Quantifying the Suitability of Biosignals Acquired During Surgery for Multimodal Analysis.

Goal: Recently, large datasets of biosignals acquired during surgery became available. As they offer multiple physiological signals measured in parallel, multimodal analysis - which involves their joint analysis - can be conducted and could provide deeper insights than unimodal analysis based on a single signal. However, it is unclear what percentage of intraoperatively acquired data is suitable for multimodal analysis. Due to the large amount of data, manual inspection and labelling into suitable and unsuitable segments are not feasible. Nevertheless, multimodal analysis is performed successfully in sleep studies since many years as their signals have proven suitable. Hence, this study evaluates the suitability to perform multimodal analysis on a surgery dataset (VitalDB) using a multi-center sleep dataset (SIESTA) as reference. Methods: We applied widely known algorithms entitled "signal quality indicators" to the common biosignals in both datasets, namely electrocardiography, electroencephalography, and respiratory signals split in segments of 10 s duration. As there are no multimodal methods available, we used only unimodal signal quality indicators. In case, all three signals were determined as being adequate by the indicators, we assumed that the whole signal segment was suitable for multimodal analysis. Results: 82% of SIESTA and 72% of VitalDB are suitable for multimodal analysis. Unsuitable signal segments exhibit constant or physiologically unreasonable values. Histogram examination indicated similar signal quality distributions between the datasets, albeit with potential statistical biases due to different measurement setups. Conclusions: The majority of data within VitalDB is suitable for multimodal analysis.

Task design for crowdsourced glioma cell annotation in microscopy images.

Crowdsourcing has been used in computational pathology to generate cell and cell nuclei annotations for machine learning. Herein, we broaden its scope to the previously unsolved challenging task of glioma cell detection. This requires multiplexed immunofluorescence microscopy due to diffuse invasiveness and exceptional similarity between glioma cells and reactive astrocytes. In four pilot experiments, we iteratively developed a task design enabling high-quality annotations by crowdworkers on Amazon Mechanical Turk. We applied majority or weighted vote and validated them against ground truth in the final setting. On the base of a YOLO convolutional neural network architecture, we used these consensus labels for training with different image representations regarding colors, intensities, and immmunohistochemical marker combinations. A crowd of 712 workers defined aggregated point annotations in 235 images with an average [Formula: see text] score of 0.627 for majority vote. The networks resulted in acceptable [Formula: see text] scores up to 0.69 for YOLOv8 on average and indicated first evidence for transferability to images lacking tumor markers, especially in IDH-wildtype glioblastoma. Our work confirms feasibility of crowdsourcing to generate labels suitable for training of machine learning tools in the challenging and clinically relevant use case of glioma microenvironment.

Crowdsourcing image segmentation for deep learning: integrated platform for citizen science, paid microtask, and gamification.

OBJECTIVES: Segmentation is crucial in medical imaging. Deep learning based on convolutional neural networks showed promising results. However, the absence of large-scale datasets and a high degree of inter- and intra-observer variations pose a bottleneck. Crowdsourcing might be an alternative, as many non-experts provide references. We aim to compare different types of crowdsourcing for medical image segmentation. METHODS: We develop a crowdsourcing platform that integrates citizen science (incentive: participating in the research), paid microtask (incentive: financial reward), and gamification (incentive: entertainment). For evaluation, we choose the use case of sclera segmentation in fundus images as a proof-of-concept and analyze the accuracy of crowdsourced masks and the generalization of learning models trained with crowdsourced masks. RESULTS: The developed platform is suited for the different types of crowdsourcing and offers an easy and intuitive way to implement crowdsourcing studies. Regarding the proof-of-concept study, citizen science, paid microtask, and gamification yield a median F-score of 82.2, 69.4, and 69.3 % compared to expert-labeled ground truth, respectively. Generating consensus masks improves the gamification masks (78.3 %). Despite the small training data (50 images), deep learning reaches median F-scores of 80.0, 73.5, and 76.5 % for citizen science, paid microtask, and gamification, respectively, indicating sufficient generalizability. CONCLUSIONS: As the platform has proven useful, we aim to make it available as open-source software for other researchers.

Assessment of Driver's Stress using Multimodal Biosignals and Regularized Deep Kernel Learning.

In this work, we classify the stress state of car drivers using multimodal physiological signals and regularized deep kernel learning. Using a driving simulator in a controlled environment, we acquire electrocardiography (ECG), electrodermal activity (EDA), photoplethysmography (PPG), and respiration rate (RESP) from N = 10 healthy drivers in experiments of 25min duration with different stress states (5min resting, 10min driving, 10min driving + answering cognitive questions). We manually remove unusable segments and approximately 4h of data remain. Multimodal time and frequency features are extracted and employed to regularized deep kernel machine learning based on a fusion framework. Task-specific representations of different physiological signals are combined using intermediate fusion. Subsequently, the fused multimodal features are fed a support vector machine (SVM) and a random forest (RF) for stress classification. The experimental results show that the proposed approach can discriminate between stress states. The combination of PPG and ECG using RF as classifier yields the highest F1-score of 0.97 in the test set. PPG only and RF yield a maximum F1-score of 0.90. Furthermore, subject-specific cross-validation improves performance. ECG and PPG signals are reliable in classifying the stress state of a car driver. In summary, the proposed framework could be extended to real-time stress state assessment in driving conditions.

Completing the Cabrera Circle: deriving adaptable leads from ECG limb leads by combining constraints with a correction factor.

Objective.We present a concept for processing 6-lead electrocardiography (ECG) signals which can be applied to various use cases in quantitative electrocardiography.Approach.Our work builds upon the mathematics of the well-known Cabrera sequence which is a re-sorting of the six limb leads (I,II,III,aVR,aVL,aVF) into a clockwise and physiologically-interpretable order. By deriving correction factors for harmonizing lead strengths and choosing an appropriate basis for the leads, we extend this concept towards what we call the 'Cabrera Circle' based on a mathematically sound foundation.Main results.To demonstrate the practical effectiveness and relevance of this concept, we analyze its suitability for deriving interpolated leads between the six limb leads and a 'radial' lead which both can be useful for specific use cases. We focus on the use cases of i) determination of the electrical heart axis by proposing a novel interactive tool for reconstructing the heart's vector loop and ii) improving accuracy in time of automatic R-wave detection and T-wave delineation in 6-lead ECG. For the first use case, we derive an equation which allows projections of the 2-dimensional vector loops to arbitrary angles of the Cabrera Circle. For the second use case, we apply several state-of-the-art algorithms to a freely-available 12-lead dataset (Lobachevsky University Database). Out-of-the-box results show that the derived radial lead outperforms the other limb leads (I,II,III,aVR,aVL,aVF) by improving F1 scores of R-peak and T-peak detection by 0.61 and 2.12, respectively. Results of on- and offset computations are also improved but on a smaller scale.Significance.In summary, the Cabrera Circle offers a methodology that might be useful for quantitative electrocardiography of the 6-lead subsystem-especially in the digital age.

Reusing Biomedical Data as Agreed - Towards Structured Metadata for Data Use Agreements.

INTRODUCTION: With increasing availability of reusable biomedical data - from cohort studies to clinical routine data, data re-users face the problem to manage transferred data according to the heterogeneous data use agreements. While structured metadata is addressed in many contexts including informed consent, contracts are to date still unstructured text documents. In particular within collaborative and active working groups the actual usage agreement's regulations are highly relevant for the daily practice - can I share the data with colleagues from the same university or the same research network, can they be stored on a PHD student's laptop, can I store the data for further approved data usage requests? METHODS: In this article, we inspect and review seven different data usage agreements. We focus on digital data that is copied and transferred to the requester's environment. RESULTS: We identified 24 metadata items in the four main categories data usage, storage, and sharing, as well as publication of results. DISCUSSION: While the topics are largely overlap in the data use agreements, the actual regulations of the topics are diverse. Although we do not explicitly investigate trusted research environments, where data is offered within an analytics platform, we consider them a as subgroup, where most of the practical questions from the data scientist's perspective also arise. CONCLUSION: With a limited set of structured metadata items, data scientists could have information about the data use agreement at hand along with the transferred data in an easily accessible way.

Benchmarking the Impact of Noise on Deep Learning-Based Classification of Atrial Fibrillation in 12-Lead ECG.

Electrocardiography analysis is widely used in various clinical applications and Deep Learning models for classification tasks are currently in the focus of research. Due to their data-driven character, they bear the potential to handle signal noise efficiently, but its influence on the accuracy of these methods is still unclear. Therefore, we benchmark the influence of four types of noise on the accuracy of a Deep Learning-based method for atrial fibrillation detection in 12-lead electrocardiograms. We use a subset of a publicly available dataset (PTB-XL) and use the metadata provided by human experts regarding noise for assigning a signal quality to each electrocardiogram. Furthermore, we compute a quantitative signal-to-noise ratio for each electrocardiogram. We analyze the accuracy of the Deep Learning model with respect to both metrics and observe that the method can robustly identify atrial fibrillation, even in cases signals are labelled by human experts as being noisy on multiple leads. False positive and false negative rates are slightly worse for data being labelled as noisy. Interestingly, data annotated as showing baseline drift noise results in an accuracy very similar to data without. We conclude that the issue of processing noisy electrocardiography data can be addressed successfully by Deep Learning methods that might not need preprocessing as many conventional methods do.

Analysis of a Deep Learning Model for 12-Lead ECG Classification Reveals Learned Features Similar to Diagnostic Criteria.

Despite their remarkable performance, deep neural networks remain unadopted in clinical practice, which is considered to be partially due to their lack of explainability. In this work, we apply explainable attribution methods to a pre-trained deep neural network for abnormality classification in 12-lead electrocardiography to open this "black box" and understand the relationship between model prediction and learned features. We classify data from two public databases (CPSC 2018, PTB-XL) and the attribution methods assign a "relevance score" to each sample of the classified signals. This allows analyzing what the network learned during training, for which we propose quantitative methods: average relevance scores over a) classes, b) leads, and c) average beats. The analyses of relevance scores for atrial fibrillation and left bundle branch block compared to healthy controls show that their mean values a) increase with higher classification probability and correspond to false classifications when around zero, and b) correspond to clinical recommendations regarding which lead to consider. Furthermore, c) visible P-waves and concordant T-waves result in clearly negative relevance scores in atrial fibrillation and left bundle branch block classification, respectively. Results are similar across both databases despite differences in study population and hardware. In summary, our analysis suggests that the DNN learned features similar to cardiology textbook knowledge.

Unobtrusive Heart Rate Monitoring using Near-Infrared Imaging During Driving.

In-vehicle health monitoring allows for continuous vital sign measurement in everyday life. Eventually, this could lead to early detection of cardiovascular diseases. In this work, we propose non-contact heart rate (HR) monitoring utilizing near-infrared (NIR) camera technology. Ten healthy volunteers are monitored in a realistic driving simulator during resting (5 min) and driving (10 min). We synchronously acquire videos using an out-of-the-shelf, low-cost NIR camera and 3-lead electrocardiography (ECG) serves as ground truth. The MediaPipe face detector delivers the region of interest (ROI) and we determine the HR from the peak with maximum amplitude within the power spectrum of skin color changes. We compare video-based with ECG-based HR, resulting in a mean absolute error (MAE) of 7.8 bpm and 13.0 bpm in resting and driving condition, respectively. As we apply only a simple signal processing pipeline without sophisticated filtering, we conclude that NIR camera-based HR measurements enables unobtrusive and non-contact monitoring to a certain extent, but artifacts from subject movement pose a challenge. If these issues can be addressed, continuous vital sign measurement in everyday life could become reality.

Human activity recognition from textile electrocardiograms.

Textile sensors for physiological signals bear the potential of unobtrusive and continuous application in daily life. Recently, textile electrocardiography (ECG) sensors became available which are of particular interest for physical activity monitoring due to the high effect of exercise on the heart rate. In this work, we evaluate the effectiveness of a single-lead ECG signal acquired using a non-medical-grade ECG shirt for human activity recognition (HAR). Healthy volunteers (N=10) wore the shirt during four different activities (sleeping, sitting, walking, running) in an uncontrolled environment and ECG data (256 Hz, 12 Bit) was stored, manually checked, and unusable segments (e.g. no sensor contact) were removed, resulting in a total of 228 hours of recording. Signals were split in short segments of different duration (10, 30, 60s), transformed using the Short-time Fourier Transform (STFT) to a spectrogram image and fed into a state-of-the-art convolutional neural network (CNN). The best configuration results in an F'l-Score of 73% and an accuracy of 77% on the test set. Results with leave-one-subject-out cross-validation show F'l-Scores ranging from 41 % to 80%. Thus, a single-lead, wearable-generated ECG has an informative value for HAR to a certain extent. In future work, we aim at using more sensors of the smart shirt and sensor fusion.

Continuous Monitoring of Vital Signs Using Cameras: A Systematic Review.

In recent years, noncontact measurements of vital signs using cameras received a great amount of interest. However, some questions are unanswered: (i) Which vital sign is monitored using what type of camera? (ii) What is the performance and which factors affect it? (iii) Which health issues are addressed by camera-based techniques? Following the preferred reporting items for systematic reviews and meta-analyses (PRISMA) statement, we conduct a systematic review of continuous camera-based vital sign monitoring using Scopus, PubMed, and the Association for Computing Machinery (ACM) databases. We consider articles that were published between January 2018 and April 2021 in the English language. We include five vital signs: heart rate (HR), respiratory rate (RR), blood pressure (BP), body skin temperature (BST), and oxygen saturation (SpO2). In total, we retrieve 905 articles and screened them regarding title, abstract, and full text. One hundred and four articles remained: 60, 20, 6, 2, and 1 of the articles focus on HR, RR, BP, BST, and SpO2, respectively, and 15 on multiple vital signs. HR and RR can be measured using red, green, and blue (RGB) and near-infrared (NIR) as well as far-infrared (FIR) cameras. So far, BP and SpO2 are monitored with RGB cameras only, whereas BST is derived from FIR cameras only. Under ideal conditions, the root mean squared error is around 2.60 bpm, 2.22 cpm, 6.91 mm Hg, 4.88 mm Hg, and 0.86 °C for HR, RR, systolic BP, diastolic BP, and BST, respectively. The estimated error for SpO2 is less than 1%, but it increases with movements of the subject and the camera-subject distance. Camera-based remote monitoring mainly explores intensive care, post-anaesthesia care, and sleep monitoring, but also explores special diseases such as heart failure. The monitored targets are newborn and pediatric patients, geriatric patients, athletes (e.g., exercising, cycling), and vehicle drivers. Camera-based techniques monitor HR, RR, and BST in static conditions within acceptable ranges for certain applications. The research gaps are large and heterogeneous populations, real-time scenarios, moving subjects, and accuracy of BP and SpO2 monitoring.

Toward a digital decision- and workflow-support system for initiation and control of long-term non-invasive ventilation in stable hypercapnic COPD patients.

Introduction: Due to an increasing demand for the initiation and control of non-invasive ventilation (NIV), digital algorithms are suggested to support therapeutic decisions and workflows in an ambulatory setting. The DIGIVENT project established and implemented such algorithms for patients with chronic hypercapnic respiratory failure due to chronic obstructive pulmonary disease (COPD) by a predefined process. Methods: Based on long-term clinical experience and guideline recommendations as provided by the German Respiratory Society, detailed graphical descriptions of how to perform NIV in stable COPD patients were created. Subsequently, these clinical workflows were implemented in the Business Process Model and Notation (BPMN) as one tool to formalize these workflows serving as input for an executable digital implementation. Results: We succeeded in creating an executable digital implementation that reflects clinical decision-making and workflows in digital algorithms. Furthermore, we built a user-friendly graphical interface that allows easy interaction with the DIGIVENT support algorithms. Conclusion: The DIGIVENT project established digital treatment algorithms and implemented a decision- and workflow-support system for NIV whose validation in a clinical cohort is planned.

SHACL-Based Report Quality Evaluation for Health IT-Induced Medication Errors.

Patient safety event (PSE) reports are an important source of information for analyzing risks in healthcare processes. However, the reports' quality is often low due to missing or imprecise information. We work towards an automatic analysis of reports and quality evaluation. To leverage a suitable data representation of health IT-induced medication error reports, we apply the Shapes Constraint Language (SHACL). We define an ontology representing these reports and construct a corresponding SHACL graph. Three authors manually annotate and transform 20 textual reports to the SHACL representation. Furthermore, we use this representation to compute a quality score for each report. The results indicate the suitability of SHACL as a representation of health IT-induced medication error reports, which paves a path of automatically extracting information from PSE reports using text mining and transform them to SHACL for quality evaluation.

Integrated Sensing Devices for Disease Prevention and Health Alerts in Smart Homes.

The rapid development of elderly population is changing demographics in Europe and North America and imposes barriers to healthcare systems that may reduce the quality of service. Telemedicine is a potential solution supporting the real-time and remote monitoring of subjects as well as bidirectional communication with medical personnel for care delivery at the point of perception. Smart homes are private spaces where young or elderly, healthy or diseased-suffering, or disabled individuals spend the majority of their time. Hence, turning smart homes into diagnostic spaces for continuous, real-time, and unobtrusive health monitoring allows disease prediction and prevention before the subject perceives any symptoms. According to the World Health Organization, health, well-being, and quality of life assessment require the monitoring of interwoven domains such as environmental, behavioral, physiological, and psychological. In this work, we give an overview on sensing devices and technologies utilized in smart homes, which can turn the home into a diagnostic space. We consider the integration of sensing devices from all four WHO domains with respect to raw and processed data, transmission, and synchronization. We apply the bus-based scalable intelligent system to construct a hybrid topology for hierarchical multi-layer data fusion. This enables event detection and alerting for short-time as well as prediction and prevention for long-time monitoring.

Sensor Fusion for Robust Heartbeat Detection during Driving.

Private spaces like apartments and vehicles are not yet fully exploited for health monitoring, which includes continuous measurement of biosignals. This work proposes sensor fusion for robust heartbeat detection in the noisy and dynamic driving environment. We use four sensors: electrocardiography (ECG), ballistocardiography (BCG), photoplethysmography (PPG), and image-based PPG (iPPG). As ground truth, we record a 3-lead ECG with wet electrodes attached to the chest. Twelve healthy volunteers are monitored in rest and during driving, each for 11 min. We propose sensor fusion using convolutional neural networks to detect the sensor combination delivering the most accurate heart rate measurement. For rest, we achieve scores of 95.16% (BCG + iPPG), 96.08% (ECG + iPPG), 96.35% (ECG + BCG), 96.53% (ECG + PPG), 96.58% (PPG + iPPG), and 97.15% (BCG + PPG). In motion, the highest scores are 92.46% (BCG + iPPG, PPG + iPPG, ECG + iPPG), 92.83% (ECG + PPG), 93.03% (BCG + PPG), and 93.08% (ECG + BCG). Fusing all four signals with the best fusion approach results in scores of 97.24% (rest) and 94.38% (motion). We conclude that sensor fusion allows robust heartbeat measurement of car drivers to support continuous and unobtrusive health monitoring for early disease detection.

Edge computing in 5G cellular networks for real-time analysis of electrocardiography recorded with wearable textile sensors.

Fifth-generation (5G) cellular networks promise higher data rates, lower latency, and large numbers of inter-connected devices. Thereby, 5G will provide important steps towards unlocking the full potential of the Internet of Things (IoT). In this work, we propose a lightweight IoT platform for continuous vital sign analysis. Electrocardiography (ECG) is acquired via textile sensors and continuously sent from a smartphone to an edge device using cellular networks. The edge device applies a state-of-the art deep learning model for providing a binary end-to-end classification if a myocardial infarction is at hand. Using this infrastructure, experiments with four volunteers were conducted. We compare 3rd, 4th-, and 5th-generation cellular networks (release 15) with respect to transmission latency, data corruption, and duration of machine learning inference. The best performance is achieved using 5G showing an average transmission latency of 110ms and data corruption in 0.07% of ECG samples. Deep learning inference took approximately 170ms. In conclusion, 5G cellular networks in combination with edge devices are a suitable infrastructure for continuous vital sign analysis using deep learning models. Future 5G releases will introduce multi-access edge computing (MEC) as a paradigm for bringing edge devices nearer to mobile clients. This will decrease transmission latency and eventually enable automatic emergency alerting in near real-time.

Feasibility Analysis of Fifth-generation (5G) Mobile Networks for Transmission of Medical Imaging Data.

Next to higher data rates and lower latency, the upcoming fifth-generation mobile network standard will introduce a new service ecosystem. Concepts such as multi-access edge computing or network slicing will enable tailoring service level requirements to specific use-cases. In medical imaging, researchers and clinicians are currently working towards higher portability of scanners. This includes i) small scanners to be wheeled inside the hospital to the bedside and ii) conventional scanners provided via trucks to remote areas. Both use-cases introduce the need for mobile networks adhering to high safety standards and providing high data rates. These requirements could be met by fifth-generation mobile networks. In this work, we analyze the feasibility of transferring medical imaging data using the current state of development of fifth-generation mobile networks (3GPP Release 15). We demonstrate the potential of reaching 100Mbit/s upload rates using already available consumer-grade hardware. Furthermore, we show an effective average data throughput of 50Mbit/s when transferring medical images using out-of-the-box open-source software based on the Digital Imaging and Communications in Medicine (DICOM) standard. During transmissions, we sample the radio frequency bands to analyse the characteristics of the mobile radio network. Additionally, we discuss the potential of new features such as network slicing that will be introduced in forthcoming releases.

Automatic Information Exchange in the Early Rescue Chain Using the International Standard Accident Number (ISAN).

Thus far, emergency calls are answered by human operators who interview the calling person in order to obtain all relevant information. In the near future-based on the Internet of (Medical) Things (IoT, IoMT)-accidents, emergencies, or adverse health events will be reported automatically by smart homes, smart vehicles, or smart wearables, without any human in the loop. Several parties are involved in this communication: the alerting system, the rescue service (responding system), and the emergency department in the hospital (curing system). In many countries, these parties use isolated information and communication technology (ICT) systems. Previously, the International Standard Accident Number (ISAN) has been proposed to securely link the data in these systems. In this work, we propose an ISAN-based communication platform that allows semantically interoperable information exchange. Our aims are threefold: (i) to enable data exchange between the isolated systems, (ii) to avoid data misinterpretation, and (iii) to integrate additional data sources. The suggested platform is composed of an alerting, responding, and curing system manager, a workflow manager, and a communication manager. First, the ICT systems of all parties in the early rescue chain register with their according system manager, which tracks the keep-alive. In case of emergency, the alerting system sends an ISAN to the platform. The responsible rescue services and hospitals are determined and interconnected for platform-based communication. Next to the conceptual design of the platform, we evaluate a proof-of-concept implementation according to (1) the registration, (2) channel establishment, (3) data encryption, (4) event alert, and (5) information exchange. Our concept meets the requirements for scalability, error handling, and information security. In the future, it will be used to implement a virtual accident registry.

Registered report protocol: Developing an artifact index for capacitive electrocardiography signals acquired with an armchair.

Continuous monitoring of an electrocardiogram (ECG) in private diagnostic spaces such as vehicles or apartments allows early detection of cardiovascular diseases. We will use an armchair with integrated capacitive electrodes to record the capacitive electrocardiogram (cECG) during everyday activities. However, movements and other artifacts affect the signal quality. Therefore, an artifact index is needed to detect artifacts and classify the cECG. The unavailability of cECG data and reliable ground truth information requires new recordings to develop an artifact index. This study is designed to test the hypothesis: an artifact index can be devised, which intends to estimate the signal quality of segments and classify signals. In a single-arm study with 44 subjects, we will record two activities of 11-minute duration: reading and watching television. During recording, we will capture cECG, ECG, and oxygen saturation (SpO2) with time synchronization as well as keypoint-based movement indicators obtained from a video camera. SpO2 provides additional information on the subject's health status. The keypoint-based movements indicate artifacts in the cECG. We will combine all ground truth data to evaluate the index. In the future, we aim at using the artifact index to exclude cECG segments with artifacts from further analysis. This will improve cECG technology for the measurement of cardiovascular parameters.

Automatic Detection of Metadata Errors in a Registry of Clinical Studies Using Shapes Constraint Language (SHACL) Graphs.

Registries of clinical studies such as ClinicalTrials.gov are an important source of information. However, the process of manually entering metadata is prone to errors which impedes their use and thereby the overall usefulness of the registry. In this work, we propose a generic approach towards detection of errors in the metadata by using the Shapes Constraint Language for defining rule templates covering constraints regarding value type and cardinality. We developed a Python 3 algorithm for the automatic validation of 15 rule instances applied to the whole ClinicalTrials.gov database (355,862 studies; 27th October 2020) resulting in more than 5 million metadata verifications. Our results show a large number of errors in different metadata fields, such as i) missing values, ii) values not coming from a predefined set or iii) wrong cardinalities, can be detected using this approach. Since 2015 approximately 5% of all studies contain one or more errors. In the future, we will apply this technique to other registries and develop more complex rules by focusing on the semantics of the metadata. This could render the possibility of automatically correcting entries, increasing the value of registries of clinical studies.