The h-ANN Model: Comprehensive Colonoscopy Concept Compilation Using Combined Contextual Embeddings.

Colonoscopy is a screening and diagnostic procedure for detection of colorectal carcinomas with specific quality metrics that monitor and improve adenoma detection rates. These quality metrics are stored in disparate documents i.e., colonoscopy, pathology, and radiology reports. The lack of integrated standardized documentation is impeding colorectal cancer research. Clinical concept extraction using Natural Language Processing (NLP) and Machine Learning (ML) techniques is an alternative to manual data abstraction. Contextual word embedding models such as BERT (Bidirectional Encoder Representations from Transformers) and FLAIR have enhanced performance of NLP tasks. Combining multiple clinically-trained embeddings can improve word representations and boost the performance of the clinical NLP systems. The objective of this study is to extract comprehensive clinical concepts from the consolidated colonoscopy documents using concatenated clinical embeddings. We built high-quality annotated corpora for three report types. BERT and FLAIR embeddings were trained on unlabeled colonoscopy related documents. We built a hybrid Artificial Neural Network (h-ANN) to concatenate and fine-tune BERT and FLAIR embeddings. To extract concepts of interest from three report types, 3 models were initialized from the h-ANN and fine-tuned using the annotated corpora. The models achieved best F1-scores of 91.76%, 92.25%, and 88.55% for colonoscopy, pathology, and radiology reports respectively.

DeIDNER Model: A Neural Network Named Entity Recognition Model for Use in the De-identification of Clinical Notes.

Clinical named entity recognition (NER) is an essential building block for many downstream natural language processing (NLP) applications such as information extraction and de-identification. Recently, deep learning (DL) methods that utilize word embeddings have become popular in clinical NLP tasks. However, there has been little work on evaluating and combining the word embeddings trained from different domains. The goal of this study is to improve the performance of NER in clinical discharge summaries by developing a DL model that combines different embeddings and investigate the combination of standard and contextual embeddings from the general and clinical domains. We developed: 1) A human-annotated high-quality internal corpus with discharge summaries and 2) A NER model with an input embedding layer that combines different embeddings: standard word embeddings, context-based word embeddings, a character-level word embedding using a convolutional neural network (CNN), and an external knowledge sources along with word features as one-hot vectors. Embedding was followed by bidirectional long short-term memory (Bi-LSTM) and conditional random field (CRF) layers. The proposed model reaches or overcomes state-of-the-art performance on two publicly available data sets and an F1 score of 94.31% on an internal corpus. After incorporating mixed-domain clinically pre-trained contextual embeddings, the F1 score further improved to 95.36% on the internal corpus. This study demonstrated an efficient way of combining different embeddings that will improve the recognition performance aiding the downstream de-identification of clinical notes.

TAX-Corpus: Taxonomy based Annotations for Colonoscopy Evaluation.

Colonoscopy plays a critical role in screening of colorectal carcinomas (CC). Unfortunately, the data related to this procedure are stored in disparate documents, colonoscopy, pathology, and radiology reports respectively. The lack of integrated standardized documentation is impeding accurate reporting of quality metrics and clinical and translational research. Natural language processing (NLP) has been used as an alternative to manual data abstraction. Performance of Machine Learning (ML) based NLP solutions is heavily dependent on the accuracy of annotated corpora. Availability of large volume annotated corpora is limited due to data privacy laws and the cost and effort required. In addition, the manual annotation process is error-prone, making the lack of quality annotated corpora the largest bottleneck in deploying ML solutions. The objective of this study is to identify clinical entities critical to colonoscopy quality, and build a high-quality annotated corpus using domain specific taxonomies following standardized annotation guidelines. The annotated corpus can be used to train ML models for a variety of downstream tasks.

Deep Learning Methods to Predict Mortality in COVID-19 Patients: A Rapid Scoping Review.

The ongoing COVID-19 pandemic has become the most impactful pandemic of the past century. The SARS-CoV-2 virus has spread rapidly across the globe affecting and straining global health systems. More than 2 million people have died from COVID-19 (as of 30 January 2021). To lessen the pandemic's impact, advanced methods such as Artificial Intelligence models are proposed to predict mortality, morbidity, disease severity, and other outcomes and sequelae. We performed a rapid scoping literature review to identify the deep learning techniques that have been applied to predict hospital mortality in COVID-19 patients. Our review findings provide insights on the important deep learning models, data types, and features that have been reported in the literature. These summary findings will help scientists build reliable and accurate models for better intervention strategies for predicting mortality in current and future pandemic situations.

Machine Learning Approach to Optimize Sedation Use in Endoscopic Procedures.

Endoscopy procedures are often performed with either moderate or deep sedation. While deep sedation is costly, procedures with moderate sedation are not always well tolerated resulting in patient discomfort, and are often aborted. Due to lack of clear guidelines, the decision to utilize moderate sedation or anesthesia for a procedure is made by the providers, leading to high variability in clinical practice. The objective of this study was to build a Machine Learning (ML) model that predicts if a colonoscopy can be successfully completed with moderate sedation based on patients' demographics, comorbidities, and prescribed medications. XGBoost model was trained and tested on 10,025 colonoscopies (70% - 30%) performed at University of Arkansas for Medical Sciences (UAMS). XGBoost achieved average area under receiver operating characteristic curve (AUC) of 0.762, F1-score to predict procedures that need moderate sedation was 0.85, and precision and recall were 0.81 and 0.89 respectively. The proposed model can be employed as a decision support tool for physicians to bolster their confidence while choosing between moderate sedation and anesthesia for a colonoscopy procedure.

Consolidated EHR Workflow for Endoscopy Quality Reporting.

Although colonoscopy is the most frequently performed endoscopic procedure, the lack of standardized reporting is impeding clinical and translational research. Inadequacies in data extraction from the raw, unstructured text in electronic health records (EHR) pose an additional challenge to procedure quality metric reporting, as vital details related to the procedure are stored in disparate documents. Currently, there is no EHR workflow that links these documents to the specific colonoscopy procedure, making the process of data extraction error prone. We hypothesize that extracting comprehensive colonoscopy quality metrics from consolidated procedure documents using computational linguistic techniques, and integrating it with discrete EHR data can improve quality of screening and cancer detection rate. As a first step, we developed an algorithm that links colonoscopy, pathology and imaging documents by analyzing the chronology of various orders placed relative to the colonoscopy procedure. The algorithm was installed and validated at the University of Arkansas for Medical Sciences (UAMS). The proposed algorithm in conjunction with Natural Language Processing (NLP) techniques can overcome current limitations of manual data abstraction.

DeIDNER Corpus: Annotation of Clinical Discharge Summary Notes for Named Entity Recognition Using BRAT Tool.

Named Entity Recognition (NER) aims to identify and classify entities into predefined categories is a critical pre-processing task in Natural Language Processing (NLP) pipeline. Readily available off-the-shelf NER algorithms or programs are trained on a general corpus and often need to be retrained when applied on a different domain. The end model's performance depends on the quality of named entities generated by these NER models used in the NLP task. To improve NER model accuracy, researchers build domain-specific corpora for both model training and evaluation. However, in the clinical domain, there is a dearth of training data because of privacy reasons, forcing many studies to use NER models that are trained in the non-clinical domain to generate NER feature-set. Thus, influencing the performance of the downstream NLP tasks like information extraction and de-identification. In this paper, our objective is to create a high quality annotated clinical corpus for training NER models that can be easily generalizable and can be used in a downstream de-identification task to generate named entities feature-set.

Application of Machine Learning in Intensive Care Unit (ICU) Settings Using MIMIC Dataset: Systematic Review.

Modern Intensive Care Units (ICUs) provide continuous monitoring of critically ill patients susceptible to many complications affecting morbidity and mortality. ICU settings require a high staff-to-patient ratio and generates a sheer volume of data. For clinicians, the real-time interpretation of data and decision-making is a challenging task. Machine Learning (ML) techniques in ICUs are making headway in the early detection of high-risk events due to increased processing power and freely available datasets such as the Medical Information Mart for Intensive Care (MIMIC). We conducted a systematic literature review to evaluate the effectiveness of applying ML in the ICU settings using the MIMIC dataset. A total of 322 articles were reviewed and a quantitative descriptive analysis was performed on 61 qualified articles that applied ML techniques in ICU settings using MIMIC data. We assembled the qualified articles to provide insights into the areas of application, clinical variables used, and treatment outcomes that can pave the way for further adoption of this promising technology and possible use in routine clinical decision-making. The lessons learned from our review can provide guidance to researchers on application of ML techniques to increase their rate of adoption in healthcare.

API Driven On-Demand Participant ID Pseudonymization in Heterogeneous Multi-Study Research.

OBJECTIVES: To facilitate clinical and translational research, imaging and non-imaging clinical data from multiple disparate systems must be aggregated for analysis. Study participant records from various sources are linked together and to patient records when possible to address research questions while ensuring patient privacy. This paper presents a novel tool that pseudonymizes participant identifiers (PIDs) using a researcher-driven automated process that takes advantage of application-programming interface (API) and the Perl Open-Source Digital Imaging and Communications in Medicine Archive (POSDA) to further de-identify PIDs. The tool, on-demand cohort and API participant identifier pseudonymization (O-CAPP), employs a pseudonymization method based on the type of incoming research data. METHODS: For images, pseudonymization of PIDs is done using API calls that receive PIDs present in Digital Imaging and Communications in Medicine (DICOM) headers and returns the pseudonymized identifiers. For non-imaging clinical research data, PIDs provided by study principal investigators (PIs) are pseudonymized using a nightly automated process. The pseudonymized PIDs (P-PIDs) along with other protected health information is further de-identified using POSDA. RESULTS: A sample of 250 PIDs pseudonymized by O-CAPP were selected and successfully validated. Of those, 125 PIDs that were pseudonymized by the nightly automated process were validated by multiple clinical trial investigators (CTIs). For the other 125, CTIs validated radiologic image pseudonymization by API request based on the provided PID and P-PID mappings. CONCLUSIONS: We developed a novel approach of an ondemand pseudonymization process that will aide researchers in obtaining a comprehensive and holistic view of study participant data without compromising patient privacy.

Role of Machine Learning Techniques to Tackle the COVID-19 Crisis: Systematic Review.

BACKGROUND: SARS-CoV-2, the novel coronavirus responsible for COVID-19, has caused havoc worldwide, with patients presenting a spectrum of complications that have pushed health care experts to explore new technological solutions and treatment plans. Artificial Intelligence (AI)-based technologies have played a substantial role in solving complex problems, and several organizations have been swift to adopt and customize these technologies in response to the challenges posed by the COVID-19 pandemic. OBJECTIVE: The objective of this study was to conduct a systematic review of the literature on the role of AI as a comprehensive and decisive technology to fight the COVID-19 crisis in the fields of epidemiology, diagnosis, and disease progression. METHODS: A systematic search of PubMed, Web of Science, and CINAHL databases was performed according to PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analysis) guidelines to identify all potentially relevant studies published and made available online between December 1, 2019, and June 27, 2020. The search syntax was built using keywords specific to COVID-19 and AI. RESULTS: The search strategy resulted in 419 articles published and made available online during the aforementioned period. Of these, 130 publications were selected for further analyses. These publications were classified into 3 themes based on AI applications employed to combat the COVID-19 crisis: Computational Epidemiology, Early Detection and Diagnosis, and Disease Progression. Of the 130 studies, 71 (54.6%) focused on predicting the COVID-19 outbreak, the impact of containment policies, and potential drug discoveries, which were classified under the Computational Epidemiology theme. Next, 40 of 130 (30.8%) studies that applied AI techniques to detect COVID-19 by using patients' radiological images or laboratory test results were classified under the Early Detection and Diagnosis theme. Finally, 19 of the 130 studies (14.6%) that focused on predicting disease progression, outcomes (ie, recovery and mortality), length of hospital stay, and number of days spent in the intensive care unit for patients with COVID-19 were classified under the Disease Progression theme. CONCLUSIONS: In this systematic review, we assembled studies in the current COVID-19 literature that utilized AI-based methods to provide insights into different COVID-19 themes. Our findings highlight important variables, data types, and available COVID-19 resources that can assist in facilitating clinical and translational research.

Toolkit to Compute Time-Based Elixhauser Comorbidity Indices and Extension to Common Data Models.

OBJECTIVE: The time-dependent study of comorbidities provides insight into disease progression and trajectory. We hypothesize that understanding longitudinal disease characteristics can lead to more timely intervention and improve clinical outcomes. As a first step, we developed an efficient and easy-to-install toolkit, the Time-based Elixhauser Comorbidity Index (TECI), which pre-calculates time-based Elixhauser comorbidities and can be extended to common data models (CDMs). METHODS: A Structured Query Language (SQL)-based toolkit, TECI, was built to pre-calculate time-specific Elixhauser comorbidity indices using data from a clinical data repository (CDR). Then it was extended to the Informatics for Integrating Biology and the Bedside (I2B2) and Observational Medical Outcomes Partnership (OMOP) CDMs. RESULTS: At the University of Arkansas for Medical Sciences (UAMS), the TECI toolkit was successfully installed to compute the indices from CDR data, and the scores were integrated into the I2B2 and OMOP CDMs. Comorbidity scores calculated by TECI were validated against: scores available in the 2015 quarter 1-3 Nationwide Readmissions Database (NRD) and scores calculated using the comorbidities using a previously validated algorithm on the 2015 quarter 4 NRD. Furthermore, TECI identified 18,846 UAMS patients that had changes in comorbidity scores over time (year 2013 to 2019). Comorbidities for a random sample of patients were independently reviewed, and in all cases, the results were found to be 100% accurate. CONCLUSION: TECI facilitates the study of comorbidities within a time-dependent context, allowing better understanding of disease associations and trajectories, which has the potential to improve clinical outcomes.

Document Oriented Graphical Analysis and Prediction.

In general, small-mid size research laboratories struggle with managing clinical and secondary datasets. In addition, faster dissemination, correlation and prediction of information from available datasets is always a bottleneck. To address these challenges, we have developed a novel approach, Document Oriented Graphical Analysis and Prediction (DO-GAP), a hybrid tool, merging strengths of Not only SQL (NoSQL) document oriented and graph databases. DO-GAP provides flexible and simple data integration mechanism using document database, data visualization and knowledge discovery with graph database. We demonstrate how the proposed tool (DO-GAP) can integrate data from heterogeneous sources such as Genomic lab findings, clinical data from Electronic Health Record (EHR) systems and provide simple querying mechanism. Application of DO-GAP can be extended to other diverse clinical studies such as supporting or identifying weakness of clinical diagnosis in comparison to molecular genetic analysis.

Near Real Time EHR Data Utilization in a Clinical Study.

Extraction and use of Electronic Health Record (EHR) data is common in retrospective observational studies. However, electronic extraction and use of EHR data is rare during longitudinal prospective studies. One of the reasons is the amount of processing needed to assess data quality and assure consistency in meaning and format across multiple investigational sites. We report a case study of and lessons learned from acquisition and processing of EHR data in an ongoing basis during a clinical study.

Prescription Patterns and Outcomes of Patients With Atrial Fibrillation Treated With Direct Oral Anticoagulants and Warfarin: A Real-World Analysis.

BACKGROUND: Direct oral anticoagulants (DOACs) have been found to be similar or superior to warfarin in reducing ischemic stroke and intracranial hemorrhage (ICH) in patients with atrial fibrillation (AF). We sought to examine the anticoagulation prescription patterns in community since the advent of DOACs and also evaluate the outcomes in terms of gastrointestinal (GI) bleeding, ischemic stroke, and ICH in real-world patients with AF receiving anticoagulation. METHODS: This is a retrospective study comprising patients who were newly diagnosed with nonvalvular AF and were prescribed anticoagulants for stroke prevention. Prescription pattern of the anticoagulants based on CHA2DS2Vasc score was studied. Clinical outcomes of GI bleeding, ischemic stroke, and ICH were analyzed using a multivariate logistic regression model. RESULTS: Of the 2362 patients with AF on anticoagulation, 44.7% were prescribed DOACs. Patients with CHA2DS2VASc score of ≥3 received a prescription for warfarin more often than DOACs (P < .001). Multivariate logistic regression analysis revealed that the incidence of GI bleed (odds ratio [OR]: 0.91, 95% confidence interval [CI]: 0.62-1.35, P = .66) and stroke (OR: 0.77, 95% CI: 0.57-1.05, P = .10) was similar between warfarin and DOAC users. However, there was a trend toward lower ICH in the DOAC group (OR: 0.60, 95% CI: 0.36-1.01, P = .06). CONCLUSIONS: Prescription rate of DOACs for nonvalvular AF has increased significantly, with apixaban being the most commonly used agent. Patients with higher CHA2DS2-VASc score (≥3) are prescribed DOACs less often than warfarin. The reason for this discrepancy is unclear. Given the favorable risk-benefit profile of DOACs, further studies are needed to identify factors that determine anticoagulant selection in patients with AF with high thromboembolic risk.