life.


While urodynamic studies (UDS) are effective in identifying the underlying causes of LUTS, they are invasive, costly, and uncomfortable for patients. UDS involves complex procedures, such as inserting catheters into the urethra to measure bladder pressure and rectal probes to assess abdominal pressure. These procedures may lead to side effects like hematuria and urinary tract infections.


To address these issues, Acryl and the research team developed an AI-based non-invasive diagnostic model. The study utilized patient data, including the International Prostate Symptom Score (IPSS), International Continence Society (ICS) questionnaire scores, uroflowmetry, and transrectal prostate ultrasound. The machine learning algorithms XGBoost and CatBoost were employed for model training.


The results showed high performance for both algorithms, with AUROC values exceeding 0.8. XGBoost demonstrated superior accuracy, while CatBoost excelled in sensitivity. The findings suggest that the models could replace existing diagnostic methods depending on the clinical environment.


Notably, the AI model enables the diagnosis of LUTS causes using only transrectal prostate ultrasound and conventional test results, eliminating the need for UDS. This innovation could expand diagnostic capabilities from university hospitals to primary and secondary healthcare facilities, significantly improving patient access to care.


Professor Lee Kyu-sung of the Department of Urology at Samsung Medical Center, who led the research, stated, “This study demonstrates the potential of AI diagnostic tools based on non-invasive technology to play a crucial role in patient-centered medical environments. It reduces the discomfort and risks associated with invasive procedures while ensuring both accuracy and accessibility.”


Acryl CEO Jin Park commented, “This research is a prime example of how AI technology can be effectively applied in healthcare. Non-invasive AI diagnostic tools will become an innovative solution that benefits both patients and healthcare providers.”


The AI-based diagnostic tool not only provides a safer experience for patients but also allows diagnoses that were previously limited to large hospitals to be performed in primary care and regional facilities, greatly enhancing healthcare accessibility. Acryl also revealed that they have developed a model capable of predicting whether LUTS patients require surgical treatment or medication. This new model, to be announced soon, will further contribute to personalized medical care by providing specific treatment direction based on AI analysis.


Acryl plans to continue its collaboration with Samsung Medical Center to commercialize this technology. They aim to enhance the accuracy and reliability of the AI diagnostic model through large-scale data validation and additional research, exploring ways to apply it across various healthcare settings. This research marks a significant milestone in patient-centered AI technology development and the commercialization of medical AI.


The study was supported by the Ministry of Science and ICT and the National IT Industry Promotion Agency (NIPA) as part of the "Dr. Answer 2.0" project. This government-led R&D initiative focuses on developing precision medical solutions based on AI to enhance their practical application in clinical settings and realize patient-centered personalized healthcare.

Do you need expert help?

We will diagnose and resolve your concerns regarding AI adoption.

7F/11F, Chungdam Venture Plaza. 704, Seolleung-ro, Gangnam-gu, Seoul, Korea (06069)

TEL. +82.2.557.4958FAX. +82.2.558.4958MAIL. info@acryl.ai