ABSTRACT
Paraquat poisoning has become a serious public health problem in some Asian countries because of misuse or suicide. We sought to develop and validate a radiomics nomogram incorporating radiomics signature and laboratory bio-markers, for differentiating bacterial pneumonia and acute paraquat lung injury. 180 patients with pneumonia and acute paraquat who underwent CT examinations between December 2014 and October 2017 were retrospectively evaluated for testing and validation. Clinical information including demographic data, clinical symptoms and laboratory test were also recorded. A prediction model was built by using backward logistic regression and presented on a nomogram. The radiomics-based features yielded areas under the receiver operating characteristic curve of 0.870 (95% CI 0.757-0.894), sensitivity of 0.857, specificity of 0.804, positive predictive value of 83.3%, negative predictive value of 0.818 in the primary cohort, while in the validation cohort the model showed similar results (0.865 (95% CI 0.686-0.907), 0.833, 0.792, 81.5%, respectively). The individualized nomogram included radiomics signature, body temperature, nausea and vomiting, and aspartate transaminase. We have developed a radiomics nomogram that combination of the radiomics features and clinical risk factors to differentiate paraquat lung injury and pneumonia for patients with an unclear medical history of exposure to paraquat poisoning, providing appropriate therapy decision support.
Subject(s)
Nomograms , Pneumonia/diagnosis , Pulmonary Edema/diagnosis , Tomography, X-Ray Computed , Acute Disease , Acute Lung Injury , Adult , Algorithms , Calibration , Clinical Decision-Making , Cohort Studies , Diagnosis, Differential , Female , Humans , Male , Pneumonia/diagnostic imaging , Pulmonary Edema/diagnostic imaging , ROC Curve , Reproducibility of ResultsABSTRACT
Purpose To investigate the diagnostic value of prenatal MRI in fetal intracranial hemorrhage (FICH). Materials and Methods The imaging and clinical data of 41 cases of FICH accepting MRI diagnosis were retrospectively analyzed. The hemorrhage location, signal characteristics and the associated intracranial abnormalities were observed. The pregnancy outcomes and clinical data after birth were followed up. The correlation between periventricular hemorrhage/intraventricular hemorrhage (PVH/IVH) classification and clinical outcomes was analyzed by combining prenatal risk factors. Results Forty-one cases of FICH were evaluated. There were 23 cases of multifocal cerebral hemorrhage and 18 cases of single focal hemorrhage. According to the bleeding site, the 41 cases were classified into PVH/IVH (33 cases), cerebral hemispheres near cortex hemorrhage (3 cases), cerebellar hemorrhage (2 cases), subdural hemorrhage (2 cases) and subarachnoid hemorrhage (1 case). Most of the FICH cases were in subacute period (36/41) and a few were in chronic period or forming encephalomalacia (5/41). The associated changes included ventriculomegaly, vascular malformation, agenesis of corpus callosum, agenesis of vermis, etc. Follow-up results showed that there were 25 cases of labor induction (autopsy after labor induction was performed in 3 cases), 16 cases were followed-up after birth. Among the 16 newborn, there was 1 case of PVH/IVH grade II fetus showing left ear hearing loss after birth, 1 case of grade II fetus showed dyskinesia within one year after birth, and 1 case of grade IV fetus showed unilateral limb movement disorder. The other 13 cases had no obvious neurological sequelae. Spearman correlation test of ranked data indicated that PVH/IVH classification was moderately correlated with birth outcome (r=0.689, P<0.05). Conclusion Prenatal MRI can evaluate the type and severity of fetal intracranial hemorrhage, and provide references for clinical diagnosis and treatment.
