Capsule Endoscopy in Inflammatory Bowel Disease: Panenteric Capsule Endoscopy and Application of Artificial Intelligence

Video capsule endoscopy (VCE) of the small-bowel has been proven to accurately diagnose small-bowel inflammation and to predict future clinical flares among patients with Crohn’s disease (CD). In 2017, the panenteric capsule (PillCam Crohn’s system) was introduced for the first time, enabling a reliable evaluation of the whole small and large intestines. The great advantage of visualization of both parts of the gastrointestinal tract in a feasible and single procedure, holds a significant promise for patients with CD, enabling determination of the disease extent and severity, and potentially optimize disease management. In recent years, applications of machine learning, for VCE have been well studied, demonstrating impressive performance and high accuracy for the detection of various gastrointestinal pathologies, among them inflammatory bowel disease lesions. The use of artificial neural network models has been proven to accurately detect/classify and grade CD lesions, and shorten the VCE reading time, resulting in a less tedious process with a potential to minimize missed diagnosis and better predict clinical outcomes. Nevertheless, prospective, and real-world studies are essential to precisely examine artificial intelligence applications in real-life inflammatory bowel disease practice.

Seroconversion following SARS-CoV-2 Infection or Vaccination in Pediatric IBD Patients

ObjectiveInflammatory bowel disease (IBD) patients are commonly treated with immunomodulatory medications, and the effect of these medications on seroconversion to SARS-CoV-2 infection and vaccination are scant, particularly in pediatrics. We sought to determine serologic responses to SARS-CoV-2 infection and vaccination in pediatric IBD patients. DesignWe conducted a single-center, retrospective study of all pediatric ([≤]21 years old) IBD patients in whom a SARS-CoV-2 IgG Antibody Assay was performed between April 2020 and May 2021 at our tertiary care center. This assay measures IgG antibody to the full-length SARS-CoV-2 spike protein and was routinely collected at infusion and outpatient clinic visits. The primary outcome was SARS-CoV-2 seroconversion, and the secondary outcome was titer level, with high titer defined as [≥]960 titer or >40 AU/mL. Clinical characteristics, including demographics, IBD location, behavior, activity, and therapy, SARS-CoV-2 exposures, COVID-19 testing and symptoms, SARS-CoV-2 infection status (WHO COVID-19: Case Definitions, 2020) and COVID-19 vaccination status and type, were gathered, and univariate analyses examined associations between clinical characteristics and outcome measures. ResultsThere were 340 pediatric patients with SARS-CoV-2 Antibody Testing; 15% for confirmed or probable COVID-19, 2% for suspected COVID-19, 16% for asymptomatic exposure to a close contact with SARS-CoV-2 infection, 61% without any prior symptoms or exposures, and 6% for history of COVID-19 vaccination. Patients with confirmed or probable COVID-19 infection had a 90% rate of seroconversion, with 76% of these patients on biologic therapy. Patients post-infection without seroconversion had a significantly longer interval between infection and antibody assay (P=0.03). Within those with asymptomatic SARS-CoV-2 exposure, 43% had seroconversion, and there were no identified clinical characteristics associated with positive titer. All pediatric patients who received vaccination seroconverted, and all who received mRNA vaccinations, including one after a single dose, achieved high titer levels; 100% of those who received vaccination were on biologic or small molecule therapy, including one on combination therapy with ustekinumab and tofacitinib. ConclusionPediatric IBD patients have strong serologic antibody responses to SARS-CoV-2 infection and COVID-19 vaccination despite high rates of immunomodulatory therapy.

Federated Learning of Electronic Health Records Improves Mortality Prediction in Patients Hospitalized with COVID-19

Machine learning (ML) models require large datasets which may be siloed across different healthcare institutions. Using federated learning, a ML technique that avoids locally aggregating raw clinical data across multiple institutions, we predict mortality within seven days in hospitalized COVID-19 patients. Patient data was collected from Electronic Health Records (EHRs) from five hospitals within the Mount Sinai Health System (MSHS). Logistic Regression with L1 regularization (LASSO) and Multilayer Perceptron (MLP) models were trained using local data at each site, a pooled model with combined data from all five sites, and a federated model that only shared parameters with a central aggregator. Both the federated LASSO and federated MLP models performed better than their local model counterparts at four hospitals. The federated MLP model also outperformed the federated LASSO model at all hospitals. Federated learning shows promise in COVID-19 EHR data to develop robust predictive models without compromising patient privacy.

Evaluation of the clinical significance of sonographic perinephric fluid in patients with renal colic.

OBJECTIVE: To evaluate the significance of sonographic perinephric fluid collection on the emergent management of patients with acute urinary stone obstruction. METHODS: We conducted a prospective study with retrospective analysis. Since January 2016 through July 2017, patients admitted to our tertiary hospital's emergency department (ED) with suspected symptomatic urinary stones underwent ultrasound evaluation. Images were prospectively interpreted by experienced radiologist who analyzed each case for the following imaging features: hydronephrosis, perinephric fluid and urethral stone identification. The presence and measurements of perinephric fluid were re-evaluated by second radiologist who was blinded for the first reader's measurements. Retrospective analysis was conducted to evaluate for an association between perinephric fluid collection and the following outcome variables: need for analgesics, the number of doses of analgesics and the amount of morphine (mg) in the ED, elevation of creatinine levels, hospitalization and need for urological interventions. RESULTS: The need for analgesics, the number of doses of analgesics and the amount of morphine were significantly associated with the presence of perinephric fluid (p < 0.05). The odds ratio for the need for analgesics was 3.8 in the presence of any perinephric fluid, and 8.9 in the presence of moderate/severe perinephric fluid. No other patient outcome variables were found to be significantly associated with the presence of perinephric fluid (p > 0.05). CONCLUSIONS: This study shows a correlation between sonographic evidence of perinephric fluid and more severe pain. Therefore, an emergency physician can consider the evidence of perinephric fluid, in acute urethral stone obstruction, a predictor for more severe pain.