Pasupathy, Kalyan S.

The analysis and interpretation of cardiac magnetic resonance (CMR) images are often time-consuming. The automated segmentation of cardiac structures can reduce the time required for image analysis. Spatial similarities between different CMR image types were leveraged to jointly segment multiple sequences using a segmentation model termed a multi-image type UNet (MI-UNet). This model was developed from 72 exams (46% female, mean age 63 ± 11 years) performed on patients with hypertrophic cardiomyopathy. The MI-UNet for steady-state free precession (SSFP) images achieved a superior Dice similarity coefficient (DSC) of 0.92 ± 0.06 compared to 0.87 ± 0.08 for a single-image type UNet (p < 0.001). The MI-UNet for late gadolinium enhancement (LGE) images also had a superior DSC of 0.86 ± 0.11 compared to 0.78 ± 0.11 for a single-image type UNet (p = 0.001). The difference across image types was most evident for the left ventricular myocardium in SSFP images and for both the left ventricular cavity and the left ventricular myocardium in LGE images. For the right ventricle, there were no differences in DCS when comparing the MI-UNet with single-image type UNets. The joint segmentation of multiple image types increases segmentation accuracy for CMR images of the left ventricle compared to single-image models. In clinical practice, the MI-UNet model may expedite the analysis and interpretation of CMR images of multiple types.

Abstract Background We aimed to determine if patient symptoms and computed tomography enterography (CTE) and magnetic resonance enterography (MRE) imaging findings can be used to predict near-term risk of surgery in patients with small bowel Crohn’s disease (CD). Methods CD patients with small bowel strictures undergoing serial CTE or MRE were retrospectively identified. Strictures were defined by luminal narrowing, bowel wall thickening, and unequivocal proximal small bowel dilation. Harvey-Bradshaw index (HBI) was recorded. Stricture observations and measurements were performed on baseline CTE or MRE and compared to with prior and subsequent scans. Patients were divided into those who underwent surgery within 2 years and those who did not. LASSO (least absolute shrinkage and selection operator) regression models were trained and validated using 5-fold cross-validation. Results Eighty-five patients (43.7 ± 15.3 years of age at baseline scan, majority male [57.6%]) had 137 small bowel strictures. Surgery was performed in 26 patients within 2 years from baseline CTE or MRE. In univariate analysis of patients with prior exams, development of stricture on the baseline exam was associated with near-term surgery (P = .006). A mathematical model using baseline features predicting surgery within 2 years included an HBI of 5 to 7 (odds ratio [OR], 1.7 × 105; P = .057), an HBI of 8 to 16 (OR, 3.1 × 105; P = .054), anastomotic stricture (OR, 0.002; P = .091), bowel wall thickness (OR, 4.7; P = .064), penetrating behavior (OR, 3.1 × 103; P = .096), and newly developed stricture (OR: 7.2 × 107; P = .062). This model demonstrated sensitivity of 67% and specificity of 73% (area under the curve, 0.62). Conclusions CTE or MRE imaging findings in combination with HBI can potentially predict which patients will require surgery within 2 years.

Introduction Diagnostic processes in the emergency department (ED) involve multiple interactions among individuals who interface with information systems to access and record information. A better understanding of diagnostic processes is needed to mitigate errors. This paper describes a study protocol to map diagnostic processes in the ED as a foundation for developing future error mitigation strategies. Methods and analysis This study of an adult and a paediatric academic ED uses a prospective mixed methods case study design informed by an ED-specific diagnostic decision-making model (the modified ED-National Academies of Sciences, Engineering and Medicine (NASEM) model) and two cognitive theories (dual process theory and distributed cognition). Data sources include audio recordings of patient and care team interactions, electronic health record data, observer field notes and stakeholder interviews. Multiple qualitative analysis methods will be used to explore diagnostic processes in situ, including systems information flow, human–human and human–system interactions and contextual factors influencing cognition. The study has three parts. Part 1 involves prospective field observations of patients with undifferentiated symptoms at high risk for diagnostic error, where each patient is followed throughout the entire care delivery process. Part 2 involves observing individual care team providers over a 4-hour window to capture their diagnostic workflow, team coordination and communication across multiple patients. Part 3 uses interviews with key stakeholders to understand different perspectives on the diagnostic process, as well as perceived strengths and vulnerabilities, in order to enrich the ED-NASEM diagnostic model. Ethics and dissemination The University of Michigan Institutional Review Board approved this study, HUM00156261. This foundational work will help identify strengths and vulnerabilities in diagnostic processes. Further, it will inform the future development and testing of patient, provider and systems-level interventions for mitigating error and improving patient safety in these and other EDs. The work will be disseminated through journal publications and presentations at national and international meetings.

AbstractBackgroundHospitals face the challenge of managing demand for limited computed tomography (CT) resources from multiple patient types while ensuring timely access.MethodsA discrete event simulation model was created to evaluate CT access time for emergency department (ED) patients at a large academic medical center with six unique CT machines that serve unscheduled emergency, semi‐scheduled inpatient, and scheduled outpatient demand. Three operational interventions were tested: adding additional patient transporters, using an alternative creatinine lab, and adding a registered nurse dedicated to monitoring CT patients in the ED.ResultsAll interventions improved access times. Adding one or two transporters improved ED access times by up to 9.8 minutes (Mann‐Whitney (MW) CI: [−11.0,−8.7]) and 10.3 minutes (MW CI [−11.5, −9.2]). The alternative creatinine and RN interventions provided 3‐minute (MW CI: [−4.0, −2.0]) and 8.5‐minute (MW CI: [−9.7, −8.3]) improvements.ConclusionsAdding one transporter provided the greatest combination of reduced delay and ability to implement. The projected simulation improvements have been realized in practice.

Abstract Hypertrophic Cardiomyopathy (HCM) is the most common genetic heart disease in the US and is known to cause sudden death (SCD) in young adults. While significant advancements have been made in HCM diagnosis and management, there is a need to identify HCM cases from electronic health record (EHR) data to develop automated tools based on natural language processing guided machine learning (ML) models for accurate HCM case identification to improve management and reduce adverse outcomes of HCM patients. Cardiac Magnetic Resonance (CMR) Imaging, plays a significant role in HCM diagnosis and risk stratification. CMR reports, generated by clinician annotation, offer rich data in the form of cardiac measurements as well as narratives describing interpretation and phenotypic description. The purpose of this study is to develop an NLP-based interpretable model utilizing impressions extracted from CMR reports to automatically identify HCM patients. CMR reports of patients with suspected HCM diagnosis between the years 1995 to 2019 were used in this study. Patients were classified into three categories of yes HCM, no HCM and, possible HCM. A random forest (RF) model was developed to predict the performance of both CMR measurements and impression features to identify HCM patients. The RF model yielded an accuracy of 86% (608 features) and 85% (30 features). These results offer promise for accurate identification of HCM patients using CMR reports from EHR for efficient clinical management transforming health care delivery for these patients.

Abstract Hypertrophic cardiomyopathy (HCM) is a heritable, phenotypically diverse, and often asymptomatic heart muscle disease which is a major cause of sudden cardiac death (SCD) in young adults. The gold-standard for the diagnosis of HCM is echocardiography (echo), which is an ultrasound-based cardiac imaging modality. Across all sites of the Mayo Clinic enterprise, echo images and measurement data are reviewed, interpreted, and reported via the Echo Information Management System (EIMS). The objective of this paper is to develop a machine learning model for the identification of HCM from cardiac measurements obtained by the echo. We developed a novel machine learning model on patient demographic information and echo measurements that were retrieved from the EIMS digital data registry and selected by cardiologists. Random forest (RF) was utilized to investigate the predictive performance of these features on the identification of HCM patients. The HCM cohort consists of 3,548 patients with at least one HCM diagnostic billing code (ICD-9 or ICD-10), from 2014 to 2019. The class labels “HCM yes” and “HCM no” were assigned by manual review of medical records as well as the outcomes of the gold standard imaging tests for HCM diagnosis. The developed model performed well in finding HCM patients with an accuracy of 95%, recall of 99%, and precision of 97%. The F1 score was 98 %, while 4% of patients were misclassified. This model will be translated into clinical practice for a clinical decision support system in EIMS to assist providers in the accurate diagnosis of HCM from echo data automatically while ensuring high-quality echo interpretation.

Abstract Real-time location systems (RTLS) such as radio frequency identification (RFID) have been shown to improve safety, save cost, and increase patient satisfaction in a healthcare setting especially in the emergency department (ED). Hospital administrators have realized the potential of these applications for improved workflow and operations and are positively adopting it despite the substantial implementation costs of such technologies. Our group has reported several studies with RFID data in the ED showing the relationship between RFID determined patient contact times and length of stay (LOS). In this study, we use ED RFID data to determine the relationship between the total LOS in ED to the overall patient satisfaction obtained from a survey report. ED survey results from 35 questions were obtained from patients after discharge. An observational cohort study was performed in the ED using RFID data from Jan 1 – Dec 31, 2017 matched with the ED survey participants. A total of 2595 survey data was used for logistic regression analysis with the RFID data. Results show that higher treatment LOS influenced overall patient satisfaction negatively. The results provide new insights into designing ideal patient-care team interactions to reduce overall LOS while providing optimal ED care, thereby improving patient satisfaction.