Reducing Outpatient MRI Appointment No-show Rate Through Artificial Intelligence Predictive Analytics
Technology
Singapore Healthcare Management Congress
SingHealth
31 December 2021
To reduce no-show rates, minimize MRI lead times, and improve service accessibility and patient care. Successfully implemented model; future applications include other imaging modalities like CT or US.
Year Submitted: 2021
Published Date: 31 December 2021
Tags: Technology, Digitalisation, Automation, Artificial Intelligence, Digital Health, Data Management, Data Analytics
About this Content
Aims
To reduce no-show rates, minimize MRI lead times, and improve service accessibility and patient care.
Background
Increasing MRI no-show rates caused resource wastage, clinic delays, and reduced healthcare accessibility.
Methods
Developed machine learning model (XGBoost) to predict high-risk no-shows; radiographers pre-contacted patients identified as high-risk.
Results
Achieved 17.2% relative reduction in no-shows; improved resource utilization; saved $180,000 annually.
Conclusion
Successfully implemented model; future applications include other imaging modalities like CT or US.
Lessons Learnt
Predictive analytics combined with preemptive actions significantly reduced no-show rates and improved care access.
Additional Information
Awarded Merit Award (Operations Category) at SHM 2021.
Keywords
Predictive Analytics, MRI No-Show, AI, Radiology, Cost Savings, XGBoost
Innovators' Details
Innovators' Details
Healthcare Cluster(s) | SingHealth |
Organization(s) Involved | Changi General Hospital |
Platform(s) | Singapore Healthcare Management Congress |
Healthcare Professional Group(s) | Healthcare Administration |
Applicable Specialty or Discipline | Healthcare Administrators |
Project Lead(s) | Lisa Tham Mui Hiong |
Project Member(s) | Lee Lee Lian |
Connect with this contributor!
Lisa Tham Mui Hiong - singaporehealthcaremanagement@singhealth.com.sg
Project Attachment
457_CGH_SHM_2021_Reducing_Outpatient_MRI_Appointment_No_show_CMBD.pdf