Developing diabetes ketoacidosis prediction using ANFIS model

Diagnosis of pathological conditions through electronic nose analysis of urine samples: a systematic review and meta-analysis

“… 28 The latest study suggested the use of a Neuro-fuzzy Inference System (ANFIS) algorithm to monitor the diabetic ketones in urine through the smell of acetone. 29 The eNose consisted of four metal oxide gas sensors, instead of the five used on the previously mentioned study. The patients were required to fast for better results of detection.…”

“…Using this process, it was possible to achieve a detection of 93%. 29 The six contemplated articles showed high sensitivity and specificity values for the detection of diabetes, suggesting that the clinical screening of this disease may be a potential application of eNose technology in the near future.…”