Time series prediction method for traumatic hemorrhagic shock injury

Abstract

The invention provides a traumatic hemorrhagic shock injury time sequence prediction method, which comprises the following steps of: extracting traumatic hemorrhagic shock injury data from a database, and performing data processing on the traumatic hemorrhagic shock injury data, including processing a data abnormal value, and performing linear vacancy filling and clustering vacancy filling on the data; designing a stepped index for the processed data; and constructing a prediction model by applying the index stepped result and different types of classifiers, and predicting a result after a preset duration through the prediction model. According to the invention, time series data with serious missing can be processed, time series rather than cross section prediction is carried out, and the obtained prediction result is more accurate; a prediction time window is introduced, a prediction index stepped concept is provided, and real-time dynamic prediction and early warning based on a time sequence can be carried out on traumatic hemorrhagic shock by using indexes capable of being monitored in real time.

Description

technical field [0001] The invention relates to the technical field of artificial intelligence, in particular to a time series prediction method of traumatic hemorrhagic shock injury. Background technique [0002] Trauma is a major event that seriously affects social stability, people's well-being, and personal health. Traumatic hemorrhagic shock (THS: Traumatic hemorrhagic shock) is a common cause of death after trauma and is a type of hypovolemic shock caused by severe trauma. . Traumatic hemorrhagic shock is one of the most serious and life-threatening complications caused by severe trauma. Due to blood loss, the effective blood volume is insufficient, and the oxygen supply to vital organs such as the heart and brain is insufficient. Even if fluid resuscitation is performed immediately, multiple Irreversible damage to organs and tissues, if not treated in time, is very likely to lead to death of the trauma wounded. [0003] Although traumatic hemorrhagic shock is a grea...

AI Technical Summary

Problems solved by technology

[0006] 1. In terms of data filling, there is no relatively mature filling system at present, and most of them use mean filling or linear filling. The filling method is single, and there are still problems such as poor data quality and large differences with real data after filling

[0007] 2. Existing technical methods mostly use cross-sectional prediction methods, such as taking the average value of the data to obtain cross-section predictions, and the results obtained are "conclusive", which cannot realize rolling prediction and real-time monitoring of disease conditions

[0008] 3. The existing small amount of time series prediction only uses vital sign indicators with low measurement cost and many times, such as heart rate and blood pressure, and the prediction effect is not good

[0011] In the treatment of war wounds or on-site treatment of disasters, due to limited equipment conditions, only vital signs can be collected, or some simple laboratory analysis and inspection can be carried out, and blood biochemical indicators can only be collected when transferred to high-level medical institutions, that is, auxiliary inspection and index collection. Gradient exists

Images