INVESTIGATION MACHINE LEARNING MODEL USING STREAMLIT

Abstract

Background. MLOps (Machine Learning Operations) is a relevant and important topic in the field of machine learning. It brings together the practices and processes needed to effectively develop, deploy, and manage machine learning models. Materials and methods. To predict complications after surgery, a Web-based user interface using Streamlit was developed. In this paper, the machine learning pipeline was applied using the Scikit-learn library and a Web application was created using the Streamlit platform, which is open source. This web application has a simple interface for users that allows you to create forecasts of postoperative complications in patients. Results. The user interface was implemented using the Streamlit library for the machine learning model. Conclusions. As a result, the features of implementing a machine learning model using the Streamlit library and developing a user interface were considered. A data set for predicting postoperative complications was used as an example.

Keywords

• machine learning
• forecasting
• prediction of postoperative complications
• logistic regression
• k-nearest neighbors
• decision tree
• support vector machine
• multilayer perceptron
• random forest
• streamlit