Publications by authors named "Azade Tabaie"
Article Synopsis
- Diagnostic errors in hospitals contribute to preventable deaths and increased patient harm, emphasizing a need for better surveillance methods.
- This study investigates the use of machine learning and natural language processing to enhance the detection of diagnostic errors by analyzing electronic health records and case review data from a health system in the mid-Atlantic U.S.
- Results show that out of 1704 patients, 126 experienced diagnostic errors, with significant differences in error rates and patient demographics between men and women, including age and admission types.
Purpose: Between 30 and 68% of patients prematurely discontinue their antidepressant treatment, posing significant risks to patient safety and healthcare outcomes. Online healthcare forums have the potential to offer a rich and unique source of data, revealing dimensions of antidepressant discontinuation that may not be captured by conventional data sources.
Methods: We analyzed 891 patient narratives from the online healthcare forum, "askapatient.
Objectives: The objective of this study was to explore the use of natural language processing (NLP) algorithm to categorise contributing factors from patient safety event (PSE). Contributing factors are elements in the healthcare process (eg, communication failures) that instigate an event or allow an event to occur. Contributing factors can be used to further investigate why safety events occurred.
View Article and Find Full Text PDFArticle Synopsis
- Intimate partner violence (IPV) encompasses various forms of violence between intimate partners, making it crucial to identify these cases in healthcare settings like emergency departments (ED).
- This study aimed to create a natural language processing (NLP) algorithm to detect IPV incidents based on unstructured clinical notes from electronic health records (EHR).
- Analyzing over 1 million patient encounters, the algorithm identified 7,399 IPV cases with an impressive precision rate of 99.5%, showcasing its effectiveness in recognizing IPV-related encounters within busy emergency departments.
Background: Hospitalized children with central venous lines (CVLs) are at higher risk of hospital-acquired infections. Information in electronic health records (EHRs) can be employed in training deep learning models to predict the onset of these infections. We incorporated clinical notes in addition to structured EHR data to predict serious bloodstream infections, defined as positive blood culture followed by at least 4 days of new antimicrobial agent administration, among hospitalized children with CVLs.
View Article and Find Full Text PDFRisks of intimate partner violence (IPV) escalated during the COVID-19 pandemic given mitigation measures, socioeconomic hardships, and isolation concerns. The objective of this study was to explore the impact of COVID-19 on the incidence of IPV. We conducted an interrupted time series analysis for IPV incidence at a single level 1 trauma center located in the United States.
View Article and Find Full Text PDFImportance: Discrepancies in oxygen saturation measured by pulse oximetry (Spo2), when compared with arterial oxygen saturation (Sao2) measured by arterial blood gas (ABG), may differentially affect patients according to race and ethnicity. However, the association of these disparities with health outcomes is unknown.
Objective: To examine racial and ethnic discrepancies between Sao2 and Spo2 measures and their associations with clinical outcomes.
Predict the onset of presumed serious infection, defined as a positive blood culture drawn and new antibiotic course of at least 4 days (PSI), among pediatric patients with Central Venous Lines (CVLs). Retrospective cohort study. Single academic children's hospital.
View Article and Find Full Text PDFArticle Synopsis
- The 'eARDS' machine learning algorithm predicts Acute Respiratory Distress Syndrome (ARDS) in COVID-19 patients in ICUs, identifying risk up to 12 hours prior to meeting the Berlin clinical criteria.
- The analysis used clinical data from 35,804 patients and demonstrated a strong predictive performance with an AUROC of 0.89 and sensitivity of 0.77.
- Key predictive features included minimum oxygen saturation and blood pressure variations, with the algorithm performing best in younger patients (ages 18-40) and showing robust consistency across different health systems.
Background: Acute respiratory failure occurs frequently in hospitalized patients and often begins outside the ICU, associated with increased length of stay, cost, and mortality. Delays in decompensation recognition are associated with worse outcomes.
Objectives: The objective of this study is to predict acute respiratory failure requiring any advanced respiratory support (including noninvasive ventilation).
Background: Presumed serious infection (PSI) is defined as a blood culture drawn and new antibiotic course of at least 4 days among pediatric patients with Central Venous Lines (CVLs). Early PSI prediction and use of medical interventions can prevent adverse outcomes and improve the quality of care.
Methods: Clinical features including demographics, laboratory results, vital signs, characteristics of the CVLs and medications used were extracted retrospectively from electronic medical records.
Article Synopsis
- This study explored the use of machine learning models to predict outcomes for patients with aneurysmal subarachnoid hemorrhage (aSAH) by analyzing clinical risk factors over time.
- Researchers examined a group of 575 aSAH patients from Emory Healthcare and used models like Logistic Regression, Neural Networks, and LSTM to make predictions based on clinical data and imaging.
- The LSTM model produced the best results, achieving an AUC of 0.89 within eight days of hospitalization, suggesting it could support treatment decisions and better utilize imaging resources for high-risk patients.
Doubly-Robust Estimation of Effect of Imaging Resource Utilization on Discharge Decisions in Emergency Departments.
Annu Int Conf IEEE Eng Med Biol Soc
July 2018
Cluster analysis provides a data-driven multidimensional approach for identifying distinct subgroups of patients in a cohort. Each of the clusters represents a particular health condition with specific clinical trajectory and medical needs. Patients visiting emergency rooms do not share the same health condition, therefore discriminating between groups may have implications for diagnostic testing and resource utilization.
View Article and Find Full Text PDF