Rehabilitation time prediction method for new coronal pneumonia patient

Abstract

The invention discloses a rehabilitation time prediction method for a new coronal pneumonia patient. The method comprises the following steps: S1, constructing a training time sequence sample for rehabilitation prediction and a rehabilitation probability prediction model; S2, calculating the similarity between the rehabilitation feature domain data at the rear time sequence and the rehabilitation feature domain data at the front time sequence as a monitoring coefficient for representing rehabilitation variation; and S3, performing feature updating on the rehabilitation feature domain data at the preposition time sequence based on the monitoring coefficient, performing rehabilitation prediction to obtain the rehabilitation probability at the postposition time sequence, and then calculating the rehabilitation time of the new coronal pneumonia patient. According to the method, calculation can be carried out only when the rehabilitation state of the new coronary pneumonia patient changes, the redundant calculation amount with the unchanged rehabilitation state can be effectively removed, the calculation efficiency is improved, only the data part with the large change degree is replaced and updated, and the redundant calculation amount of model calculation in the data part with the low change degree is avoided as well.

Description

technical field [0001] The invention relates to the technical field of COVID-19, in particular to a method for predicting the recovery time of patients with COVID-19. Background technique [0002] COVID-19 is a highly contagious disease. The main manifestations of novel coronavirus pneumonia are fever, dry cough, and fatigue. A small number of patients are accompanied by upper respiratory and digestive tract symptoms such as nasal congestion, runny nose, and diarrhea. Severe cases often develop dyspnea after 1 week, and severe cases rapidly progress to acute respiratory distress syndrome, septic shock, difficult-to-correct metabolic acidosis, coagulation dysfunction, and multiple organ failure, etc. Function is an effective means of diagnosis and treatment to determine the recovery of patients. [0003] At present, a corresponding rehabilitation efficiency prediction model has been developed. This model can search relevant medical records based on the user's basic data, and...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a method for predicting the recovery time of patients with new coronary pneumonia, so as to solve the technical problem of low prediction accuracy in the prior art that cannot truly reflect the real illness of the test object

Images