The UAE's Emirates Health Services deployed AI to predict appointment no-shows across all primary health centres in October 2022. No-show rates fell 51% (21%→10%), average wait time dropped 5.7 min (54→48.5 min), saving 387,000 patient-minutes in 3 months.
appointment management, no-show prediction, primary health care, random forest, real-time analytics, healthcare operations, patient access
Context
Emirates Health Services (EHS), the UAE federal authority for primary health care in the Northern Emirates, manages over 140,000 patient visits monthly across its primary health centres and faced a 21% baseline appointment no-show rate causing resource waste, longer waits, and reduced access.
Objectives
Reduce appointment no-shows and improve resource allocation through predictive risk alerts.
Activities
In October 2022, EHS deployed the 'Footstep Insights Solution', a random-forest classification model trained on 16 demographic, clinical, and appointment-specific features, categorising patients as high-risk (≥90%), medium-risk (80-89%), or low-risk (70-79%) of no-show; clinical staff receive proactive alerts to contact high-risk patients or reallocate slots via a real-time dashboard.
Results
A peer-reviewed before-after study (JMIR Formative Research, January 2025) compared 67,429 pre-implementation appointments (Jul-Sep 2022) with 67,964 post-implementation appointments (Nov 2022-Jan 2023): no-show rates fell from 20.82% to 10.25% (a statistically significant 50.7% reduction; OR 0.43, 95% CI 0.42-0.45, P<.001); average wait time fell from 54 to 48.5 minutes, saving 387,394 patient-minutes over three months; the model achieved 86% accuracy.
Conclusions
The study received Dubai Research Ethics Committee approval and EHS has published an organisational AI Policy; limitations include the mitigation workflow operating outside the EHR system and the absence of long-term follow-up, financial-impact analysis, or demographic bias assessment.
Implementation
Implementation detail (cost, timeline, staffing, conditions for success) is not yet available for this practice.
Commonly funded by
National / regional programmes
Indicative funding routes for practices of this type — always check each programme's current calls and eligibility rules.
Do you run this practice?
Claim it —
verified implementers get a public contact pathway and can propose corrections.
Data sources
Where this practice's information was retrieved from, and when.
Moscow's public health department centrally benchmarks and deploys a marketplace of 50+ vetted computer-vision diagnostic tools as a mandatory "second …
Estonia's open-source virtual-assistant ecosystem giving citizens a single conversational channel to public services, integrated across 18+ organisations, with human hand-off …
Sweden's National Archives built an in-house AI handwriting-recognition model, trained via a three-year citizen-science transcription effort, to make over a …