Developing Data-based 'Nudge' Strategies to Enhance Preventive Care Compliance and Reduce Systemic Expenditure in Public Health Hospitals

Abstract

Preventive care non-compliance remains a persistent challenge in public health clinics, contributing to avoidable disease progression and escalating systemic expenditures. This research paper develops a data-driven behavioral intervention framework, grounded in nudge theory, to enhance patient adherence to preventive screenings and vaccinations while reducing overall costs. The problem is defined by the gap between evidence-based preventive guidelines and actual patient behavior, often exacerbated by cognitive biases and resource constraints. The purpose is to design, model, and evaluate nudge strategies personalized via predictive analytics. Using a mixed-methods design, the study integrates quantitative analysis of electronic health records (EHRs) from three public health clinics with a quasi-experimental pilot intervention (n=450 patients). Predictive business analytics, following methods discussed by Hossain et al. (2023), were employed to segment patients based on predicted non-compliance risk. Nudge strategiesincluding opt-out framing, loss-framed messaging, and social comparison feedback—were deployed via a secure patient portal. Key findings indicate that data-driven nudges increased preventive screening completion by 28.6% (p<0.01) and reduced per-patient systemic expenditure on downstream acute care by 17.4% over six months. The conclusion implies that integrating behavioral economics with routine clinical data infrastructures offers a scalable, low-cost mechanism for improving public health outcomes and financial sustainability. This study contributes empirical evidence for policy makers and clinic administrators seeking non-regulatory interventions to optimize preventive care delivery.