Machine Learning-Based Prediction of COVID-19 Severity and Progression to Critical Illness Using CT Imaging and Clinical Data

Objective@#To develop a machine learning (ML) pipeline based on radiomics to predict Coronavirus Disease 2019 (COVID-19) severity and the future deterioration to critical illness using CT and clinical variables. @*Materials and Methods@#Clinical data were collected from 981 patients from a multi-institutional international cohort with real-time polymerase chain reaction-confirmed COVID-19. Radiomics features were extracted from chest CT of the patients. The data of the cohort were randomly divided into training, validation, and test sets using a 7:1:2 ratio. A ML pipeline consisting of a model to predict severity and time-to-event model to predict progression to critical illness were trained on radiomics features and clinical variables. The receiver operating characteristic area under the curve (ROC-AUC), concordance index (C-index), and time-dependent ROC-AUC were calculated to determine model performance, which was compared with consensus CT severity scores obtained by visual interpretation by radiologists. @*Results@#Among 981 patients with confirmed COVID-19, 274 patients developed critical illness. Radiomics features and clinical variables resulted in the best performance for the prediction of disease severity with a highest test ROC-AUC of 0.76 compared with 0.70 (0.76 vs. 0.70, p = 0.023) for visual CT severity score and clinical variables. The progression prediction model achieved a test C-index of 0.868 when it was based on the combination of CT radiomics and clinical variables compared with 0.767 when based on CT radiomics features alone (p < 0.001), 0.847 when based on clinical variables alone (p = 0.110), and 0.860 when based on the combination of visual CT severity scores and clinical variables (p = 0.549). Furthermore, the model based on the combination of CT radiomics and clinical variables achieved time-dependent ROC-AUCs of 0.897, 0.933, and 0.927 for the prediction of progression risks at 3, 5 and 7 days, respectively. @*Conclusion@#CT radiomics features combined with clinical variables were predictive of COVID-19 severity and progression to critical illness with fairly high accuracy.

Machine Learning-Based Prediction of COVID-19 Severity and Progression to Critical Illness Using CT Imaging and Clinical Data

Objective@#To develop a machine learning (ML) pipeline based on radiomics to predict Coronavirus Disease 2019 (COVID-19) severity and the future deterioration to critical illness using CT and clinical variables. @*Materials and Methods@#Clinical data were collected from 981 patients from a multi-institutional international cohort with real-time polymerase chain reaction-confirmed COVID-19. Radiomics features were extracted from chest CT of the patients. The data of the cohort were randomly divided into training, validation, and test sets using a 7:1:2 ratio. A ML pipeline consisting of a model to predict severity and time-to-event model to predict progression to critical illness were trained on radiomics features and clinical variables. The receiver operating characteristic area under the curve (ROC-AUC), concordance index (C-index), and time-dependent ROC-AUC were calculated to determine model performance, which was compared with consensus CT severity scores obtained by visual interpretation by radiologists. @*Results@#Among 981 patients with confirmed COVID-19, 274 patients developed critical illness. Radiomics features and clinical variables resulted in the best performance for the prediction of disease severity with a highest test ROC-AUC of 0.76 compared with 0.70 (0.76 vs. 0.70, p = 0.023) for visual CT severity score and clinical variables. The progression prediction model achieved a test C-index of 0.868 when it was based on the combination of CT radiomics and clinical variables compared with 0.767 when based on CT radiomics features alone (p < 0.001), 0.847 when based on clinical variables alone (p = 0.110), and 0.860 when based on the combination of visual CT severity scores and clinical variables (p = 0.549). Furthermore, the model based on the combination of CT radiomics and clinical variables achieved time-dependent ROC-AUCs of 0.897, 0.933, and 0.927 for the prediction of progression risks at 3, 5 and 7 days, respectively. @*Conclusion@#CT radiomics features combined with clinical variables were predictive of COVID-19 severity and progression to critical illness with fairly high accuracy.

Magnetic Resonance Imaging Features and Their Pathological Mechanisms of Hashimoto's Encephalopathy / 中国医学科学院学报

Objective To analyze the routine and functional magnetic resonance imaging(MRI) features and their potential pathological mechanisms of Hashimoto's encephalopathy(HE). Methods The clinical data and routine and functional MRI images of 30 HE patients who were treated in our center from January 2010 to April 2017 were retrospectively reviewed. Among them,15 patients were examined with contrast-enhanced MRI,16 with diffusion-weighed imaging(DWI),8 with magnetic resonance angiography,2 with magnetic resonance spectroscopy,and 1 with both arterial spin labeled perfusion imaging and diffusion tensor imaging. Seven patients had consecutive clinical and imaging data. The distribution,MRI signals,and functional MRI features of HE were analyzed. Results Among 30 HE patients,routine MRI showed negative results in 8 cases and abnormal findings in 22 cases. Among 22 abnormal cases,9 were characterized by small cerebral vascular disease and 13 had non-specific abnormalities;of these 13 cases,12 had lesions mainly located at the supratentorial white matter,11 had multiple lesions,and 2 had lesions complicated with cerebellum atrophy. The lesions were focal or confluent,punctate or small patchy,showing abnormal signal intensity with iso-or hypo-intensity on T1-weighed imaging,hyper-intensity on both T2-weighed imaging and fluid-attenuated inversion recovery. Most of the lesions had no enhancement(12/15). Among 7 cases with abnormalities on DWI,hyper-intensity on DWI and hypo-intensity on apparent diffusion coefficient were seen in 3 sudden acute cases and hyper-intensity on DWI and increased apparent diffusion coefficient value in 4 sub-acute or slow onset cases. Three cases showed localized intracranial artery stenosis. In 2 cases,magnetic resonance spectroscopy revealed significant lower N-acetylaspartate peak,higher choline peak,and visible lactate peak or lipid peak. Of 7 cases with follow-up data,3 cases had no change,4 cases had changes including softening lesions(2/4),remitted and relapsed lesions(1/4),and rapid progression of brain atrophy with negative finding on the initial MRI(1/4). Conclusion Routine MRI combined with functional imaging can show the features of HE from different perspectives. Routine MRI shows multifocal or confluent lesions in the white matter,mostly without enhancement,while functional imaging may reveal pathological characteristics of different phases of acute or chronic ischemia and demyelinating changes of HE. Combined with clinical data,MRI can differentiate HE from other diseases based on routine and functional MRI appearances.

Effect of Scalp Acupuncture plus Real-time Cognitive Training on Speech Function in Cognitive Impairment of Alzheimer Disease / 上海针灸杂志

Objective To observe the effect of scalp acupuncture plus real-time cognitive training on the speech function in cognitive impairment of Alzheimer disease (AD).Method A hundred patients with AD cognitive impairment were randomized into a treatment group and a control group by using random number table method according to hospitalization order, 50 cases each. The treatment group was given scalp acupuncture plus real-time cognitive training, while the control group was treated with Ginkgo biloba extract tablets. Before and after the treatment, the Western Aphasia Battery (WAB) was adopted to evaluate the spontaneous speech, comprehension, repetition and naming in the two groups.Result In the treatment group, the scores of spontaneous speech, comprehension, repetition and naming of WAB were significantly changed after the treatment (P<0.05). After the treatment, the scores of spontaneous speech, comprehension, repetition and naming of WAB in the treatment group were significantly different from those in the control group (P<0.05).Conclusion Scalp acupuncture plus real-time cognitive training can improve the speech function of patients with AD cognitive impairment.

Effect of Scalp Acupuncture plus Real-time Cognitive Training on Speech Function in Cognitive Impairment of Alzheimer Disease / 上海针灸杂志

Objective To observe the effect of scalp acupuncture plus real-time cognitive training on the speech function in cognitive impairment of Alzheimer disease (AD).Method A hundred patients with AD cognitive impairment were randomized into a treatment group and a control group by using random number table method according to hospitalization order, 50 cases each. The treatment group was given scalp acupuncture plus real-time cognitive training, while the control group was treated with Ginkgo biloba extract tablets. Before and after the treatment, the Western Aphasia Battery (WAB) was adopted to evaluate the spontaneous speech, comprehension, repetition and naming in the two groups.Result In the treatment group, the scores of spontaneous speech, comprehension, repetition and naming of WAB were significantly changed after the treatment (P<0.05). After the treatment, the scores of spontaneous speech, comprehension, repetition and naming of WAB in the treatment group were significantly different from those in the control group (P<0.05).Conclusion Scalp acupuncture plus real-time cognitive training can improve the speech function of patients with AD cognitive impairment.

Differentiation of hypoxic-ischemic encephalopathy and acute bilirubin encephalopathy with magnetic resonance imaging in neonates / 中国当代儿科杂志

<p><b>OBJECTIVE</b>To investigate the value of conventional magnetic resonance imaging (MRI) and diffusion weighed imaging (DWI) in the differentiation of hypoxic-ischemic encephalopathy (HIE) and acute bilirubin encephalopathy in neonates.</p><p><b>METHODS</b>The MRI findings along with DWI characteristics in 15 neonates with HIE involving basal ganglia and in 18 neonates with acute bilirubin encephalopathy between November 2006 and June 2008 were retrospectively reviewed.</p><p><b>RESULTS</b>On T1WI, only 5 patients presented hyperintensity in the globus pallidus in the HIE group, but 16 in the acute bilirubin encephalopathy group (p<0.01). Nine patients in the HIE group showed hyperintensity in the putamen, but the hyperintensity in the putamen was not found in the acute bilirubin encephalopathy group. The frequency of hyperintensity in the subthalamus in the acute bilirubin encephalopathy group (55.6%) was significantly higher than that in the HIE group (13.3%) (p<0.05). Eight patients in the HIE group showed abnormal signals in the other regions on T1WI, but only two patients in the acute bilirubin encephalopathy group (p<0.05). On DWI, 7 out of 11 patients with HIE presented hyperintensity in the basal ganglia, while all 10 patients of the acute bilirubin encephalopathy group presented normal in the basal ganglia.</p><p><b>CONCLUSIONS</b>Conventional MRI along with DWI is useful in differentiating HIE from acute bilirubin encephalopathy in neonates.</p>

Correlation between dynamic contrast-enhanced MRI and expression of microvascular density in the glioma / 中南大学学报(医学版)

OBJECTIVE@#To explore the correlation between microvascular density (MVD) and dynamic contrast-enhanced MRI in the glioma.@*METHODS@#We examined 35 patients with histologically verified glioma. Gadolinium-enhanced dynamic TurboFLASH imaging was performed preoperatively in all patients followed by conventional MRI. The steepest slope (SSmax) of curve and corresponding Tm1 in "first-pass" phase were obtained by analyzing time-signal curve. All specimens were immunostained with anti-human Factor VIII relative antigen monoclonal antibody postoperatively by streptavidin-peroxidase method to obtain the MVD. The correlation between SSmax, Tm1, and MVD was analyzed.@*RESULTS@#SSmax was positively correlated with MVD (r = 0.640, P < 0.01). Tml was negatively correlated with MVD (r = -0.671, P < 0.01).@*CONCLUSION@#The MVD correlates obviously with SSmax and Tml in the glioma. Analyzing the time-signal curve of dynamic contrast-enhanced MRI is helpful to predict the angiogenesis in the glioma.