Magnetic resonance detection data analysis method based on consciousness recovery prediction of patient with consciousness disorder

Abstract

The invention belongs to the field of medical image processing and application, relates to a functional image analysis method for predicting the consciousness recovery of a patient with consciousnessdisorder, and particularly relates to a magnetic resonance detection data analysis method based on the function of the patient with consciousness disorder. The data analysis method based on machine learning comprises the steps that based on resting state functional magnetic resonance data (RS-fMRI), a weighted group sparse algorithm is used to construct a human brain functional connection matrix;from the matrix, a sparse representation feature selection method is used to select functional connection features with high contribution to classification for automatic prediction; and a linear support vector machine is used to construct a prediction model to acquire the final prediction result of consciousness recovery. The method is useful as a reference for predicting whether a long-term unconscious patient with brain damage can recover consciousness.

Description

technical field [0001] The invention belongs to the field of medical image processing and application, and relates to a functional image analysis method for predicting the recovery of consciousness of a person with impaired consciousness, in particular to a data analysis method for magnetic resonance detection based on the function of a person with impaired consciousness. Background technique [0002] The prior art discloses that coma (Coma) is a severe disturbance of consciousness caused by extensive damage to the ascending reticular activating system of the brainstem or neurons in the cerebral cortex under the action of various pathogenic factors. stage. With the increasing number of accidents such as traffic accidents and cardiovascular and cerebrovascular diseases and the rapid development of intensive care medicine, the number of patients with severe brain injury who survived is increasing, resulting in an increasing number of patients with disturbance of consciousness....

AI Technical Summary

Problems solved by technology

[0004] Behavioral judgment based on clinical scales is currently the most commonly used evaluation method. Wijdicks et al. conducted a pooled analysis and found that the Glasgow Coma Scale (GCS) can well predict the prognosis of coma patients with mixed etiologies. The area under the receiver operating curve (ROC) was 0.87; Estraneo et al. found that patients with responsive recovery had higher coma recovery scale (Coma Recovery Scale-Revised, CRS-R) scores and low disability rating scale (Disability rating Scale, DRS) score, the presence of median nerve SEP and CRS-R>6 points are effective predictors of responsive recovery, but this type of method is highly subjective, and the results are easily affected by the evaluator's experience and training level

[0005] Neuroelectrophysiology has excellent time resolution and can be monitored continuously at the bedside. Gütling et al. found that the correct rate of EEG reactivity (EEG-R) in distinguishing good prognosis from poor prognosis was 92%, while central conduction time (Central conduction time, CCT) correct rate is only 82%, GCS correct rate is 72%, but the spatial resolution of neural electrophysiology is poor. As the disease progresses, the sensitivity of such indicators gradually decreases

Images