AI–IOT CONVERGENCE IN MODERN HEALTHCARE: A FRAMEWORK FOR PREDICTIVE, DATA-DRIVEN, AND PERSONALIZED MEDICAL SYSTEMS

Abstract

This study addresses an implementation gap in healthcare digitalization: organizations deploy connected sensing and AI analytics yet lack case-based quantitative evidence on which AI-IoT convergence capabilities drive predictive, data-driven, and personalized care benefits. The purpose was to test a convergence framework in a quantitative, cross-sectional, case-study design within a healthcare enterprise case. A five-point Likert survey was administered to 210 stakeholders across clinical, administrative, and health IT roles. Independent variables were AI Analytics Capability (AIC), IoT Data Acquisition Capability (IDC), Interoperability and System Integration (ISI), Data Quality and Governance (DQG), Security and Privacy Assurance (SPA), Infrastructure Readiness (IR), and Clinician/User Acceptance (CUA); outcomes were Predictive Healthcare Effectiveness (PHE), Data-Driven Decision Quality (DDDQ), and Personalized Care Effectiveness (PCE). The analysis plan used descriptive statistics, Cronbach’s alpha, Pearson correlations, and multiple regression. Reliability supported composite scoring (α = .83–.91; PHE α = .90, DDDQ α = .88, PCE α = .91). Baseline ratings exceeded the neutral midpoint (AIC M = 3.86; PHE M = 3.77). Correlations supported positive capability-outcome links (AIC with PHE r = .54; DQG with DDDQ r = .51; p < .01). Regression models showed differentiated drivers: PHE variance explained was 46% (R² = .46), with AIC (β = .31, p < .001), IDC (β = .21, p = .002), DQG (β = .18, p = .006), and IR (β = .20, p = .003) significant; DDDQ variance explained was 44% (R² = .44), led by DQG (β = .34, p < .001) and ISI (β = .22, p = .001), with SPA (β = .16, p = .012) and IR (β = .11, p = .049) also significant; PCE variance explained was 52% (R² = .52), driven by DDDQ (β = .36, p < .001), CUA (β = .29, p < .001), and PHE (β = .19, p = .004). Implications are that healthcare enterprises should prioritize governed data and integration to raise decision quality, pair analytics capability with robust sensing and infrastructure for predictive gains and invest in clinician trust and workflow adoption to convert decision improvements into scalable personalization and inform roadmap priorities for similar enterprise care systems.