Transporting an Artificial Intelligence Model to Predict Emergency Cesarean Delivery: Overcoming Challenges Posed by Interfacility Variation

Abstract

Research using artificial intelligence (AI) in medicine is expected to significantly influence the practice of medicine and the delivery of health care in the near future. However, for successful deployment, the results must be transported across health care facilities. We present a cross-facilities application of an AI model that predicts the need for an emergency caesarean during birth. The transported model showed benefit; however, there can be challenges associated with interfacility variation in reporting practices.

Keywords: AI; ML; algorithm transport; artificial intelligence; birth; health care facilities; health outcomes; machine learning; neonatal; pediatrics; pregnancy; prenatal.

Figure 1

(A) Comparing the performance of Hospital A labor progression model (in blue) transported to Hospital B (yellow/blue bar) versus Hospital B local model (in yellow) and (B) Comparing the performance of Hospital B labor progression model (in yellow) transported to Hospital A (blue/yellow bar) versus Hospital A local model (in blue). AUC: area under the curve.

Figure 2

(A) Comparing the performance of Hospital B labor progression model (in yellow) transported to Hospital A versus Hospital B model after alignment adjustments transported to Hospital A (blue/yellow bars) versus Hospital A local model (in blue) and (B) Comparing the performance of Hospital A labor progression model transported to Hospital B (yellow/blue bar) versus Hospital B local models trained on progressively larger local electronic medical record (EMR) data sets of 5000, 15,000, and 25,000 (in yellow). AUC: area under the curve.