An Interoperable Machine Learning Pipeline for Pediatric Obesity Risk Estimation

Abstract

Reliable prediction of pediatric obesity can offer a valuable resource to providers, helping them engage in timely preventive interventions before the disease is established. Many efforts have been made to develop ML-based predictive models of obesity, and some studies have reported high predictive performances. However, no commonly used clinical decision support tool based on existing ML models currently exists. This study presents a novel end-to-end pipeline specifically designed for pediatric obesity prediction, which supports the entire process of data extraction, inference, and communication via an API or a user interface. While focusing only on routinely recorded data in pediatric electronic health records (EHRs), our pipeline uses a diverse expert-curated list of medical concepts to predict the 1-3 years risk of developing obesity. Furthermore, by using the Fast Healthcare Interoperability Resources (FHIR) standard in our design procedure, we specifically target facilitating low-effort integration of our pipeline with different EHR systems. In our experiments, we report the effectiveness of the predictive model as well as its alignment with the feedback from various stakeholders, including ML scientists, providers, health IT personnel, health administration representatives, and patient group representatives.

Keywords: Clinical Decision Support; Deep Learning; FHIR; HER; Interoperability; Pediatric Obesity; Prevention; Primary care.

Figure 5:

Evaluating the predictive model’s robustness by comparing AUROCs (in the test dataset) across five groups (13 subgroups): last WFL before age 2 (3 categories), race (Asian, Black, White, Other), ethnicity (Hispanic, Non-Hispanic), sex (female, male), and payer (private, public).

Figure 1:

Overview of the proposed system. It consists of three main components. (1) A predictive model that has been trained using EHR data to predict the risk of obesity in the next three years. (2) A backend that uses the model to predict the risk of obesity for new patients. (3) A frontend (user interface) for expert interaction with the system.

Figure 2:

The data flow in the pipeline.

Figure 3:

An overview of the machine learning model, using a sample scenario of using 0–2 yr data to predict obesity at 3–7 yr. The encoder (Enc) is a two-layer LSTM network, and the decoder (Dec) consists of two fully connected layers. || shows concatenation.

Figure 4:

The user interface of our pipeline for a hypothetical (synthetic) patient, showing the predictions of the model and the resources the providers and families can use.