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) (remove)
Keywords
- artificial intelligence (1)
- cancer imaging (1)
- cancer immunotherapy (1)
- imaging (1)
- multiple myeloma (1)
- natural language processing (1)
- ontology (1)
- real world evidence (1)
Institute
- Medizinische Klinik und Poliklinik II (2) (remove)
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.
Immunotherapy with chimeric antigen receptor-engineered T-cells (CAR-T) is under investigation in multiple myeloma. There are reports of myeloma remission after CD19 CAR-T therapy, although CD19 is hardly detectable on myeloma cells by flow cytometry (FC). We apply single molecule-sensitive direct stochastic optical reconstruction microscopy (dSTORM), and demonstrate CD19 expression on a fraction of myeloma cells (10.3–80%) in 10 out of 14 patients (density: 13–5,000 molecules per cell). In contrast, FC detects CD19 in only 2 of these 10 patients, on a smaller fraction of cells. Treatment with CD19 CAR-T in vitro results in elimination of CD19-positive myeloma cells, including those with <100 CD19 molecules per cell. Similar data are obtained by dSTORM analyses of CD20 expression on myeloma cells and CD20 CAR-T. These data establish a sensitivity threshold for CAR-T and illustrate how super-resolution microscopy can guide patient selection in immunotherapy to exploit ultra-low density antigens.