The project MACSS (Medical Allround-Care Service Solutions) proposes a new patient-centered smart electronic health care service platform with partners from research, industry, health insurance companies, patient organizations and health care service providers. The project focuses on improving patient safety after kidney transplants. Moreover, the project aims at improving the drug safety of patients as well as patient-physician and physician-physician communication.

MACSS develops a mobile application that allows the bidirectional transfer of patient data onto smartphones within the patient's clinical routine treatment. To protect such highly sensitive data, a security and authorization concept had been created and was already approved. MACSS integrates patient data from other medical services and hospital systems by using advanced memory databases for different information services. Innovative technologies aggregate, analyze and recombine medical data in order to provide personalized real-time therapy. In addition, MACSS will help to reduce costs in the healthcare system in the long term.

Within the MACSS project, DFKI researchers work on topics such as natural language processing, text analysis and information extraction from clinical reports. This involves processing textual data to detect medical concepts and relations, which are then connected to a large biomedical knowledge source (e.g. UMLS) for the purpose of improving the interaction between patients and healthcare providers.

18th of March 2019 - MACSS closing event at Charité [slides]

4.-5.12.2018 - Presentation of our mEx demo at Semantic Web Applications and Tools for Healthcare and Life Sciences (SWAT4HCLS'2018) in Antwerp

12th of November 2018 - Joint talk with Wiebke Düttmann-Rehnolt at European Big Data Value Forum (EBDVF) 2018 in Vienna: "Optimizing the care of kidney transplant patients using Big Data". Further infos: [1]

7th of November 2018 - Talk at Future Medicine 2018 in Berlin: "Early detection of complications in patients after kidney transplant"

16th of October 2018 - Talk at Smart Data Forum in Berlin: "Medical Data Analytics for Chronic Kidney Disease"

15th of October 2018 - Our demo mEx - an Information Extraction Platform for German Medical Text is online now: http://biomedical.dfki.de/mEx

8th of October 2018 - Talk at Berlin-Brandenburgische Akademie der Wissenschaften in context of Medizindiagnostik und KI: "Informationszugriff und Medizindiagnostik in der Nephrologie"

25-26th of September 2018 - BigMedilytics Milestone Meeting in Rotterdam

20th of September 2018 - Presenting our paper "A Domain-adapted Dependency Parser for German Clinical Text" at KONVENS in Vienna

08th of May 2018 - Talk at MutlilingualBIO in Miyazaki: "Cross-lingual Candidate Search for Biomedical Concept Normalization"

23th of March 2018 - XPOMET podium discussion in Leipzig

06-07th of March 2018 - BigMedilytics KickOff in Eindhoven

29th of January 2018 - MACSS Milestone Meeting in Berlin

18-19th of October 2017 - Attending ii2030 in Berlin

14th of September 2017 - Talk at GSCL 2017 in Berlin: "Detecting Named Entities and Relations in German Clinical Reports"

06th of September 2017 - Talk at RANLP 2017 in Varna: "Annotation of Entities and Relations in Spanish Radiology Reports"

12th of June 2017 - Talk at Potsdam Computational Linguistics Colloquium

27th of April 2017 - Talk at BioCreative V.5 Challenge Evaluation Workshop in Barcelona

05-06th of April 2017 - MACSS Milestone Meeting in Potsdam

20-24th of March 2017 - Presentation of MACSS at CeBIT in Hannover

October 2016 - Accepted papers for COLING 2016 Workshops Clinical NLP and BioTxtM.

05th of August 2016 - Talk at the 7th International Symposium on Semantic Mining in Biomedicine (SMBM) in Potsdam, Germany

12th of May 2016 - MACSS-Annotation Workshop at DFKI

07th of March 2016 - MACSS Kick-off Meeting at Charité in Berlin

2018

SIA: a scalable interoperable annotation server for biomedical named entities, Johannes Kirschnick, Philippe Thomas, Roland Roller, Leonhard Hennig. In: Journal of Cheminformatics (JCheminf) 10:63, BioMed Central 12/2018. [pdf]

A Domain-adapted Dependency Parser for German Clinical Text, Elif Kara, Tatjana Zeen, Aleksandra Gabryszak, Klemens Budde, Danilo Schmidt and Roland Roller. 2018. In Proceedings of the 14th Conference on Natural Language Processing (KONVENS 2018), Vienna, Austria [pdf][poster]

Integrierte Versorgung chronisch kranker Patienten am Beispiel von MACSS, Danilo Schmidt, Verena Graf, Roland Roller, Oliver Staeck, Thomas Tolxdorff, Thorsten Schaaf, Alexander Löser, Feiyu Xu, Hans Uszkoreit, Philipp Legge, Gero Lurz, Marco Wedekind, Kai Sachs, Sonja Oechsler, Klemens Budde, Sebastian Gaede and Fabian Halleck. 2018. In Aljoscha Burchardt, Hans Uszkoreit (Eds.), IT für soziale Inklusion: Digitalisierung - Künstliche Intelligenz - Zukunft für alle (pp. 41-50). Berlin, Boston: De Gruyter. [pdf]

Cross-lingual Candidate Search for Biomedical Concept Normalization, Roland Roller, Madeleine Kittner, Dirk Weissenborn, Ulf Leser. 2018. In Proceedings of MultilingualBIO, Miyazaki, Japan [pdf][presentation]

‌

2017

Detecting Named Entities and Relations in German Clinical Reports, Roland Roller, Nils Rethmeier, Philippe Thomas, Marc Hübner, Hans Uszkoreit, Oliver Staeck, Klemens Budde, Fabian Halleck and Danilo Schmidt. 2017. In Proceedings of the International Conference of the German Society for Computational Linguistics and Language Technology, Berlin, Germany. [pdf]

mHealth und digitales Management nach Nierentransplantation, F. Halleck, D. Schmidt, S. Georgi, V. Graf, S. Gaede, R. Roller, K. Budde und O. Staeck. In Nieren- und Hochdruckkrankheiten, November 2017 [link]

Sia: Scalable interoperable annotation server, Johannes Kirschnick and Philippe Thomas. 2017. In Proceedings of the BioCreative V.5 Challenge Evaluation Workshop, Barcelona, Spain. [source]

‌

2016

Negation Detection in Clinical Reports Written in German, Viviana Cotik, Roland Roller, Feiyu Xu, Hans Uszkoreit, Klemens Budde and Danilo Schmidt, In Proceedings of the 5th Workshop on Building and Evaluating Resources for Biomedical Text Mining (BioTxtM), 2016, Osaka, Japan, Association for Computational Linguistics [pdf]

A fine-grained corpus annotation schema of German nephrology records, Roland Roller, Hans Uszkoreit, Feiyu Xu, Laura Seiffe, Michael Mikhailov, Oliver Staeck, Klemens Budde, Fabian Halleck and Danilo Schmidt, In Proceedings of the Clinical Natural Language Processing Workshop, 2016, Osaka, Japan, Association for Computational Linguistics [pdf]

A Light-weight & Robust System for Clinical Concept Disambiguation, Dirk Weissenborn, Roland Roller, Feiyu Xu, Hans Uszkoreit and Enrique Garcia Perez, In Proceedings of the 7th International Symposium on Semantic Mining in Biomedicine, SMBM 2016, Potsdam, Germany [pdf]

Integrierte Versorgung nierentransplantierter Patienten, Entwicklung einer E-Health-Plattform, Fabian Hillock, Danilo Schmidt, Oliver Staeck, Thorsten Schaaf, Thomas Tolxdorff, Alexander Löser, Feiyu Xu, Hans Uszkoreit, Philipp Legge, Kai Sachs, Sonja Oechsler and Klemens Budde, Dialyse aktuell, Vol. 20, No. 06, Pages 285-290, Georg Thieme Verlag, Stuttgart, New York, 7/2016

- Dependency Parser for German Clinical Text, KONVENS 2018

- CharTranslator: Cross-lingual Candidate Search for Biomedical Concept Normalization, MultilingualBIO 2018

- Sia: Scalable interoperable annotation server

- synthetic clinical text corpus: partly annotated with POS and dependencies

- Negex Negation Detection for German Clinical Text: trigger set & data, BioTxtM 2016 paper

- Pre-Annotation Tool, ClinicalNLP 2016 paper

official project website: macss-projekt.de

• Charité, Universitätsklinik Berlin (Konsortialführer/lead)
• Beuth-Hochschule für Technik Berlin
• DFKI GmbH
• SAP SE
• smartpatient GmbH (Anbieter der MyTherapy App für iOS und Android)

This research is supported by the German Federal Ministry of Economics and Energy (BMWi) through the project MACSS (01MD16011F).