Predicting Healthcare Provider Engagement in SMS Campaigns

TL;DR

The paper tackles predicting healthcare provider engagement in SMS campaigns by identifying factors that drive click-through on embedded links. It employs three predictive approaches—logistic regression, random forest, and a neural network—trained on millions of Impiricus messages from 2024–2025. The results show that prior positive demeanor, concise messages, and fewer links robustly predict engagement, with demographics and specialty having limited impact. The findings offer practical guidance for designing SMS outreach that is faster to read, more credible, and more likely to elicit action, and point to future work on temporal features and reinforcement learning to optimize delivery in real time.

Abstract

As digital communication grows in importance when connecting with healthcare providers, traditional behavioral and content message features are imbued with renewed significance. If one is to meaningfully connect with them, it is crucial to understand what drives them to engage and respond. In this study, the authors analyzed several million text messages sent through the Impiricus platform to learn which factors influenced whether or not a doctor clicked on a link in a message. Several key insights came to light through the use of logistic regression, random forest, and neural network models, the details of which the authors discuss in this paper.

Figures (2)

• Figure 1: Top feature importances from the Random Forest model. Demeanor dominates, followed by links sent and message length.
• Figure 2: Training and validation loss curves for the Neural Network across 20 epochs, showing stable convergence without overfitting.