Using Artificial Intelligence With Natural Language Processing to Combine Electronic Health Record's Structured and Free Text Data to Identify Nonvalvular Atrial Fibrillation to Decrease Strokes and Death: Evaluation and Case-Control Study.

BACKGROUND: Nonvalvular atrial fibrillation (NVAF) affects almost 6 million Americans and is a major contributor to stroke but is significantly undiagnosed and undertreated despite explicit guidelines for oral anticoagulation. OBJECTIVE: The aim of this study is to investigate whether the use of semisupervised natural language processing (NLP) of electronic health record's (EHR) free-text information combined with structured EHR data improves NVAF discovery and treatment and perhaps offers a method to prevent thousands of deaths and save billions of dollars. METHODS: We abstracted 96,681 participants from the University of Buffalo faculty practice's EHR. NLP was used to index the notes and compare the ability to identify NVAF, congestive heart failure, hypertension, age ≥75 years, diabetes mellitus, stroke or transient ischemic attack, vascular disease, age 65 to 74 years, sex category (CHA2DS2-VASc), and Hypertension, Abnormal liver/renal function, Stroke history, Bleeding history or predisposition, Labile INR, Elderly, Drug/alcohol usage (HAS-BLED) scores using unstructured data (International Classification of Diseases codes) versus structured and unstructured data from clinical notes. In addition, we analyzed data from 63,296,120 participants in the Optum and Truven databases to determine the NVAF frequency, rates of CHA2DS2­VASc ≥2, and no contraindications to oral anticoagulants, rates of stroke and death in the untreated population, and first year's costs after stroke. RESULTS: The structured-plus-unstructured method would have identified 3,976,056 additional true NVAF cases (P<.001) and improved sensitivity for CHA2DS2-VASc and HAS-BLED scores compared with the structured data alone (P=.002 and P<.001, respectively), causing a 32.1% improvement. For the United States, this method would prevent an estimated 176,537 strokes, save 10,575 lives, and save >US $13.5 billion. CONCLUSIONS: Artificial intelligence-informed bio-surveillance combining NLP of free-text information with structured EHR data improves data completeness, prevents thousands of strokes, and saves lives and funds. This method is applicable to many disorders with profound public health consequences.

Longitudinal K-means approaches to clustering and analyzing EHR opioid use trajectories for clinical subtypes.

Identification of patient subtypes from retrospective Electronic Health Record (EHR) data is fraught with inherent modeling issues, such as missing data and variable length time intervals, and the results obtained are highly dependent on data pre-processing strategies. As we move towards personalized medicine, assessing accurate patient subtypes will be a key factor in creating patient specific treatment plans. Partitioning longitudinal trajectories from irregularly spaced and variable length time intervals is a well-established, but open problem. In this work, we present and compare k-means approaches for subtyping opioid use trajectories from EHR data. We then interpret the resulting subtypes using decision trees, examining how each subtype is influenced by opioid medication features and patient diagnoses, procedures, and demographics. Finally, we discuss how the subtypes can be incorporated in static machine learning models as features in predicting opioid overdose and adverse events. The proposed methods are general, and can be extended to other EHR prescription dosage trajectories.

COVID-19: Incidental Diagnosis by 18F-FDG PET/CT.

A 73-year-old man with chronic obstructive pulmonary disease and no known malignancies was evaluated for back pain. MR examination showed lumbar spine compression fractures, and an F-FDG PET/CT scan was requested to assess for skeletal metastatic disease and potential detection of a primary neoplasm. The PET/CT examination revealed scattered FDG-avid pulmonary opacities with upper lobe preponderance highly suspicious for COVID-19. Real-time polymerase chain reaction testing of nasopharyngeal swabs confirmed the diagnosis.

Clinical Data Warehouse Query and Learning Tool Using a Human-Centered Participatory Design Process.

BMI Investigator (BMII) is an interactive web-based tool with a learning knowledge base, which provides a way for researchers to query structured, unstructured, genomic and image data contained in a data warehouse. We demonstrate how development of an efficient, usable, and learnable web interface for a diverse group of research stakeholders benefits from an iterative human-centered participatory design process utilizing a team of clinicians, students, programmers, and informatics experts.

Safe Opioid Prescription: A SMART on FHIR Approach to Clinical Decision Support.

Background Prescription opioid pain medication overuse, misuse and abuse have been a significant contributing factor in the opioid epidemic. The rising death rates from opioid overdose have caused healthcare practitioners and researchers to work on optimizing pain therapy and limiting the prescriptions for pain medications. The state of New York has implemented a prescription drug monitoring program(PDMP), amended public health law to limit the prescription of opioids for acute pain and utilized the resources of the state and county health departments to help in curbing this epidemic. The recent publication of guidelines for prescription opioids from CDC [1] and ASIPP (American Society of Interventional pain practitioners) have independently reviewed literature and found good evidence of limiting opioid prescription for acute and chronic non cancer pain. [2] Method Over the last decade, advanced technology has increased the complexity of electronic health records systems leading to the development of Clinical Decision Support Systems (CDSS) to aid the work flow of healthcare providers. There are several systematic reviews on the effectiveness and utility of CDSSs. A common consensus is that commercially and locally developed CDSS are effective in improving patient measures while actual workload improvement and efficient cost-cutting measure are not significantly improved by CDSS. Patient provider involvement in developing CDSS is a determinant of its success and utilization rates. [7] Therefore, a plug and play form of CDSS which can be implemented from an external platform through secure channels would be more effective. Design The Health Level Seven's (HL7) open licensed interoperability standard Fast Health Interoperability Resources (FHIR) has a platform, Substitutable Medical Applications and Reusable Technologies (SMART) for CDSS app development by a third party. [3] We adopted these open source standard to plan to develop an app for accessible and efficient implementation of the recently published guidelines for management of pain with prescription opioid medications.

Secondary Use of EHR: Interpreting Clinician Inter-Rater Reliability Through Qualitative Assessment.

In a retrospective secondary-use EHR study identifying a cohort of Non-Valvular Atrial Fibrillation (NVAF) patients, chart abstraction was done by two sets of clinicians to create a gold standard for risk measures CHA2DS2-VASc and HAS-BLED. Inter-rater reliability between each set of clinicians for NVAF and the outcomes of interest were variable, ranging from extremely low agreement to high agreement. To assess the chart abstraction process, a focus group and a survey was conducted. Survey findings revealed patterns of difficulty in assessing certain items dealing with temporality and social data. The focus group raised issues on the quality and completeness of EHR data, including missing encounters, truncated notes, and low granularity. It also raised the issue of the usability of the data system, the Clinical Data Viewer, which did not mirror a live EHR and made it difficult to record outcomes. Finally, the focus group found it was difficult to infer certain outcomes, like severity, from the provided data. These factors produced differences in clinician rated outcomes.

Prescription Opioid Dependence in Western New York: Using Data Analytics to Find an Answer to the Opioid Epidemic.

Opioid dependence and overdose is on the rise. One indicator is the increasing trends of prescription buprenorphine use among patient on chronic pain medication. In addition to the New York State Department of Health's prescription drug monitoring programs and training programs for providers and first responders to detect and treat a narcotic overdose, further examination of the population may provide important information for multidisciplinary interventions to address this epidemic. This paper uses an observational database with a Natural Language Processing (NLP) based Not Only Structured Query Language architecture to examine Electronic Health Record (EHR) data at a regional level to study the trends of prescription opioid dependence. We aim to help prioritize interventions in vulnerable population subgroups. This study provides a report of the demographic patterns of opioid dependent patients in Western New York using High Throughput Phenotyping NLP of EHR data.

Comparison of iodixanol with iohexol for delayed pelvic venous opacification: a preliminary study of potential use for CT venography.

OBJECTIVE: The goal of this prospective randomized study was to determine whether isosmolar contrast material offers an advantage over low-osmolar contrast material for delayed venous opacification in CT venography. SUBJECTS AND METHODS. We prospectively enrolled 200 adult outpatients. Patients were randomized to receive either the low-osmolar (hyperosmolar to blood) nonionic contrast medium, iohexol, or the nonionic isosmolar contrast medium, iodixanol. Images were obtained before contrast administration and 180 sec after contrast administration through the pelvis at the level of the external iliac vessels. Opacification of the external iliac vessels was assessed both objectively and subjectively. RESULTS: The arterial and venous densities before contrast administration were approximately 45 H for both groups. On delayed images obtained after contrast administration, the mean venous density was 95.2 H for iohexol and 101.4 H for iodixanol. Changes in venous density due to administration of iohexol and iodixanol were 49.8 and 56.1 H, respectively. This 12.5% difference was highly significant (p = 0.002). Sixty-six percent of the images in the iodixanol group were rated either 4 (good) or 5 (excellent), whereas only 36% of the iohexol group achieved a similar rating on our subjective rating scale. This difference was statistically significant (chi(2) = 16.4, p < 0.001, df = 1). CONCLUSION: Our study shows that isosmolar contrast material provides significant improvement in delayed opacification of the external iliac vessels in comparison with conventional low-osmolar contrast medium (hyperosmolar to blood).