Refine
Has Fulltext
- yes (2)
Is part of the Bibliography
- yes (2)
Document Type
- Journal article (2)
Language
- English (2)
Keywords
- MTB (1)
- artificial intelligence (1)
- cancer care (1)
- multiple myeloma (1)
- natural language processing (1)
- ontology (1)
- outcomes research (1)
- outreach (1)
- patient access (1)
- precision oncology (1)
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.
(1) Background: molecular tumor boards (MTBs) are crucial instruments for discussing and allocating targeted therapies to suitable cancer patients based on genetic findings. Currently, limited evidence is available regarding the regional impact and the outreach component of MTBs; (2) Methods: we analyzed MTB patient data from four neighboring Bavarian tertiary care oncology centers in Würzburg, Erlangen, Regensburg, and Augsburg, together constituting the WERA Alliance. Absolute patient numbers and regional distribution across the WERA-wide catchment area were weighted with local population densities; (3) Results: the highest MTB patient numbers were found close to the four cancer centers. However, peaks in absolute patient numbers were also detected in more distant and rural areas. Moreover, weighting absolute numbers with local population density allowed for identifying so-called white spots—regions within our catchment that were relatively underrepresented in WERA MTBs; (4) Conclusions: investigating patient data from four neighboring cancer centers, we comprehensively assessed the regional impact of our MTBs. The results confirmed the success of existing collaborative structures with our regional partners. Additionally, our results help identifying potential white spots in providing precision oncology and help establishing a joint WERA-wide outreach strategy.