Annals of clinical and translational neurology · 2023
Radiologic grading scores enhance clinical model's prognostic ability for Guillain-Barré syndrome.
СтатьяПоддержка исследования: вне правительства СШАНазвание и аннотация: Перевод пока не подготовлен
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Fang Qiang, Wu Danyang, Wang Bao, Cao Lili, Cai Shifeng, Sun Xiubin, He Jingzhen
Аннотация
OBJECTIVE: To assess the value of magnetic resonance imaging (MRI) grading scores based on lumbosacral muscle denervation edema in predicting the course of Guillain-Barré syndrome (GBS).
METHODS: We collected data from 354 GBS patients and developed MRI grading criteria (5-point scale) based on the transverse area and longitudinal length of lumbosacral edema. Univariate and multivariate logistic regression analyses were conducted to identify factors associated with GBS prognosis among 12 demographic and radiological features. Clinical models and clinical-MRI models were separately trained and validated by data from Institution 1. External test was performed using data from Institution 2. Differences between the models were assessed using the z-test.
RESULTS: Four clinical factors (sex, albumin cytological dissociation in cerebrospinal fluid, medical research council [MRC] sum score at admission, and MRC sum score at discharge [odds ratio, 0.24-5.15; all p < 0.001]) and MRI grading scores (odds ratio, 2.44; p < 0.001) are independent prognostic factors for GBS patients. The shallow neural network achieved the best prognostic performance both clinical model (accuracy of external test cohort, 83.96%) and clinical-MRI model (accuracy of external test cohort, 90.56%). A significant difference between clinical and clinical-MRI model was also found (clinical model vs. clinical-MRI model, area under the receiver operating curve, 0.84 (95% CI: [0.71, 0.91]) vs. 0.97 (95% CI: [0.86, 0.99]), p < 0.001).
INTERPRETATION: The MRI grading scores for muscle denervation edema may serve as a potential prognostic risk factor for GBS. Furthermore, they significantly improve the prognostic performance of standalone clinical model in predicting GBS prognosis.
METHODS: We collected data from 354 GBS patients and developed MRI grading criteria (5-point scale) based on the transverse area and longitudinal length of lumbosacral edema. Univariate and multivariate logistic regression analyses were conducted to identify factors associated with GBS prognosis among 12 demographic and radiological features. Clinical models and clinical-MRI models were separately trained and validated by data from Institution 1. External test was performed using data from Institution 2. Differences between the models were assessed using the z-test.
RESULTS: Four clinical factors (sex, albumin cytological dissociation in cerebrospinal fluid, medical research council [MRC] sum score at admission, and MRC sum score at discharge [odds ratio, 0.24-5.15; all p < 0.001]) and MRI grading scores (odds ratio, 2.44; p < 0.001) are independent prognostic factors for GBS patients. The shallow neural network achieved the best prognostic performance both clinical model (accuracy of external test cohort, 83.96%) and clinical-MRI model (accuracy of external test cohort, 90.56%). A significant difference between clinical and clinical-MRI model was also found (clinical model vs. clinical-MRI model, area under the receiver operating curve, 0.84 (95% CI: [0.71, 0.91]) vs. 0.97 (95% CI: [0.86, 0.99]), p < 0.001).
INTERPRETATION: The MRI grading scores for muscle denervation edema may serve as a potential prognostic risk factor for GBS. Furthermore, they significantly improve the prognostic performance of standalone clinical model in predicting GBS prognosis.