This device is capable of detecting kidney disease through exhaled breath. The air exhaled from the mouth will be analyzed by the device quickly to indicate five levels of kidney conditions. It is non-invasive and does not require a blood sample, making it suitable for patients with needle phobia. The device is also internet-based, allowing the stored data to be accessed by doctors or medical professionals wherever they are.

Patients with kidney failure can emit bad breath with a certain level of ammonia content. The interpretation of ammonia levels in patients with renal failure was identified in this work. The ppb (parts per billion) of ammonia converted into eGFR (estimated Glomerular Filtration Rate) which will determined, the severity of kidney failure was divided into 5 categories, namely normal (Stage 1), mild (stage 2), moderate (stage 3), severe (stage 4) and failure (stage 5). The values of eGFR features are used as input for the machine learning technique to predict the level of kidney failure. AI-based kidney failure severity identification system with KNN algorithm had an average accuracy of 89.9% and 95.65% for training and testing accuracy, respectfully.