Search

The Paris Agreement under the United Nations Framework Convention on Climate Change aims to reduce global greenhouse gas emissions, targeting a maximum 2-degree Celsius temperature increase this century. A key strategy involves increasing renewable energy share and storage capabilities within existing energy supply system infrastructures, necessitating major restructuring processes. Energy supply system modelling and optimisation software can facilitate these changes, which resulted in many commercial and open-source tools with varying backgrounds, objectives, and use cases. Researchers, engineers, and decision-makers face challenges in selecting the most appropriate software for specific purposes. Although structured comparisons of available options are valuable case and tool-specific nuances often only emerge during result analysis. The current literature lacks a comprehensive result-based approach for choosing energy supply system modelling and optimisation software. This thesis proposes a result-based Comparative Method for selecting and comparing energy supply system modelling and optimisation software, enabling systematic comparison centred on optimisation results. The Comparative Method encompasses a rigorous preselection phase, a modelling step, and a versatile, application-oriented result-analysis phase. In addition, an outside-of-this-method reusable structured procedure involving a graph-theory-inspired post-processing strategy for energy supply system models is proposed. To support the scientific community in terms of compiling result-based comparisons, several energy supply system model scenario combinations have been devised. These address modern energy infrastructure challenges and serve as a basis for generating result-based comparisons in subsequent research. In this work, the developed combinations are utilised during an extensive case study to compare four modern, highly capable free and open-source software tools and to illustrate the method's fe, Das Pariser Abkommen im Zuge des Rahmenübereinkommens der Vereinten Nationen über Klimaänderungen zielt darauf ab, die weltweiten Treibhausgasemissionen zu reduzieren und den Temperaturanstieg in diesem Jahrhundert auf maximal 2 Grad Celsius zu begrenzen. Eine Schlüsselstrategie spielt dabei die Erhöhung des Anteils erneuerbarer Energien und Speicherkapazitäten innerhalb der existierenden Energieversorgungs-Infrastruktur. Entsprechend umfangreiche Umstrukturierungsprozesse sind zu erwarten. Software zur Modellierung und Optimierung von Energieversorgungssystemen ist in der Lage, diese Umstrukturierungsprozesse sinnvoll zu begleiten. Deshalb existiert inzwischen eine große Anzahl entsprechender kommerzieller und quelloffener Sotware-Werkzeuge mit unterschiedlichen Hintergründen, Zielen und Anwendungsfällen. Forscher, Ingenieure und Entscheidungsträger stehen vor der Herausforderung, die am besten geeignete Software für bestimmte Zwecke auszuwählen. Obwohl strukturierte Vergleiche der verfügbaren Optionen existieren und wertvoll sind, werden wichtige fall- und werkzeugspezifische Einzelheiten oft erst während der Ergebnisanalyse identifiziert. In der gegenwärtigen Literatur fehlt ein umfassender ergebnisbasierter Ansatz für die Auswahl von Software zur Modellierung und Optimierung von Energieversorgungssystemmodellen. Diese Arbeit schlägt eine ergebnisbasierte Methode zur Auswahl und zum Vergleich von Software zur Modellierung und Optimierung von Energiesystemen vor, die einen systematischen Vergleich auf Basis der Optimierungsergebnisse durchführt. Die Methode umfasst dabei eine detaillierte Vorauswahlphase, eine Modellierungsphase und eine vielseitige, anwendungsorientierte Ergebnisanalysephase. Darüber hinaus wird ein effizientes, außerhalb dieser Methode, wiederverwendbares Verfahren mit einer von der Graphentheorie inspirierten Post-Processing-Strategie vorgeschlagen. Um die wissenschaftliche Gemeinschaft in Bezug auf die Zusammenstellung Ergebnis basierender Ver

The study of humpback whale song using passive acoustic monitoring devices requires bioacousticians to manually review hours of audio recordings to annotate the signals. To vastly reduce the time of manual annotation throughautomation, a machine learning model was developed. Convolutional neural networks have made major advances in the previous decade, leading to a wide range of applications, including the detection of frequency modulatedvocalizations by cetaceans. A large dataset of over 60 000 audio segments of 4 s length is collected from the North Atlantic and used to fine-tune an existing model for humpback whale song detection in the North Pacific (see Allen,Harvey, Harrell, Jansen, Merkens, Wall, Cattiau, and Oleson (2021). Front. Mar. Sci. 8, 607321). Furthermore, different data augmentation techniques (time-shift, noise augmentation, and masking) are used to artificially increasethe variability within the training set. Retraining and augmentation yield F-score values of 0.88 on context window basis and 0.89 on hourly basis with false positive rates of 0.05 on context window basis and 0.01 on hourly basis. Ifnecessary, usage and retraining of the existing model is made convenient by a framework (AcoDet, acoustic detector) built during this project. Combining the tools provided by this framework could save researchers hours of manualannotation time and, thus, accelerate their research.

The text-guided diffusion model GLIDE (Guided Language to Image Diffusion for Generation and Editing) is the state of the art in text-to-image generative artificial intelligence (AI). GLIDE has rich representations, but medical applications of this model have not been systematically explored. If GLIDE had useful medical knowledge, it could be used for medical image analysis tasks, a domain in which AI systems are still highly engineered towards a single use-case. Here we show that the publicly available GLIDE model has reasonably strong representations of key topics in cancer research and oncology, in particular the general style of histopathology images and multiple facets of diseases, pathological processes and laboratory assays. However, GLIDE seems to lack useful representations of the style and content of radiology data. Our findings demonstrate that domain-agnostic generative AI models can learn relevant medical concepts without explicit training. Thus, GLIDE and similar models might be useful for medical image processing tasks in the future - particularly with additional domain-specific fine-tuning.

Medical image classification requires labeled, task-specific datasets which are used to train deep learning networks de novo, or to fine-tune foundation models. However, this process is computationally and technically demanding. In language processing, in-context learning provides an alternative, where models learn from within prompts, bypassing the need for parameter updates. Yet, in-context learning remains underexplored in medical image analysis. Here, we systematically evaluate the model Generative Pretrained Transformer 4 with Vision capabilities (GPT-4V) on cancer image processing with in-context learning on three cancer histopathology tasks of high importance: Classification of tissue subtypes in colorectal cancer, colon polyp subtyping and breast tumor detection in lymph node sections. Our results show that in-context learning is sufficient to match or even outperform specialized neural networks trained for particular tasks, while only requiring a minimal number of samples. In summary, this study demonstrates that large vision language models trained on non-domain specific data can be applied out-of-the box to solve medical image-processing tasks in histopathology. This democratizes access of generalist AI models to medical experts without technical background especially for areas where annotated data is scarce., Comment: 40 pages, 5 figures

Deep Learning models have been successfully utilized to extract clinically actionable insights from routinely available histology data. Generally, these models require annotations performed by clinicians, which are scarce and costly to generate. The emergence of self-supervised learning (SSL) methods remove this barrier, allowing for large-scale analyses on non-annotated data. However, recent SSL approaches apply increasingly expansive model architectures and larger datasets, causing the rapid escalation of data volumes, hardware prerequisites, and overall expenses, limiting access to these resources to few institutions. Therefore, we investigated the complexity of contrastive SSL in computational pathology in relation to classification performance with the utilization of consumer-grade hardware. Specifically, we analyzed the effects of adaptations in data volume, architecture, and algorithms on downstream classification tasks, emphasizing their impact on computational resources. We trained breast cancer foundation models on a large public patient cohort and validated them on various downstream classification tasks in a weakly supervised manner on two external public patient cohorts. Our experiments demonstrate that we can improve downstream classification performance whilst reducing SSL training duration by 90%. In summary, we propose a set of adaptations which enable the utilization of SSL in computational pathology in non-resource abundant environments., Comment: Submitted to MICCAI 2024

Deep Learning (DL) can predict biomarkers directly from digitized cancer histology in a weakly-supervised setting. Recently, the prediction of continuous biomarkers through regression-based DL has seen an increasing interest. Nonetheless, clinical decision making often requires a categorical outcome. Consequently, we developed a weakly-supervised joint multi-task Transformer architecture which has been trained and evaluated on four public patient cohorts for the prediction of two key predictive biomarkers, microsatellite instability (MSI) and homologous recombination deficiency (HRD), trained with auxiliary regression tasks related to the tumor microenvironment. Moreover, we perform a comprehensive benchmark of 16 approaches of task balancing for weakly-supervised joint multi-task learning in computational pathology. Using our novel approach, we improve over the state-of-the-art area under the receiver operating characteristic by +7.7% and +4.1%, as well as yielding better clustering of latent embeddings by +8% and +5% for the prediction of MSI and HRD in external cohorts, respectively.

Background: Recent advancements in large language models (LLMs) offer potential benefits in healthcare, particularly in processing extensive patient records. However, existing benchmarks do not fully assess LLMs' capability in handling real-world, lengthy clinical data. Methods: We present the LongHealth benchmark, comprising 20 detailed fictional patient cases across various diseases, with each case containing 5,090 to 6,754 words. The benchmark challenges LLMs with 400 multiple-choice questions in three categories: information extraction, negation, and sorting, challenging LLMs to extract and interpret information from large clinical documents. Results: We evaluated nine open-source LLMs with a minimum of 16,000 tokens and also included OpenAI's proprietary and cost-efficient GPT-3.5 Turbo for comparison. The highest accuracy was observed for Mixtral-8x7B-Instruct-v0.1, particularly in tasks focused on information retrieval from single and multiple patient documents. However, all models struggled significantly in tasks requiring the identification of missing information, highlighting a critical area for improvement in clinical data interpretation. Conclusion: While LLMs show considerable potential for processing long clinical documents, their current accuracy levels are insufficient for reliable clinical use, especially in scenarios requiring the identification of missing information. The LongHealth benchmark provides a more realistic assessment of LLMs in a healthcare setting and highlights the need for further model refinement for safe and effective clinical application. We make the benchmark and evaluation code publicly available., Comment: 11 pages, 3 figures, 5 tables

The Transformer model has been pivotal in advancing fields such as natural language processing, speech recognition, and computer vision. However, a critical limitation of this model is its quadratic computational and memory complexity relative to the sequence length, which constrains its application to longer sequences. This is especially crucial in medical imaging where high-resolution images can reach gigapixel scale. Efforts to address this issue have predominantely focused on complex techniques, such as decomposing the softmax operation integral to the Transformer's architecture. This paper addresses this quadratic computational complexity of Transformer models and introduces a remarkably simple and effective method that circumvents this issue by eliminating the softmax function from the attention mechanism and adopting a sequence normalization technique for the key, query, and value tokens. Coupled with a reordering of matrix multiplications this approach reduces the memory- and compute complexity to a linear scale. We evaluate this approach across various medical imaging datasets comprising fundoscopic, dermascopic, radiologic and histologic imaging data. Our findings highlight that these models exhibit a comparable performance to traditional transformer models, while efficiently handling longer sequences.

Multimodal artificial intelligence (AI) systems have the potential to enhance clinical decision-making by interpreting various types of medical data. However, the effectiveness of these models across all medical fields is uncertain. Each discipline presents unique challenges that need to be addressed for optimal performance. This complexity is further increased when attempting to integrate different fields into a single model. Here, we introduce an alternative approach to multimodal medical AI that utilizes the generalist capabilities of a large language model (LLM) as a central reasoning engine. This engine autonomously coordinates and deploys a set of specialized medical AI tools. These tools include text, radiology and histopathology image interpretation, genomic data processing, web searches, and document retrieval from medical guidelines. We validate our system across a series of clinical oncology scenarios that closely resemble typical patient care workflows. We show that the system has a high capability in employing appropriate tools (97%), drawing correct conclusions (93.6%), and providing complete (94%), and helpful (89.2%) recommendations for individual patient cases while consistently referencing relevant literature (82.5%) upon instruction. This work provides evidence that LLMs can effectively plan and execute domain-specific models to retrieve or synthesize new information when used as autonomous agents. This enables them to function as specialist, patient-tailored clinical assistants. It also simplifies regulatory compliance by allowing each component tool to be individually validated and approved. We believe, that our work can serve as a proof-of-concept for more advanced LLM-agents in the medical domain., Comment: 91 pages, 2 Figures

Autoimmune liver diseases (AiLDs) are rare autoimmune conditions of the liver and the biliary tree with unknown etiology and limited treatment options. AiLDs are inherently characterized by a high degree of complexity, which poses great challenges in understanding their etiopathogenesis, developing novel biomarkers and risk-stratification tools, and, eventually, generating new drugs. Artificial intelligence (AI) is considered one of the best candidates to support researchers and clinicians in making sense of biological complexity. In this review, we offer a primer on AI and machine learning for clinicians, and discuss recent available literature on its applications in medicine and more specifically how it can help to tackle major unmet needs in AiLDs.

C-reactive protein (CRP) is an early-stage acute phase protein and highly upregulated in response to inflammatory reactions. We recently identified a novel mechanism that leads to a conformational change from the native, functionally relatively inert, pentameric CRP (pCRP) structure to a pentameric CRP intermediate (pCRP*) and ultimately to the monomeric CRP (mCRP) form, both exhibiting highly pro-inflammatory effects. This transition in the inflammatory profile of CRP is mediated by binding of pCRP to activated/damaged cell membranes via exposed phosphocholine lipid head groups. We designed a tool compound as a low molecular weight CRP inhibitor using the structure of phosphocholine as a template. X-ray crystallography revealed specific binding to the phosphocholine binding pockets of pCRP. We provide in vitro and in vivo proof-of-concept data demonstrating that the low molecular weight tool compound inhibits CRP-driven exacerbation of local inflammatory responses, while potentially preserving pathogen-defense functions of CRP. The inhibition of the conformational change generating pro-inflammatory CRP isoforms via phosphocholine-mimicking compounds represents a promising, potentially broadly applicable anti-inflammatory therapy.

The vast pool of structurally and functionally distinct secondary metabolites (i.e., natural products (NPs)) is constantly being expanded, a process also driven by the rapid progress in the development of analytical techniques. Such NPs often show potent biological activities and are therefore prime candidates for drug development and medical applications. The ethyl acetate extract of the tuber of Citrullus naudinianus (C. naudinianus), an African melon with edible fruits and seeds, shows in vitro immunomodulatory activity presumably elicited by cucurbitacins that are known major constituents of this plant. Further potentially immunomodulatory cucurbitacins or cucurbitacin derivatives were assumed to be in the tuber. Given the typically high content of cucurbitacins with similar physicochemical features but often distinct bioactivities, an efficient and reliable separation process is a prerequisite for their detailed characterization and assessment in terms of bioactivity. We therefore developed a detection method to screen and differentiate cucurbitacins via high-performance liquid chromatography/quadrupole-time-of-flight tandem mass spectrometry (HPLC-QTOF-MS/MS). In order to confirm the identification, the fragmentation patterns of two cucurbitacins and one 23,24-dihydrocucurbitacin were also investigated. Six characteristic fragments were identified and three of them were employed for the identification of cucurbitacins and 23,24- dihydrocucurbitacins in the extract. As a result, in addition to eight previously reported cucurbitacins from this plant four distinct 23,24-dihydrocucurbitacins (B, D, E, and I) were putatively identified and newly found in the ethyl acetate extract of the tuber of C. naudinianus. The established methodology enables rapid and efficient LC-MS-based analysis and identification of cucurbitacins and 23,24- dihydrocucurbitacins in plant extracts.

Background: Deep learning (DL) can extract predictive and prognostic biomarkers from routine pathology slides in colorectal cancer. For example, a DL test for the diagnosis of microsatellite instability (MSI) in CRC has been approved in 2022. Current approaches rely on convolutional neural networks (CNNs). Transformer networks are outperforming CNNs and are replacing them in many applications, but have not been used for biomarker prediction in cancer at a large scale. In addition, most DL approaches have been trained on small patient cohorts, which limits their clinical utility. Methods: In this study, we developed a new fully transformer-based pipeline for end-to-end biomarker prediction from pathology slides. We combine a pre-trained transformer encoder and a transformer network for patch aggregation, capable of yielding single and multi-target prediction at patient level. We train our pipeline on over 9,000 patients from 10 colorectal cancer cohorts. Results: A fully transformer-based approach massively improves the performance, generalizability, data efficiency, and interpretability as compared with current state-of-the-art algorithms. After training on a large multicenter cohort, we achieve a sensitivity of 0.97 with a negative predictive value of 0.99 for MSI prediction on surgical resection specimens. We demonstrate for the first time that resection specimen-only training reaches clinical-grade performance on endoscopic biopsy tissue, solving a long-standing diagnostic problem. Interpretation: A fully transformer-based end-to-end pipeline trained on thousands of pathology slides yields clinical-grade performance for biomarker prediction on surgical resections and biopsies. Our new methods are freely available under an open source license., Comment: Updated Figure 2 and Table A.5

Background: Convolutional neural network (CNN)-based melanoma classifiers face several challenges that limit their usefulness in clinical practice. Objective: To investigate the impact of multiple real-world dermoscopic views of a single lesion of interest on a CNN-based melanoma classifier. Methods: This study evaluated 656 suspected melanoma lesions. Classifier performance was measured using area under the receiver operating characteristic curve (AUROC), expected calibration error (ECE) and maximum confidence change (MCC) for (I) a single-view scenario, (II) a multiview scenario using multiple artificially modified images per lesion and (III) a multiview scenario with multiple real-world images per lesion. Results: The multiview approach with real-world images significantly increased the AUROC from 0.905 (95% CI, 0.879-0.929) in the single-view approach to 0.930 (95% CI, 0.909-0.951). ECE and MCC also improved significantly from 0.131 (95% CI, 0.105-0.159) to 0.072 (95% CI: 0.052-0.093) and from 0.149 (95% CI, 0.125-0.171) to 0.115 (95% CI: 0.099-0.131), respectively. Comparing multiview real-world to artificially modified images showed comparable diagnostic accuracy and uncertainty estimation, but significantly worse robustness for the latter. Conclusion: Using multiple real-world images is an inexpensive method to positively impact the performance of a CNN-based melanoma classifier.

Whole-Slide Imaging allows for the capturing and digitization of high-resolution images of histological specimen. An automated analysis of such images using deep learning models is therefore of high demand. The transformer architecture has been proposed as a possible candidate for effectively leveraging the high-resolution information. Here, the whole-slide image is partitioned into smaller image patches and feature tokens are extracted from these image patches. However, while the conventional transformer allows for a simultaneous processing of a large set of input tokens, the computational demand scales quadratically with the number of input tokens and thus quadratically with the number of image patches. To address this problem we propose a novel cascaded cross-attention network (CCAN) based on the cross-attention mechanism that scales linearly with the number of extracted patches. Our experiments demonstrate that this architecture is at least on-par with and even outperforms other attention-based state-of-the-art methods on two public datasets: On the use-case of lung cancer (TCGA NSCLC) our model reaches a mean area under the receiver operating characteristic (AUC) of 0.970 $\pm$ 0.008 and on renal cancer (TCGA RCC) reaches a mean AUC of 0.985 $\pm$ 0.004. Furthermore, we show that our proposed model is efficient in low-data regimes, making it a promising approach for analyzing whole-slide images in resource-limited settings. To foster research in this direction, we make our code publicly available on GitHub: XXX.

Accurate and automatic segmentation of fibroglandular tissue in breast MRI screening is essential for the quantification of breast density and background parenchymal enhancement. In this retrospective study, we developed and evaluated a transformer-based neural network for breast segmentation (TraBS) in multi-institutional MRI data, and compared its performance to the well established convolutional neural network nnUNet. TraBS and nnUNet were trained and tested on 200 internal and 40 external breast MRI examinations using manual segmentations generated by experienced human readers. Segmentation performance was assessed in terms of the Dice score and the average symmetric surface distance. The Dice score for nnUNet was lower than for TraBS on the internal testset (0.909$\pm$0.069 versus 0.916$\pm$0.067, P<0.001) and on the external testset (0.824$\pm$0.144 versus 0.864$\pm$0.081, P=0.004). Moreover, the average symmetric surface distance was higher (=worse) for nnUNet than for TraBS on the internal (0.657$\pm$2.856 versus 0.548$\pm$2.195, P=0.001) and on the external testset (0.727$\pm$0.620 versus 0.584$\pm$0.413, P=0.03). Our study demonstrates that transformer-based networks improve the quality of fibroglandular tissue segmentation in breast MRI compared to convolutional-based models like nnUNet. These findings might help to enhance the accuracy of breast density and parenchymal enhancement quantification in breast MRI screening.

Deep Learning (DL) can predict biomarkers from cancer histopathology. Several clinically approved applications use this technology. Most approaches, however, predict categorical labels, whereas biomarkers are often continuous measurements. We hypothesized that regression-based DL outperforms classification-based DL. Therefore, we developed and evaluated a new self-supervised attention-based weakly supervised regression method that predicts continuous biomarkers directly from images in 11,671 patients across nine cancer types. We tested our method for multiple clinically and biologically relevant biomarkers: homologous repair deficiency (HRD) score, a clinically used pan-cancer biomarker, as well as markers of key biological processes in the tumor microenvironment. Using regression significantly enhances the accuracy of biomarker prediction, while also improving the interpretability of the results over classification. In a large cohort of colorectal cancer patients, regression-based prediction scores provide a higher prognostic value than classification-based scores. Our open-source regression approach offers a promising alternative for continuous biomarker analysis in computational pathology.

BACKGROUND Artificial intelligence (AI) is influencing our society on many levels and has broad implications for the future practice of hematology and oncology. However, for many medical professionals and researchers, it often remains unclear what AI can and cannot do, and what are promising areas for a sensible application of AI in hematology and oncology. Finally, the limits and perils of using AI in oncology are not obvious to many healthcare professionals. METHODS In this article, we provide an expert-based consensus statement by the joint Working Group on "Artificial Intelligence in Hematology and Oncology" by the German Society of Hematology and Oncology (DGHO), the German Association for Medical Informatics, Biometry and Epidemiology (GMDS), and the Special Interest Group Digital Health of the German Informatics Society (GI). We provide a conceptual framework for AI in hematology and oncology. RESULTS First, we propose a technological definition, which we deliberately set in a narrow frame to mainly include the technical developments of the last ten years. Second, we present a taxonomy of clinically relevant AI systems, structured according to the type of clinical data they are used to analyze. Third, we show an overview of potential applications, including clinical, research, and educational environments with a focus on hematology and oncology. CONCLUSION Thus, this article provides a point of reference for hematologists and oncologists, and at the same time sets forth a framework for the further development and clinical deployment of AI in hematology and oncology in the future.

Hematoxylin- and eosin (H&E) stained whole-slide images (WSIs) are the foundation of diagnosis of cancer. In recent years, development of deep learning-based methods in computational pathology enabled the prediction of biomarkers directly from WSIs. However, accurately linking tissue phenotype to biomarkers at scale remains a crucial challenge for democratizing complex biomarkers in precision oncology. This protocol describes a practical workflow for solid tumor associative modeling in pathology (STAMP), enabling prediction of biomarkers directly from WSIs using deep learning. The STAMP workflow is biomarker agnostic and allows for genetic- and clinicopathologic tabular data to be included as an additional input, together with histopathology images. The protocol consists of five main stages which have been successfully applied to various research problems: formal problem definition, data preprocessing, modeling, evaluation and clinical translation. The STAMP workflow differentiates itself through its focus on serving as a collaborative framework that can be used by clinicians and engineers alike for setting up research projects in the field of computational pathology. As an example task, we applied STAMP to the prediction of microsatellite instability (MSI) status in colorectal cancer, showing accurate performance for the identification of MSI-high tumors. Moreover, we provide an open-source codebase which has been deployed at several hospitals across the globe to set up computational pathology workflows. The STAMP workflow requires one workday of hands-on computational execution and basic command line knowledge.

Stain normalisation is thought to be a crucial preprocessing step in computational pathology pipelines. We question this belief in the context of weakly supervised whole slide image classification, motivated by the emergence of powerful feature extractors trained using self-supervised learning on diverse pathology datasets. To this end, we performed the most comprehensive evaluation of publicly available pathology feature extractors to date, involving more than 8,000 training runs across nine tasks, five datasets, three downstream architectures, and various preprocessing setups. Notably, we find that omitting stain normalisation and image augmentations does not compromise downstream slide-level classification performance, while incurring substantial savings in memory and compute. Using a new evaluation metric that facilitates relative downstream performance comparison, we identify the best publicly available extractors, and show that their latent spaces are remarkably robust to variations in stain and augmentations like rotation. Contrary to previous patch-level benchmarking studies, our approach emphasises clinical relevance by focusing on slide-level biomarker prediction tasks in a weakly supervised setting with external validation cohorts. Our findings stand to streamline digital pathology workflows by minimising preprocessing needs and informing the selection of feature extractors. Code and data are available at https://georg.woelflein.eu/good-features.

Detecting misleading patterns in automated diagnostic assistance systems, such as those powered by Artificial Intelligence, is critical to ensuring their reliability, particularly in healthcare. Current techniques for evaluating deep learning models cannot visualize confounding factors at a diagnostic level. Here, we propose a self-conditioned diffusion model termed DiffChest and train it on a dataset of 515,704 chest radiographs from 194,956 patients from multiple healthcare centers in the United States and Europe. DiffChest explains classifications on a patient-specific level and visualizes the confounding factors that may mislead the model. We found high inter-reader agreement when evaluating DiffChest's capability to identify treatment-related confounders, with Fleiss' Kappa values of 0.8 or higher across most imaging findings. Confounders were accurately captured with 11.1% to 100% prevalence rates. Furthermore, our pretraining process optimized the model to capture the most relevant information from the input radiographs. DiffChest achieved excellent diagnostic accuracy when diagnosing 11 chest conditions, such as pleural effusion and cardiac insufficiency, and at least sufficient diagnostic accuracy for the remaining conditions. Our findings highlight the potential of pretraining based on diffusion models in medical image classification, specifically in providing insights into confounding factors and model robustness.

Large language models (LLMs) have broad medical knowledge and can reason about medical information across many domains, holding promising potential for diverse medical applications in the near future. In this study, we demonstrate a concerning vulnerability of LLMs in medicine. Through targeted manipulation of just 1.1% of the model's weights, we can deliberately inject an incorrect biomedical fact. The erroneous information is then propagated in the model's output, whilst its performance on other biomedical tasks remains intact. We validate our findings in a set of 1,038 incorrect biomedical facts. This peculiar susceptibility raises serious security and trustworthiness concerns for the application of LLMs in healthcare settings. It accentuates the need for robust protective measures, thorough verification mechanisms, and stringent management of access to these models, ensuring their reliable and safe use in medical practice.

A knowledge gap persists between machine learning (ML) developers (e.g., data scientists) and practitioners (e.g., clinicians), hampering the full utilization of ML for clinical data analysis. We investigated the potential of the ChatGPT Advanced Data Analysis (ADA), an extension of GPT-4, to bridge this gap and perform ML analyses efficiently. Real-world clinical datasets and study details from large trials across various medical specialties were presented to ChatGPT ADA without specific guidance. ChatGPT ADA autonomously developed state-of-the-art ML models based on the original study's training data to predict clinical outcomes such as cancer development, cancer progression, disease complications, or biomarkers such as pathogenic gene sequences. Following the re-implementation and optimization of the published models, the head-to-head comparison of the ChatGPT ADA-crafted ML models and their respective manually crafted counterparts revealed no significant differences in traditional performance metrics (P>0.071). Strikingly, the ChatGPT ADA-crafted ML models often outperformed their counterparts. In conclusion, ChatGPT ADA offers a promising avenue to democratize ML in medicine by simplifying complex data analyses, yet should enhance, not replace, specialized training and resources, to promote broader applications in medical research and practice., Comment: Published in Nature Communications

Pre-training datasets, like ImageNet, have become the gold standard in medical image analysis. However, the emergence of self-supervised learning (SSL), which leverages unlabeled data to learn robust features, presents an opportunity to bypass the intensive labeling process. In this study, we explored if SSL for pre-training on non-medical images can be applied to chest radiographs and how it compares to supervised pre-training on non-medical images and on medical images. We utilized a vision transformer and initialized its weights based on (i) SSL pre-training on natural images (DINOv2), (ii) SL pre-training on natural images (ImageNet dataset), and (iii) SL pre-training on chest radiographs from the MIMIC-CXR database. We tested our approach on over 800,000 chest radiographs from six large global datasets, diagnosing more than 20 different imaging findings. Our SSL pre-training on curated images not only outperformed ImageNet-based pre-training (P<0.001 for all datasets) but, in certain cases, also exceeded SL on the MIMIC-CXR dataset. Our findings suggest that selecting the right pre-training strategy, especially with SSL, can be pivotal for improving artificial intelligence (AI)'s diagnostic accuracy in medical imaging. By demonstrating the promise of SSL in chest radiograph analysis, we underline a transformative shift towards more efficient and accurate AI models in medical imaging., Comment: Published in European Radiology Experimental

Classical mathematical models of tumor growth have shaped our understanding of cancer and have broad practical implications for treatment scheduling and dosage. However, even the simplest textbook models have been barely validated in real world-data of human patients. In this study, we fitted a range of differential equation models to tumor volume measurements of patients undergoing chemotherapy or cancer immunotherapy for solid tumors. We used a large dataset of 1472 patients with three or more measurements per target lesion, of which 652 patients had six or more data points. We show that the early treatment response shows only moderate correlation with the final treatment response, demonstrating the need for nuanced models. We then perform a head-to-head comparison of six classical models which are widely used in the field: The Exponential, Logistic, Classic Bertalanffy, General Bertalanffy, Classic Gompertz and General Gompertz model. Several models provide a good fit to tumor volume measurements, with the Gompertz model providing the best balance between goodness of fit and number of parameters. Similarly, when fitting to early treatment data, the general Bertalanffy and Gompertz models yield the lowest mean absolute error to forecasted data, indicating that these models could potentially be effective at predicting treatment outcome. In summary, we provide a quantitative benchmark for classical textbook models and state-of-the art models of human tumor growth. We publicly release an anonymized version of our original data, providing the first benchmark set of human tumor growth data for evaluation of mathematical models., Transport and Logistics, Mathematical Physics

Multimodal deep learning has been used to predict clinical endpoints and diagnoses from clinical routine data. However, these models suffer from scaling issues: they have to learn pairwise interactions between each piece of information in each data type, thereby escalating model complexity beyond manageable scales. This has so far precluded a widespread use of multimodal deep learning. Here, we present a new technical approach of "learnable synergies", in which the model only selects relevant interactions between data modalities and keeps an "internal memory" of relevant data. Our approach is easily scalable and naturally adapts to multimodal data inputs from clinical routine. We demonstrate this approach on three large multimodal datasets from radiology and ophthalmology and show that it outperforms state-of-the-art models in clinically relevant diagnosis tasks. Our new approach is transferable and will allow the application of multimodal deep learning to a broad set of clinically relevant problems.

The success of Deep Learning applications critically depends on the quality and scale of the underlying training data. Generative adversarial networks (GANs) can generate arbitrary large datasets, but diversity and fidelity are limited, which has recently been addressed by denoising diffusion probabilistic models (DDPMs) whose superiority has been demonstrated on natural images. In this study, we propose Medfusion, a conditional latent DDPM for medical images. We compare our DDPM-based model against GAN-based models, which constitute the current state-of-the-art in the medical domain. Medfusion was trained and compared with (i) StyleGan-3 on n=101,442 images from the AIROGS challenge dataset to generate fundoscopies with and without glaucoma, (ii) ProGAN on n=191,027 from the CheXpert dataset to generate radiographs with and without cardiomegaly and (iii) wGAN on n=19,557 images from the CRCMS dataset to generate histopathological images with and without microsatellite stability. In the AIROGS, CRMCS, and CheXpert datasets, Medfusion achieved lower (=better) FID than the GANs (11.63 versus 20.43, 30.03 versus 49.26, and 17.28 versus 84.31). Also, fidelity (precision) and diversity (recall) were higher (=better) for Medfusion in all three datasets. Our study shows that DDPM are a superior alternative to GANs for image synthesis in the medical domain.

Due to the rapid advancements in recent years, medical image analysis is largely dominated by deep learning (DL). However, building powerful and robust DL models requires training with large multi-party datasets. While multiple stakeholders have provided publicly available datasets, the ways in which these data are labeled vary widely. For Instance, an institution might provide a dataset of chest radiographs containing labels denoting the presence of pneumonia, while another institution might have a focus on determining the presence of metastases in the lung. Training a single AI model utilizing all these data is not feasible with conventional federated learning (FL). This prompts us to propose an extension to the widespread FL process, namely flexible federated learning (FFL) for collaborative training on such data. Using 695,000 chest radiographs from five institutions from across the globe - each with differing labels - we demonstrate that having heterogeneously labeled datasets, FFL-based training leads to significant performance increase compared to conventional FL training, where only the uniformly annotated images are utilized. We believe that our proposed algorithm could accelerate the process of bringing collaborative training methods from research and simulation phase to the real-world applications in healthcare., Comment: Published in Nature Scientific Reports

Recent advances in computer vision have shown promising results in image generation. Diffusion probabilistic models in particular have generated realistic images from textual input, as demonstrated by DALL-E 2, Imagen and Stable Diffusion. However, their use in medicine, where image data typically comprises three-dimensional volumes, has not been systematically evaluated. Synthetic images may play a crucial role in privacy preserving artificial intelligence and can also be used to augment small datasets. Here we show that diffusion probabilistic models can synthesize high quality medical imaging data, which we show for Magnetic Resonance Images (MRI) and Computed Tomography (CT) images. We provide quantitative measurements of their performance through a reader study with two medical experts who rated the quality of the synthesized images in three categories: Realistic image appearance, anatomical correctness and consistency between slices. Furthermore, we demonstrate that synthetic images can be used in a self-supervised pre-training and improve the performance of breast segmentation models when data is scarce (dice score 0.91 vs. 0.95 without vs. with synthetic data). The code is publicly available on GitHub: https://github.com/FirasGit/medicaldiffusion.

The spread of early-stage (T1 and T2) adenocarcinomas to locoregional lymph nodes is a key event in disease progression of colorectal cancer (CRC). The cellular mechanisms behind this event are not completely understood and existing predictive biomarkers are imperfect. Here, we used an end-to-end deep learning algorithm to identify risk factors for lymph node metastasis (LNM) status in digitized histopathology slides of the primary CRC and its surrounding tissue. In two large population-based cohorts, we show that this system can predict the presence of more than one LNM in pT2 CRC patients with an area under the receiver operating curve (AUROC) of 0.733 (0.67–0.758) and patients with any LNM with an AUROC of 0.711 (0.597–0.797). Similarly, in pT1 CRC patients, the presence of more than one LNM or any LNM was predictable with an AUROC of 0.733 (0.644–0.778) and 0.567 (0.542–0.597), respectively. Based on these findings, we used the deep learning system to guide human pathology experts towards highly predictive regions for LNM in the whole slide images. This hybrid human observer and deep learning approach identified inflamed adipose tissue as the highest predictive feature for LNM presence. Our study is a first proof of concept that artificial intelligence (AI) systems may be able to discover potentially new biological mechanisms in cancer progression. Our deep learning algorithm is publicly available and can be used for biomarker discovery in any disease setting.

Integrated Energy Systems (IES) are assumed to be an appropriate concept to enable a 100 % renewable energy supply. In IES, the energy grids of the energy sectors electricity, gas and heat are connected by coupling technologies such as Power-to-Gas and Power-to-Heat. These physical and technical couplings can lead to intended and unintended interactions between the three subsystems. On the one hand, these interactions can provide supporting flexibility. On the other hand, these interactions can compromise the system stability. A future energy system must feature resilience, the ability to withstand and recover from disturbances, to enable the necessary security of supply. This paper presents a dynamic system model that is suitable to analyze the dynamic interactions of subsystems and to develop required resilience strategies. Furthermore, a Resilience Index concept is applied to quantify and evaluate system resilience. Given the dynamic simulation approach and the Resilience Index, a set of scenarios are analyzed, showing that dynamic interactions in IES with Power-to-Gas and Power-to-Heat have an influence on the frequency and voltage stability of the electric subsystem. This can affect the resilience positively as well as negatively. Consequently, modifications in the overall energy system must be investigated precisely and these modifications should focus on resilience based on redundancy., Bundesministerium für Wirtschaft und Klimaschutz (BMWK)

Tissue typology annotation in Whole Slide histological images is a complex and tedious, yet necessary task for the development of computational pathology models. We propose to address this problem by applying Open Set Recognition techniques to the task of jointly classifying tissue that belongs to a set of annotated classes, e.g. clinically relevant tissue categories, while rejecting in test time Open Set samples, i.e. images that belong to categories not present in the training set. To this end, we introduce a new approach for Open Set histopathological image recognition based on training a model to accurately identify image categories and simultaneously predict which data augmentation transform has been applied. In test time, we measure model confidence in predicting this transform, which we expect to be lower for images in the Open Set. We carry out comprehensive experiments in the context of colorectal cancer assessment from histological images, which provide evidence on the strengths of our approach to automatically identify samples from unknown categories. Code is released at https://github.com/agaldran/t3po ., Comment: Accepted to MICCAI 2022

info:eu-repo/semantics/published

Background Response to immunotherapy in gastric cancer is associated with microsatellite instability (or mismatch repair deficiency) and Epstein-Barr virus (EBV) positivity. We therefore aimed to develop and validate deep learning based classifiers to detect microsatellite instability and EBV status from routine histology slides. Methods In this retrospective, multicentre study, we collected tissue samples from ten cohorts of patients with gastric cancer from seven countries (South Korea, Switzerland, Japan, Italy, Germany, the UK and the USA). We trained a deep learning-based classifier to detect microsatellite instability and EBV positivity from digitised, haematoxylin and eosin stained resection slides without annotating tumour containing regions. The performance of the classifier was assessed by within-cohort cross-validation in all ten cohorts and by external validation, for which we split the cohorts into a five-cohort training dataset and a five-cohort test dataset. We measured the area under the receiver operating curve (AUROC) for detection of microsatellite instability and EBV status. Microsatellite instability and EBV status were determined to be detectable if the lower bound of the 95% CI for the AUROC was above 0middot5. Findings Across the ten cohorts, our analysis included 2823 patients with known microsatellite instability status and 2685 patients with known EBV status. In the within-cohort cross-validation, the deep learning-based classifier could detect microsatellite instability status in nine of ten cohorts, with AUROCs ranging from 0middot597 (95% CI 0middot522-0middot737) to 0middot836 (0middot795-0middot880) and EBV status in five of eight cohorts, with AUROCs ranging from 0middot819 (0middot752-0middot841) to 0middot897 (0middot513-0middot966). Training a classifier on the pooled training dataset and testing it on the five remaining cohorts resulted in high classification performance with AUROCs ranging from 0middot723 (95% CI 0middot676-0mid

Disease-modifying management aims to prevent deterioration and progression of the disease, not just relieve symptoms. Unfortunately, the development of necessary therapies is often hampered by the failure to recognize the presymptomatic disease and limited understanding of disease development. We present a generic solution for this problem by a methodology that allows the prediction of progression risk and morphology in individuals using a latent extrapolation optimization approach. To this end, we combined a regularized generative adversarial network (GAN) and a latent nearest neighbor algorithm for joint optimization to generate plausible images of future time points. We evaluated our method on osteoarthritis (OA) data from a multi-center longitudinal study (the Osteoarthritis Initiative, OAI). With presymptomatic baseline data, our model is generative and significantly outperforms the end-to-end learning model in discriminating the progressive cohort. Two experiments were performed with seven experienced radiologists. When no synthetic follow-up radiographs were provided, our model performed better than all seven radiologists. In cases where the synthetic follow-ups generated by our model were available, the specificity and sensitivity of all readers in discriminating progressors increased from $72.3\%$ to $88.6\%$ and from $42.1\%$ to $51.6\%$, respectively. Our results open up a new possibility of using model-based morphology and risk prediction to make predictions about future disease occurrence, as demonstrated in the example of OA.

The structural complexity and bioactivity of natural products often depend on enzymatic redox tailoring steps. This is exemplified by the generation of the bisbenzannulated [5,6]-spiroketal pharmacophore in the bacterial rubromycin family of aromatic polyketides, which exhibit a wide array of bioactivities such as the inhibition of HIV reverse transcriptase or DNA helicase. Here we elucidate the complex flavoenzyme-driven formation of the rubromycin pharmacophore that is markedly distinct from conventional (bio)synthetic strategies for spiroketal formation. Accordingly, a polycyclic aromatic precursor undergoes extensive enzymatic oxidative rearrangement catalyzed by two flavoprotein monooxygenases and a flavoprotein oxidase that ultimately results in a drastic distortion of the carbon skeleton. The one-pot in vitro reconstitution of the key enzymatic steps as well as the comprehensive characterization of reactive intermediates allow to unravel the intricate underlying reactions, during which four carbon-carbon bonds are broken and two CO2 become eliminated. This work provides detailed insight into perplexing redox tailoring enzymology that sets the stage for the (chemo)enzymatic production and bioengineering of bioactive spiroketal-containing polyketides.Rubromycin family of natural products belongs to aromatic polyketides with diverse bioactivities, but details of their biosynthesis are limited. Here, the authors report the complete in vitro reconstitution of enzymatic formation of the spiroketal moiety of rubromycin polyketides, driven by flavin-dependent enzymes, and characterize reaction intermediates., DFG Grants; Baden-Württemberg; bwHPC; Projekt DEAL

Ausgehend von Anwendungsproblemen des Werkzeugs „Modellierung und Simulation“ wird eine praxisnahe Vorgehensweise abgeleitet, die simulationsbasierte Vergleichsstudien unter den Aspekten Nachvollziehbarkeit, Vergleichbarkeit und Realitätsnähe erlaubt. Diese wird am Beispiel der Entwicklungsoptionen der Großkraftwerkstechnik hinsichtlich Wirkungsgradsteigerung und CO2-Emissionsminderung genutzt. Betrachtet werden stein- und braunkohlebefeuerte Dampfkraftwerke nach dem Stand der Technik, deren möglichen Fortentwicklung durch gesteigerte Dampfparameter, Braunkohlevortrocknung sowie CO2-Abtrennung im Post-Combustion- und Oxyfuel-Verfahren. Zudem werden die Unterschiede verschiedener Gasturbinenmodelle bei erdgasbefeuerten GuD-Kraftwerken untersucht., A methodology with a practical orientation is derived from experienced issues in the application of modelling and simulation. This methodology allows the simulation based comparative studies in terms of their replicability, comparability and modelling close to reality. It is used to investigate development options of utility sized power plants with regard to efficiency improvements and/or CO2 emission reductions. The study compares current state of the art hard coal fired and lignite fired steam power plants and their improvements by increasing steam parameters, lignite pre-dying as well as the application of CO2 capture by post combustion or oxyfuel technology. Furthermore, the impact of using different gas turbine models for natural gas fired combined cycle power plants are studied.

As a potential approach for enhanced energy generation fromanaerobic digestion, iron-based conductive nanoparticles have been proposed to enhance the methane production yield and rate. In this study, the impact of two different types of iron nanoparticles, namely the nano-zero-valent-iron particles (NZVIs) and magnetite (Fe3O4) nanoparticles (NPs) was investigated, using batch test under mesophilic conditions (35 °C). Magnetite NPs have been applied in doses of 25, 50 and 80 mg/L, corresponding to 13.1, 26.2 and 41.9 mg magnetite NPs/gTS of substrate, respectively. The results reveal that supplementing anaerobic batches with magnetite NPs at a dose of 25 mg/L induces an insignificant effect on hydrolysis and methane production. However, incubation with 50 and 80 mg/L magnetite NPs have instigated comparable positive impact with hydrolysis percentages reaching approximately 95% compared to 63% attained in control batches, in addition to a 50% enhancement in methane production yield. A biodegradability percentage of 94% was achieved with magnetite NP doses of 50 and 80 mg/L, compared to only 62.7% obtained with control incubation. NZVIs were applied in doses of 20, 40 and 60 mg/L, corresponding to 10.8, 21.5 and 32.2 mg NZVIs/gTS of substrate, respectively. The results have shown that supplementing anaerobic batches with NZVIs revealed insignificant impact, most probably due to the agglomeration of NZVI particles and consequently the reduction in available surface area, making the applied doses insufficient for measurable effect., Sanitary Engineering

Disorders of cobalamin (vitamin B$_{12}$ ) metabolism are increasingly recognized in small animal medicine and have a variety of causes ranging from chronic gastrointestinal disease to hereditary defects in cobalamin metabolism. Measurement of serum cobalamin concentration, often in combination with serum folate concentration, is routinely performed as a diagnostic test in clinical practice. While the detection of hypocobalaminemia has therapeutic implications, interpretation of cobalamin status in dogs can be challenging. The aim of this review is to define hypocobalaminemia and cobalamin deficiency, normocobalaminemia, and hypercobalaminemia in dogs, describe known cobalamin deficiency states, breed predispositions in dogs, discuss the different biomarkers of importance for evaluating cobalamin status in dogs, and discuss the management of dogs with hypocobalaminemia.

Molecular alterations in cancer can cause phenotypic changes in tumor cells and their microenvironment. Routine histopathology tissue slides, which are ubiquitously available, can reflect such morphological changes. Here, we show that deep learning can consistently infer a wide range of genetic mutations, molecular tumor subtypes, gene expression signatures and standard pathology biomarkers directly from routine histology. We developed, optimized, validated and publicly released a one-stop-shop workflow and applied it to tissue slides of more than 5,000 patients across multiple solid tumors. Our findings show that a single deep learning algorithm can be trained to predict a wide range of molecular alterations from routine, paraffin-embedded histology slides stained with hematoxylin and eosin. These predictions generalize to other populations and are spatially resolved. Our method can be implemented on mobile hardware, potentially enabling point-of-care diagnostics for personalized cancer treatment. More generally, this approach could elucidate and quantify genotype-phenotype links in cancer. Two papers by Kather and colleagues and Gerstung and colleagues develop workflows to predict a wide range of molecular alterations from pan-cancer digital pathology slides.

Temporal variations in CO2 stream composition and mass flow rates may occur in a CO2 transport network, as well as further downstream when CO2 streams of different compositions and temporally variable mass flow rates are fed in. To assess the potential impacts of such variations on CO2 transport, injection, and storage, their characteristics must be known. We investigated variation characteristics in a scenario of a regional CO2 emitter cluster of seven fossil-fired power plants and four industrial plants that feed captured CO2 streams into a pipeline network. Variations of CO2 stream composition and mass flow rates in the pipelines were simulated using a network analysis tool. In addition, the potential effects of changes in the energy mix on resulting mass flow rates and CO2 stream compositions were investigated for two energy mix scenarios that consider higher shares of renewable energy sources or a replacement of lignite by hard coal and natural gas. While resulting maximum mass flow rates in the trunk line were similar in all considered scenarios, minimum flow rates and pipeline capacity utilisation differed substantially between them. Variations in CO2 stream composition followed the power plants’ operational load patterns resulting e.g., in stronger composition variations in case of higher renewable energy production., Temporal variations in CO2 stream composition and mass flow rates may occur in a CO2 transport network, as well as further downstream when CO2 streams of different compositions and temporally variable mass flow rates are fed in. To assess the potential impacts of such variations on CO2 transport, injection, and storage, their characteristics must be known. We investigated variation characteristics in a scenario of a regional CO2 emitter cluster of seven fossil-fired power plants and four industrial plants that feed captured CO2 streams into a pipeline network. Variations of CO2 stream composition and mass flow rates in the pipelines were simulated using a network analysis tool. In addition, the potential effects of changes in the energy mix on resulting mass flow rates and CO2 stream compositions were investigated for two energy mix scenarios that consider higher shares of renewable energy sources or a replacement of lignite by hard coal and natural gas. While resulting maximum mass flow rates in the trunk line were similar in all considered scenarios, minimum flow rates and pipeline capacity utilisation differed substantially between them. Variations in CO2 stream composition followed the power plants’ operational load patterns resulting e.g., in stronger composition variations in case of higher renewable energy production.

© 2014 The Authors. Published by Elsevier Ltd. The Octavius FP7 project focuses on demonstration of CO2 capture for zero emission power generation. As part of this work many partners are involved using different rate based simulation tools to develop tomorrow's new power plants. A benchmarking is performed, in order to synchronize accuracy and quality control the used modeling tools. The aim is to have 6 independent partners produce results on simulation tasks which are well defined in this work. The results show the performance of a typical simulation tool ranging from in-house process simulator to Aspen Plus® and combination of the two, using CAPE-Open. Definitions of the models are outlined describing the used assumptions on mass transfer correlations, hydraulics, thermodynamic models, kinetics, and property packages. A sensitivity study is carried out for absorption and desorption which shows the performance of capture percentage, specific reboiler duties, loading of rich and lean solutions, pressure drop, flooding, concentration and temperature profiles, product purity, and condenser performance. The overall conclusion is that most predicted properties vary in the order of 5-10% percent, often more than accuracy in experimental pilot plant measurements. There is a general good resemblance between modeling results. A few important properties like specific reboiler duty and reboiler temperature plus concentration and temperature profiles vary more than expected. Also high flooding scenarios in the stripper are difficult cases. Efficiencies are discussed as part of the summary. Recommendations for modeling principles and best practice are given.

Zur Erreichung der Klimaschutzziele stützt sich die deutsche Energiewende insbesondere auf den Ausbau der regenerativen Stromerzeugungskapazitäten. Als Möglichkeit zur Erreichung der Emissionsziele in den Sektoren Wärme und Verkehr wird dabei zumeist eine zunehmende Elektrifizierung angesehen. In dieser Arbeit werden für das Energiesystem Deutschlands Ganglinien der regenerativen Stromerzeugung sowie der sektorspezifischen Energiebedarfe in hoher zeitlicher und regionaler Auflösung ermittelt. Die daraus resultierende elektrische Residuallast wird für verschiedene Szenarien untersucht. Dabei kann festgestellt werden, dass eine Kopplung der Sektoren zu einem steigenden elektrischen Energiebedarf führt, der durch den derzeit geplanten Ausbau der erneuerbaren Energien bilanziell nicht gedeckt werden kann.