Predicting a Positive Antibody Response After 2 SARS-CoV-2 mRNA Vaccines in Transplant Recipients: A Machine Learning Approach With External Validation.

BACKGROUND: Solid organ transplant recipients (SOTRs) are less likely to mount an antibody response to SARS-CoV-2 mRNA vaccines. Understanding risk factors for impaired vaccine response can guide strategies for antibody testing and additional vaccine dose recommendations. METHODS: Using a nationwide observational cohort of 1031 SOTRs, we created a machine learning model to explore, identify, rank, and quantify the association of 19 clinical factors with antibody responses to 2 doses of SARS-CoV-2 mRNA vaccines. External validation of the model was performed using a cohort of 512 SOTRs at Houston Methodist Hospital. RESULTS: Mycophenolate mofetil use, a shorter time since transplant, and older age were the strongest predictors of a negative antibody response, collectively contributing to 76% of the model's prediction performance. Other clinical factors, including transplanted organ, vaccine type (mRNA-1273 versus BNT162b2), sex, race, and other immunosuppressants, showed comparatively weaker associations with an antibody response. This model showed moderate prediction performance, with an area under the receiver operating characteristic curve of 0.79 in our cohort and 0.67 in the external validation cohort. An online calculator based on our prediction model is available at http://transplantmodels.com/covidvaccine/ . CONCLUSIONS: Our machine learning model helps understand which transplant patients need closer follow-up and additional doses of vaccine to achieve protective immunity. The online calculator based on this model can be incorporated into transplant providers' practice to facilitate patient-centric, precision risk stratification and inform vaccination strategies among SOTRs.

One-stop shop for variceal surveillance: integration of unsedated ultrathin endoscopy into the routine clinic visit.

BACKGROUND: The endoscopic appearance of oesophageal varices determines the need for prophylaxis. However, as the point prevalence of varices is low (25%), the majority of surveillance endoscopies are unnecessary and costly. Narrow diameter, ultrathin (UT) endoscopes are more tolerable than conventional upper gastrointestinal (UGI) endoscopes and can be used without sedation. We hypothesised that unsedated UT endoscopy for variceal surveillance could be implemented during the routine outpatient clinic visit allowing accurate diagnosis of varices and the timely provision of prophylaxis. METHODS: Patients with cirrhosis awaiting surveillance endoscopy were identified. UT endoscopy was scheduled during routine clinic review at the same time as ultrasound surveillance for hepatocellular carcinoma. UGI endoscopy was performed unsedated using the E.G Scan II disposable endoscope. Varices were graded using the modified Paquet classification. Video recordings of procedures were reviewed by blinded assessors and agreement was assessed using the kappa statistic. RESULTS: 40 patients (80% male) underwent unsedated UT endoscopy. All procedures were successful and tolerated well in 98% of cases. Median procedure time was 2 min (IQR 1-3). Varices were found in 37.5% (17.5% grade 1 and 20% grade 2). Patients with grade 2 varices were prescribed non-selective beta blockers at the clinic appointment. Kappa statistic for the finding of any varices was 0.636 (p=0.001) and 0.8-1.0 for diagnosis of grade 2 varices (p<0.0001). CONCLUSIONS: Outpatient unsedated ultrathin endoscopy in patients with cirrhosis is accurate, safe and feasible. This integrative care model is convenient, particularly for regional communities, and is likely to result in significant cost savings associated with variceal surveillance.