Method for predicting delirium through artificial intelligence

Abstract

The invention provides a method for predicting delirium through artificial intelligence, and belongs to the field of critical patient evaluation. The method comprises the steps: related data of a patient and a hospital are included through a structured language; feature variables are screened based on a random forest, and a prediction model is constructed through regularization logistic regression, K nearest neighbor, a support vector machine, the random forest, limit gradient lifting and a deep neural network algorithm; and through prediction probabilities of different methods, ensemble learning is carried out through a limit gradient lifting algorithm to finally predict whether a critical patient has delirium or not, and the occurrence probability of the delirium is further calculated. According to the method, patient data and hospital feature information are utilized as much as possible, and individualized evaluation for predicting the critical patient is carried out, so that prediction bias caused by a certain model is weakened, and prediction accuracy is improved.

Description

technical field [0001] A method for predicting delirium in critically ill patients, especially a method for constructing predictions for critically ill patients based on big data. Background technique [0002] Delirium is a syndrome of acute fluctuating altered mental status, characterized primarily by disturbance of consciousness, often accompanied by disturbed sleep-wake cycles, attention deficits, and cognitive and affective disturbances. Studies have found that the incidence of delirium in ICU patients without mechanical ventilation is 20% to 50%, and the incidence of delirium is as high as 60% to 80% when patients are mechanically ventilated. Delirium can lead to prolonged mechanical ventilation, prolonged ICU stay, increased medical costs, decreased ability of daily living after discharge, and poor prognosis. It is particularly important to identify and correct reversible causes of delirium early and accurately. [0003] The clinical models for evaluating delirium ma...

AI Technical Summary

Problems solved by technology

However, this type of model has three deficiencies in clinical use: ① The reliability of the model depends on whether the scoring personnel have received professional training

②Most of the original data for building the model is the clinical information of the patient on the first day of admission to the ICU, which cannot accurately reflect the pathological state and medical intervention measures of the patient at the time of delirium assessment

③The model variables are too old and need to be updated, and many factors that have been confirmed to be strongly related to delirium in recent years are missing in the model

Images