RESUMEN
OBJECTIVES: To evaluate the use of shear wave elastography in assessment of kidney allograft tubulointerstitial fibrosis. METHODS: Shear wave elastography assessment was carried out by two independent operators in kidney transplant recipients who underwent allograft biopsy for clinical indications (i.e. rising creatinine >15% or proteinuria >1 g/day). Allograft biopsies were interpreted by the same pathologist according to the 2013 Banff Classification. RESULTS: A total of 40 elastography scans were carried out (median creatinine 172.5 µmol/L [interquartile range 133.8-281.8 µmol/L]). Median tissue stiffness at the cortex (22.6 kPa [interquartile range 18.8-25.7 kPa] vs 22.3 kPa [interquartile range 19.0-26.5 kPa], P = 0.70) and medulla (15.0 kPa [interquartile range 13.7-18.0 kPa] vs 15.6 kPa [interquartile range 14.4-18.2 kPa]) showed no significant differences between the two observers. Interobserver agreement was satisfactory (intraclass correlation coefficient of the cortex 0.84, 95% CI 0.70-0.92 and intraclass correlation coefficient of the medulla 0.88, 95% CI 0.78-0.94). The areas under the receiver operating characteristic curves for detection of tubulointerstitial fibrosis were estimated to be 0.75 (95% CI 0.61-0.89), 0.85 (95% CI 0.75-0.95) and 0.65 (95% CI 0.53-0.78) for cortical, medullary tissue stiffness and serum creatinine, respectively. CONCLUSIONS: Shear wave elastography can be used as a non-invasive tool to evaluate kidney allograft fibrosis with reasonable interobserver agreement and superior test performance to serum creatinine in detecting early tubulointerstitial fibrosis.
Asunto(s)
Diagnóstico por Imagen de Elasticidad , Enfermedades Renales/diagnóstico por imagen , Trasplante de Riñón , Riñón/diagnóstico por imagen , Adulto , Aloinjertos , Biopsia , Femenino , Fibrosis , Supervivencia de Injerto , Hong Kong , Humanos , Riñón/patología , Enfermedades Renales/patología , Masculino , Persona de Mediana Edad , Curva ROC , Reproducibilidad de los ResultadosRESUMEN
BACKGROUND: Similarity-based retrieval of Electronic Health Records (EHRs) from large clinical information systems provides physicians the evidence support in making diagnoses or referring examinations for the suspected cases. Clinical Terms in EHRs represent high-level conceptual information and the similarity measure established based on these terms reflects the chance of inter-patient disease co-occurrence. The assumption that clinical terms are equally relevant to a disease is unrealistic, reducing the prediction accuracy. Here we propose a term weighting approach supported by PubMed search engine to address this issue. METHODS: We collected and studied 112 abdominal computed tomography imaging examination reports from four hospitals in Hong Kong. Clinical terms, which are the image findings related to hepatocellular carcinoma (HCC), were extracted from the reports. Through two systematic PubMed search methods, the generic and specific term weightings were established by estimating the conditional probabilities of clinical terms given HCC. Each report was characterized by an ontological feature vector and there were totally 6216 vector pairs. We optimized the modified direction cosine (mDC) with respect to a regularization constant embedded into the feature vector. Equal, generic and specific term weighting approaches were applied to measure the similarity of each pair and their performances for predicting inter-patient co-occurrence of HCC diagnoses were compared by using Receiver Operating Characteristics (ROC) analysis. RESULTS: The Areas under the curves (AUROCs) of similarity scores based on equal, generic and specific term weighting approaches were 0.735, 0.728 and 0.743 respectively (p < 0.01). In comparison with equal term weighting, the performance was significantly improved by specific term weighting (p < 0.01) but not by generic term weighting. The clinical terms "Dysplastic nodule", "nodule of liver" and "equal density (isodense) lesion" were found the top three image findings associated with HCC in PubMed. CONCLUSIONS: Our findings suggest that the optimized similarity measure with specific term weighting to EHRs can improve significantly the accuracy for predicting the inter-patient co-occurrence of diagnosis when compared with equal and generic term weighting approaches.