Silver
Award

Bronze
Award

Honorable
Mention Award

Honorable
Mention Award

A Healthcare AI Data Collection Platform for Detection of Kidney Stone Formation

榮獲獎項:

​作品名稱:

學校名稱:

老師姓名:

作者姓名:

作品摘要:

佳作 Honorable Mention Award

A Healthcare AI Data Collection Platform for Detection of Kidney Stone Formation in Early Stages from Urine Sample

中原大學

鍾文耀老師

盧思博、鍾夕德、李政新、黃琳順、吳冠毅、王宜巧

This work presents a healthcare artificial intelligence (AI) platform used for the detection of kidney stone formation in the early stages. The system measures three parameters, pH, conductivity, and uric acid concentration in urine samples. The system utilizes Analog Devices® ADuCM355 chip in EVAL-CN0428-EBZ module. The rate of kidney stone formation disease or urolithiasis has been rising in recent decades worldwide. Urolithiasis only shows the symptoms in the late stages with patients experiencing severe pain. The disease also places a large economic burden on the public and the private healthcare system. The presented system intended to address these issues by providing aid to detect the formation of kidney stones in the early stages. That allows physicians to correct the abnormality using methods such as metabolic screening, diet control, or medical management. An ion-sensitive field-effect transistor (ISFET) as a sensor along with an external potentiometric readout circuit forms the pH measurement section. A gold- coated two-electrode conductivity sensor directly connected to the module is used for urine sample electrical conductivity measurement. The disposable commercial electrochemical strip is used for the measurement of uric acid concentration. The system is designed for measurement of pH from 2 to 10, conductivity from 1mS/cm to 40mS/cm, and uric acid concentration from 20ppm to 500ppm. In the first phase, the presented system is used for the collection of measured data from both healthy individuals and kidney stone formers. Such stored data will be utilized in the training of machine learning algorithms. After successful training and implementation of the model, the hardware will have the potential of being a point-of-care device for early detection of kidney stone formation. AI healthcare solutions presented in this work will contribute to relieving the patients’ extreme pain and frees the resource of the healthcare system.