Accurate and Reliable Classification of Unstructured Reports on Their Diagnostic Goal Using BERT Models.

Understanding the diagnostic goal of medical reports is valuable information for understanding patient flows. This work focuses on extracting the reason for taking an MRI scan of Multiple Sclerosis (MS) patients using the attached free-form reports: Diagnosis, Progression or Monitoring. We investigate the performance of domain-dependent and general state-of-the-art language models and their alignment with domain expertise. To this end, eXplainable Artificial Intelligence (XAI) techniques are used to acquire insight into the inner workings of the model, which are verified on their trustworthiness. The verified XAI explanations are then compared with explanations from a domain expert, to indirectly determine the reliability of the model. BERTje, a Dutch Bidirectional Encoder Representations from Transformers (BERT) model, outperforms RobBERT and MedRoBERTa.nl in both accuracy and reliability. The latter model (MedRoBERTa.nl) is a domain-specific model, while BERTje is a generic model, showing that domain-specific models are not always superior. Our validation of BERTje in a small prospective study shows promising results for the potential uptake of the model in a practical setting.

Explainable AI in medical imaging: An overview for clinical practitioners - Saliency-based XAI approaches.

Since recent achievements of Artificial Intelligence (AI) have proven significant success and promising results throughout many fields of application during the last decade, AI has also become an essential part of medical research. The improving data availability, coupled with advances in high-performance computing and innovative algorithms, has increased AI's potential in various aspects. Because AI rapidly reshapes research and promotes the development of personalized clinical care, alongside its implementation arises an urgent need for a deep understanding of its inner workings, especially in high-stake domains. However, such systems can be highly complex and opaque, limiting the possibility of an immediate understanding of the system's decisions. Regarding the medical field, a high impact is attributed to these decisions as physicians and patients can only fully trust AI systems when reasonably communicating the origin of their results, simultaneously enabling the identification of errors and biases. Explainable AI (XAI), becoming an increasingly important field of research in recent years, promotes the formulation of explainability methods and provides a rationale allowing users to comprehend the results generated by AI systems. In this paper, we investigate the application of XAI in medical imaging, addressing a broad audience, especially healthcare professionals. The content focuses on definitions and taxonomies, standard methods and approaches, advantages, limitations, and examples representing the current state of research regarding XAI in medical imaging. This paper focuses on saliency-based XAI methods, where the explanation can be provided directly on the input data (image) and which naturally are of special importance in medical imaging.

Explainable AI in medical imaging: An overview for clinical practitioners - Beyond saliency-based XAI approaches.

Driven by recent advances in Artificial Intelligence (AI) and Computer Vision (CV), the implementation of AI systems in the medical domain increased correspondingly. This is especially true for the domain of medical imaging, in which the incorporation of AI aids several imaging-based tasks such as classification, segmentation, and registration. Moreover, AI reshapes medical research and contributes to the development of personalized clinical care. Consequently, alongside its extended implementation arises the need for an extensive understanding of AI systems and their inner workings, potentials, and limitations which the field of eXplainable AI (XAI) aims at. Because medical imaging is mainly associated with visual tasks, most explainability approaches incorporate saliency-based XAI methods. In contrast to that, in this article we would like to investigate the full potential of XAI methods in the field of medical imaging by specifically focusing on XAI techniques not relying on saliency, and providing diversified examples. We dedicate our investigation to a broad audience, but particularly healthcare professionals. Moreover, this work aims at establishing a common ground for cross-disciplinary understanding and exchange across disciplines between Deep Learning (DL) builders and healthcare professionals, which is why we aimed for a non-technical overview. Presented XAI methods are divided by a method's output representation into the following categories: Case-based explanations, textual explanations, and auxiliary explanations.

Diagnosis of Inflammatory Bowel Disease and Colorectal Cancer through Multi-View Stacked Generalization Applied on Gut Microbiome Data.

Most of the microbiome studies suggest that using ensemble models such as Random Forest results in best predictive power. In this study, we empirically evaluate a more powerful ensemble learning algorithm, multi-view stacked generalization, on pediatric inflammatory bowel disease and adult colorectal cancer patients' cohorts. We aim to check whether stacking would lead to better results compared to using a single best machine learning algorithm. Stacking achieves the best test set Average Precision (AP) on inflammatory bowel disease dataset reaching AP = 0.69, outperforming both the best base classifier (AP = 0.61) and the baseline meta learner built on top of base classifiers (AP = 0.63). On colorectal cancer dataset, the stacked classifier also outperforms (AP = 0.81) both the best base classifier (AP = 0.79) and the baseline meta learner (AP = 0.75). Stacking achieves best predictive performance on test set outperforming the best classifiers on both patient cohorts. Application of the stacking solves the issue of choosing the most appropriate machine learning algorithm by automating the model selection procedure. Clinical application of such a model is not limited to diagnosis task only, but it also can be extended to biomarker selection thanks to feature selection procedure.

Radiology report generation for proximal femur fractures using deep classification and language generation models.

Proximal femur fractures represent a major health concern, and substantially contribute to the morbidity of elderly. Correct classification and diagnosis of hip fractures has a significant impact on mortality, costs and hospital stay. In this paper, we present a method and empirical validation for automatic subclassification of proximal femur fractures and Dutch radiological report generation that does not rely on manually curated data. The fracture classification model was trained on 11,000 X-ray images obtained from 5000 electronic health records in a general hospital. To generate the Dutch reports, we first trained an embedding model on 20,000 radiological reports of pelvic region fractures, and used its embeddings in the report generation model. We trained the report generation model on the 5000 radiological reports associated with the fracture cases. Our report generation model is on par with state-of-the-art in terms of BLEU and ROUGE scores. This is promising, because in contrast to those earlier works, our approach does not require manual preprocessing of either images or the reports. This boosts the applicability of automatic clinical report generation in practice. A quantitative and qualitative user study among medical students found no significant difference in provenance of real and generated reports. A qualitative, in-depth clinical relevance study with medical domain experts showed that from a human perspective the quality of the generated reports approximates the quality of the original reports and highlights challenges in creating sufficiently detailed and versatile training data for automatic radiology report generation.

Channel Contribution In Deep Learning Based Automatic Sleep Scoring - How Many Channels Do We Need?

Machine learning based sleep scoring methods aim to automate the process of annotating polysomnograms with sleep stages. Although sleep signals of multiple modalities and channels should contain more information according to sleep guidelines, most multi-channel multi-modal models in the literature showed only a little performance improvement compared to single-channel EEG models and sometimes even failed to outperform them. In this paper, we investigate whether the high performance of single-channel EEG models can be attributed to specific model features in their deep learning architectures and to which extent multi-channel multi-modal models take the information from different channels of modalities into account. First, we transfer the model features from single-channel EEG models, such as combinations of small and large filters in CNNs, to multi-channel multi-modal models and measure their impacts. Second, we employ two explainability methods, the layer-wise relevance propagation as post-hoc and the embedded channel attention network as intrinsic interpretability methods, to measure the contribution of different channels on predictive performance. We find that i) single-channel model features can improve the performance of multi-channel multi-modal models and ii) multi-channel multi-modal models focus on one important channel per modality and use the remaining channels to complement the information of the focused channels. Our results suggest that more advanced methods for aggregating channel information using complementary information from other channels may improve sleep scoring performance for multi-channel multi-modal models.

STQS: Interpretable multi-modal Spatial-Temporal-seQuential model for automatic Sleep scoring.

Sleep scoring is an important step for the detection of sleep disorders and usually performed by visual analysis. Since manual sleep scoring is time consuming, machine-learning based approaches have been proposed. Though efficient, these algorithms are black-box in nature and difficult to interpret by clinicians. In this paper, we propose a deep learning architecture for multi-modal sleep scoring, investigate the model's decision making process, and compare the model's reasoning with the annotation guidelines in the AASM manual. Our architecture, called STQS, uses convolutional neural networks (CNN) to automatically extract spatio-temporal features from 3 modalities (EEG, EOG and EMG), a bidirectional long short-term memory (Bi-LSTM) to extract sequential information, and residual connections to combine spatio-temporal and sequential features. We evaluated our model on two large datasets, obtaining an accuracy of 85% and 77% and a macro F1 score of 79% and 73% on SHHS and an in-house dataset, respectively. We further quantify the contribution of various architectural components and conclude that adding LSTM layers improves performance over a spatio-temporal CNN, while adding residual connections does not. Our interpretability results show that the output of the model is well aligned with AASM guidelines, and therefore, the model's decisions correspond to domain knowledge. We also compare multi-modal models and single-channel models and suggest that future research should focus on improving multi-modal models.

Life cycle assessment as decision support tool for environmental management in hospitals: A literature review.

BACKGROUND: Life cycle assessment (LCA) is an environmental accounting tool aimed at determining environmental impacts of products, processes, or organizational activities over the entire life cycle. Although this technique already provides decision-makers in other sectors with valuable information, its application in the health care setting has not yet been examined. PURPOSE: The aim of this study was to provide a comprehensive overview of scientific research on the application of LCA in hospitals and its contribution to management decision-making. METHOD: We perform a systematic literature review by searching a range of databases with synonyms of "LCA" in combination with the term "hospital" in order to identify peer-reviewed studies. The final sample of 43 studies were then subjected to a content analysis. RESULTS: We categorize existing research and show that single and multi-indicator LCA approaches are used to examine several products and processes in hospitals. The various approaches are favored by different scientific communities. Whereas researchers from environmental sciences perform complex multi-indicator LCA studies, researchers from health care sciences focus on footprints. The studies compare alternatives and identify environmental impacts and harmful hotspots. PRACTICE IMPLICATIONS: LCA results can support health care managers' traditional decision-making by providing environmental information. With this additional information regarding the environmental impacts of products and processes, managers can implement organizational changes to improve their environmental performance. Furthermore, they can influence upstream and downstream activities. However, we recommend more transdisciplinary cooperation for LCA studies and to place more focus on actionable recommendations when publishing the results.

Uncovering and Correcting Shortcut Learning in Machine Learning Models for Skin Cancer Diagnosis.

Machine learning models have been successfully applied for analysis of skin images. However, due to the black box nature of such deep learning models, it is difficult to understand their underlying reasoning. This prevents a human from validating whether the model is right for the right reasons. Spurious correlations and other biases in data can cause a model to base its predictions on such artefacts rather than on the true relevant information. These learned shortcuts can in turn cause incorrect performance estimates and can result in unexpected outcomes when the model is applied in clinical practice. This study presents a method to detect and quantify this shortcut learning in trained classifiers for skin cancer diagnosis, since it is known that dermoscopy images can contain artefacts. Specifically, we train a standard VGG16-based skin cancer classifier on the public ISIC dataset, for which colour calibration charts (elliptical, coloured patches) occur only in benign images and not in malignant ones. Our methodology artificially inserts those patches and uses inpainting to automatically remove patches from images to assess the changes in predictions. We find that our standard classifier partly bases its predictions of benign images on the presence of such a coloured patch. More importantly, by artificially inserting coloured patches into malignant images, we show that shortcut learning results in a significant increase in misdiagnoses, making the classifier unreliable when used in clinical practice. With our results, we, therefore, want to increase awareness of the risks of using black box machine learning models trained on potentially biased datasets. Finally, we present a model-agnostic method to neutralise shortcut learning by removing the bias in the training dataset by exchanging coloured patches with benign skin tissue using image inpainting and re-training the classifier on this de-biased dataset.

Automatic Process Comparison for Subpopulations: Application in Cancer Care.

Processes in organisations, such as hospitals, may deviate from the intended standard processes, due to unforeseeable events and the complexity of the organisation. For hospitals, the knowledge of actual patient streams for patient populations (e.g., severe or non-severe cases) is important for quality control and improvement. Process discovery from event data in electronic health records can shed light on the patient flows, but their comparison for different populations is cumbersome and time-consuming. In this paper, we present an approach for the automatic comparison of process models that were extracted from events in electronic health records. Concretely, we propose comparing processes for different patient populations by cross-log conformance checking, and standard graph similarity measures obtained from the directed graph underlying the process model. We perform a user study with 20 participants in order to obtain a ground truth for similarity of process models. We evaluate our approach on two data sets, the publicly available MIMIC database with the focus on different cancer patients in intensive care, and a database on breast cancer patients from a Dutch hospital. In our experiments, we found average fitness to be a good indicator for visual similarity in the ZGT use case, while the average precision and graph edit distance are strongly correlated with visual impression for cancer process models on MIMIC. These results are a call for further research and evaluation for determining which similarity or combination of similarities is needed in which type of process model comparison.

Post-Structuring Radiology Reports of Breast Cancer Patients for Clinical Quality Assurance.

Hospitals often set protocols based on well defined standards to maintain the quality of patient reports. To ensure that the clinicians conform to the protocols, quality assurance of these reports is needed. Patient reports are currently written in free-text format, which complicates the task of quality assurance. In this paper, we present a machine learning based natural language processing system for automatic quality assurance of radiology reports on breast cancer. This is achieved in three steps: we i) identify the top-level structure (headings) of the report, ii) classify the report content into the top-level headings, and iii) convert the free-text detailed findings in the report to a semi-structured format (post-structuring). Top level structure and content of report were predicted with an F1 score of 0.97 and 0.94, respectively, using Support Vector Machine (SVM) classifiers. For automatic structuring, our proposed hierarchical Conditional Random Field (CRF) outperformed the baseline CRF with an F1 score of 0.78 versus 0.71. The determined structure of the report is represented in semi-structured XML format of the free-text report, which helps to easily visualize the conformance of the findings to the protocols. This format also allows easy extraction of specific information for other purposes such as search, evaluation, and research.

Gearing up sustainability thinking and reducing the bystander effect - A case study of wastewater treatment plants.

The United Nations Sustainable Development Goals (SDG) emphasize the task of organizations to implement sustainability and especially environmental issues. So far, scholars have focused on private sector and manufacturing organizations as they are regarded as the main polluters. However, despite their positive influence to a circular economy, public service organizations such as wastewater treatment plants (WWTPs) have negative environmental impacts as well. WWTPs shoulder the important task of mitigating environmental impacts caused by organizations and households at the end-of-pipe. We question whether WWTPs are mainly guided by their core mission of wastewater treatment or have an environmental thinking beyond this core activity and, thus, pursue a holistic environmental sustainability management approach. We investigate WWTPs' experienced sources for pressure regarding environmental thinking and management in a multiple case study with three exemplary WWTPs by means of conducting semi-standardized interviews, analyzing homepages as well as reports, and attending internal meetings. Results indicate that WWTPs focus on the operational environmental performance of wastewater treatment, either regulated by laws, contributing to financial savings, or increasing customer satisfaction. However, WWTPs are highly reliant on the incoming wastewater streams on which they have little influence. To achieve the SDG, we conclude that it is important to gear up environmental sustainability thinking beyond reducing wastewater contamination in WWTPs as an end-of-pipe solution. To do so, WWTPs have to take responsibility beyond their core business and stakeholders have to rethink their prevailing wastewater discharging behavior at the pollution source. Rethinking habits and practices by all actors along the entire water cycle can contribute more to sustainable societies than taking a passive bystander role that attributes all responsibility towards WWTPs that continuously have to implement costly and elaborate upgrades.

The efficiency of human cytomegalovirus pp65(495-503) CD8+ T cell epitope generation is determined by the balanced activities of cytosolic and endoplasmic reticulum-resident peptidases.

Control of human CMV (HCMV) infection depends on the cytotoxic activity of CD8(+) CTLs. The HCMV phosphoprotein (pp)65 is a major CTL target Ag and pp65(495-503) is an immunodominant CTL epitope in infected HLA-A*0201 individuals. As immunodominance is strongly determined by the surface abundance of the specific epitope, we asked for the components of the cellular Ag processing machinery determining the efficacy of pp65(495-503) generation, in particular, for the proteasome, cytosolic peptidases, and endoplasmic reticulum (ER)-resident peptidases. In vitro Ag processing experiments revealed that standard proteasomes and immunoproteasomes generate the minimal 9-mer peptide epitope as well as N-terminal elongated epitope precursors of different lengths. These peptides are largely degraded by the cytosolic peptidases leucine aminopeptidase and tripeptidyl peptidase II, as evidenced by increased pp65(495-503) epitope presentation after leucine aminopeptidase and tripeptidyl peptidase II knockdown. Additionally, with prolyl oligopeptidase and aminopeptidase B we identified two new Ag processing machinery components, which by destroying the pp65(495-503) epitope limit the availability of the specific peptide pool. In contrast to cytosolic peptidases, silencing of ER aminopeptidases 1 and 2 strongly impaired pp65(495-503)-specific T cell activation, indicating the importance of ER aminopeptidases in pp65(495-503) generation. Thus, cytosolic peptidases primarily interfere with the generation of the pp65(495-503) epitope, whereas ER-resident aminopeptidases enhance such generation. As a consequence, our experiments reveal that the combination of cytosolic and ER-resident peptidase activities strongly shape the pool of specific antigenic peptides and thus modulate MHC class I epitope presentation efficiency.