Simplifying Multimodal Clinical Research Data Management: Introducing an Integrated and User-friendly Database Concept.

BACKGROUND: Clinical research, particularly in scientific data, grapples with the efficient management of multimodal and longitudinal clinical data. Especially in neuroscience, the volume of heterogeneous longitudinal data challenges researchers. While current research data management systems offer rich functionality, they suffer from architectural complexity that makes them difficult to install and maintain and require extensive user training. OBJECTIVES: The focus is the development and presentation of a data management approach specifically tailored for clinical researchers involved in active patient care, especially in the neuroscientific environment of German university hospitals. Our design considers the implementation of FAIR (Findable, Accessible, Interoperable, and Reusable) principles and the secure handling of sensitive data in compliance with the General Data Protection Regulation. METHODS: We introduce a streamlined database concept, featuring an intuitive graphical interface built on Hypertext Markup Language revision 5 (HTML5)/Cascading Style Sheets (CSS) technology. The system can be effortlessly deployed within local networks, that is, in Microsoft Windows 10 environments. Our design incorporates FAIR principles for effective data management. Moreover, we have streamlined data interchange through established standards like HL7 Clinical Document Architecture (CDA). To ensure data integrity, we have integrated real-time validation mechanisms that cover data type, plausibility, and Clinical Quality Language logic during data import and entry. RESULTS: We have developed and evaluated our concept with clinicians using a sample dataset of subjects who visited our memory clinic over a 3-year period and collected several multimodal clinical parameters. A notable advantage is the unified data matrix, which simplifies data aggregation, anonymization, and export. THIS STREAMLINES DATA EXCHANGE AND ENHANCES DATABASE INTEGRATION WITH PLATFORMS LIKE KONSTANZ INFORMATION MINER (KNIME): . CONCLUSION: Our approach offers a significant advancement for capturing and managing clinical research data, specifically tailored for small-scale initiatives operating within limited information technology (IT) infrastructures. It is designed for immediate, hassle-free deployment by clinicians and researchers.The database template and precompiled versions of the user interface are available at: https://github.com/stebro01/research_database_sqlite_i2b2.git.

TrustNShare: Development of a Blockchain-Based Data Trust Model for Secure and Controlled Health Data Sharing Grounded on Empirical Research.

Ensuring data quality and protecting data are key requirements when working with health-related data. Re-identification risks of feature-rich data sets have led to the dissolution of the hard boundary between data protected by data protection laws (GDPR) and anonymized data sets. To solve this problem, the TrustNShare project is creating a transparent data trust that acts as a trusted intermediary. This allows for secure and controlled data exchange, while offering flexible datasharing options, considering trustworthiness, risk tolerance, and healthcare interoperability. Empirical studies and participatory research will be conducted to develop a trustworthy and effective data trust model.

Medical multivariate time series imputation and forecasting based on a recurrent conditional Wasserstein GAN and attention.

OBJECTIVE: In the fields of medical care and research as well as hospital management, time series are an important part of the overall data basis. To ensure high quality standards and enable suitable decisions, tools for precise and generic imputations and forecasts that integrate the temporal dynamics are of great importance. Since forecasting and imputation tasks involve an inherent uncertainty, the focus of our work lay on a probabilistic multivariate generative approach that samples infillings or forecasts from an analysable distribution rather than producing deterministic results. MATERIALS AND METHODS: For this task, we developed a system based on generative adversarial networks that consist of recurrent encoders and decoders with attention mechanisms and can learn the distribution of intervals from multivariate time series conditioned on the periods before and, if available, periods after the values that are to be predicted. For training, validation and testing, a data set of jointly measured blood pressure series (ABP) and electrocardiograms (ECG) (length: 1,250=ˆ10s) was generated. For the imputation tasks, one interval of fixed length was masked randomly and independently in both channels of every sample. For the forecasting task, all masks were positioned at the end. RESULTS: The models were trained on around 65,000 bivariate samples and tested against 14,000 series of different persons. For the evaluation, 50 samples were produced for every masked interval to estimate the range of the generated infillings or forecasts. The element-wise arithmetic average of these samples served as an estimator for the mean of the learned conditional distribution. The approach showed better results than a state-of-the-art probabilistic multivariate forecasting mechanism based on Gaussian copula transformation and recurrent neural networks. On the imputation task, the proposed method reached a mean squared error (MSE) of 0.057 on the ECG channel and an MSE of 28.30 on the ABP channel, while the baseline approach reached MSEs of 0.095 (ECG) and 229.1 (ABP). Moreover, on the forecasting task, the presented system achieved MSEs of 0.069 (ECG) and 33.73 (ABP), outperforming the recurrent copula approach, which reached MSEs of 0.082 (ECG) and 196.53 (ABP). CONCLUSION: The presented generative probabilistic system for the imputation and forecasting of (medical) time series features the flexibility to handle masks of different sizes and positions, the ability to quantify uncertainty due to its probabilistic predictions, and an adjustable trade-off between the goals of minimising errors in individual predictions and minimising the distance between the learned and the real conditional distribution of the infillings or forecasts.

Generative adversarial networks for biomedical time series forecasting and imputation.

In the present systematic review we identified and summarised current research activities in the field of time series forecasting and imputation with the help of generative adversarial networks (GANs). We differentiate between imputation which describes the filling of missing values at intermediate steps and forecasting defining the prediction of future values. Especially the utilisation of such methods in the biomedical domain was to be investigated. To this end, 1057 publications were identified with the help of PubMed, Web of Science and Scopus. All studies that describe the use of GANs for the imputation/forecasting of time series were included irrespective of the application domain. Finally, 33 records were identified as eligible and grouped according to the topologies, losses, inputs and outputs of the presented GANs. In combination with a summary of all described application domains, this grouping served as a basis for analysing the peculiarities of the method in the biomedical context. Due to the broad spectrum of biomedical research, nearly all recognised methodologies are also applied in this domain. We could not identify any approach that proved itself superior in the biomedical area. Although GANs were initially designed to work in the image domain, many publications show that they are capable of imputing/forecasting non-visual time series.

Using machine learning to estimate the calendar age based on autonomic cardiovascular function.

Introduction: Aging is accompanied by physiological changes in cardiovascular regulation that can be evaluated using a variety of metrics. In this study, we employ machine learning on autonomic cardiovascular indices in order to estimate participants' age. Methods: We analyzed a database including resting state electrocardiogram and continuous blood pressure recordings of healthy volunteers. A total of 884 data sets met the inclusion criteria. Data of 72 other participants with an BMI indicating obesity (>30 kg/m²) were withheld as an evaluation sample. For all participants, 29 different cardiovascular indices were calculated including heart rate variability, blood pressure variability, baroreflex function, pulse wave dynamics, and QT interval characteristics. Based on cardiovascular indices, sex and device, four different approaches were applied in order to estimate the calendar age of healthy subjects, i.e., relevance vector regression (RVR), Gaussian process regression (GPR), support vector regression (SVR), and linear regression (LR). To estimate age in the obese group, we drew normal-weight controls from the large sample to build a training set and a validation set that had an age distribution similar to the obesity test sample. Results: In a five-fold cross validation scheme, we found the GPR model to be suited best to estimate calendar age, with a correlation of r=0.81 and a mean absolute error of MAE=5.6 years. In men, the error (MAE=5.4 years) seemed to be lower than that in women (MAE=6.0 years). In comparison to normal-weight subjects, GPR and SVR significantly overestimated the age of obese participants compared with controls. The highest age gap indicated advanced cardiovascular aging by 5.7 years in obese participants. Discussion: In conclusion, machine learning can be used to estimate age on cardiovascular function in a healthy population when considering previous models of biological aging. The estimated age might serve as a comprehensive and readily interpretable marker of cardiovascular function. Whether it is a useful risk predictor should be investigated in future studies.

GAN-Based Prediction of Time Series.

The study aims at generating initial and directional insights in the applicability of conditional recurrent generative adversarial nets for the imputation and forecasting of medical time series data. Our experiment with blood pressure series showed that a generative recurrent autoencoder exhibits significant individual learning progress but needs further tuning to benefit from joint training.

Semantic Anomaly Detection in Medical Time Series.

The main goal of this project was to define and evaluate a new unsupervised deep learning approach that can differentiate between normal and anomalous intervals of signals like the electrical activity of the heart (ECG). Denoising autoencoders based on recurrent neural networks with gated recurrent units were used for the semantic encoding of such time frames. A subsequent cluster analysis conducted in the code space served as the decision mechanism labelling samples as anomalies or normal intervals, respectively. The cluster ensemble method called cluster-based similarity partitioning proved itself well suited for this task when used in combination with density-based spatial clustering of applications with noise. The best performing system reached an adjusted Rand index of 0.11 on real-world ECG signals labelled by medical experts. This corresponds to a precision and recall regarding the detection task of around 0.72. The new general approach outperformed several state-of-the-art outlier recognition methods and can be applied to all kinds of (medical) time series data. It can serve as a basis for more specific detectors that work in an unsupervised fashion or that are partially guided by medical experts.

Privacy-Preserving Deep Learning for the Detection of Protected Health Information in Real-World Data: Comparative Evaluation.

BACKGROUND: Collaborative privacy-preserving training methods allow for the integration of locally stored private data sets into machine learning approaches while ensuring confidentiality and nondisclosure. OBJECTIVE: In this work we assess the performance of a state-of-the-art neural network approach for the detection of protected health information in texts trained in a collaborative privacy-preserving way. METHODS: The training adopts distributed selective stochastic gradient descent (ie, it works by exchanging local learning results achieved on private data sets). Five networks were trained on separated real-world clinical data sets by using the privacy-protecting protocol. In total, the data sets contain 1304 real longitudinal patient records for 296 patients. RESULTS: These networks reached a mean F1 value of 0.955. The gold standard centralized training that is based on the union of all sets and does not take data security into consideration reaches a final value of 0.962. CONCLUSIONS: Using real-world clinical data, our study shows that detection of protected health information can be secured by collaborative privacy-preserving training. In general, the approach shows the feasibility of deep learning on distributed and confidential clinical data while ensuring data protection.

A Visualisation and Extraction Tool for Time Series in the MIMIC III Database.

We developed a tool based on the KNIME analytics platform for the extraction and visualisation of medical time series stored in the Medical Information Mart for Intensive Care III (MIMIC III) and the related MIMIC-III Waveform Database Matched Subset. The large number of data points and the free accessibility make these data sets an attractive source for data-driven projects in the medical domain. The problem that we tackled with our tool was the lack of an easy and extensible way of selecting, reading, and visualising stored time series. Especially the fact that medical data science projects are often conducted by interdisciplinary teams called for a software solution that can be utilised by medical practitioners without programming experiences and that still offers enough flexibility for data scientists.

Word Sense Disambiguation of Medical Terms via Recurrent Convolutional Neural Networks.

BACKGROUND: Tagging text data with codes representing biomedical concepts plays an important role in medical data management and analysis. A problem occurs if there are ambiguous words linked to several concepts. OBJECTIVES AND METHODS: This study aims at investigating word sense disambiguation based on word embedding and recurrent convolutional neural networks. The study focuses on terms mapped to multiple concepts of the Unified Medical Language System (UMLS). RESULTS: We created 20 text processing pipelines trained on a subset of the MeSH Word Sense Disambiguation (MSH WSD) data set, each pipeline disambiguating the sense of one word. The pipelines were then tested on a disjoint subset of MSH WSD data. Most pipelines achieved good or even excellent results (70% of the pipelines achieved at least 90% accuracy, 40% achieved at least 98% accuracy). One poor-performing outlier was detected. CONCLUSION: The proposed approach can serve as a basis for an up-scaled system combining pipelines for many ambiguous words. The methods used here recently proved very successful in other fields of text understanding and can be expected to scale-up with improved availability of training data.