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

Area of Science:

• Immunology
• Vaccinology
• Transplant Medicine

Background:

• Solid organ transplant recipients (SOTRs) exhibit diminished antibody responses to SARS-CoV-2 mRNA vaccines.
• Identifying factors associated with poor vaccine response is crucial for optimizing SOTR immunity.

Purpose of the Study:

• To develop and validate a machine learning model predicting antibody response to SARS-CoV-2 mRNA vaccines in SOTRs.
• To identify and rank clinical factors influencing vaccine immunogenicity in this vulnerable population.

Main Methods:

• A nationwide cohort of 1031 SOTRs was used to build a machine learning model.
• 19 clinical factors were analyzed for their association with antibody response after two vaccine doses.
• External validation was performed on a separate cohort of 512 SOTRs.

Main Results:

• Mycophenolate mofetil use, shorter time since transplant, and older age were the strongest predictors of a negative antibody response.
• These factors accounted for 76% of the model's predictive performance.
• The model achieved an AUC of 0.79 in the primary cohort and 0.67 in the validation cohort.

Conclusions:

• The machine learning model aids in identifying SOTRs requiring closer monitoring and potential additional vaccine doses.
• An accessible online calculator can assist clinicians in risk stratification and tailoring vaccination strategies for SOTRs.