Refine
Has Fulltext
- yes (2)
Is part of the Bibliography
- yes (2)
Year of publication
- 2019 (2) (remove)
Document Type
- Journal article (2)
Language
- English (2)
Keywords
- APRI (1)
- FIB-4 (1)
- HBV (1)
- acoustic radiation force impulse imaging (1)
- artificial intelligence (1)
- fibrotest (1)
- multiple myeloma (1)
- natural language processing (1)
- non-invasive fibrosis assessment (1)
- ontology (1)
Institute
Background: Accurate assessment of hepatic fibrosis in patients with chronic HBeAg-negative Hepatitis B is of crucial importance not only to predict the long-term clinical course, but also to evaluate antiviral therapy indication. The aim of this study was to prospectively assess the utility of point shear wave elastography (pSWE) for longitudinal non-invasive fibrosis assessment in a large cohort of untreated patients with chronic HBeAg-negative hepatitis B virus (HBV) infection. Methods: 407 consecutive patients with HBeAg-negative HBV infection who underwent pSWE, transient elastography (TE) as well as laboratory fibrosis markers, including fibrosis index based on four factors (FIB-4), aspartate to platelet ratio index (APRI) and FibroTest, on the same day were prospectively followed up for six years. Patients were classified into one of the three groups: inactive carriers (IC; HBV-DNA <2000 IU/mL and ALT <40 U/L); grey zone group 1 (GZ-1; HBV DNA <2000 IU/mL and ALT >40 U/L); grey zone group 2 (GZ-2; HBV-DNA >2000 IU/mL and ALT <40 U/L). Results: pSWE results were significantly correlated with TE (r = 0.29, p < 0.001) and APRI (r = 0.17; p = 0.005). Median pSWE values did not differ between IC, GZ-1 and GZ-2 patients (p = 0.82, p = 0.17, p = 0.34). During six years of follow-up, median pSWE and TE values did not differ significantly over time (TE: p = 0.27; pSWE: p = 0.05). Conclusion: Our data indicate that pSWE could be useful for non-invasive fibrosis assessment and follow-up in patients with HBeAg-negative chronic HBV infection.
Background: Natural language processing (NLP) is a powerful tool supporting the generation of Real-World Evidence (RWE). There is no NLP system that enables the extensive querying of parameters specific to multiple myeloma (MM) out of unstructured medical reports. We therefore created a MM-specific ontology to accelerate the information extraction (IE) out of unstructured text. Methods: Our MM ontology consists of extensive MM-specific and hierarchically structured attributes and values. We implemented “A Rule-based Information Extraction System” (ARIES) that uses this ontology. We evaluated ARIES on 200 randomly selected medical reports of patients diagnosed with MM. Results: Our system achieved a high F1-Score of 0.92 on the evaluation dataset with a precision of 0.87 and recall of 0.98. Conclusions: Our rule-based IE system enables the comprehensive querying of medical reports. The IE accelerates the extraction of data and enables clinicians to faster generate RWE on hematological issues. RWE helps clinicians to make decisions in an evidence-based manner. Our tool easily accelerates the integration of research evidence into everyday clinical practice.