JMIR Publications

ABSTRACT

Background:

Big data technology provides unlimited potential for efficient storage, processing, query and analysis of medical data. Technologies such as deep learning and machine learning simulate human thinking, assist doctors in diagnosis and treatment, provide personalized health services, and promote the intelligent process of health care applications.

Objective:

This paper aims at the analysis of health care data and the development of intelligent application-related issues, predicting the number of hospital outpatient visits for mass health impacts, and analyzing the characteristics of health care big data. Designing a corresponding data feature learning model will help patients get more effective treatment and rational use of medical resources.

Methods:

A cascaded depth model is successfully implemented by studying and analyzing the specific feature transformation, feature selection and classifier algorithm used in the constructed cascaded depth learning framework. Aiming at the research of medical health data feature learning model based on probabilistic and deep learning mining, this paper mining information from large medical data and developing intelligent application, studies the differences of medical data for disease risk assessment and the related contents of multi-modal data feature representation learning, and proposes a cascade data feature learning model.

Results:

The depth model created in this paper is more suitable for the daily outpatient volume forecast, and analyzes the causes of this phenomenon. It is believed that there are two reasons. On the one hand, the training data in the daily outpatient volume forecast model is larger, so that the training parameters of the model more fit the actual data relationship. On the other hand, the weekly and monthly outpatient volume is cumulative daily outpatient volume, so the errors caused by the prediction will gradually accumulate, is the greater the interval of the prediction accuracy is lower.

Conclusions:

Several data feature learning models are put forward to extract the relationship between the outpatient volume data and obtain the precise predictive value of outpatient volume, which is very helpful to the rational allocation of medical resources and the promotion of intelligent medical treatment.