Common gynecological disease prediction model construction method and prediction system

Abstract

The invention relates to a common gynecologic disease prediction model construction method and a prediction system. The prediction model construction method comprises the following steps: acquiring examination items, examination indexes, gynecologic disease knowledge and medical record samples required by common gynecologic diseases; deducing the probability of each inspection item index data andthe overall similarity probability of each inspection item according to the medical record sample; establishing a database which contains gynecological disease knowledge, the probability of examination item index data and the probability of clinical symptoms of the patient and is matched with one another; and performing text feature extraction on the database, and constructing a prediction model through text similarity calculation. According to the invention, a high-accuracy common gynecological disease prediction model and system are constructed by using a machine learning method based on a database constructed by multiple data sources, can be used for primary doctors to learn and refer, are convenient for early prediction and prevention of patients, and have certain popularization and application values.

Description

technical field [0001] The present invention relates to the field of intelligent medical treatment and medical information technology, in particular to a method for constructing a common gynecological disease prediction model and a prediction system. Background technique [0002] According to the survey of the World Health Organization (WHO), more than 96% of married women in my country suffer from various degrees of gynecological diseases, and the incidence rate of common gynecological diseases is more than 87.6%. Among them, the incidence of cervical cancer in women accounts for about 1 / 3 of the world. In real life, many women lack sufficient understanding and understanding of their own bodies and gynecological diseases. [0003] At present, imaging technologies such as ultrasound, magnetic resonance, computerized tomography, colposcopy, and hysteroscopy, as well as liquid-based cytology, genetic testing, leucorrhea analysis, and cervical slices are important for screenin...

AI Technical Summary

Problems solved by technology

These examinations basically rely on various equipment and conditions as well as the doctor's personal clinical experience, which is easy to cause misdiagnosis and missed diagnosis, and it takes a long time for screening, diagnosis and characterization

With the ever-increasing workload and the imminent shortage of doctors, self-examination, assessment and prediction of common gynecological diseases require a simpler, faster and smarter alternative that is not limited by various subjective and objective conditions, thus changing the above technologies Due to the limitation of subjective and objective conditions, the diagnosis and qualitative time is long, and the inaccuracy leads to the passive situation of the processing work.

Images