Identifying influential factors in MRI & CT No-Show prediction

08 August 2024, 13:00 
zoom & Room 206 
Identifying influential factors in MRI & CT No-Show prediction

Join us with Zoom

Identifying influential factors in MRI & CT No-Show prediction

Liat Kaufman-Milo, Tel-Aviv University  Advisors: Prof. Yossi Bukchin, Prof. Neta Rabin

Abstract:

Operational inefficiencies, resource underutilization, and long waiting times, particularly in medical imaging sectors such as MRI and CT scans, present significant challenges in healthcare. This research explores the use of machine learning to predict and mitigate appointment no-shows, a major factor contributing to these inefficiencies. Utilizing a dataset of over 1.1 million appointments from Assuta Medical Centers, this research employs predictive models to identify key factors associated with patient no-shows. The study bridges gaps in existing literature by extending predictions beyond the traditional short horizon before appointments to include forecasting from the booking date, providing earlier opportunities for intervention. Novel factors are introduced to enhance the models' predictive accuracy by integrating operational and patient-specific factors, including time since the last no-show, patient cancellation history, the availability of alternative medical centers, and patient preparation requirements. Our findings show that short horizon forecasts are just slightly more accurate than booking date predictions, making booking date predictions better suited for proactive management. Several models, notably GB, RF, and XGBoost, perform well. The key factors consistently important across these models are recent patient no-show (less than 1 month), cancellation history, and lead time.

 

Bio:

Liat Kaufman-Milo boasts a diverse background in operational management across multiple industries, including insurance and medical devices. She currently holds the position of Head of Organization and Methods at Meitav Provident and Pension Funds Ltd, following a similar role at Clal Insurance Company Ltd. Liat began her professional journey at Tefen Consulting, where she made significant contributions to process optimization. She subsequently ascended to prominent management roles, such as Supply Chain Division Manager at Johnson & Johnson MD&D and VP Integration at Ilex Medical, highlighting her extensive expertise in the medical devices field. For the past 15 years, Liat has also been supervising graduate projects at the Department of Industrial Engineering at Tel Aviv University, demonstrating her commitment to academic mentorship and excellence. With an MBA, a B.Sc in Industrial Engineering and Management, and a master track in Data Science and Big Data at Tel Aviv University, her comprehensive educational and professional experiences have uniquely positioned her to implement innovative approaches that enhance efficiency and effectiveness in healthcare operations using machine learning tools.

Tel Aviv University makes every effort to respect copyright. If you own copyright to the content contained
here and / or the use of such content is in your opinion infringing Contact us as soon as possible >>