@article{DakroubVermaFuehringAgorastouetal.2022, author = {Dakroub, Mohamad and Verma-Fuehring, Raoul and Agorastou, Vaia and Sch{\"o}n, Julian and Hillenkamp, Jost and Puppe, Frank and Loewen, Nils A.}, title = {Inter-eye correlation analysis of 24-h IOPs and glaucoma progression}, series = {Graefe's Archive for Clinical and Experimental Ophthalmology}, volume = {260}, journal = {Graefe's Archive for Clinical and Experimental Ophthalmology}, number = {10}, doi = {10.1007/s00417-022-05651-4}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-323831}, pages = {3349-3356}, year = {2022}, abstract = {Purpose To determine whether 24-h IOP monitoring can be a predictor for glaucoma progression and to analyze the inter-eye relationship of IOP, perfusion, and progression parameters. Methods We extracted data from manually drawn IOP curves with HIOP-Reader, a software suite we developed. The relationship between measured IOPs and mean ocular perfusion pressures (MOPP) to retinal nerve fiber layer (RNFL) thickness was analyzed. We determined the ROC curves for peak IOP (T\(_{max}\)), average IOP(T\(_{avg}\)), IOP variation (IOP\(_{var}\)), and historical IOP cut-off levels to detect glaucoma progression (rate of RNFL loss). Bivariate analysis was also conducted to check for various inter-eye relationships. Results Two hundred seventeen eyes were included. The average IOP was 14.8 ± 3.5 mmHg, with a 24-h variation of 5.2 ± 2.9 mmHg. A total of 52\% of eyes with RNFL progression data showed disease progression. There was no significant difference in T\(_{max}\), T\(_{avg}\), and IOP\(_{var}\) between progressors and non-progressors (all p > 0.05). Except for T\(_{avg}\) and the temporal RNFL, there was no correlation between disease progression in any quadrant and T\(_{max}\), T\(_{avg}\), and IOP\(_{var}\). Twenty-four-hour and outpatient IOP variables had poor sensitivities and specificities in detecting disease progression. The correlation of inter-eye parameters was moderate; correlation with disease progression was weak. Conclusion In line with our previous study, IOP data obtained during a single visit (outpatient or inpatient monitoring) make for a poor diagnostic tool, no matter the method deployed. Glaucoma progression and perfusion pressure in left and right eyes correlated weakly to moderately with each other. Key messages What is known: ● Our prior study showed that manually obtained 24-hour inpatient IOP measurements in right eyes are poor predictors for glaucoma progression. The inter-eye relationship of 24-hour IOP parameters and disease progression on optical coherence tomography (OCT) has not been examined. What we found: ● 24-hour IOP profiles of left eyes from the same study were a poor diagnostic tool to detect worsening glaucoma. ● Significant inter-eye correlations of various strengths were found for all tested parameters}, language = {en} } @article{DietrichKrebsLimanetal.2019, author = {Dietrich, Georg and Krebs, Jonathan and Liman, Leon and Fette, Georg and Ertl, Maximilian and Kaspar, Mathias and St{\"o}rk, Stefan and Puppe, Frank}, title = {Replicating medication trend studies using ad hoc information extraction in a clinical data warehouse}, series = {BMC Medical Informatics and Decision Making}, volume = {19}, journal = {BMC Medical Informatics and Decision Making}, doi = {10.1186/s12911-018-0729-0}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-200409}, pages = {15}, year = {2019}, abstract = {Background Medication trend studies show the changes of medication over the years and may be replicated using a clinical Data Warehouse (CDW). Even nowadays, a lot of the patient information, like medication data, in the EHR is stored in the format of free text. As the conventional approach of information extraction (IE) demands a high developmental effort, we used ad hoc IE instead. This technique queries information and extracts it on the fly from texts contained in the CDW. Methods We present a generalizable approach of ad hoc IE for pharmacotherapy (medications and their daily dosage) presented in hospital discharge letters. We added import and query features to the CDW system, like error tolerant queries to deal with misspellings and proximity search for the extraction of the daily dosage. During the data integration process in the CDW, negated, historical and non-patient context data are filtered. For the replication studies, we used a drug list grouped by ATC (Anatomical Therapeutic Chemical Classification System) codes as input for queries to the CDW. Results We achieve an F1 score of 0.983 (precision 0.997, recall 0.970) for extracting medication from discharge letters and an F1 score of 0.974 (precision 0.977, recall 0.972) for extracting the dosage. We replicated three published medical trend studies for hypertension, atrial fibrillation and chronic kidney disease. Overall, 93\% of the main findings could be replicated, 68\% of sub-findings, and 75\% of all findings. One study could be completely replicated with all main and sub-findings. Conclusion A novel approach for ad hoc IE is presented. It is very suitable for basic medical texts like discharge letters and finding reports. Ad hoc IE is by definition more limited than conventional IE and does not claim to replace it, but it substantially exceeds the search capabilities of many CDWs and it is convenient to conduct replication studies fast and with high quality.}, language = {en} } @article{DjebkoPuppeKayal2019, author = {Djebko, Kirill and Puppe, Frank and Kayal, Hakan}, title = {Model-based fault detection and diagnosis for spacecraft with an application for the SONATE triple cube nano-satellite}, series = {Aerospace}, volume = {6}, journal = {Aerospace}, number = {10}, issn = {2226-4310}, doi = {10.3390/aerospace6100105}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-198836}, pages = {105}, year = {2019}, abstract = {The correct behavior of spacecraft components is the foundation of unhindered mission operation. However, no technical system is free of wear and degradation. A malfunction of one single component might significantly alter the behavior of the whole spacecraft and may even lead to a complete mission failure. Therefore, abnormal component behavior must be detected early in order to be able to perform counter measures. A dedicated fault detection system can be employed, as opposed to classical health monitoring, performed by human operators, to decrease the response time to a malfunction. In this paper, we present a generic model-based diagnosis system, which detects faults by analyzing the spacecraft's housekeeping data. The observed behavior of the spacecraft components, given by the housekeeping data is compared to their expected behavior, obtained through simulation. Each discrepancy between the observed and the expected behavior of a component generates a so-called symptom. Given the symptoms, the diagnoses are derived by computing sets of components whose malfunction might cause the observed discrepancies. We demonstrate the applicability of the diagnosis system by using modified housekeeping data of the qualification model of an actual spacecraft and outline the advantages and drawbacks of our approach.}, language = {en} } @article{FischerHarteltPuppe2023, author = {Fischer, Norbert and Hartelt, Alexander and Puppe, Frank}, title = {Line-level layout recognition of historical documents with background knowledge}, series = {Algorithms}, volume = {16}, journal = {Algorithms}, number = {3}, issn = {1999-4893}, doi = {10.3390/a16030136}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-310938}, year = {2023}, abstract = {Digitization and transcription of historic documents offer new research opportunities for humanists and are the topics of many edition projects. However, manual work is still required for the main phases of layout recognition and the subsequent optical character recognition (OCR) of early printed documents. This paper describes and evaluates how deep learning approaches recognize text lines and can be extended to layout recognition using background knowledge. The evaluation was performed on five corpora of early prints from the 15th and 16th Centuries, representing a variety of layout features. While the main text with standard layouts could be recognized in the correct reading order with a precision and recall of up to 99.9\%, also complex layouts were recognized at a rate as high as 90\% by using background knowledge, the full potential of which was revealed if many pages of the same source were transcribed.}, language = {en} } @article{GehrkeBalbachRauchetal.2019, author = {Gehrke, Alexander and Balbach, Nico and Rauch, Yong-Mi and Degkwitz, Andreas and Puppe, Frank}, title = {Erkennung von handschriftlichen Unterstreichungen in Alten Drucken}, series = {Bibliothek Forschung und Praxis}, volume = {43}, journal = {Bibliothek Forschung und Praxis}, number = {3}, issn = {1865-7648}, doi = {10.1515/bfp-2019-2083}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-193377}, pages = {447 -- 452}, year = {2019}, abstract = {Die Erkennung handschriftlicher Artefakte wie Unterstreichungen in Buchdrucken erm{\"o}glicht R{\"u}ckschl{\"u}sse auf das Rezeptionsverhalten und die Provenienzgeschichte und wird auch f{\"u}r eine OCR ben{\"o}tigt. Dabei soll zwischen handschriftlichen Unterstreichungen und waagerechten Linien im Druck (z. B. Trennlinien usw.) unterschieden werden, da letztere nicht ausgezeichnet werden sollen. Im Beitrag wird ein Ansatz basierend auf einem auf Unterstreichungen trainierten Neuronalen Netz gem{\"a}ß der U-Net Architektur vorgestellt, dessen Ergebnisse in einem zweiten Schritt mit heuristischen Regeln nachbearbeitet werden. Die Evaluationen zeigen, dass Unterstreichungen sehr gut erkannt werden, wenn bei der Binarisierung der Scans nicht zu viele Pixel der Unterstreichung wegen geringem Kontrast verloren gehen. Zuk{\"u}nftig sollen die Worte oberhalb der Unterstreichung mit OCR transkribiert werden und auch andere Artefakte wie handschriftliche Notizen in alten Drucken erkannt werden.}, language = {de} } @article{HarteltPuppe2022, author = {Hartelt, Alexander and Puppe, Frank}, title = {Optical Medieval Music Recognition using background knowledge}, series = {Algorithms}, volume = {15}, journal = {Algorithms}, number = {7}, issn = {1999-4893}, doi = {10.3390/a15070221}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-278756}, year = {2022}, abstract = {This paper deals with the effect of exploiting background knowledge for improving an OMR (Optical Music Recognition) deep learning pipeline for transcribing medieval, monophonic, handwritten music from the 12th-14th century, whose usage has been neglected in the literature. Various types of background knowledge about overlapping notes and text, clefs, graphical connections (neumes) and their implications on the position in staff of the notes were used and evaluated. Moreover, the effect of different encoder/decoder architectures and of different datasets for training a mixed model and for document-specific fine-tuning based on an extended OMR pipeline with an additional post-processing step were evaluated. The use of background models improves all metrics and in particular the melody accuracy rate (mAR), which is based on the insert, delete and replace operations necessary to convert the generated melody into the correct melody. When using a mixed model and evaluating on a different dataset, our best model achieves without fine-tuning and without post-processing a mAR of 90.4\%, which is raised by nearly 30\% to 93.2\% mAR using background knowledge. With additional fine-tuning, the contribution of post-processing is even greater: the basic mAR of 90.5\% is raised by more than 50\% to 95.8\% mAR.}, language = {en} } @article{HoernleinMandelIflandetal.2011, author = {H{\"o}rnlein, Alexander and Mandel, Alexander and Ifland, Marianus and L{\"u}neberg, Edeltraud and Deckert, J{\"u}rgen and Puppe, Frank}, title = {Akzeptanz medizinischer Trainingsf{\"a}lle als Erg{\"a}nzung zu Vorlesungen}, series = {GMS Zeitschrift f{\"u}r Medizinische Ausbildung}, volume = {28}, journal = {GMS Zeitschrift f{\"u}r Medizinische Ausbildung}, number = {3}, doi = {10.3205/zma000754}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-133569}, pages = {Doc42}, year = {2011}, abstract = {Introduction: Medical training cases (virtual patients) are in widespread use for student education. Most publications report about development and experiences in one course with training cases. In this paper we compare the acceptance of different training case courses with different usages deployed as supplement to lectures of the medical faculty of Wuerzburg university during a period of three semesters. Methods: The training cases were developed with the authoring tool CaseTrain and are available for students via the Moodle-based eLearning platform WueCampus at Wuerzburg university. Various data about usage and acceptance is automatically collected. Results: From WS (winter semester) 08/09 till WS 09/10 19 courses with about 200 cases were available. In each semester, about 550 different medical students from W{\"u}rzburg and 50 students from other universities processed about 12000 training cases and filled in about 2000 evaluation forms. In different courses, the usage varied between less than 50 and more than 5000 processed cases. Discussion: Although students demand training cases as supplement to all lectures, the data show that the usage does not primarily depend on the quality of the available training cases. Instead, the training cases of nearly all case collections were processed extremely often shortly before the examination. It shows that the degree of usage depends primarily on the perceived relevance of the training cases for the examination."}, language = {de} } @inproceedings{JannidisRegerWeimeretal.2015, author = {Jannidis, Fotis and Reger, Isabella and Weimer, Lukas and Krug, Markus and Puppe, Frank}, title = {Automatische Erkennung von Figuren in deutschsprachigen Romanen}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-143332}, pages = {7}, year = {2015}, abstract = {Eine wichtige Grundlage f{\"u}r die quantitative Analyse von Erz{\"a}hltexten, etwa eine Netzwerkanalyse der Figurenkonstellation, ist die automatische Erkennung von Referenzen auf Figuren in Erz{\"a}hltexten, ein Sonderfall des generischen NLP-Problems der Named Entity Recognition. Bestehende, auf Zeitungstexten trainierte Modelle sind f{\"u}r literarische Texte nur eingeschr{\"a}nkt brauchbar, da die Einbeziehung von Appellativen in die Named Entity-Definition und deren h{\"a}ufige Verwendung in Romantexten zu einem schlechten Ergebnis f{\"u}hrt. Dieses Paper stellt eine anhand eines manuell annotierten Korpus auf deutschsprachige Romane des 19. Jahrhunderts angepasste NER-Komponente vor.}, subject = {Digital Humanities}, language = {de} } @article{KasparFetteHankeetal.2021, author = {Kaspar, Mathias and Fette, Georg and Hanke, Monika and Ertl, Maximilian and Puppe, Frank and St{\"o}rk, Stefan}, title = {Automated provision of clinical routine data for a complex clinical follow-up study: A data warehouse solution}, series = {Health Informatics Journal}, volume = {28}, journal = {Health Informatics Journal}, number = {1}, doi = {10.1177/14604582211058081}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-260828}, year = {2021}, abstract = {A deep integration of routine care and research remains challenging in many respects. We aimed to show the feasibility of an automated transformation and transfer process feeding deeply structured data with a high level of granularity collected for a clinical prospective cohort study from our hospital information system to the study's electronic data capture system, while accounting for study-specific data and visits. We developed a system integrating all necessary software and organizational processes then used in the study. The process and key system components are described together with descriptive statistics to show its feasibility in general and to identify individual challenges in particular. Data of 2051 patients enrolled between 2014 and 2020 was transferred. We were able to automate the transfer of approximately 11 million individual data values, representing 95\% of all entered study data. These were recorded in n = 314 variables (28\% of all variables), with some variables being used multiple times for follow-up visits. Our validation approach allowed for constant good data quality over the course of the study. In conclusion, the automated transfer of multi-dimensional routine medical data from HIS to study databases using specific study data and visit structures is complex, yet viable.}, language = {en} } @article{KempfKrugPuppe2023, author = {Kempf, Sebastian and Krug, Markus and Puppe, Frank}, title = {KIETA: Key-insight extraction from scientific tables}, series = {Applied Intelligence}, volume = {53}, journal = {Applied Intelligence}, number = {8}, issn = {0924-669X}, doi = {10.1007/s10489-022-03957-8}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-324180}, pages = {9513-9530}, year = {2023}, abstract = {An important but very time consuming part of the research process is literature review. An already large and nevertheless growing ground set of publications as well as a steadily increasing publication rate continue to worsen the situation. Consequently, automating this task as far as possible is desirable. Experimental results of systems are key-insights of high importance during literature review and usually represented in form of tables. Our pipeline KIETA exploits these tables to contribute to the endeavor of automation by extracting them and their contained knowledge from scientific publications. The pipeline is split into multiple steps to guarantee modularity as well as analyzability, and agnosticim regarding the specific scientific domain up until the knowledge extraction step, which is based upon an ontology. Additionally, a dataset of corresponding articles has been manually annotated with information regarding table and knowledge extraction. Experiments show promising results that signal the possibility of an automated system, while also indicating limits of extracting knowledge from tables without any context.}, language = {en} }