Development and validation of an open-source pipeline for automatic population of case report forms from electronic health records: a pediatric multi-center prospective study.

BACKGROUND: Clinical trials and registry studies are essential for advancing research and developing novel treatments. However, these studies rely on manual entry of thousands of variables for each patient. Repurposing real-world data can significantly simplify the data collection, reduce transcription errors, and make the data entry process more efficient, consistent, and cost-effective. METHODS: We developed an open-source computational pipeline to collect laboratory and medication information from the electronic health record (EHR) data and populate case report forms. The pipeline was developed and validated with data from two independent pediatric hospitals in the US as part of the Long-terM OUtcomes after Multisystem Inflammatory Syndrome In Children (MUSIC) study. Our pipeline allowed the completion of two of the most time-consuming forms. We compared automatically extracted results with manually entered values in one hospital and applied the pipeline to a second hospital, where the output served as the primary data source for case report forms. FINDINGS: We extracted and populated 51,845 laboratory and 4913 medication values for 159 patients in two hospitals participating in a prospective pediatric study. We evaluated pipeline performance against data for 104 patients manually entered by clinicians in one of the hospitals. The highest concordance was found during patient hospitalization, with 91.59% of the automatically extracted laboratory and medication values corresponding with the manually entered values. In addition to the successfully populated values, we identified an additional 13,396 laboratory and 567 medication values of interest for the study. INTERPRETATION: The automatic data entry of laboratory and medication values during admission is feasible and has a high concordance with the manually entered data. By implementing this proof of concept, we demonstrate the quality of automatic data extraction and highlight the potential of secondary use of EHR data to advance medical science by improving data entry efficiency and expediting clinical research. FUNDING: NIH Grant 1OT3HL147154-01, U24HL135691, UG1HL135685.

Medication Use in the Management of Comorbidities Among Individuals With Autism Spectrum Disorder From a Large Nationwide Insurance Database.

Importance: Although there is no pharmacological treatment for autism spectrum disorder (ASD) itself, behavioral and pharmacological therapies have been used to address its symptoms and common comorbidities. A better understanding of the medications used to manage comorbid conditions in this growing population is critical; however, most previous efforts have been limited in size, duration, and lack of broad representation. Objective: To use a nationally representative database to uncover trends in the prevalence of co-occurring conditions and medication use in the management of symptoms and comorbidities over time among US individuals with ASD. Design, Setting, and Participants: This retrospective, population-based cohort study mined a nationwide, managed health plan claims database containing more than 86 million unique members. Data from January 1, 2014, to December 31, 2019, were used to analyze prescription frequency and diagnoses of comorbidities. A total of 26 722 individuals with ASD who had been prescribed at least 1 of 24 medications most commonly prescribed to treat ASD symptoms or comorbidities during the 6-year study period were included in the analysis. Exposures: Diagnosis codes for ASD based on International Classification of Diseases, Ninth Revision, and International Statistical Classification of Diseases and Related Health Problems, Tenth Revision. Main Outcomes and Measures: Quantitative estimates of prescription frequency for the 24 most commonly prescribed medications among the study cohort and the most common comorbidities associated with each medication in this population. Results: Among the 26 722 individuals with ASD included in the analysis (77.7% male; mean [SD] age, 14.45 [9.40] years), polypharmacy was common, ranging from 28.6% to 31.5%. Individuals' prescription regimens changed frequently within medication classes, rather than between classes. The prescription frequency of a specific medication varied considerably, depending on the coexisting diagnosis of a given comorbidity. Of the 24 medications assessed, 15 were associated with at least a 15% prevalence of a mood disorder, and 11 were associated with at least a 15% prevalence of attention-deficit/hyperactivity disorder. For patients taking antipsychotics, the 2 most common comorbidities were combined type attention-deficit/hyperactivity disorder (11.6%-17.8%) and anxiety disorder (13.1%-30.1%). Conclusions and Relevance: This study demonstrated considerable variability and transiency in the use of prescription medications by US clinicians to manage symptoms and comorbidities associated with ASD. These findings support the importance of early and ongoing surveillance of patients with ASD and co-occurring conditions and offer clinicians insight on the targeted therapies most commonly used to manage co-occurring conditions. Future research and policy efforts are critical to assess the extent to which pharmacological management of comorbidities affects quality of life and functioning in patients with ASD while continuing to optimize clinical guidelines, to ensure effective care for this growing population.

ECG Language processing (ELP): A new technique to analyze ECG signals.

BACKGROUND: A language is constructed of a finite/infinite set of sentences composing of words. Similar to natural languages, the Electrocardiogram (ECG) signal, the most common noninvasive tool to study the functionality of the heart and diagnose several abnormal arrhythmias, is made up of sequences of three or four distinct waves, including the P-wave, QRS complex, T-wave, and U-wave. An ECG signal may contain several different varieties of each wave (e.g., the QRS complex can have various appearances). For this reason, the ECG signal is a sequence of heartbeats similar to sentences in natural languages) and each heartbeat is composed of a set of waves (similar to words in a sentence) of different morphologies. METHODS: Analogous to natural language processing (NLP), which is used to help computers understand and interpret the human's natural language, it is possible to develop methods inspired by NLP to aid computers to gain a deeper understanding of Electrocardiogram signals. In this work, our goal is to propose a novel ECG analysis technique, ECG language processing (ELP), focusing on empowering computers to understand ECG signals in a way physicians do. RESULTS: We evaluated the proposed approach on two tasks, including the classification of heartbeats and the detection of atrial fibrillation in the ECG signals. Overall, our technique resulted in better performance or comparable performance with smaller neural networks compared to other deep neural networks and existing algorithms. CONCLUSION: Experimental results on three databases (i.e., PhysioNet's MIT-BIH, MIT-BIH AFIB, and PhysioNet Challenge 2017 AFIB Dataset databases) reveal that the proposed approach as a general idea can be applied to a variety of biomedical applications and can achieve remarkable performance.

HAN-ECG: An interpretable atrial fibrillation detection model using hierarchical attention networks.

Atrial fibrillation (AF) is one of the most prevalent cardiac arrhythmias that affects the lives of many people around the world and is associated with a five-fold increased risk of stroke and mortality. Like other problems in the healthcare domain, artificial intelligence (AI)-based models have been used to detect AF from patients' ECG signals. The cardiologist level performance in detecting this arrhythmia is often achieved by deep learning-based methods, however, they suffer from the lack of interpretability. In other words, these approaches are unable to explain the reasons behind their decisions. The lack of interpretability is a common challenge toward a wide application of machine learning (ML)-based approaches in the healthcare which limits the trust of clinicians in such methods. To address this challenge, we propose HAN-ECG, an interpretable bidirectional-recurrent-neural-network-based approach for the AF detection task. The HAN-ECG employs three attention mechanism levels to provide a multi-resolution analysis of the patterns in ECG leading to AF. The detected patterns by this hierarchical attention model facilitate the interpretation of the neural network decision process in identifying the patterns in the signal which contributed the most to the final detection. Experimental results on two AF databases demonstrate that our proposed model performs better than the existing algorithms. Visualization of these attention layers illustrates that our proposed model decides upon the important waves and heartbeats which are clinically meaningful in the detection task (e.g., absence of P-waves, and irregular R-R intervals for the AF detection task).

Single-modal and multi-modal false arrhythmia alarm reduction using attention-based convolutional and recurrent neural networks.

This study proposes a deep learning model that effectively suppresses the false alarms in the intensive care units (ICUs) without ignoring the true alarms using single- and multi- modal biosignals. Most of the current work in the literature are either rule-based methods, requiring prior knowledge of arrhythmia analysis to build rules, or classical machine learning approaches, depending on hand-engineered features. In this work, we apply convolutional neural networks to automatically extract time-invariant features, an attention mechanism to put more emphasis on the important regions of the segmented input signal(s) that are more likely to contribute to an alarm, and long short-term memory units to capture the temporal information presented in the signal segments. We trained our method efficiently using a two-step training algorithm (i.e., pre-training and fine-tuning the proposed network) on the dataset provided by the PhysioNet computing in cardiology challenge 2015. The evaluation results demonstrate that the proposed method obtains better results compared to other existing algorithms for the false alarm reduction task in ICUs. The proposed method achieves a sensitivity of 93.88% and a specificity of 92.05% for the alarm classification, considering three different signals. In addition, our experiments for 5 separate alarm types leads significant results, where we just consider a single-lead ECG (e.g., a sensitivity of 90.71%, a specificity of 88.30%, an AUC of 89.51 for alarm type of Ventricular Tachycardia arrhythmia).

SleepEEGNet: Automated sleep stage scoring with sequence to sequence deep learning approach.

Electroencephalogram (EEG) is a common base signal used to monitor brain activities and diagnose sleep disorders. Manual sleep stage scoring is a time-consuming task for sleep experts and is limited by inter-rater reliability. In this paper, we propose an automatic sleep stage annotation method called SleepEEGNet using a single-channel EEG signal. The SleepEEGNet is composed of deep convolutional neural networks (CNNs) to extract time-invariant features, frequency information, and a sequence to sequence model to capture the complex and long short-term context dependencies between sleep epochs and scores. In addition, to reduce the effect of the class imbalance problem presented in the available sleep datasets, we applied novel loss functions to have an equal misclassified error for each sleep stage while training the network. We evaluated the performance of the proposed method on different single-EEG channels (i.e., Fpz-Cz and Pz-Oz EEG channels) from the Physionet Sleep-EDF datasets published in 2013 and 2018. The evaluation results demonstrate that the proposed method achieved the best annotation performance compared to current literature, with an overall accuracy of 84.26%, a macro F1-score of 79.66% and κ = 0.79. Our developed model can be applied to other sleep EEG signals and aid the sleep specialists to arrive at an accurate diagnosis. The source code is available at https://github.com/SajadMo/SleepEEGNet.

An Unsupervised Feature Learning Approach to Reduce False Alarm Rate in ICUs.

The high rate of false alarms in intensive care units (ICUs) is one of the top challenges of using medical technology in hospitals. These false alarms are often caused by patients' movements, detachment of monitoring sensors, or different sources of noise and interference that impact the collected signals from different monitoring devices. In this paper, we propose a novel set of high-level features based on unsupervised feature learning technique in order to effectively capture the characteristics of different arrhythmia in electrocardiogram (ECG) signal and differentiate them from irregularity in signals due to different sources of signal disturbances. This unsupervised feature learning technique, first extracts a set of low-level features from all existing heart cycles of a patient, and then clusters these segments for each individual patient to provide a set of prominent high-level features. The objective of the clustering phase is to enable the classification method to differentiate between the high-level features extracted from normal and abnormal cycles (i.e., either due to arrhythmia or different sources of distortions in signal) in order to put more attention to the features extracted from abnormal portion of the signal that contribute to the alarm.

Inter- and intra-patient ECG heartbeat classification for arrhythmia detection: A sequence to sequence deep learning approach.

Electrocardiogram (ECG) signal is a common and powerful tool to study heart function and diagnose several abnormal arrhythmias. While there have been remarkable improvements in cardiac arrhythmia classification methods, they still cannot offer acceptable performance in detecting different heart conditions, especially when dealing with imbalanced datasets. In this paper, we propose a solution to address this limitation of current classification approaches by developing an automatic heartbeat classification method using deep convolutional neural networks and sequence to sequence models. We evaluated the proposed method on the MIT-BIH arrhythmia database, considering the intra-patient and inter-patient paradigms, and the AAMI EC57 standard. The evaluation results for both paradigms show that our method achieves the best performance in the literature (a positive predictive value of 96.46% and sensitivity of 100% for the category S, and a positive predictive value of 98.68% and sensitivity of 97.40% for the category F for the intra-patient scheme; a positive predictive value of 92.57% and sensitivity of 88.94% for the category S, and a positive predictive value of 99.50% and sensitivity of 99.94% for the category V for the inter-patient scheme.).

A Feature Selection Method Based on Shapley Value to False Alarm Reduction in ICUs A Genetic-Algorithm Approach.

High false alarm rate in intensive care units (ICUs) has been identified as one of the most critical medical challenges in recent years. This often results in overwhelming the clinical staff by numerous false or unurgent alarms and decreasing the quality of care through enhancing the probability of missing true alarms as well as causing delirium, stress, sleep deprivation and depressed immune systems for patients. One major cause of false alarms in clinical practice is that the collected signals from different devices are processed individually to trigger an alarm, while there exists a considerable chance that the signal collected from one device is corrupted by noise or motion artifacts. In this paper, we propose a low-computational complexity yet accurate game-theoretic feature selection method which is based on a genetic algorithm that identifies the most informative biomarkers across the signals collected from various monitoring devices and can considerably reduce the rate of false alarms 1.