Log In Sign Up

Prediction of Oral Food Challenges via Machine Learning

by   Justin Zhang, et al.

Oral Food Challenges (OFCs) are essential to accurately diagnosing food allergy in patients. However, patients are hesitant to undergo OFCs, and for those that do, there is limited access to allergists in rural/community healthcare settings. The prediction of OFC outcomes through machine learning methods can facilitate the de-labeling of food allergens at home, improve patient and physician comfort during OFCs, and economize medical resources by minimizing the number of OFCs performed. Clinical data was gathered from 1,112 patients who collectively underwent a total of 1,284 OFCs, and consisted of clinical factors including serum specific IgE, total IgE, skin prick tests (SPTs), symptoms, sex, and age. Using these clinical features, machine learning models were constructed to predict outcomes for peanut, egg, and milk challenge. The best performing model for each allergen was created using the Learning Using Concave and Convex Kernels (LUCCK) method, which achieved an Area under the Curve (AUC) for peanut, egg, and milk OFC prediction of 0.76, 0.68, and 0.70, respectively. Model interpretation via SHapley Additive exPlanations (SHAP) indicate that specific IgE, along with wheal and flare values from SPTs, are highly predictive of OFC outcomes. The results of this analysis suggest that machine learning has the potential to predict OFC outcomes and reveal relevant clinical factors for further study.


page 3

page 5

page 7


Predicting Post-Concussion Syndrome Outcomes with Machine Learning

In this paper, machine learning models are used to predict outcomes for ...

Machine Learning-Based Analysis of Sperm Videos and Participant Data for Male Fertility Prediction

Methods for automatic analysis of clinical data are usually targeted tow...

Using Deep Learning-based Features Extracted from CT scans to Predict Outcomes in COVID-19 Patients

The COVID-19 pandemic has had a considerable impact on day-to-day life. ...

An Interpretable Web-based Glioblastoma Multiforme Prognosis Prediction Tool using Random Forest Model

We propose predictive models that estimate GBM patients' health status o...

Prediction of Blood Lactate Values in Critically Ill Patients: A Retrospective Multi-center Cohort Study

Purpose. Elevations in initially obtained serum lactate levels are stron...