ABSTRACT
Purpose: The purpose of this study is to identify clinical and imaging characteristics associated with post-COVID pulmonary function decline. Methods: This study included 22 patients recovering from COVID-19 who underwent serial spirometry pulmonary function testing (PFT) before and after diagnosis. Patients were divided into two cohorts by difference between baseline and post-COVID follow-up PFT: Decline group (>10 % decrease in FEV1), and Stable group (≤10 % decrease or improvement in FEV1). Demographic, clinical, and laboratory data were collected, as well as PFT and chest computed tomography (CT) at the time of COVID diagnosis and follow-up. CTs were semi-quantitatively scored on a five-point severity scale for disease extent in each lobe by two radiologists. Mann-Whitney U-tests, T-tests, and Chi-Squared tests were used for comparison. P-values <0.05 were considered statistically significant. Results: The Decline group had a higher proportion of neutrophils (79.47 ± 4.83 % vs. 65.45 ± 10.22 %; p = 0.003), a higher absolute neutrophil count (5.73 ± 2.68 × 109/L vs. 3.43 ± 1.74 × 109/L; p = 0.031), and a lower proportion of lymphocytes (9.90 ± 4.20 % vs. 21.21 ± 10.97 %; p = 0.018) compared to the Stable group. The Decline group also had significantly higher involvement of ground-glass opacities (GGO) on follow-up chest CT [8.50 (4.50, 14.50) vs. 3.0 (1.50, 9.50); p = 0.032] and significantly higher extent of reticulations on chest CT at time of COVID diagnosis [6.50 (4.00, 9.00) vs. 2.00 (0.00, 6.00); p = 0.039] and follow-up [5.00 (3.00, 13.00) vs. 2.00 (0.00, 5.00); p = 0.041]. ICU admission was higher in the Decline group than in the Stable group (71.4 % vs. 13.3 %; p = 0.014). Conclusions: This study provides novel insight into factors influencing post-COVID lung function, irrespective of pre-existing pulmonary conditions. Our findings underscore the significance of neutrophil counts, reduced lymphocyte counts, pulmonary reticulation on chest CT at diagnosis, and extent of GGOs on follow-up chest CT as potential indicators of decreased post-COVID lung function. This knowledge may guide prediction and further understanding of long-term sequelae of COVID-19 infection.
ABSTRACT
PURPOSE: To develop and evaluate a deep convolutional neural network (DCNN) model for the classification of acute and chronic lung nodules from nontuberculous mycobacterial-lung disease (NTM-LD) on computed tomography (CT). MATERIALS AND METHODS: We collected a data set of 650 nodules (316 acute and 334 chronic) from the CT scans of 110 patients with NTM-LD. The data set was divided into training, validation, and test sets in a ratio of 4:1:1. Bounding boxes were used to crop the 2D CT images down to the area of interest. A DCNN model was built using 11 convolutional layers and trained on these images. The performance of the model was evaluated on the hold-out test set and compared with that of 3 radiologists who independently reviewed the images. RESULTS: The DCNN model achieved an area under the receiver operating characteristic curve of 0.806 for differentiating acute and chronic NTM-LD nodules, corresponding to sensitivity, specificity, and accuracy of 76%, 68%, and 72%, respectively. The performance of the model was comparable to that of the 3 radiologists, who had area under the receiver operating characteristic curve, sensitivity, specificity, and accuracy of 0.693 to 0.771, 61% to 82%, 59% to 73%, and 60% to 73%, respectively. CONCLUSIONS: This study demonstrated the feasibility of using a DCNN model for the classification of the activity of NTM-LD nodules on chest CT. The model performance was comparable to that of radiologists. This approach can potentially and efficiently improve the diagnosis and management of NTM-LD.
Subject(s)
Deep Learning , Lung Neoplasms , Pneumonia , Humans , Neural Networks, Computer , Tomography, X-Ray Computed/methods , Radiographic Image Interpretation, Computer-Assisted/methods , Retrospective Studies , Lung Neoplasms/diagnostic imagingABSTRACT
Stereotactic ablative body radiation (SABR) delivers high rates of local control in early-stage non-small cell lung cancer (NSCLC); however, systemic immune effects are poorly understood. Here, we evaluate the early pathologic and immunologic effects of SABR. Blood/core-needle tumor biopsies were collected from six patients with stage I NSCLC before and 5-7 days after SABR (48 Gy/4 or 50 Gy/5 fractions). Serial blood was collected up to 1-year post-SABR. We used immunohistochemistry to evaluate pathological changes, immune-cell populations (CD8, FoxP3), and PD-L1/PD-1 expression within the tumor. We evaluated T-cell receptor (TCR) profile changes in the tumor using TCR sequencing. We used the MANAFEST (Mutation-Associated Neoantigen Functional Expansion of Specific T-cells) assay to detect peripheral neoantigen-specific T-cell responses and dynamics. At a median follow-up of 40 months, 83% of patients (n=5) were alive without tumor progression. Early post-SABR biopsies showed viable tumor and similar distribution of immune-cell populations as compared with baseline samples. Core-needle samples proved insufficient to detect population-level TCR-repertoire changes. Functionally, neoantigen-specific T-cells were detected in the blood prior to SABR. A subset of these patients had a transient increase in the frequency of neoantigen-specific T-cells between 1 week and 3-6 months after SABR. SABR alone could induce a delayed, transient neoantigen-specific T-cell immunologic response in patients with stage I NSCLC.
Subject(s)
Carcinoma, Non-Small-Cell Lung , Lung Neoplasms , Small Cell Lung Carcinoma , Humans , Carcinoma, Non-Small-Cell Lung/pathology , Prospective Studies , Treatment Outcome , Receptors, Antigen, T-Cell/geneticsABSTRACT
Rationale: Strict adherence to procedural protocols and diagnostic definitions is critical to understand the efficacy of new technologies. Electromagnetic navigational bronchoscopy (ENB) for lung nodule biopsy has been used for decades without a solid understanding of its efficacy, but offers the opportunity for simultaneous tissue acquisition via electromagnetic navigational transthoracic biopsy (EMN-TTNA) and staging via endobronchial ultrasound (EBUS). Objective: To evaluate the diagnostic yield of EBUS, ENB, and EMN-TTNA during a single procedure using a strict a priori definition of diagnostic yield with central pathology adjudication. Methods: A prospective, single-arm trial was conducted at eight centers enrolling participants with pulmonary nodules (<3 cm; without computed tomography [CT]- and/or positron emission tomography-positive mediastinal lymph nodes) who underwent a staged procedure with same-day CT, EBUS, ENB, and EMN-TTNA. The procedure was staged such that, when a diagnosis had been achieved via rapid on-site pathologic evaluation, the procedure was ended and subsequent biopsy modalities were not attempted. A study finding was diagnostic if an independent pathology core laboratory confirmed malignancy or a definitive benign finding. The primary endpoint was the diagnostic yield of the combination of CT, EBUS, ENB, and EMN-TTNA. Measurements and Main Results: A total of 160 participants at 8 centers with a mean nodule size of 18 ± 6 mm were enrolled. The diagnostic yield of the combined procedure was 59% (94 of 160; 95% confidence interval [CI], 51-66%). Nodule regression was found on same-day CT in 2.5% of cases (4 of 160; 95% CI, 0.69-6.3%), and EBUS confirmed malignancy in 7.1% of cases (11 of 156; 95% CI, 3.6-12%). The yield of ENB alone was 49% (74 of 150; 95% CI, 41-58%), that of EMN-TTNA alone was 27% (8 of 30; 95% CI, 12-46%), and that of ENB plus EMN-TTNA was 53% (79 of 150; 95% CI, 44-61%). Complications included a pneumothorax rate of 10% and a 2% bleeding rate. When EMN-TTNA was performed, the pneumothorax rate was 30%. Conclusions: The diagnostic yield for ENB is 49%, which increases to 59% with the addition of same-day CT, EBUS, and EMN-TTNA, lower than in prior reports in the literature. The high complication rate and low diagnostic yield of EMN-TTNA does not support its routine use. Clinical trial registered with www.clinicaltrials.gov (NCT03338049).
ABSTRACT
BACKGROUND/AIM: Flammulina velutipes (FV), also known as the golden needle mushroom, is an edible and medicinal fungus that contains bioactive substances regulating various physiological functions. While the fruiting bodies of FV are commonly consumed, their stipes are often discarded despite containing polysaccharides. In this study, the biological functions of FV stipes (FV-S) were investigated to reduce waste and pollution while increasing their value. MATERIALS AND METHODS: The antioxidant activity of FV was evaluated using three methods: the DPPH radical-scavenging capacity assay, ferrous ion chelating assay, and reducing power analysis. The anti-cancer potential was assessed through MTT viability and immunoblotting analyses. RESULTS: Results showed that FV-S had higher polysaccharide and total phenolic contents and greater antioxidant abilities, particularly in ethanolic extracts. FV-S also exhibited significant anticancer properties, specifically in hot water extracts with high polysaccharide contents, and suppressed prostate cancer cell viability by inhibiting androgen receptor and PCa-specific antigen mRNA expression while inducing caspase-3/7 activation. CONCLUSION: FV-S is rich in bioactive components, possesses higher antioxidant and anticancer abilities, and has potential as an anticancer agent, which could enhance the value of FV.
Subject(s)
Antineoplastic Agents , Flammulina , Neoplasms , Male , Humans , Antioxidants/metabolism , Flammulina/chemistry , Flammulina/genetics , Flammulina/metabolism , Polysaccharides/pharmacology , Antineoplastic Agents/pharmacology , Antineoplastic Agents/metabolismABSTRACT
ChatGPT's responses to questions about lung cancer and LCS, although deemed clinically appropriate by cardiothoracic radiologists, were difficult to read. Simplified responses from three LLMs (ChatGPT, GPT-4, and Bard) had improved reading ease and readability (in terms of U.S. grade levels). However, some simplified responses were no longer clinically appropriate.
ABSTRACT
OBJECTIVES: To describe a single-centre North American adult cohort of anti-MDA5-positive dermatomyositis patients, with emphasis on drug-free long-term remission. METHODS: We conducted an observational retrospective cohort study of anti-MDA5-positive DM patients. All consented patients seen in the Johns Hopkins Myositis Centre from 2003-2020 with suspected muscle disease were routinely screened for myositis-specific autoantibodies. All sera were screened for anti-MDA5 autoantibodies by line blot; positives were verified by enzyme-linked immunoassay. Patients whose sera were anti-MDA5 positive by both assays (n=52) were followed longitudinally. If clinical status was unavailable, structured telephone interviews were conducted. Clinical remission was defined as being off all immunosuppression >1 year while remaining asymptomatic. RESULTS: 38/52 (73%) of the patients were women with a median age at disease-onset of 47 (IQR 40-54). Twenty-five of the patients (48%) were White, 16 (30%) were Black and 3 (6%) were Asian. Most patients (42/52, 80%) had interstitial lung disease, defined by inflammatory or fibrotic changes on high resolution computed tomography (HRCT). 18/52 (35%) of patients required pulse-dose methylprednisolone, 4/52 (8%) experienced spontaneous pneumothorax/pneumomediastinum, 6/52 (12%) required intubation, and 5/52 (10%) died. Over longitudinal follow-up (median 3.5 years), 9 (18%) patients achieved clinical remission. The median time from symptom onset to clinical remission was 4 years, and the median duration of sustained remission was 3.5 years (range 1.4-7.8). No demographic or disease characteristics were significantly associated with remission. CONCLUSIONS: In this single centre, tertiary referral population of anti-MDA5-positive dermatomyositis, ~20% of patients experienced long-term drug-free remission after a median disease duration of 4 years. No clinical or biologic factors were associated with clinical remission.
Subject(s)
Dermatomyositis , Myositis , Adult , Female , Humans , Male , Autoantibodies , Dermatomyositis/complications , Interferon-Induced Helicase, IFIH1 , Myositis/complications , Retrospective Studies , Middle AgedABSTRACT
As novel therapeutic regimens continue to lead to increased survival of patients with lung cancer, it is imperative to remain mindful of the accompanying increase in the incidence of new primary malignancies. Although the most common secondary malignancies in patients with lung cancer have historically included colon, rectal, esophageal, and thyroid cancers, we report here two rare cases of new primary hepatocellular carcinomas in patients receiving immune checkpoint inhibitor therapy for NSCLC. In both cases, the diagnosis of hepatocellular carcinoma, rather than assuming a hepatic metastasis, was crucial for determining the appropriate approach for treatment. These cases thus underscore the importance of appropriate diagnostics to ensure that the proper therapeutics are chosen and present important considerations for the lung cancer community going forward.
ABSTRACT
Rationale: Indoor air pollution represents a modifiable risk factor for respiratory morbidity in chronic obstructive pulmonary disease (COPD). The effects of indoor air pollution, as well as the impact of interventions to improve indoor air quality, on cardiovascular morbidity in COPD remain unknown. Objectives: To determine the association between indoor particulate matter (PM) and heart rate variability (HRV), a measure of cardiac autonomic function tied to cardiovascular morbidity and mortality, as well as the impact of household air purifiers on HRV. Methods: Former smokers with moderate-severe COPD were recruited from a 6-month randomized controlled trial of a portable air cleaner intervention to undergo paired assessment of both in-home PM and HRV using 24-hour Holter monitoring at up to five time points. Primary outcomes were HRV measures tied to cardiovascular morbidity (standard deviation of normal-to-normal intervals [SDNN] and root mean square of successive differences between normal-to-normal intervals [RMSSD]). Measurements and Results: Eighty-five participants contributed 317 HRV measurements. A twofold increase in household PM ⩽2.5 µm in aerodynamic diameter was associated with decreases in SDNN (ß, -2.98% [95% confidence interval (CI), -5.12 to -0.78]) and RMSSD (ß, -4.57% [95% CI, -10.1 to -1.60]). The greatest effects were observed with ultrafine particles (<100 nm) (RMSSD; ß, -16.4% [95% CI, -22.3 to -10.1]) and among obese participants. Participants randomized to the active air cleaner saw improvements in RMSSD (ß, 25.2% [95% CI, 2.99 to 52.1]), but not SDNN (ß, 2.65% [95% CI, -10.8 to 18.1]), compared with the placebo group. Conclusions: This is the first U.S. study to describe the association between household PM and cardiac autonomic function among individuals with COPD, as well as the potential cardiovascular health benefits of household air cleaners.
Subject(s)
Air Pollutants , Air Pollution, Indoor , Air Pollution , Cardiovascular Diseases , Pulmonary Disease, Chronic Obstructive , Humans , Air Pollution, Indoor/adverse effects , Particulate Matter/adverse effects , Heart , Heart Rate/physiology , Air Pollutants/adverse effectsABSTRACT
Introduction: Antiplatelet therapy has been associated with fewer exacerbations and reduced respiratory symptoms in chronic obstructive pulmonary disease (COPD). Whether platelet activation is associated with respiratory symptoms in COPD is unknown. Methods: Former smokers with spirometry-confirmed COPD had urine 11-dehydro-thromboxane B2 (11dTxB2), plasma soluble CD40L (sCD40L), and soluble P-selectin (sP-selectin) repeatedly measured during a 6- to 9-month study period. Multivariate mixed-effects models adjusted for demographics, clinical characteristics, and medication use evaluated the association of each biomarker with respiratory symptoms, health status, and quality of life. Results: Among 169 participants (average age 66.5±8.2 years, 51.5% female, 47.5±31 pack years, forced expiratory volume in 1 second percent predicted 53.8±17.1), a 100% increase in 11dTxB2 was associated with worse respiratory symptoms reflected by higher scores on the COPD Assessment Test (ß 0.77, 95% confidence interval [CI]: 0.11-1.4) and Ease of Cough and Sputum Clearance Questionnaire ß 0.77, 95%CI: 0.38-1.2, worse health status (Clinical COPD Questionnaire ß 0.13, 95%CI: 0.03-0.23) and worse quality of life (St George's Respiratory Questionnaire ß 1.9, 95%CI: 0.39-3.4). No statistically significant associations were observed for sCD40L or sP-selectin. There was no consistent statistically significant effect modification of the relationship between urine 11dTxB2 and respiratory outcomes by history of cardiovascular disease, subclinical coronary artery disease, antiplatelet therapy, or COPD severity. Conclusions: In stable moderate-severe COPD, elevated urinary11dTxB2, a metabolite of the platelet activation product thromboxane A2, was associated with worse respiratory symptoms, health status, and quality of life.
ABSTRACT
BACKGROUND: Anti-melanoma differentiation-associated gene 5 (anti-MDA5) antibodies in patients with dermatomyositis are associated with rapidly progressive interstitial lung disease (RP-ILD). Computed tomography (CT) plays a central role in the diagnosis of RP-ILD and may help characterize the temporal changes. METHODS: We report five anti-MDA5-positive dermatomyositis patients with serial CT scans spanning their acute RP-ILD disease course. RESULTS: Our case series highlights the variable imaging pattern that can manifest in this setting, including diffuse alveolar damage and nonspecific interstitial pneumonia patterns. Three patients in our series died within 4 months of their disease onset, whereas the other two patients survived. CONCLUSION: The serial CT changes in anti-MDA5 disease are dynamic and variable; therefore, it is imperative to maintain a broad differential when faced with these HRCT patterns to improve the diagnosis and management of this underrecognized entity.
Subject(s)
Dermatomyositis , Lung Diseases, Interstitial , Humans , Interferon-Induced Helicase, IFIH1 , Dermatomyositis/diagnostic imaging , Dermatomyositis/complications , Lung Diseases, Interstitial/diagnostic imaging , Lung Diseases, Interstitial/complications , Autoantibodies , Disease ProgressionABSTRACT
An elderly man with refractory Mycobacterium abscessus lung disease previously developed anti-phage neutralizing antibodies while receiving intravenous phage therapy. Subsequent phage nebulization resulted in transient weight gain, decreased C-reactive protein, and reduced Mycobacterium burden. Weak sputum neutralization may have limited the outcomes, but phage resistance was not a contributing factor.
ABSTRACT
Although natural language processing (NLP) can rapidly extract disease labels from radiology reports to create datasets for deep learning models, this may be less accurate than having radiologists manually review the images. In this study, we compared agreement between natural language processing (NLP) and radiologist-curated labels for possible tuberculosis (TB) on chest radiographs (CXR) and evaluated the performance of deep convolutional neural networks (DCNN) trained to identify TB using the preceding two sets of labels. We collected 10,951 CXRs from the NIH ChestX-ray14 dataset and labeled them as positive or negative for possible TB based on two methods: 1) NLP-derived disease labels and 2) radiologist-review of images. These images were used to train DCNNs on varying dataset sizes for possible TB and tested on an external dataset of 800 CXRs. Area under the ROC curve (AUC) was used to evaluate DCNNs. There was poor agreement between NLP and radiologist-curated labels for potential TB (Kappa coefficient 0.34). DCNNs trained using radiologist-curated labels had higher performance than the algorithm trained using the NLP-labels, regardless of the number of images used for training. The best-performing DCNN had an AUC of 0.88, which was trained on 10,951 images using the radiologist-annotated sets. DCNNs trained on CXRs labeled by a radiologist consistently outperformed those trained on the same CXRs labeled by NLP, highlighting the benefit of radiologists' determining groundtruth for machine learning dataset curation.
Subject(s)
Deep Learning , Data Curation , Humans , Natural Language Processing , Radiography, Thoracic/methods , Radiologists , Retrospective StudiesABSTRACT
OBJECTIVE: Patients with anti-melanoma-differentiation-associated 5 (anti-MDA5)-positive dermatomyositis (DM) share several striking similarities to patients with SARS-CoV-2. Our objective was to assess the prevalence of anti-angiotensin converting enzyme-2 (ACE2) immunoglobulin M (IgM) antibodies, found in patients with severe SARS-CoV-2, in two independent anti-MDA5-positive DM cohorts. METHODS: Anti-ACE2 IgM antibodies were assayed by enzyme-linked immunosorbent assay (ELISA) in two anti-MDA5-positive DM cohorts: a predominantly outpatient North American cohort (n = 52) and a Japanese cohort enriched for new-onset disease (n = 32). Additionally, 118 patients with SARS-CoV-2 with a spectrum of clinical severity were tested for anti-MDA5 antibodies by ELISA. RESULTS: Five of fifty-two (9.6%) North American patients and five of thirty-two (15%) Japanese patients were positive for anti-ACE2 IgM. In the North American cohort, all five patients with anti-ACE2 IgM antibodies had proximal muscle weakness, had interstitial lung disease, were significantly more likely to receive pulse dose methylprednisolone (80% vs 30%, P = 0.043), and had worse forced vital capacity (median 59% predicted vs 78%, P = 0.056) compared with the anti-ACE2-IgM-negative group. In the Japanese cohort, all five anti-ACE2-IgM-positive patients also required pulse dose methylprednisolone, and three of five (60%) patients died. Japanese patients with anti-ACE2 IgM had significantly worse oxygenation, as defined by a lower partial pressure of oxygen (PaO2)/fraction of inspired oxygen (FiO2) ratio (233 vs 390, P = 0.021), and a higher alveolar-arterial oxygenation gradient (91 vs 23 mm Hg, P = 0.024) than the IgM-negative group. CONCLUSION: We describe anti-ACE2 IgM autoantibodies in two independent cohorts with anti-MDA5-positive DM. These autoantibodies may be biomarkers for severe disease and provide insight into disease pathogenesis.
ABSTRACT
OBJECTIVES: We aimed to develop deep learning models using longitudinal chest X-rays (CXRs) and clinical data to predict in-hospital mortality of COVID-19 patients in the intensive care unit (ICU). METHODS: Six hundred fifty-four patients (212 deceased, 442 alive, 5645 total CXRs) were identified across two institutions. Imaging and clinical data from one institution were used to train five longitudinal transformer-based networks applying five-fold cross-validation. The models were tested on data from the other institution, and pairwise comparisons were used to determine the best-performing models. RESULTS: A higher proportion of deceased patients had elevated white blood cell count, decreased absolute lymphocyte count, elevated creatine concentration, and incidence of cardiovascular and chronic kidney disease. A model based on pre-ICU CXRs achieved an AUC of 0.632 and an accuracy of 0.593, and a model based on ICU CXRs achieved an AUC of 0.697 and an accuracy of 0.657. A model based on all longitudinal CXRs (both pre-ICU and ICU) achieved an AUC of 0.702 and an accuracy of 0.694. A model based on clinical data alone achieved an AUC of 0.653 and an accuracy of 0.657. The addition of longitudinal imaging to clinical data in a combined model significantly improved performance, reaching an AUC of 0.727 (p = 0.039) and an accuracy of 0.732. CONCLUSIONS: The addition of longitudinal CXRs to clinical data significantly improves mortality prediction with deep learning for COVID-19 patients in the ICU. KEY POINTS: ⢠Deep learning was used to predict mortality in COVID-19 ICU patients. ⢠Serial radiographs and clinical data were used. ⢠The models could inform clinical decision-making and resource allocation.
Subject(s)
COVID-19 , Deep Learning , Humans , Intensive Care Units , Radiography , X-RaysABSTRACT
BACKGROUND: Deep convolutional neural networks (DCNNs) for diagnosis of disease on chest radiographs (CXR) have been shown to be biased against males or females if the datasets used to train them have unbalanced sex representation. Prior work has suggested that DCNNs can predict sex on CXR, which could aid forensic evaluations, but also be a source of bias. OBJECTIVE: To (1) evaluate the performance of DCNNs for predicting sex across different datasets and architectures and (2) evaluate visual biomarkers used by DCNNs to predict sex on CXRs. MATERIALS AND METHODS: Chest radiographs were obtained from the Stanford CheXPert and NIH Chest XRay14 datasets which comprised of 224,316 and 112,120 CXRs, respectively. To control for dataset size and class imbalance, random undersampling was used to reduce each dataset to 97,560 images that were balanced for sex. Each dataset was randomly split into training (70%), validation (10%), and test (20%) sets. Four DCNN architectures pre-trained on ImageNet were used for transfer learning. DCNNs were externally validated using a test set from the opposing dataset. Performance was evaluated using area under the receiver operating characteristic curve (AUC). Class activation mapping (CAM) was used to generate heatmaps visualizing the regions contributing to the DCNN's prediction. RESULTS: On the internal test set, DCNNs achieved AUROCs ranging from 0.98 to 0.99. On external validation, the models reached peak cross-dataset performance of 0.94 for the VGG19-Stanford model and 0.95 for the InceptionV3-NIH model. Heatmaps highlighted similar regions of attention between model architectures and datasets, localizing to the mediastinal and upper rib regions, as well as to the lower chest/diaphragmatic regions. CONCLUSION: DCNNs trained on two large CXR datasets accurately predicted sex on internal and external test data with similar heatmap localizations across DCNN architectures and datasets. These findings support the notion that DCNNs can leverage imaging biomarkers to predict sex and potentially confound the accurate prediction of disease on CXRs and contribute to biased models. On the other hand, these DCNNs can be beneficial to emergency radiologists for forensic evaluations and identifying patient sex for patients whose identities are unknown, such as in acute trauma.
Subject(s)
Deep Learning , Algorithms , Female , Humans , Male , Neural Networks, Computer , Radiography , RadiologistsABSTRACT
RATIONALE AND OBJECTIVES: The coronavirus pandemic upended in-person radiology education and led to a transition to virtual platforms. We needed a new method to monitor lecture attendance, previously relying on a physical badge system. Our goal was to develop and implement a virtual conference attendance system that is user-friendly, automated, useable in any virtual conference environment, and accurate. MATERIALS AND METHODS: We developed a web-based platform to serve as a virtual conference attendance tracking and evaluation platform. Daily, the application synchronizes with our lecture calendar to identify scheduled conferences and generates a unique attendance link for each event. The link is automatically posted in the conference chat and attendees must be logged in by the time it is posted to click the link, prompting single sign-on authentication. We integrated the system with resident schedules to excuse residents when appropriate. Real-time attendance reports are accessible in a user-friendly dashboard with a 5-star lecture review and comment system. We surveyed residents on satisfaction with the application after 1-year of use. RESULTS: Over the 2020-2021 academic year, we registered 376 conferences with 5,040 virtual swipes from 65 users. Once set up, virtual swipes take seconds to perform with minimal disruption to the conference. Average satisfaction for the platform was rated as 4.69 on a scale of 1 to 5. All respondents agreed or strongly agreed that use of the platform should be continued for future years, with 85% strongly agreeing. CONCLUSION: We developed an online platform for radiology conference attendance logging and evaluation, designed for virtual conferences.