Theatre case duration prediction

Status

This project is currently work in progress.

About the project

Key to maximising this session utilisation is the ability to accurately predict the duration of surgical cases at the time of booking (around one month in advance). As well as allowing sessions to be more optimally filled, this may enable booking staff to rebook cancelled sessions at short notice.

There are several published studies which indicate accuarte predictions of case durations are obtainable by machine learning approaches:

• Spence et al (2023)
• Bartek et al (2019)
• Kendale et al (2023)
• Korzhenevich et al (2024)

Note: Only public or dummy data are shared in this repository

Project Structure

• Project currently under development.

Built with

Relevant packages to be captured in requirements file.

Contributing

Contributions and identification of issues are welcomed. Please open an issue if you identify one.

1. Fork the Project
2. Create your Feature Branch (git checkout -b feature/Feature)
3. Commit your Changes (git commit -m 'Add some Feature')
4. Push to the Branch (git push origin feature/Feature)
5. Open a Pull Request

Acknowledgements

• This project was primarily developed by Patrick Devaney as part of a Cambridge Spark Level 7 Apprenticeship in Data Science and AI.