Computerized Clinical Decision Support Systems; Opportunities and future trends (original) (raw)

We used data from population-based studies to determine the accuracy of the Fatty Liver Index (FLI) and the Hepatic Steatosis Index (HSI) in determining individual risk of hepatic steatosis. We also developed a new risk scoring system and validated all three indices using external data. We used data from the Study of Health in Pomerania (SHIP; n=4,222), conducted in North-eastern Germany, to validate the existing scoring systems and to develop our own index. Data from the South German Echinococcus Multilocularis and Internal Diseases in Leutkirch (EMIL) study (n=2,177) were used as an external validation data set. Diagnostic performance was evaluated in terms of discrimination (area under the receiver operating characteristic curve (AUC)) and calibration plots. We applied boosting for generalized linear models to select relevant diagnostic separators. The FLI accurately discriminated patients with fatty liver disease from those without (AUC=0.817) but had poor calibration, in that p...

BACKGROUND: Histopathologic assessment of liver tissue is an essential step in management and follow-up of non-alcoholic fatty liver disease (NAFLD) while inter- and intra-observer variations limit the accuracy of these assessments. OBJECTIVES: The aim of this study was to assess the inter- and intra-observer reproducibility of histopathologic assessment of liver biopsies based on NAFLD activity score (NAS) scoring system. MATERIALS AND METHODS: The anonymous liver biopsy samples of 100 consecutive NAFLD suspected adults were randomly assigned to four pathologists. Then, the samples were randomly reassigned to the pathologists for the second time in a way that each sample would be evaluated by two different pathologists. Biopsies were revisited by their first evaluator after two months. The results were reported based on NAS scoring system. RESULTS: Inter-observer agreement of the pathology scores based on NAS scoring system was acceptable for steatosis, lobular inflammation, and fibrosis, but not for hepatocyte ballooning. The intra-observer agreement was acceptable in all scales, with lowest intra-class correlation observed for lobular inflammation. CONCLUSIONS: NAS scoring system has good overall inter- and intra-observer agreement, but more attention should be given to defining the hepatocyte ballooning and lobular inflammation, and training the pathologists to improve the accuracy of pathology reports.

Objectives: To determine the inter observer agreement of ultrasound diagnosis of the severity and grading of steatosis in patients with HCV Methods: Patients with HCV were evaluated, from March 2008-August 2010 at Radiology department, Dow Medical College and Civil Hospital Karachi, with ultrasound for detection and grading of steatosis and fibrosis using a standardized set of criteria. The same sets of images were reviewed by the same radiologists 5 years later (2015) for determining the agreement in the grading. Kappa (k) statistics were utilized. Present results were compared with that of the pilot study conducted in 2007 on 100 images. Results: 452 set of images were reviewed by three radiologists, designated A, B and C. The inter observer agreement was satisfactory to good with k=0.8 for no steatosis, 0.4 for mild steatosis, 0.7 for moderate steatosis and 0.9 for severe steatosis. The inter-observer agreement in the pilot study in 2007 had shown k – values of 0.81 for no steat...

The objectives of our study were to assess the accuracy of hepatorenal index (HRI) in detection and grading of hepatic steatosis and to evaluate various factors that can affect the HRI measurement. Forty-five patients, who had undergone an abdominal sonographic examination within 30 days of liver biopsy, were enrolled. The HRI was calculated as the ratio of the mean brightness levels of the liver and renal parenchymas. The effect of the measurement technique on the HRI was evaluated by using various sizes, depths, and locations of the regions of interest (ROIs) in the liver. The measurements were obtained by two observers. The HRI was compared with the subjective grading of steatosis. The optimal HRI cutoff to detect steatosis was 2.01, yielding a sensitivity of 62.5% and specificity of 95.2%. Subjective grading had a sensitivity of 87.5% and specificity of 62.5%. HRIs of the hepatic steatosis group were statistically different from the no-steatosis group (p < 0.05). However, the...