Personalized care in dilated cardiomyopathy: Rationale and study design of the activeDCM trial.

BACKGROUND: Dilated cardiomyopathy (DCM) is a leading cause of heart failure, particularly in younger individuals. Low physical strength is a global risk factor for cardiovascular mortality, and physical activity and a healthy lifestyle have been shown to improve outcomes in patients with heart failure. However, inappropriate exercise may increase the risk of arrhythmias in certain individuals with DCM. The determinants for predicting individual risks in this setting are poorly understood, and clinicians are hesitant to recommend sports for cardiomyopathy patients. The activeDCM trial aims to assess the safety and efficacy of a personalized exercise and activity programme for individuals with DCM. STUDY DESIGN: The activeDCM trial is a prospective, randomized, interventional trial with a 12 month follow-up. Three hundred patients, aged 18-75 years with DCM, left ventricular ejection fraction (LVEF) ≤ 50% and New York Heart Association (NYHA) classes I-III, will be enrolled. The intervention includes a personalized exercise and activity programme. The primary outcome is the increase in peak oxygen uptake (VO2max, mL/kg/min) from baseline to 12 months. Secondary endpoints include adherence to personalized activity programmes, freedom from clinically relevant arrhythmia, unplanned hospitalization for heart failure and changes in NYHA class, quality of life scores, 6 min walk distance, muscular strength, N-terminal pro-B-type natriuretic peptide (NT-proBNP) and high-sensitivity troponin T (hsTnT) levels and cardiac function. Advanced research questions include high-density phenome and omics analysis combined with digital biomarkers derived from Apple Watch devices. DISCUSSION: The activeDCM trial will provide valuable insights into the safety and efficacy of personalized exercise training in DCM patients, inform clinical practice and contribute to the development of heart failure management programmes. The study will generate data on the impact of exercise on various aspects of cardiovascular disease, including genetic, metabolic, phenotypic and longitudinal aspects, facilitating the development of future digital tools and strategies, including the incorporation of smart wearable devices.

Interpretation of elevated baseline concentrations and serial changes of high-sensitivity cardiac troponin T in confirmed muscular dystrophies.

AIMS: Concentrations of high-sensitivity cardiac troponin T (hs-cTnT) are frequently elevated in stable patients with confirmed muscle dystrophies. However, sparse information is available on the interpretation of serial concentration changes. METHODS: Hs-cTnT was collected in 35 stable outpatients with confirmed skeletal muscle dystrophies at 0 and 1 h and after 6-12 months during scheduled outpatient visits. We simulated the effectiveness of the European Society of Cardiology (ESC) 0/1 h algorithm and assessed biological variation at 6-12 months using two established methods: reference change value (RCV) and minimal important difference (MID). RESULTS: Median baseline hs-cTnT concentrations were 34.4 ng/L [inter-quartile range (IQR): 17.5-46.2], and values > 99th percentile upper limit of normal were present in 34 of 35 patients. All patients were stable without cardiovascular adverse events during a follow-up of 6.6 months (IQR: 6-7). Median concentration change was 1.9 ng/L (IQR: 0.7-3.2) and 0.8 ng/L (IQR: 0-7.0) at 60 min and 6-9 months, respectively. Applying the criteria of the ESC 0/1 h algorithm for triage of suspected acute coronary syndrome (ACS) showed poor overall effectiveness of baseline hs-cTnT values. No patient would qualify for rule-out based on hs-cTnT less than the limit of detection, whereas five cases would qualify for rule-in based on hs-cTnT ≥ 52 ng/L. Biological variabilities at 6-12 months per MID and RCV were 1.2 ng/L [95% confidence interval (CI): 0.7-2.1] and 28.6% (95% CI: 27.9-29.6), respectively. A total of 8 (22.9%) and 25 (71.4%) cases exceeded the biological variation range, suggesting some additional myocardial damage. CONCLUSIONS: The high prevalence of elevated hs-cTnT could negatively impact the effectiveness of rule-out and rule-in strategies based on a single hs-cTnT value. Knowledge of the physiological and biological variation of hs-cTnT after 6-12 months is helpful to detect the progression of cardiac involvement or to search for cardiac complications including but not limited to arrhythmias that may trigger acute or chronic myocardial damage.

Prediction of diagnosis and diastolic filling pressure by AI-enhanced cardiac MRI: a modelling study of hospital data.

BACKGROUND: With increasing numbers of patients and novel drugs for distinct causes of systolic and diastolic heart failure, automated assessment of cardiac function is important. We aimed to provide a non-invasive method to predict diagnosis of patients undergoing cardiac MRI (cMRI) and to obtain left ventricular end-diastolic pressure (LVEDP). METHODS: For this modelling study, patients who had undergone cardiac catheterisation at University Hospital Heidelberg (Heidelberg, Germany) between July 15, 2004 and March 16, 2023, were identified, as were individual left ventricular pressure measurements. We used existing patient data from routine cardiac diagnostics. From this initial group, we extracted patients who had been diagnosed with ischaemic cardiomyopathy, dilated cardiomyopathy, hypertrophic cardiomyopathy, or amyloidosis, as well as control individuals with no structural phenotype. Data were pseudonymised and only processed within the university hospital's AI infrastructure. We used the data to build different models to predict either demographic (ie, AI-age and AI-sex), diagnostic (ie, AI-coronary artery disease and AI-cardiomyopathy [AI-CMP]), or functional parameters (ie, AI-LVEDP). We randomly divided our datasets via computer into training, validation, and test datasets. AI-CMP was not compared with other models, but was validated in a prospective setting. Benchmarking was also done. FINDINGS: 66 936 patients who had undergone cardiac catheterisation at University Hospital Heidelberg were identified, with more than 183 772 individual left ventricular pressure measurements. We extracted 4390 patients from this initial group, of whom 1131 (25·8%) had been diagnosed with ischaemic cardiomyopathy, 1064 (24·2%) had been diagnosed with dilated cardiomyopathy, 816 (18·6%) had been diagnosed with hypertrophic cardiomyopathy, 202 (4·6%) had been diagnosed with amyloidosis, and 1177 (26·7%) were control individuals with no structural phenotype. The core cohort only included patients with cardiac catherisation and cMRI within 30 days, and emergency cases were excluded. AI-sex was able to predict patient sex with areas under the receiver operating characteristic curves (AUCs) of 0·78 (95% CI 0·77-0·78) and AI-age was able to predict patient age with a mean absolute error of 7·86 years (7·77-7·95), with a Pearson correlation of 0·57 (95% CI 0·56-0·57). The AUCs for the classification tasks ranged between 0·82 (95% CI 0·79-0·84) for ischaemic cardiomyopathy and 0·92 (0·91-0·94) for hypertrophic cardiomyopathy. INTERPRETATION: Our AI models could be easily integrated into clinical practice and provide added value to the information content of cMRI, allowing for disease classification and prediction of diastolic function. FUNDING: Informatics for Life initiative of the Klaus-Tschira Foundation, German Center for Cardiovascular Research, eCardiology section of the German Cardiac Society, and AI Health Innovation Cluster Heidelberg.

Comparison of the clinical chemistry score to other biomarker algorithms for rapid rule-out of acute myocardial infarction and risk stratification in patients with suspected acute coronary syndrome.

BACKGROUND: The clinical chemistry score (CCS) comprising high-sensitivity cardiac troponins (hs-cTn), glucose and estimated glomerular filtration rate has been previously validated with superior accuracy for detection and risk stratification of acute myocardial infarction (AMI) compared to hs-cTn alone. METHODS: The CCS was compared to other biomarker-based algorithms for rapid rule-out and prognostication of AMI including the hs-cTnT limit-of-blank (LOB, <3 ng/L) or limit-of-detection (LOD, <5 ng/L) and a dual marker strategy (DMS) (copeptin <10 pmol/L and hs-cTnT ≤14 ng/L) in 1506 emergency department (ED) patients with symptoms suggestive of acute coronary syndrome. Negative predictive values (NPV) and sensitivities for AMI rule-out, and 12-month combined endpoint rates encompassing mortality, myocardial re-infarction, as well as stroke were assessed. RESULTS: NPVs of 100% (95% CI: 98.3-100%) were observed for CCS = 0, hs-cTnT LoB and hs-cTnT LoD with rule-out efficacies of 11.1%, 7.6% and 18.3% as well as specificities of 13.0% (95% CI: 9.9-16.6%), 8.8% (95% CI: 7.3-10.5%) and 21.4% (95% CI: 19.2-23.8%), respectively. A CCS ≤ 1 achieved a rule-out in 32.2% of all patients with a NPV of 99.6% (95% CI: 98.4-99.9%) and specificity of 37.4% (95% CI: 34.2-40.5%) compared to a rule-out efficacy of 51.2%, NPV of 99.0 (95% CI: 98.0-99.5) and specificity of 59.7% (95% CI: 57.0-62.4%) for the DMS. Rates of the combined end-point of death/AMI within 30 days ranged between 0.0% and 0.7% for all fast-rule-out protocols. CONCLUSIONS: The CCS ensures reliable AMI rule-out with low short and long-term outcome rates for a specific ED patient subset. However, compared to a single or dual biomarker strategy, the CCS displays reduced efficacy and specificity, limiting its clinical utility.

Improving sudden cardiac death risk stratification in hypertrophic cardiomyopathy using established clinical variables and genetic information.

BACKGROUND AND AIMS: The cardiac societies of Europe and the United States have established different risk models for preventing sudden cardiac death (SCD) in hypertrophic cardiomyopathy (HCM). The aim of this study is to validate current SCD risk prediction methods in a German HCM cohort and to improve them by the addition of genotype information. METHODS: HCM patients without prior SCD or equivalent arrhythmic events ≥ 18 years of age were enrolled in an expert cardiomyopathy center in Germany. The primary endpoint was defined as SCD/-equivalent within 5 years of baseline evaluation. 5-year SCD-risk estimates and recommendations for ICD implantations, as defined by the ESC and AHA/ACC guidelines, were analyzed. Multivariate cox proportional hazards analyses were integrated with genetic findings as additive SCD risk. RESULTS: 283 patients were included and followed for in median 5.77 years (2.92; 8.85). A disease-causing variant was found in 138 (49%) patients. 14 (5%) patients reached the SCD endpoint (5-year incidence 4.9%). Kaplan-Meier survival analysis shows significantly lower overall SCD event-free survival for patients with an identified disease-causing variant (p < 0.05). The ESC HCM Risk-SCD model showed an area-under-the-curve (AUC) of 0.74 (95% CI 0.68-0.79; p < 0.0001) with a sensitivity of 0.29 (95% CI 0.08-0.58) and specificity of 0.83 (95% CI 0.78-0.88) for a risk estimate ≥ 6%/5-years. By comparison, the AHA/ACC HCM SCD risk stratification model showed an AUC of 0.70 (95% CI 0.65-0.76; p = 0.003) with a sensitivity of 0.93 (95% CI, 0.66-0.998) and specificity of 0.28 (95% CI 0.23-0.34) at the respective cut-off. The modified SCD Risk Score with genetic information yielded an AUC of 0.76 (95% CI 0.71-0.81; p < 0.0001) with a sensitivity of 0.86 (95% CI 0.57-0.98) and specificity of 0.69 (95% CI 0.63-0.74). The number-needed-to-treat (NNT) to prevent 1 SCD event by prophylactic ICD-implantation is 13 for the ESC model, 28 for AHA/ACC and 9 for the modified Genotype-model. CONCLUSION: This study confirms the performance of current risk models in clinical decision making. The integration of genetic findings into current SCD risk stratification methods seem feasible and can add in decision making, especially in borderline risk-groups. A subgroup of patients with high SCD risk remains unidentified by current risk scores.

An Instance Segmentation Dataset of Yeast Cells in Microstructures.

Extracting single-cell information from microscopy data requires accurate instance-wise segmentations. Obtaining pixel-wise segmentations from microscopy imagery remains a challenging task, especially with the added complexity of microstructured environments. This paper presents a novel dataset for segmenting yeast cells in microstructures. We offer pixel-wise instance segmentation labels for both cells and trap microstructures. In total, we release 493 densely annotated microscopy images. To facilitate a unified comparison between novel segmentation algorithms, we propose a standardized evaluation strategy for our dataset. The aim of the dataset and evaluation strategy is to facilitate the development of new cell segmentation approaches. The dataset is publicly available at https://christophreich1996.github.io/yeast_in_microstructures_dataset/.

A Study on the Reliability of Visual XAI Methods for X-Ray Images.

The YOLO series of object detection algorithms, including YOLOv4 and YOLOv5, have shown superior performance in various medical diagnostic tasks, surpassing human ability in some cases. However, their black-box nature has limited their adoption in medical applications that require trust and explainability of model decisions. To address this issue, visual explanations for AI models, known as visual XAI, have been proposed in the form of heatmaps that highlight regions in the input that contributed most to a particular decision. Gradient-based approaches, such as Grad-CAM [1], and non-gradient-based approaches, such as Eigen-CAM [2], are applicable to YOLO models and do not require new layer implementation. This paper evaluates the performance of Grad-CAM and Eigen-CAM on the VinDrCXR Chest X-ray Abnormalities Detection dataset [3] and discusses the limitations of these methods for explaining model decisions to data scientists.

The User, the Watch, and the Bestseller: Study on the Utilization of Smart Medical Wearables and Their User Manuals.

In this paper, we present a study on the utilization of smart medical wearables and the user manuals of such devices. A total of 342 individuals provided input for 18 questions that address user behavior in the investigated context and the connections between various assessments and preferences. The presented work clusters individuals based on their professional relation to user manuals and analyzes the obtained results separately for these groups.

Health Informatics Training Programs to Strengthen Health Workforce in Montenegro.

Health informatics plays a crucial role in modern healthcare provision. Training and continuous education are essential to bolster the healthcare workforce on health informatics. In this work, we present the training events within EU-funded DigNest project. The aim of the training events, the subjects offered, and the overall evaluation of the results are described in this paper.

Montenegrin Digital Academic Innovation Hub: Supporting Digital Education, Business and Innovations in Medical Informatics.

This poster presents a Montenegrin Digital Academic Innovation Hub aimed to support education, innovations, and academia-business cooperation in medical informatics (as one of four priority areas) at national level in Montenegro. The Hub topology and its organisation in the form of two main nodes, with services established within key pillars: Digital Education; Digital Business Support; Innovations and cooperation with industry; and Employment support.

The Heart and Artificial Intelligence-How Can We Improve Medicine Without Causing Harm.

PURPOSE OF REVIEW: The introduction of Artificial Intelligence into the healthcare system offers enormous opportunities for biomedical research, the improvement of patient care, and cost reduction in high-end medicine. Digital concepts and workflows are already playing an increasingly important role in cardiology. The fusion of computer science and medicine offers great transformative potential and enables enormous acceleration processes in cardiovascular medicine. RECENT FINDINGS: As medical data becomes smart, it is also becoming more valuable and vulnerable to malicious actors. In addition, the gap between what is technically possible and what is allowed by privacy legislation is growing. Principles of the General Data Protection Regulation that have been in force since May 2018, such as transparency, purpose limitation, and data minimization, seem to hinder the development and use of Artificial Intelligence. Concepts to secure data integrity and incorporate legal and ethical principles can help to avoid the potential risks of digitization and may result in an European leadership in regard to privacy protection and AI. The following review provides an overview of relevant aspects of Artificial Intelligence and Machine Learning, highlights selected applications in cardiology, and discusses central ethical and legal considerations.

Personalized diagnosis in suspected myocardial infarction.

BACKGROUND: In suspected myocardial infarction (MI), guidelines recommend using high-sensitivity cardiac troponin (hs-cTn)-based approaches. These require fixed assay-specific thresholds and timepoints, without directly integrating clinical information. Using machine-learning techniques including hs-cTn and clinical routine variables, we aimed to build a digital tool to directly estimate the individual probability of MI, allowing for numerous hs-cTn assays. METHODS: In 2,575 patients presenting to the emergency department with suspected MI, two ensembles of machine-learning models using single or serial concentrations of six different hs-cTn assays were derived to estimate the individual MI probability (ARTEMIS model). Discriminative performance of the models was assessed using area under the receiver operating characteristic curve (AUC) and logLoss. Model performance was validated in an external cohort with 1688 patients and tested for global generalizability in 13 international cohorts with 23,411 patients. RESULTS: Eleven routinely available variables including age, sex, cardiovascular risk factors, electrocardiography, and hs-cTn were included in the ARTEMIS models. In the validation and generalization cohorts, excellent discriminative performance was confirmed, superior to hs-cTn only. For the serial hs-cTn measurement model, AUC ranged from 0.92 to 0.98. Good calibration was observed. Using a single hs-cTn measurement, the ARTEMIS model allowed direct rule-out of MI with very high and similar safety but up to tripled efficiency compared to the guideline-recommended strategy. CONCLUSION: We developed and validated diagnostic models to accurately estimate the individual probability of MI, which allow for variable hs-cTn use and flexible timing of resampling. Their digital application may provide rapid, safe and efficient personalized patient care. TRIAL REGISTRATION NUMBERS: Data of following cohorts were used for this project: BACC ( www. CLINICALTRIALS: gov ; NCT02355457), stenoCardia ( www. CLINICALTRIALS: gov ; NCT03227159), ADAPT-BSN ( www.australianclinicaltrials.gov.au ; ACTRN12611001069943), IMPACT ( www.australianclinicaltrials.gov.au , ACTRN12611000206921), ADAPT-RCT ( www.anzctr.org.au ; ANZCTR12610000766011), EDACS-RCT ( www.anzctr.org.au ; ANZCTR12613000745741); DROP-ACS ( https://www.umin.ac.jp , UMIN000030668); High-STEACS ( www. CLINICALTRIALS: gov ; NCT01852123), LUND ( www. CLINICALTRIALS: gov ; NCT05484544), RAPID-CPU ( www. CLINICALTRIALS: gov ; NCT03111862), ROMI ( www. CLINICALTRIALS: gov ; NCT01994577), SAMIE ( https://anzctr.org.au ; ACTRN12621000053820), SEIGE and SAFETY ( www. CLINICALTRIALS: gov ; NCT04772157), STOP-CP ( www. CLINICALTRIALS: gov ; NCT02984436), UTROPIA ( www. CLINICALTRIALS: gov ; NCT02060760).

Evaluating different combination methods to analyse ultrasound and shear wave elastography images automatically through discriminative convolutional neural network in breast cancer imaging.

PURPOSE: Ultrasound (US) and Shear Wave Elastography (SWE) imaging are non-invasive methods used for breast lesion characterization. While US and SWE images provide both morphological information, SWE visualizes in addition the elasticity of tissue. In this study a Discriminative Convolutional Neural Network (DCNN) model is applied to US and SWE images and their combination to classify the breast lesions into malignant or benign cases. Furthermore, it is identified whether analysing only the region of the elastogram or including the surrounding B-mode image gives a superior performance. METHODS: The dataset used in this study consists of 746 images obtained from 207 patients comprising 486 malignant and 260 benign breast lesions. From each image the US and SWE image was extracted, once including only the region of the elastogram and once including also the surrounding B-mode image. These four datasets were applied individually to a DCNN to determine their predictive capability. Each the best US and SWE dataset were used to examine different combination methods with DCNN. The results were compared to the manual assessment by an expert radiologist. RESULTS: The combination of US and SWE images with the surrounding B-mode image using two ensembled DCNN models achieved best results with an accuracy of 93.53 %, sensitivity of 94.42 %, specificity of 90.75 % and area under the curve (AUC) of 96.55 %. CONCLUSION: This study showed that using the whole US and SWE images through DCNN was superior to methods, in which only the region of elastogram was used. Combining breast cancer US and SWE images with two ensembled DCNN models in parallel improved the results. The accuracy, sensitivity and AUC of the best combination method were significantly superior to the results of using a single dataset through DCNN and to the results of the expert radiologist.

Exploring novel algorithms for atrial fibrillation detection by driving graduate level education in medical machine learning.

During the lockdown of universities and the COVID-Pandemic most students were restricted to their homes. Novel and instigating teaching methods were required to improve the learning experience and so recent implementations of the annual PhysioNet/Computing in Cardiology (CinC) Challenges posed as a reference. For over 20 years, the challenges have proven repeatedly to be of immense educational value, besides leading to technological advances for specific problems. In this paper, we report results from the class 'Artificial Intelligence in Medicine Challenge', which was implemented as an online project seminar at Technical University Darmstadt, Germany, and which was heavily inspired by the PhysioNet/CinC Challenge 2017 'AF Classification from a Short Single Lead ECG Recording'. Atrial fibrillation is a common cardiac disease and often remains undetected. Therefore, we selected the two most promising models of the course and give an insight into the Transformer-based DualNet architecture as well as into the CNN-LSTM-based model and finally a detailed analysis for both. In particular, we show the model performance results of our internal scoring process for all submitted models and the near state-of-the-art model performance for the two named models on the official 2017 challenge test set. Several teams were able to achieve F1scores above/close to 90% on a hidden test-set of Holter recordings. We highlight themes commonly observed among participants, and report the results from the self-assessed student evaluation. Finally, the self-assessment of the students reported a notable increase in machine learning knowledge.

Digital Entrepreneurial Nest: Supporting Digitization of Healthcare at National Level in Montenegro.

Health and health systems are not excluded from the influence of digitalization. In Montenegro, regarding the digitization process, when compared to other sectors, the health sector is lagging. In this poster presentation, we present an ambitious Erasmus+ DigN€ST project aimed on modernization of digitalization of healthcare system in Montenegro, as one of priority fields at national level.

Yeast cell segmentation in microstructured environments with deep learning.

Cell segmentation is a major bottleneck in extracting quantitative single-cell information from microscopy data. The challenge is exasperated in the setting of microstructured environments. While deep learning approaches have proven useful for general cell segmentation tasks, previously available segmentation tools for the yeast-microstructure setting rely on traditional machine learning approaches. Here we present convolutional neural networks trained for multiclass segmenting of individual yeast cells and discerning these from cell-similar microstructures. An U-Net based semantic segmentation approach, as well as a direct instance segmentation approach with a Mask R-CNN are demonstrated. We give an overview of the datasets recorded for training, validating and testing the networks, as well as a typical use-case. We showcase the methods' contribution to segmenting yeast in microstructured environments with a typical systems or synthetic biology application. The models achieve robust segmentation results, outperforming the previous state-of-the-art in both accuracy and speed. The combination of fast and accurate segmentation is not only beneficial for a posteriori data processing, it also makes online monitoring of thousands of trapped cells or closed-loop optimal experimental design feasible from an image processing perspective. Code is and data samples are available at https://git.rwth-aachen.de/bcs/projects/tp/multiclass-yeast-seg.

Attred: Attribute Based Resource Discovery for IoT.

While the number of devices connected together as the Internet of Things (IoT) is growing, the demand for an efficient and secure model of resource discovery in IoT is increasing. An efficient resource discovery model distributes the registration and discovery workload among many nodes and allow the resources to be discovered based on their attributes. In most cases this discovery ability should be restricted to a number of clients based on their attributes, otherwise, any client in the system can discover any registered resource. In a binary discovery policy, any client with the shared secret key can discover and decrypt the address data of a registered resource regardless of the attributes of the client. In this paper we propose Attred, a decentralized resource discovery model using the Region-based Distributed Hash Table (RDHT) that allows secure and location-aware discovery of the resources in IoT network. Using Attribute Based Encryption (ABE) and based on predefined discovery policies by the resources, Attred allows clients only by their inherent attributes, to discover the resources in the network. Attred distributes the workload of key generations and resource registration and reduces the risk of central authority management. In addition, some of the heavy computations in our proposed model can be securely distributed using secret sharing that allows a more efficient resource registration, without affecting the required security properties. The performance analysis results showed that the distributed computation can significantly reduce the computation cost while maintaining the functionality. The performance and security analysis results also showed that our model can efficiently provide the required security properties of discovery correctness, soundness, resource privacy and client privacy.

Machine learning-based risk prediction of intrahospital clinical outcomes in patients undergoing TAVI.

BACKGROUND: Currently, patient selection in TAVI is based upon a multidisciplinary heart team assessment of patient comorbidities and surgical risk stratification. In an era of increasing need for precision medicine and quickly expanding TAVI indications, machine learning has shown promise in making accurate predictions of clinical outcomes. This study aims to predict different intrahospital clinical outcomes in patients undergoing TAVI using a machine learning-based approach. The main clinical outcomes include all-cause mortality, stroke, major vascular complications, paravalvular leakage, and new pacemaker implantations. METHODS AND RESULTS: The dataset consists of 451 consecutive patients undergoing elective TAVI between February 2014 and June 2016. The applied machine learning methods were neural networks, support vector machines, and random forests. Their performance was evaluated using five-fold nested cross-validation. Considering all 83 features, the performance of all machine learning models in predicting all-cause intrahospital mortality (AUC 0.94-0.97) was significantly higher than both the STS risk score (AUC 0.64), the STS/ACC TAVR score (AUC 0.65), and all machine learning models using baseline characteristics only (AUC 0.72-0.82). Using an extreme boosting gradient, baseline troponin T was found to be the most important feature among all input variables. Overall, after feature selection, there was a slightly inferior performance. Stroke, major vascular complications, paravalvular leakage, and new pacemaker implantations could not be accurately predicted. CONCLUSIONS: Machine learning has the potential to improve patient selection and risk management of interventional cardiovascular procedures, as it is capable of making superior predictions compared to current logistic risk scores.

Rearrangement of the RNA polymerase subunit H and the lower jaw in archaeal elongation complexes.

The lower jaws of archaeal RNA polymerase and eukaryotic RNA polymerase II include orthologous subunits H and Rpb5, respectively. The tertiary structure of H is very similar to the structure of the C-terminal domain of Rpb5, and both subunits are proximal to downstream DNA in pre-initiation complexes. Analyses of reconstituted euryarchaeal polymerase lacking subunit H revealed that H is important for open complex formation and initial transcription. Eukaryotic Rpb5 rescues activity of the DeltaH enzyme indicating a strong conservation of function for this subunit from archaea to eukaryotes. Photochemical cross-linking in elongation complexes revealed a striking structural rearrangement of RNA polymerase, bringing subunit H near the transcribed DNA strand one helical turn downstream of the active center, in contrast to the positioning observed in preinitiation complexes. The rearrangement of subunits H and A'' suggest a major conformational change in the archaeal RNAP lower jaw upon formation of the elongation complex.

The archaeal RNA polymerase subunit P and the eukaryotic polymerase subunit Rpb12 are interchangeable in vivo and in vitro.

The general subunit of all three eukaryotic RNA polymerases, Rpb12, and subunit P of the archaeal enzyme show sequence similarities in their N-terminal zinc ribbon and some highly conserved residues in the C-terminus. We report here that archaeal subunit P under the control of a strong yeast promoter could complement the lethal phenotype of a RPB12 deletion mutant and that subunit Rpb12 from yeast can functionally replace subunit P during reconstitution of the archaeal RNA polymerase. The DeltaP enzyme is unable to form stable open complexes, but can efficiently extend a dinucleotide on a premelted template or RNA on an elongation scaffold. This suggests that subunit P is directly or indirectly involved in promoter opening. The activity of the DeltaP enzyme can be rescued by the addition of Rpb12 or subunit P to transcription reactions. Mutation of cysteine residues in the zinc ribbon impair the activity of the enzyme in several assays and this mutated form of P is rapidly replaced by wild-type P in transcription reactions. The conserved zinc ribbon in the N-terminus seems to be important for proper interaction of the complete subunit with other RNA polymerase subunits and a 17-amino-acid C-terminal peptide is sufficient to support all basic RNA polymerase functions in vitro.