Search

Objective We present the Berlin-Tübingen-Oncology corpus (BRONCO), a large and freely available corpus of shuffled sentences from German oncological discharge summaries annotated with diagnosis, treatments, medications, and further attributes including negation and speculation. The aim of BRONCO is to foster reproducible and openly available research on Information Extraction from German medical texts. Materials and Methods BRONCO consists of 200 manually deidentified discharge summaries of cancer patients. Annotation followed a structured and quality-controlled process involving 2 groups of medical experts to ensure consistency, comprehensiveness, and high quality of annotations. We present results of several state-of-the-art techniques for different IE tasks as baselines for subsequent research. Results The annotated corpus consists of 11 434 sentences and 89 942 tokens, annotated with 11 124 annotations for medical entities and 3118 annotations of related attributes. We publish 75% of the corpus as a set of shuffled sentences, and keep 25% as held-out data set for unbiased evaluation of future IE tools. On this held-out dataset, our baselines reach depending on the specific entity types F1-scores of 0.72–0.90 for named entity recognition, 0.10–0.68 for entity normalization, 0.55 for negation detection, and 0.33 for speculation detection. Discussion Medical corpus annotation is a complex and time-consuming task. This makes sharing of such resources even more important. Conclusion To our knowledge, BRONCO is the first sizable and freely available German medical corpus. Our baseline results show that more research efforts are necessary to lift the quality of information extraction in German medical texts to the level already possible for English.

Purpose Precision oncology holds the promise of improving patient outcome. It is based on the idea that the testing of genomic biomarkers can lead to the recommendation of a treatment option tailored to the specific patient. To derive treatment recommendations from molecular profiles, interdisciplinary molecular tumor boards (MTBs) have been established recently in many academic institutions. The recommendation process in MTBs, however, has not been well defined, which limits applicability to larger clinical trials and patient populations. Methods We created four fictional patients on the basis of recent real cases with genomic information on mutations, fusions, copy numbers, and gene expression. We identified 29 tumor boards from nine countries worldwide and asked them to provide treatment recommendations for the sample patients. In addition, a questionnaire regarding the setup and methods used by MTBs was circulated. Results Five MTBs from four countries provided treatment recommendations and answered the questionnaire. For one patient, three tumor board treatment recommendations were identical, and two tumor boards had identical treatment strategies for the other three patients. There was heterogeneity in the interpretation of tumor and germline aberrations as well as in standards of prioritization. Conclusion Differences in the interpretation and recommendation process contribute to heterogeneity in MTB recommendations. Additional comparative analyses of recommendations could help improve rational decision making and lead to standardization.

Purpose Despite promising achievements in precision cancer medicine (PCM), participating patients are still faced with manifold uncertainties, especially regarding a potential treatment benefit of molecular diagnostics (MD). Hence, MD poses considerable challenges for patient information and communication. To meet these challenges, healthcare professionals need to gain deeper insight into patients’ subjective experiences. Therefore, this qualitative study examined information aspects of MD programs in cancer patients. Methods In two German Comprehensive Cancer Centers, 30 cancer patients undergoing MD participated in semi-structured interviews on information transfer and information needs regarding MD. Additionally, patients provided sociodemographic and medical data and indicated their subjective level of information (visual analogue scale, VAS, 0–10). Results On average patients had high levels of information (mean = 7, median = 8); nevertheless 20% (n = 6) showed an information level below 5 points. Qualitative analysis revealed that patients show limited understanding of the complex background of MD and have uncertainties regarding their personal benefit. Further, patients described unmet information needs. Existential threat in awaiting the results was experienced as burdensome. To withstand the strains of their situation, patients emphasized the importance of trusting their physician. Conclusion The challenges in PCM consist in providing unambiguous information, especially concerning treatment benefit, and providing guidance and support. Therefore, psycho-oncology needs to develop guidelines for adequate patient communication in order to help healthcare providers and cancer patients to handle these challenges in the developing field of PCM.

Background Reliable and reproducible interpretation of molecular aberrations constitutes a bottleneck of precision medicine. Evidence-based decision management systems may improve rational therapy recommendations. To cope with an increasing amount of complex molecular data in the clinical care of patients with cancer, we established a workflow for the interpretation of molecular analyses. Methods A specialized physician screened results from molecular analyses for potential biomarkers, irrespective of the diagnostic modality. Best available evidence was retrieved and categorized through establishment of an in-house database and interrogation of publicly available databases. Annotated biomarkers were ranked using predefined evidence levels and subsequently discussed at a molecular tumour board (MTB), which generated treatment recommendations. Subsequent translation into patient treatment and clinical outcomes were followed up. Results One hundred patients were discussed in the MTB between January 2016 and May 2017. Molecular data were obtained for 70 of 100 patients (50 whole exome/RNA sequencing, 18 panel sequencing, 2 immunohistochemistry (IHC)/microsatellite instability analysis). The MTB generated a median of two treatment recommendations each for 63 patients. Thirty-nine patients were treated: 6 partial responses and 12 stable diseases were achieved as best responses. Genetic counselling for germline events was recommended for seven patients. Conclusion The development of an evidence-based workflow allowed for the clinical interpretation of complex molecular data and facilitated the translation of personalized treatment strategies into routine clinical care. The high number of treatment recommendations in patients with comprehensive genomic data and promising responses in patients treated with combination therapy warrant larger clinical studies.

Background Diagnosis and treatment decisions in cancer increasingly depend on a detailed analysis of the mutational status of a patient’s genome. This analysis relies on previously published information regarding the association of variations to disease progression and possible interventions. Clinicians to a large degree use biomedical search engines to obtain such information; however, the vast majority of scientific publications focus on basic science and have no direct clinical impact. We develop the Variant-Information Search Tool (VIST), a search engine designed for the targeted search of clinically relevant publications given an oncological mutation profile. Results VIST indexes all PubMed abstracts and content from ClinicalTrials.gov. It applies advanced text mining to identify mentions of genes, variants and drugs and uses machine learning based scoring to judge the clinical relevance of indexed abstracts. Its functionality is available through a fast and intuitive web interface. We perform several evaluations, showing that VIST’s ranking is superior to that of PubMed or a pure vector space model with regard to the clinical relevance of a document’s content. Conclusion Different user groups search repositories of scientific publications with different intentions. This diversity is not adequately reflected in the standard search engines, often leading to poor performance in specialized settings. We develop a search engine for the specific case of finding documents that are clinically relevant in the course of cancer treatment. We believe that the architecture of our engine, heavily relying on machine learning algorithms, can also act as a blueprint for search engines in other, equally specific domains. VIST is freely available at https://vist.informatik.hu-berlin.de/ Electronic supplementary material The online version of this article (10.1186/s12859-019-2958-3) contains supplementary material, which is available to authorized users.

Purpose Rapidly evolving genomics technologies, in particular comprehensive next-generation sequencing (NGS), have led to exponential growth in the understanding of cancer biology, shifting oncology toward personalized treatment strategies. However, comprehensive NGS approaches, such as whole-exome sequencing, have limitations that are related to the technology itself as well as to the input source. Hence, clinical implementation of comprehensive NGS in a quality-controlled diagnostic workflow requires both the standardization of sequencing procedures and continuous validation of sequencing results by orthogonal methods in an ongoing program to enable the determination of key test parameters and continuous improvement of NGS and bioinformatics pipelines. Patients and Methods We present validation data on 220 patients who were enrolled between 2013 and 2016 in a multi-institutional, genomics-guided precision oncology program (Molecularly Aided Stratification for Tumor Eradication Research) of the National Center for Tumor Diseases Heidelberg and the German Cancer Consortium. Results More than 90% of clinically actionable genomic alterations identified by combined whole-exome sequencing and transcriptome sequencing were successfully validated, with varying frequencies of discordant results across different types of alterations (fusions, 3.7%; single-nucleotide variants, 2.6%; amplifications, 1.1%; overexpression, 0.9%; deletions, 0.6%). The implementation of new computational methods for NGS data analysis led to a substantial improvement of gene fusion calling over time. Conclusion Collectively, these data demonstrate the value of a rigorous validation program that partners with comprehensive NGS to successfully implement and continuously improve cancer precision medicine in a clinical setting.

Therapeutic options for neuroendocrine neoplasms (NEN) are limited. Within the MASTER program, a multi-institutional registry trial for prospective stratification of younger adults with advanced-stage cancer across all histologies and patients with rare tumors conducted under the auspices of NCT Heidelberg/Dresden and the German Cancer Consortium, we apply prospective whole-exome/genome sequencing (WES/WGS) and RNA sequencing (RNA-seq) to determine therapeutic choices for individual patients who have exhausted standard therapy options. We here report the clinical and molecular characteristics of the NEN cohort within this study. Between 2013 and 2018, 108 patients (male, n=65; female, n=43) were enrolled. Histologies according to the 2017 WHO Classification were neuroendocrine tumor grade 1 (NET G1), n=8; NET G2, n=31; NET G3, n=9; neuroendocrine carcinoma, n=49; and mixed neuroendocrine/non-neuroendocrine neoplasm, n=11. Primary tumor sites were gastrointestinal tract, n=30; pancreas, n=31; thorax, n=21; genitourinary system, n=11; head and neck, n=5; and other regions, n=10. All patients had advanced-stage disease and had received a median of 2 prior lines of systemic therapy. WES, WGS, and RNA-seq were performed in 69, 40, and 87 patients, respectively. Clinical evaluation of germline and somatic molecular data (single-nucleotide variants, small insertions and deletions, copy number variations, mutational burden, mutational signatures, homologous recombination deficiency scores, gene expression patterns, etc.) from 105 patients by a dedicated molecular tumor board yielded evidence-based recommendations for clinical management in 91 cases (87%). Treatment recommendations were grouped as follows: PARP inhibition, n=35; immunotherapy, n=27; mTOR inhibition, n=22; CDK4/6 inhibition, n=15; tyrosine or serine/threonine kinase inhibition, n=57 (ALK, n=1; ERBB, n=6; FGFR, n=10; MET, n=5; RET, n=12; VEGFR, n=4, MEK, n=9; other, n=10), DNA-crosslinking chemotherapy, n=16; anti-claudin18.2 antibody, n=5; BET inhibition, n=5; and DLL3 antibody, n=5. As of November 2018, at least 18 patients had received molecularly guided treatment (PARP inhibition, immunotherapy, mTOR inhibition, tyrosine or serine/threonine kinase inhibition) of which 11 were evaluable for response (partial response, n=4; stable disease, n=2; progressive diseases, n=5). Twenty-seven patients died before therapy could be started, 16 are currently receiving other regimens, and for the remaining patients no follow-up data are available yet. In conclusion, comprehensive molecular profiling offers valuable insight into to the genomic and transcriptomic landscape of NEN and creates additional therapeutic opportunities in a subset of patients. Citation Format: Simon Kreutzfeldt, Leonidas Apostolidis, Malgorzata Oles, Peter Horak, Christoph E. Heilig, Christoph Heining, Barbara Hutter, Laura Gieldon, Barbara Klink, Mario Lamping, Damian T. Rieke, Sebastian Uhrig, Henning Jann, Ulrich F. Pape, Albrecht Stenzinger, Eva C. Winkler, Bertram Wiedenmann, Dirk Jäger, Benedikt Brors, Evelin Schröck, Ulrich Keilholz, Marianne Pavel, Hanno Glimm, Stefan Fröhling. Clinical relevance of comprehensive genomic analysis in patients with advanced-stage neuroendocrine neoplasms: Results from the MASTER trial of the German Cancer Consortium [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2019; 2019 Mar 29-Apr 3; Atlanta, GA. Philadelphia (PA): AACR; Cancer Res 2019;79(13 Suppl):Abstract nr 919.