Method and diagnostic apparatus for determining enteritis using machine learning model

An apparatus for diagnosing the presence or absence of enteritis by using a machine learning model, comprising:

• a processor;
• a microbial data extraction unit configured to extract multiple microbial data by analyzing a mixture of a gut-derived substance collected from a subject and a gut environment-like composition, the analyzing comprising culturing the mixture under anaerobic conditions for a period of 18 to 24 hours, centrifuging the cultured mixture to separate a supernatant and a precipitate, and analyzing the supernatant and the precipitate;
• a feature selection unit configured to select microbe-related features to be used in the machine learning model from the multiple microbial data based on a predetermined feature selection algorithm;
• a training unit configured to train the machine learning model with the selected microbe-related features;
• and
• a diagnosis unit configured to input, to the trained machine learning model, microbial data collected from a test subject and diagnose whether enteritis is present in the test subject,
• wherein the microbe-related features include the amount of one or more microbes selected from genera included in families, Lachnospiraceae, Veillonellaceae, Tannerellaceae, Clostridia, Coriobacteriaceae, Butyricicoccaceae, Streptococcaceae, Bacteroidaceae, UCG.010, and Prevotellaceae,
• wherein the gut environment-like composition includes sodium chloride (NaCl), sodium carbonate (NaHCO3), potassium chloride (KCl), hemin, or any combination thereof, and
• wherein the feature selection algorithm includes at least one of a Boruta algorithm, a recursive feature elimination (RFE) algorithm, or any combination thereof.