Identifying and improving the "ground truth" of race in disparities research through improved EMR data reporting. A systematic review.

BACKGROUND: Studies about racial disparities in healthcare are increasing in quantity; however, they are subject to vast differences in definition, classification, and utilization of race/ethnicity data. Improved standardization of this information can strengthen conclusions drawn from studies using such data. The objective of this study is to examine how data related to race/ethnicity are recorded in research through examining articles on race/ethnicity health disparities and examine problems and solutions in data reporting that may impact overall data quality. METHODS: In this systematic review, Business Source Complete, Embase.com, IEEE Xplore, PubMed, Scopus and Web of Science Core Collection were searched for relevant articles published from 2000 to 2020. Search terms related to the concepts of electronic medical records, race/ethnicity, and data entry related to race/ethnicity were used. Exclusion criteria included articles not in the English language and those describing pediatric populations. Data were extracted from published articles. This review was organized and reported in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) 2020 statement for systematic reviews. FINDINGS: In this systematic review, 109 full text articles were reviewed. Weaknesses and possible solutions have been discussed in current literature, with the predominant problem and solution as follows: the electronic medical record (EMR) is vulnerable to inaccuracies and incompleteness in the methods that research staff collect this data; however, improved standardization of the collection and use of race data in patient care may help alleviate these inaccuracies. INTERPRETATION: Conclusions drawn from large datasets concerning peoples of certain race/ethnic groups should be made cautiously, and a careful review of the methodology of each publication should be considered prior to implementation in patient care.

Fusion of imaging and non-imaging data for disease trajectory prediction for coronavirus disease 2019 patients.

Purpose: Our study investigates whether graph-based fusion of imaging data with non-imaging electronic health records (EHR) data can improve the prediction of the disease trajectories for patients with coronavirus disease 2019 (COVID-19) beyond the prediction performance of only imaging or non-imaging EHR data. Approach: We present a fusion framework for fine-grained clinical outcome prediction [discharge, intensive care unit (ICU) admission, or death] that fuses imaging and non-imaging information using a similarity-based graph structure. Node features are represented by image embedding, and edges are encoded with clinical or demographic similarity. Results: Experiments on data collected from the Emory Healthcare Network indicate that our fusion modeling scheme performs consistently better than predictive models developed using only imaging or non-imaging features, with area under the receiver operating characteristics curve of 0.76, 0.90, and 0.75 for discharge from hospital, mortality, and ICU admission, respectively. External validation was performed on data collected from the Mayo Clinic. Our scheme highlights known biases in the model prediction, such as bias against patients with alcohol abuse history and bias based on insurance status. Conclusions: Our study signifies the importance of the fusion of multiple data modalities for the accurate prediction of clinical trajectories. The proposed graph structure can model relationships between patients based on non-imaging EHR data, and graph convolutional networks can fuse this relationship information with imaging data to effectively predict future disease trajectory more effectively than models employing only imaging or non-imaging data. Our graph-based fusion modeling frameworks can be easily extended to other prediction tasks to efficiently combine imaging data with non-imaging clinical data.

Decoding radiology reports: Potential application of OpenAI ChatGPT to enhance patient understanding of diagnostic reports.

PURPOSE: To evaluate the complexity of diagnostic radiology reports across major imaging modalities and the ability of ChatGPT (Early March 2023 Version, OpenAI, California, USA) to simplify these reports to the 8th grade reading level of the average U.S. adult. METHODS: We randomly sampled 100 radiographs (XR), 100 ultrasound (US), 100 CT, and 100 MRI radiology reports from our institution's database dated between 2022 and 2023 (N = 400). These were processed by ChatGPT using the prompt "Explain this radiology report to a patient in layman's terms in second person: ". Mean report length, Flesch reading ease score (FRES), and Flesch-Kincaid reading level (FKRL) were calculated for each report and ChatGPT output. T-tests were used to determine significance. RESULTS: Mean report length was 164 ± 117 words, FRES was 38.0 ± 11.8, and FKRL was 10.4 ± 1.9. FKRL was significantly higher for CT and MRI than for US and XR. Only 60/400 (15%) had a FKRL <8.5. The mean simplified ChatGPT output length was 103 ± 36 words, FRES was 83.5 ± 5.6, and FKRL was 5.8 ± 1.1. This reflects a mean decrease of 61 words (p < 0.01), increase in FRES of 45.5 (p < 0.01), and decrease in FKRL of 4.6 (p < 0.01). All simplified outputs had FKRL <8.5. DISCUSSION: Our study demonstrates the effective use of ChatGPT when tasked with simplifying radiology reports to below the 8th grade reading level. We report significant improvements in FRES, FKRL, and word count, the last of which requires modality-specific context.

Graph-based Fusion Modeling and Explanation for Disease Trajectory Prediction.

We propose a relational graph to incorporate clinical similarity between patients while building personalized clinical event predictors with a focus on hospitalized COVID-19 patients. Our graph formation process fuses heterogeneous data, i.e., chest X-rays as node features and non-imaging EHR for edge formation. While node represents a snap-shot in time for a single patient, weighted edge structure encodes complex clinical patterns among patients. While age and gender have been used in the past for patient graph formation, our method incorporates complex clinical history while avoiding manual feature selection. The model learns from the patient's own data as well as patterns among clinically-similar patients. Our visualization study investigates the effects of 'neighborhood' of a node on its predictiveness and showcases the model's tendency to focus on edge-connected patients with highly suggestive clinical features common with the node. The proposed model generalizes well by allowing edge formation process to adapt to an external cohort.

Graph-based Fusion Modeling and Explanation forDisease Trajectory Prediction.

We propose a relational graph to incorporate clinical similarity between patients while building personalized clinical event predictors with a focus on hospitalized COVID-19 patients. Our graph formation process fuses heterogeneous data, i.e., chest X-rays as node features and non-imaging EHR for edge formation. While node represents a snap-shot in time for a single patient, weighted edge structure encodes complex clinical patterns among patients. While age and gender have been used in the past for patient graph formation, our method incorporates complex clinical history while avoiding manual feature selection. The model learns from the patient's own data as well as patterns among clinically-similar patients. Our visualization study investigates the effects of 'neighborhood' of a node on its predictiveness and showcases the model's tendency to focus on edge-connected patients with highly suggestive clinical features common with the node. The proposed model generalizes well by allowing edge formation process to adapt to an external cohort.

Academic Radiology in the United States: Defining Gender Disparities in Faculty Leadership and Academic Rank.

RATIONALE AND OBJECTIVES: Female physicians in academic medicine have faced barriers that potentially affect representation in different fields and delay promotion. Little is known about gender representation differences in United States academic radiology departments, particularly within the most pursued subspecialties. PURPOSE: To determine whether gender differences exist in United States academic radiology departments across seven subspecialties with respect to academic ranks, departmental leadership positions, experience, and scholarly metrics. MATERIALS AND METHODS: In this cross-sectional study from November 2018 to June 2020, a database of United States academic radiologists at 129 academic departments in seven subspecialties was created. Each radiologist's academic rank, departmental leadership position (executive-level - Chair, Director, Chief, and Department or Division Head vs vice-level - vice, assistant, or associate positions of executive level), self-identified gender, years in practice, and measures of scholarly productivity (number of publications, citations, and h-index) were compiled from institutional websites, Doximity, LinkedIn, Scopus, and official NPI profiles. The primary outcome, gender composition differences in these cohorts, was analyzed using Chi2 while continuous data were analyzed using Kruskal-Wallis rank sum test. The adjusted gender difference for all factors was determined using a multivariate logistic regression model. RESULTS: Overall, 5086 academic radiologists (34.7% women) with a median 14 years of practice (YOP) were identified and indexed. There were 919 full professors (26.1% women, p < 0.01) and 1055 executive-level leadership faculty (30.6% women, p < 0.01). Within all subspecialties except breast imaging, women were in the minority (35.4% abdominal, 79.1% breast, 12.1% interventional, 27.5% musculoskeletal, 22.8% neuroradiology, 45.1% pediatric, and 19.5% nuclear; p < 0.01). Relative to subspecialty gender composition, women full professors were underrepresented in abdominal, pediatric, and nuclear radiology (p < 0.05) and women in any executive-level leadership were underrepresented in abdominal and nuclear radiology (p < 0.05). However, after adjusting for h-index and YOP, gender did not influence rates of professorship or executive leadership. The strongest single predictors for professorship or executive leadership were h-index and YOP. CONCLUSION: Women academic radiologists in the United States are underrepresented among senior faculty members despite having similar levels of experience as men. Gender disparities regarding the expected number of women senior faculty members relative to individual subspecialty gender composition were more pronounced in abdominal and nuclear radiology, and less pronounced in breast and neuroradiology. Overall, h-index and YOP were the strongest predictors for full-professorship and executive leadership among faculty. KEY RESULTS: ● Though women comprise 34.7% of all academic radiologists, women are underrepresented among senior faculty members (26.1% of full professors and 30.6% of executive leadership) ● Women in junior faculty positions had higher median years of practice than their male counterparts (10 vs 8 for assistant professors, 21 vs 13 for vice leadership) ● Years of practice and h-index were the strongest predictors for full professorship and executive leadership.

Patient-specific COVID-19 resource utilization prediction using fusion AI model.

The strain on healthcare resources brought forth by the recent COVID-19 pandemic has highlighted the need for efficient resource planning and allocation through the prediction of future consumption. Machine learning can predict resource utilization such as the need for hospitalization based on past medical data stored in electronic medical records (EMR). We conducted this study on 3194 patients (46% male with mean age 56.7 (±16.8), 56% African American, 7% Hispanic) flagged as COVID-19 positive cases in 12 centers under Emory Healthcare network from February 2020 to September 2020, to assess whether a COVID-19 positive patient's need for hospitalization can be predicted at the time of RT-PCR test using the EMR data prior to the test. Five main modalities of EMR, i.e., demographics, medication, past medical procedures, comorbidities, and laboratory results, were used as features for predictive modeling, both individually and fused together using late, middle, and early fusion. Models were evaluated in terms of precision, recall, F1-score (within 95% confidence interval). The early fusion model is the most effective predictor with 84% overall F1-score [CI 82.1-86.1]. The predictive performance of the model drops by 6 % when using recent clinical data while omitting the long-term medical history. Feature importance analysis indicates that history of cardiovascular disease, emergency room visits in the past year prior to testing, and demographic factors are predictive of the disease trajectory. We conclude that fusion modeling using medical history and current treatment data can forecast the need for hospitalization for patients infected with COVID-19 at the time of the RT-PCR test.

Clinical Approach to and Work-up of Bleeding Patients.

A bleeding patient is a common consult for interventional radiologists. Prompt triage, preprocedural evaluation specific to the site of hemorrhage, and knowledge of resuscitative strategies allow for a potentially life-saving procedure to be appropriately and safely performed. Having a firm understanding of the clinical work-up and management of a bleeding patient has never been more important. In this article, a discussion of the clinical approach and work-up of a bleeding patient for whom interventional radiology is consulted is followed by a discussion of etiology-specific preprocedural work-up.

Correlation of CT Angiography and 99mTechnetium-Labeled Red Blood Cell Scintigraphy to Catheter Angiography for Lower Gastrointestinal Bleeding: A Single-Institution Experience.

PURPOSE: To investigate the correlation of computed tomography (CT) angiography and 99mTechnetium-labeled red blood cell (RBC) scintigraphy to catheter angiography (CA) in the management of lower gastrointestinal bleeding (LGIB) while considering potential nephrotoxic effects of iodinated contrast. MATERIALS AND METHODS: From November 2012 to August 2017, 223 CAs performed for LGIB, including massive, ongoing, and obscure bleeding, were retrospectively identified in patients with pre-procedural CT angiography or RBC scintigraphy. Positive correlations and sensitivities were calculated for CT angiography and RBC scintigraphy using CA results as reference. Correlations were then compared while considering certain clinical presentations of LGIB. Contrast dose was compared with maximum creatinine recorded 48-72 hours after. RESULTS: Thirty-eight patients underwent CT angiography; 173 patients underwent RBC scintigraphy; and 12 patients completed both studies. CT angiography had a positive correlation of 67.7% (95% confidence interval [CI]: 57.0, 76.7) and sensitivity of 85.2% (95% CI: 66.3, 95.8), whereas RBC scintigraphy had a positive correlation of 29.3% (95% CI: 27.7, 31.0) and sensitivity of 94.4% (95% CI: 84.6, 98.8). CT angiography had higher positive correlation across all clinical presentations. No dose-toxicity relationship was observed between contrast and renal function (R2: 0.008), nor was there a difference in incidence of contrast-induced nephropathy between CT angiography and RBC scintigraphy (P = .30). CONCLUSIONS: CT angiography has greater positive correlation to CA than RBC scintigraphy for assessing LGIB in active stable as well as hemodynamically unstable LGIB. As such, greater adoption of CT angiography may reduce the number of nontherapeutic CAs performed. Additional contrast associated with CT angiography does not result in increased nephrotoxicity.

Percutaneous Image-Guided Cryoneurolysis.

OBJECTIVE: The aim of this article is to review the available evidence regarding image-guided percutaneous cryoneurolysis, with a focus on indications, technique, efficacy, and potential complications. CONCLUSION: Percutaneous image-guided cryoneurolysis is safe and effective for the management of several well-described syndromes involving neuropathic pain. Additional rigorous prospective study is warranted to further define the efficacy and specific role of these interventions.