TY - JOUR A1 - Burkart, Nadia A1 - Robert, Sebastian A1 - Huber, Marco F. T1 - Are you sure? Prediction revision in automated decision-making JF - Expert Systems N2 - With the rapid improvements in machine learning and deep learning, decisions made by automated decision support systems (DSS) will increase. Besides the accuracy of predictions, their explainability becomes more important. The algorithms can construct complex mathematical prediction models. This causes insecurity to the predictions. The insecurity rises the need for equipping the algorithms with explanations. To examine how users trust automated DSS, an experiment was conducted. Our research aim is to examine how participants supported by an DSS revise their initial prediction by four varying approaches (treatments) in a between-subject design study. The four treatments differ in the degree of explainability to understand the predictions of the system. First we used an interpretable regression model, second a Random Forest (considered to be a black box [BB]), third the BB with a local explanation and last the BB with a global explanation. We noticed that all participants improved their predictions after receiving an advice whether it was a complete BB or an BB with an explanation. The major finding was that interpretable models were not incorporated more in the decision process than BB models or BB models with explanations. KW - experiment KW - explainable ML KW - interpretability KW - prediction revision Y1 - 2021 UR - https://doi.org/10.1111/exsy.12577 VL - 38 IS - 1 SP - e12577 ER - TY - CHAP A1 - Mucha, Henrik A1 - Robert, Sebastian T1 - Emerging Perspectives on Medical Decision Support: Co-Designing XAI T2 - Fair & Responsible AI Workshop, Conference on Human Factors in Computing Systems (CHI), 2020, Honolulu, Hawaii N2 - Artificial Intelligence (AI) and Machine Learning (ML) promise to significantly enhance the capabilities of decision support systems in medicine. Yet, if these systems fail to providean understandable rationale of the decision making process the adoption of this powerful technology will be difficult. Hence, there is growing interest in Explainable Artificial Intelligence (XAI). Explanations that speak the language of the user are a cornerstone for Fair AI. In this position paper, we reflect on research about XAI and designing decision support in medicine. From there, we lay out an approach to use co-design methodology to explore how users perceive and interact with explanations of decision support systems. KW - XAI KW - Medical Decision Support KW - Co-Design Y1 - 2021 ER - TY - CHAP A1 - Philipp, Patrick A1 - Morales Georgi, Rafael X. A1 - Beyerer, Jürgen A1 - Robert, Sebastian A1 - Beyerer, Jürgen T1 - Analysis of Control Flow Graphs Using Graph Convolutional Neural Networks T2 - 2019 6th International Conference on Soft Computing & Machine Intelligence (ISCMI) N2 - With the digital transformation of companies, ever larger amounts of data are generated and available for analysis. Process mining techniques can be used to extract and analyze process models from these data. Related techniques have quickly developed into an important field with constantly increasing investments in recent years. Thus, the automated analysis of processes has gained an important role in many companies. In this context, graphs have been shown to be an intuitive representation of how the gathered processes are carried out using the aforementioned techniques. For the analysis of these so-called control flow graphs, we investigate the use of convolution neural networks, which are specially designed for graphs: graph convolution networks (GCNs). In our contribution, GCNs are used to perform a regression task based on individual control flows of a process in which farmers apply for specific governmental payments. The approach achieved promising results on this publicly available data set. KW - workflow KW - process analysis KW - process mining KW - convolutional neural networks KW - digital transformation KW - control flow Y1 - 2021 UR - https://doi.org/10.1109/ISCMI47871.2019.9004296 SP - 73 EP - 77 ER - TY - JOUR A1 - Mucha, Henrik A1 - Robert, Sebastian A1 - Breitschwerdt, Rüdiger A1 - Fellmann, Michael T1 - Usability of clinical decision support systems JF - Zeitschrift für Arbeitswissenschaft N2 - Usability is considered a major success factor for current and future decision support systems. Such systems are increasingly used to assist human decision-makers in high-stakes tasks in complex domains such as health care, jurisdiction or finance. Yet, many if not most expert systems—especially in health care—fail to deliver the degree of quality in terms of usability that its expert users are used to from their personal digital consumer products. In this article, we focus on clinical decision support systems (CDSS) as an example for how important a human-centered design approach is when designing complex software in complex contexts. We provide an overview of CDSS classes, discuss the importance of systematically exploring mental models of users, and formulate challenges and opportunities of future design work on CDSS. We further provide a case study from a current research project to illustrate how we used codesign as a practical approach to produce usable software in a real-world context. Practical Relevance: We make a point for usability to be considered a major success factor and non-negotiable characteristic of expert software. With software evolving into virtual coworkers in terms of supporting human decision-making in complex, high-risk domains, the necessity of and demand for systems that are unambiguously understandable and interpretable for their expert users have never been higher. We show that this is a real-world problem with high practical relevance by describing our work in the domain of clinical decision support systems (CDSS) as an example. We introduce the topic and a classification of CDSS. Thus, we highlight a conceptual framework of how to approach complex domains from a technology designer’s point of view. We continue by explaining why usability must be regarded as a major goal in software development. We derive challenges and opportunities that may well be transferred to other domains. Finally, be including a real-world example from our own professional work we propose a practical approach towards taking the challenges and exploiting the associated opportunities. N2 - Die Benutzerfreundlichkeit gilt als ein wichtiger Erfolgsfaktor für aktuelle und zukünftige Entscheidungsunterstützungssysteme. Solche Systeme werden zunehmend eingesetzt, um menschliche Entscheidungsträger bei anspruchsvollen Aufgaben in komplexen Bereichen wie dem Gesundheitswesen, der Rechtsprechung oder dem Finanzwesen zu unterstützen. Viele, wenn nicht sogar die meisten Expertensysteme – insbesondere im Gesundheitswesen – bieten jedoch nicht die Qualität in Bezug auf die Benutzerfreundlichkeit, die die Experten von ihren persönlichen digitalen Konsumgütern gewohnt sind. In diesem Artikel konzentrieren wir uns auf klinische Entscheidungsunterstützungssysteme (CDSS) als Beispiel dafür, wie wichtig ein menschenzentrierter Designansatz bei der Entwicklung komplexer Software in komplexen Kontexten ist. Wir geben einen Überblick über CDSS-Klassen, erörtern die Bedeutung der systematischen Erforschung mentaler Modelle von Nutzern und formulieren Herausforderungen und Chancen für die zukünftige Designarbeit an CDSS. Darüber hinaus stellen wir eine Fallstudie aus einem aktuellen Forschungsprojekt vor, um zu veranschaulichen, wie wir Codesign als praktischen Ansatz eingesetzt haben, um brauchbare Software in einem realen Kontext zu entwickeln. Praktische Relevanz: Wir setzen uns dafür ein, dass die Benutzerfreundlichkeit als ein wichtiger Erfolgsfaktor und nicht verhandelbares Merkmal von Expertensoftware angesehen wird. Mit der Entwicklung von Software zu virtuellen Mitarbeitern, die den Menschen bei der Entscheidungsfindung in komplexen, risikoreichen Bereichen unterstützen, sind die Notwendigkeit und die Nachfrage nach Systemen, die für ihre Expertenanwender eindeutig verständlich und interpretierbar sind, so hoch wie nie zuvor. Wir zeigen, dass dies ein reales Problem mit hoher praktischer Relevanz ist, indem wir unsere Arbeit im Bereich der klinischen Entscheidungsunterstützungssysteme (CDSS) als Beispiel beschreiben. Wir stellen das Thema und eine Klassifizierung von CDSS vor. So zeigen wir einen konzeptionellen Rahmen auf, wie man sich komplexen Domänen aus der Sicht eines Technologieentwicklers nähert. Wir fahren fort, indem wir erklären, warum die Benutzerfreundlichkeit als ein Hauptziel bei der Softwareentwicklung angesehen werden muss. Daraus leiten wir Herausforderungen und Möglichkeiten ab, die sich durchaus auf andere Bereiche übertragen lassen. Schließlich schlagen wir anhand eines praktischen Beispiels aus unserer eigenen beruflichen Tätigkeit einen praktischen Ansatz vor, um die Herausforderungen anzunehmen und die damit verbundenen Chancen zu nutzen. KW - Usability KW - Human-centered Design KW - Participatory Design KW - Software Engineering in Expert Domains KW - (Clinical) Decision Support Systems Y1 - 2022 U6 - https://doi.org/10.1007/s41449-022-00324-8 ER - TY - CHAP A1 - Robert, Sebastian A1 - Mucha, H. A1 - Hempel, D. ED - Glocke, P. ED - Elsner, C. ED - Schneider, H. T1 - Clinical Decision Support Systems T2 - Toolbook Digitale Transformation Krankenhaus KW - Clinical Decision Support Systems Y1 - 2022 PB - MWV Medizinisch Wissenschaftlicher Verlagsgesellschaft CY - Berlin ER - TY - JOUR A1 - Hempel, Louisa A1 - Lapa, Constantin A1 - Dierks, Alexander A1 - Gaumann, Andreas A1 - Scheiber, Josef A1 - Veloso de Oliveira, Julia A1 - Philipp, Patrick A1 - Oyarzun Laura, Cristina A1 - Wesarg, Stefan A1 - Robert, Sebastian A1 - Hempel, Dirk T1 - A new promising oncogenic target (p.C382R) for treatment with pemigatinib in patients with cholangiocarcinoma JF - Therapeutic Advances in Medical Oncology N2 - Point mutations of the fibroblast growth factor receptor (FGFR)2 receptor in intrahepatic cholangiocarcinoma (iCC) are mainly of unknown functional significance compared to FGFR2 fusions. Pemigatinib, a tyrosine kinase inhibitor, is approved for the treatment of cholangiocarcinoma with FGFR2 fusion/rearrangement. Although it is hypothesized that FGFR2 mutations may cause uncontrolled activation of the signaling pathway, the data for targeted therapies for FGFR2 mutations remain unclear. In vitro analyses demonstrated the importance of the p.C382R mutation for ligand-independent constitutive activation of FGFR2 with transforming potential. The following report describes the clinical case of a patient diagnosed with an iCC carrying a FGFR2 p.C382R point mutation which was detected in liquid, as well as in tissue-based biopsies. The patient was treated with pemigatinib, resulting in a sustained complete functional remission in fluorodeoxyglucose-positron emission tomography/computed tomography over 10 months to date. The reported case is the first description of a complete functional remission under the treatment with pemigatinib in a patient with p.C383R mutation. Y1 - 2022 U6 - https://doi.org/10.1177/17588359221125096 VL - 14 ER - TY - JOUR A1 - Hempel, Louisa A1 - Piehler, Armin A1 - Gandorfer, Beate A1 - De Oliveira, Julia Veloso A1 - Philipp, Patrick A1 - Robert, Sebastian A1 - Axel, Kleespies A1 - Schick, Cordula A1 - Fleischmann, Bastian A1 - Schweneker, Katrin A1 - Milani, Valeria A1 - Schenk, Kristina A1 - Ebner, Florian A1 - Donhauser, Lara A1 - Zehn, Dietmar A1 - Hempel, Dirk T1 - Clinical impact of SARS-CoV-2 delta variant infection in tumor patients and the impact of vaccination on different cancer treatment regimens. JF - Journal of Clinical Oncology N2 - Background: Data on SARS-CoV-2 infections in oncological patients in the outpatient settings are scarce. Methods: During the spread of the delta variant between April 2021 and September 2021, a total of 10.677 patients were tested for SARS-CoV-2 infection by RT-qPCR in seven outpatient clinics in Bavaria, Germany. Results: Within the tested patient cohort, 4.960 patients (46.5%) suffered from a malignant disease (74% solid tumors and 26% malignant hematological diseases). This group was compared with 5.717 patients (53.5%) without a malignant disease (33.1% with other hematological diseases and 66.9% patients without a hematological or oncological disease). During the observation period, 119 (2.4%) patients with malignancies were tested positive (88 patients with solid tumors; 31 patients with malignant hematological diseases) compared to 115 positive patients (2.0%) in the control group. 32 of 119 positively tested patients (26.9%) suffering from malignant disease required hospitalization and 9/32 patients (28.1%) died during the clinical course. Conclusions: These observations are in clear contrast to data from patients we evaluated during the pre-delta variants period between 15 and 26 April 2020 in the same seven outpatient clinics. In this period, a total of 1.227 patients were tested for SARS-CoV-2 by RT-qPCR. 78/1227 patients (6.3%) were tested positive in RT-qPCR and most showed mild symptoms of infection. None of the SARS-CoV-2 infected patients died. These data were analyzed when no vaccination was available. These data were evaluated during a period where no vaccine was available. Vaccination of patients with malignancies with BiontechPfizer's mRNA vaccines was started in April 2021. The response to the vaccine was tested by an antibody assay (Elecsys Anti-SARS-CoV-2 S-immunoassay, Roche) at the earliest four weeks after the second vaccination. To assess the response, we compared five patient cohorts: Patients who received (i) B cell depleting antibodies, (ii) checkpoint inhibitors (ICI), (iii) chemotherapy, or (iv) tyrosin kinase inhibitors (TKIs), and (v) healthy controls. The patients treated with ICI or TKI showed a comparable vaccination response to the healthy patients, while patients receiving Rituximab/Obinutuzumab showed no significant humoral vaccination response at all. The more severe disease course of patients infected by the SARS-CoV-2 delta variant compared to the initial waves of infections strongly underline the importance of vaccination in cancer patients. Y1 - 2022 U6 - https://doi.org/10.1200/JCO.2022.40.16_suppl.e18750 VL - 40 IS - 16_suppl SP - E18750 EP - E18750 ER - TY - JOUR A1 - Hempel, L.C. A1 - Lapa, C. A1 - Gaumann, A. A1 - Veloso de Oliveira, J. A1 - Scheiber, J. A1 - Philipp, P. A1 - Oyarzun, C. A1 - Wesarg, S. A1 - Robert, Sebastian A1 - Hempel, D. T1 - 36P A point mutation replacing cysteine with arginine at position 382 (C382R) in the transmembrane domain of FGFR2 leads to response to FGF2-inhibitor pemigatinib in chemo-refractory intrahepatic cholangiocarcinoma JF - Annals of Oncology N2 - Background To date, targeted tyrosine kinase inhibitors have been approved for FGFR2 and FGFR3 fusions (pemigatinib and erdafitinib, respectively), but the importance of FGFR2 mutations for transformation activity and as a druggable gene variant with response to different FGFR inhibitors is poorly understood. FGFR2 inhibitors present a mainstay of treatment for locally advanced or metastatic intrahepatic cholangiocellular carcinoma (iCCA). Methods A 74-year-old male was diagnosed with iCCA in liver segments seven and eight with infiltration of the hepatic veins and inferior vena cava revealed a C382R mutation of the intramembrane domain of FGRR2 receptor. We performed an in-silico study to understand the potential mode-of-action of the mutant FGFR2 targets. Based on experimentally determined structures we then used a structure generated by AlphaFold2 as the variation in question is located at a position not determined well in the experiments. This revealed that the C382R mutation is located in the trans-membranal domain at a position crucial for signal transduction, both for activation and inhibition of downstream-signaling. The Molecular Tumor Board decided to start the treatment with 13.5 mg pemigatinib once daily for 14 days, followed by 7 days of free therapy interval resulting in a sustained partial response. The patient continues to be treated of 13.5 mg as described above. Results In our case report, we were able to show that the patient in whom an C382R mutation was detected responded to the therapy with pemigatinib. This shows that real-world scenarios differ from the data of the approval studies, thereby illustrating how complex data on patients with FGFR mutations is. One of the main problems of large approval studies is that the functionality of the respective alterations is often disregarded. Conclusions Our results suggest that respective mutation may be successfully targeted by FGFR-selective tyrosine-kinase inhibitors, demonstrating the importance of the functional characterization of mutations. no conflicts of interest. Y1 - 2022 U6 - https://doi.org/https://doi.org/10.1016/j.annonc.2022.01.045 VL - 33 SP - S17 EP - S17 ER - TY - JOUR A1 - Victoria Donhauser, Lara A1 - Veloso de Oliveira, Julia A1 - Schick, Cordula A1 - Manlik, Wenzel A1 - Styblova, Sabrina A1 - Lutzenberger, Sarah A1 - Aigner, Michael A1 - Philipp, Patrick A1 - Robert, Sebastian A1 - Gandorfer, Beate A1 - Hempel, Dirk A1 - Hempel, Louisa A1 - Zehn, Dietmar T1 - Responses of patients with cancer to mRNA vaccines depend on the time interval between vaccination and last treatment JF - Journal for ImmunoTherapy of Cancer N2 - Background Personalized mRNA vaccines are promising new therapeutic options for patients with cancer. Because mRNA vaccines are not yet approved for first-line therapy, the vaccines are presently applied to individuals that received prior therapies that can have immunocompromising effects. There is a need to address how prior treatments impact mRNA vaccine outcomes. Method Therefore, we analyzed the response to BioNTech/Pfizer’s anti-SARS-CoV-2 mRNA vaccine in 237 oncology outpatients, which cover a broad spectrum of hematologic malignancies and solid tumors and a variety of treatments. Patients were stratified by the time interval between the last treatment and first vaccination and by the presence or absence of florid tumors and IgG titers and T cell responses were analyzed 14 days after the second vaccination. Results Regardless of the last treatment time point, our data indicate that vaccination responses in patients with checkpoint inhibition were comparable to healthy controls. In contrast, patients after chemotherapy or cortisone therapy did not develop an immune response until 6 months after the last systemic therapy and patients after Cht-immune checkpoint inhibitor and tyrosine kinase inhibitor therapy only after 12 months. Conclusion Accordingly, our data support that timing of mRNA-based therapy is critical and we suggest that at least a 6-months or 12-months waiting interval should be observed before mRNA vaccination in systemically treated patients. Y1 - 2023 U6 - https://doi.org/10.1136/jitc-2023-007387 VL - 11 IS - 9 ER - TY - GEN A1 - Philipp, Patrick A1 - Jacob, Ruben A1 - Robert, Sebastian A1 - Beyerer, Jurgen T1 - Predictive Analysis of Business Processes Using Neural Networks with Attention Mechanism T2 - 2020 International Conference on Artificial Intelligence in Information and Communication (ICAIIC) N2 - The analysis of ongoing processes is an important task in business process management. This is not surprising, since (e.g.) being able to predict future events in processes enables companies to intervene at an early stage if deviations from a desired workflow are likely to occur. Subsequently, errors and associated financial losses can be prevented or avoided. A common basis for being able to predict future events is a sequence of previous events that are typically stored in a socalled event log. In this work we present a neural network with attention mechanism, which is trained using publicly available event logs (e.g. BPI Challenge 2013). Furthermore, we elaborate the proposed model with an extensive dataset of events of a worldwide known German software company. In addition to promising results (e.g.) with regard to n-gram models, the training time of the proposed model is shorter than that of typical reference models such as neural networks with a long short-term memory architecture (LSTM). Y1 - 2020 U6 - https://doi.org/10.1109/ICAIIC48513.2020.9065057 SP - 225 EP - 230 PB - IEEE ER - TY - GEN A1 - Hempel, L. A1 - Gaumann, A. A1 - Veloso de Oliveira, J. A1 - Philipp, P. A1 - Hempel, D. A1 - Robert, Sebastian A1 - Ebner, F. T1 - Zielgerichtete Therapien für das Endometriumkarzinom im Real-World-Setting T2 - Geburtshilfe und Frauenheilkunde N2 - Mit wachsenden Erkenntnissen zu grundlegenden molekularen Mechanismen werden zunehmend Zielstrukturen für neuartige personalisierte Therapien für das Endometriumkarzinoms (EC) identifiziert. Diese Therapien haben das Potenzial, das Langzeitüberleben von Krebspatientinnen mit geeigneten Biomarkern zu verbessern. In der vorliegenden Studie wurde bei 11 Patientinnen mit EC, ein Panel Hybrid Capture-basiertes Next Generation Sequencing (FoundationOne CDx, Penzberg, Deutschland) durchgeführt. Bei allen untersuchten Patientinnen wurden genetische Veränderungen festgestellt, die potenzielle Ziele für personalisierte Therapien darstellen. Signifikante Veränderungen wurden bei 7 (63,6%) Patientinnen in TP53, bei 4 (36,4%) in PIK2CA, bei 3 (27,3%) in ERBB2, bei 3 (27,3%) in ARIDA1A, bei 2 (18,2%) in NF1, bei 2 (18,2%) in PTEN und bei einer Patientin in PIK3R1, festgestellt. TMB konnte bei 10 von 11 Patientinnen analysiert werden und war bei 5 (45,5%) niedrig, bei 3 (27,3%) intermediate und bei 2 Patientinnen (18,2%) hoch. Die Mikrosatelliten waren bei 2 Patientinnen (18,2 %) instabil (MSI) und bei 7 Patientinnen (63,6 %) stabil (MSS). Außerdem wurden die Ergebnisse der Immunhistochemie (IHC) mit den NGS-Daten vergleichen. Drei Patientinnen waren in der IHC Her2 positiv, obwohl keine ERBB2-Amplifikation nachweisbar war. Im Gegensatz dazu identifizierte die NGS-Analyse eine Patientin, die in der IHC negativ für Her2 war jedoch eine ERBB2-Amplifikationen aufwies und sich somit für Her2/neu-gerichtete Therapien qualifizierte. Diese Daten unterstreichen die Bedeutung der Identifizierung molekularer Muster, da 100 % der analysierten Patientinnen potenziell therapierelevante Alterationen aufwiesen. Alle Patientinnen mit EC sollten eine NGS-Analyse, sowie eine Untersuchung auf Her2/neu und PD-L1 mittels IHC erhalten. Y1 - 2022 U6 - https://doi.org/10.1055/s-0042-1756859 VL - 82 IS - 10 PB - Georg Thieme Verlag ER -