Tag Archives: HiGHmed

Job Opportunity: Research Assistant (f/m/*) with focus on “Knowledge Discovery for Digital Health”


Summary

We are looking for you as a qualified colleague to extend our team working in the German capital region Berlin/Potsdam. You will be part of one of our interdisciplinary cooperation project HiGHmed and contribute to research and education. If you are interested to learn more, please feel free to contact us.

Details

Additional details are available in the (German-speaking) job posting.

Availability

The position as full-time research assistant (40h per week) is available as soon as possible.

Location (Berlin/Potsdam)

Hasso Plattner Institute
Campus Griebnitzsee
14482 Potsdam (near Berlin)
Germany

Molecular Tumor Board

Executive Summary

Today, treatment alternatives for every oncology patient are individually discussed by medical

experts in so-called tumor boards. However, the molecular analysis of each tumors is very complex and the assessment of individual tumor variants time-consuming. Therefore, specialized molecular tumor boards focus also on the analysis and therapy assessment incorporating fine-grained molecular data.

We worked together with subject-matter experts to defined and evaluate a standardized clinical process, designed adequate tool support, and integrated relevant data source for an improved tumor board experience in molecular tumor boards. For example, we applied the scrum board approach, which is well-known from software engineering, to the clinical challenge.

Background

Molecular analysis of tumors is the key driver of precision medicine in oncology. It enables the matching of mutations to targeted drugs and hence more personalized treatments. With its steady advances and ever decreasing costs, it is likely to become a standard procedure for diagnosis and treatment. In molecular tumor boards, regular meetings among medical experts, treatment options are discussed and suggested for each patient based on the tumor’s genetic markup. A molecular tumor board (MTB) consists of 4 major phases: preparation, meeting, treatment suggestion documentation and follow-up. Our MTB Support Engine aims to streamline the entire process in order to tackle the key challenges of molecular tumor boards. The tool lends the Scrum methodology that has already proven itself in software development.

The most critical part of a MTB is the preparation. Genetic variants need to be researched upon available medication. For this purpose, oncologists query various databases and search engines. This is time-consuming and therefore constitutes a key bottleneck for a comprehensive rollout. The MTB support engine accelerates the preparatory research work by

  1. Showing available information resources for a given variant
  2. Ranking and visualizing variants by various criteria and displaying most important ones first.
  3. Simplifying the saving of reviewed information in a click-and-collect fashion

The MTB Support Engine furthermore lets doctors generate a presentation view of relevant information with a single click. In addition, an emphasis it put on collaborative work. Every participant has access to the system allowing preparing themselves. During the meeting, decided upon treatment suggestions can be documented for inspection by the treating physician and allows a structured follow-up.

Most importantly, all information including researched annotations are saved. This allows the rapid retrieval of historic cases with genetically similar patients. Leveraging data integrated from multiple hospitals, even the discovery of novel correlations between variants and diseases is made possible in the long run.

Related Content

Project Partners

Publications

Research Publications

  • Llorca, I., Borchert, F., Schapranow, M.-P.: A Meta-dataset of German Medical Corpora: Harmonization of Annotations and Cross-corpus NER Evaluation. Proceedings of the 5th Clinical Natural Language Processing Workshop. bll. 171–181. Association for Computational Linguistics, Toronto, Canada (2023).
  • Kämmer, N., and Borchert, F., and Winkler, S., and de Melo, G., and Schapranow, M.-P.: Resolving Elliptical Compounds in German Medical Text. The 22nd Workshop on Biomedical Natural Language Processing and BioNLP Shared Tasks. bll. 292–305. Association for Computational Linguistics, Toronto, Canada (2023).
  • Steinwand, S., Borchert, F., Winkler, S., Schapranow, M.-P.: GGTWEAK: Gene Tagging with Weak Supervision for German Clinical Text. In: Juarez, J.M., Marcos, M., Stiglic, G., en Tucker, A. (reds.) Artificial Intelligence in Medicine. bll. 183–192. Springer Nature Switzerland, Cham (2023).
  • Schapranow, M.-P., Borchert, F., Bougatf, N., Hund, H., Eils, R.: Software-Tool Support for Collaborative, Virtual, Multi-Site Molecular Tumor Boards. SN Computer Science. 4, 358 (2023).
  • Ladas, N., Borchert, F., Franz, S., Rehberg, A., Strauch, N., Sommer, K.K., Marschollek, M., Gietzelt, M.: Programming techniques for improving rule readability for rule-based information extraction natural language processing pipelines of unstructured and semi-structured medical texts. Health Informatics Journal. 29, 14604582231164696 (2023).
  • Richter-Pechanski, P., Wiesenbach, P., Schwab, D.M., Kiriakou, C., He, M., Allers, M.M., Tiefenbacher, A.S., Kunz, N., Martynova, A., Spiller, N., Mierisch, J., Borchert, F., Schwind, C., Frey, N., Dieterich, C., Geis, N.A.: A Distributable German Clinical Corpus Containing Cardiovascular Clinical Routine Doctor’s Letters. Scientific Data. 10, 207 (2023).
  • Borchert, F., Schapranow, M.-P.: HPI-DHC @ BioASQ DisTEMIST: Spanish Biomedical Entity Linking with Pre-trained Transformers and Cross-lingual Candidate Retrieval. Proceedings of the Working Notes of CLEF 2022 - Conference and Labs of the Evaluation Forum. bll. 244–258. , Bologna, Italy (2022).
  • Borchert, F., Lohr, C., Modersohn, L., Witt, J., Langer, T., Follmann, M., Gietzelt, M., Arnrich, B., Hahn, U., Schapranow, M.-P.: GGPONC 2.0 - The German Clinical Guideline Corpus for Oncology: Curation Workflow, Annotation Policy, Baseline NER Taggers. Proceedings of the Language Resources and Evaluation Conference. bll. 3650–3660. European Language Resources Association, Marseille, France (2022).
  • Henkenjohann, R., Bergner, B., Borchert, F., Bougatf, N., Hund, H., Eils, R., Schapranow, M.-P.: An Engineering Approach towards Multi-Site Virtual Molecular Tumor Board Software Support. In: Pissaloux, E., Papadopoulos, G., Achilleos, A., en Velázquez, R. (reds.) ICT for Health, Accessibility and Wellbeing. IHAW 2021. bll. 156–170. Springer, Cham (2022).
  • Ganzinger, M., Schapranow, M.-P.: FAIRe Datennutzung: Erfahrungen aus Verbundprojekten. gesundhyte.de: Das Magazin für Digitale Gesundheit in Deutschland. 14, 57–61 (2021).
  • Rasheed, A., Borchert, F., Kohlmeyer, L., Henkenjohann, R., Schapranow, M.-P.: A Comparison of Concept Embeddings for German Clinical Corpora. 2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM). bll. 2314–2321 (2021).

Sponsors

BMBF Logo