@phdthesis{Dietrich2019,
  author    = {Dietrich, Georg},
  title     = {Ad Hoc Information Extraction in a Clinical Data Warehouse with Case Studies for Data Exploration and Consistency Checks},
  doi       = {10.25972/OPUS-18464},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-184642},
  school      = {Universit{\"a}t W{\"u}rzburg},
  year      = {2019},
  abstract  = {The importance of Clinical Data Warehouses (CDW) has increased significantly in recent years as they support or enable many applications such as clinical trials, data mining, and decision making. CDWs integrate Electronic Health Records which still contain a large amount of text data, such as discharge letters or reports on diagnostic findings in addition to structured and coded data like ICD-codes of diagnoses. Existing CDWs hardly support features to gain information covered in texts. Information extraction methods offer a solution for this problem but they have a high and long development effort, which can only be carried out by computer scientists. Moreover, such systems only exist for a few medical domains. This paper presents a method empowering clinicians to extract information from texts on their own. Medical concepts can be extracted ad hoc from e.g. discharge letters, thus physicians can work promptly and autonomously. The proposed system achieves these improvements by efficient data storage, preprocessing, and with powerful query features. Negations in texts are recognized and automatically excluded, as well as the context of information is determined and undesired facts are filtered, such as historical events or references to other persons (family history). Context-sensitive queries ensure the semantic integrity of the concepts to be extracted. A new feature not available in other CDWs is to query numerical concepts in texts and even filter them (e.g. BMI > 25). The retrieved values can be extracted and exported for further analysis. This technique is implemented within the efficient architecture of the PaDaWaN CDW and evaluated with comprehensive and complex tests. The results outperform similar approaches reported in the literature. Ad hoc IE determines the results in a few (milli-) seconds and a user friendly GUI enables interactive working, allowing flexible adaptation of the extraction. In addition, the applicability of this system is demonstrated in three real-world applications at the W{\"u}rzburg University Hospital (UKW). Several drug trend studies are replicated: Findings of five studies on high blood pressure, atrial fibrillation and chronic renal failure can be partially or completely confirmed in the UKW. Another case study evaluates the prevalence of heart failure in inpatient hospitals using an algorithm that extracts information with ad hoc IE from discharge letters and echocardiogram report (e.g. LVEF < 45 ) and other sources of the hospital information system. This study reveals that the use of ICD codes leads to a significant underestimation (31\%) of the true prevalence of heart failure. The third case study evaluates the consistency of diagnoses by comparing structured ICD-10-coded diagnoses with the diagnoses described in the diagnostic section of the discharge letter. These diagnoses are extracted from texts with ad hoc IE, using synonyms generated with a novel method. The developed approach can extract diagnoses from the discharge letter with a high accuracy and furthermore it can prove the degree of consistency between the coded and reported diagnoses.},
  subject      = {Information Extraction},
  language  = {en}
}
@article{LodaKrebsDanhofetal.2019,
  author    = {Loda, Sophia and Krebs, Jonathan and Danhof, Sophia and Schreder, Martin and Solimando, Antonio G. and Strifler, Susanne and Rasche, Leo and Kort{\"u}m, Martin and Kerscher, Alexander and Knop, Stefan and Puppe, Frank and Einsele, Hermann and Bittrich, Max},
  title     = {Exploration of artificial intelligence use with ARIES in multiple myeloma research},
  series = {Journal of Clinical Medicine},
  volume    = {8},
  journal   = {Journal of Clinical Medicine},
  number    = {7},
  issn      = {2077-0383},
  doi       = {10.3390/jcm8070999},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-197231},
  pages     = {999},
  year      = {2019},
  abstract  = {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.},
  language  = {en}
}
@article{AhmedZeeshanDandekar2016,
  author    = {Ahmed, Zeeshan and Zeeshan, Saman and Dandekar, Thomas},
  title     = {Mining biomedical images towards valuable information retrieval in biomedical and life sciences},
  series = {Database - The Journal of Biological Databases and Curation},
  volume    = {2016},
  journal   = {Database - The Journal of Biological Databases and Curation},
  doi       = {10.1093/database/baw118},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-162697},
  pages     = {baw118},
  year      = {2016},
  abstract  = {Biomedical images are helpful sources for the scientists and practitioners in drawing significant hypotheses, exemplifying approaches and describing experimental results in published biomedical literature. In last decades, there has been an enormous increase in the amount of heterogeneous biomedical image production and publication, which results in a need for bioimaging platforms for feature extraction and analysis of text and content in biomedical images to take advantage in implementing effective information retrieval systems. In this review, we summarize technologies related to data mining of figures. We describe and compare the potential of different approaches in terms of their developmental aspects, used methodologies, produced results, achieved accuracies and limitations. Our comparative conclusions include current challenges for bioimaging software with selective image mining, embedded text extraction and processing of complex natural language queries.},
  language  = {en}
}