Register now After registration you will be able to apply for this opportunity online.
This opportunity is not published. No applications will be accepted.
Automated Outcome Prediction for Pediatric Orthopedic Surgery
The project aims to develop a predictive model to identify motion features associated with motion improvement in children after surgery.
Keywords: Time-series analysis, biosignal analysis, statistical analysis, biomedical signal processing, and machine learning
Motion analysis data are used for indications and intraoperative dosage in selected pediatric orthopedic surgeries. However, motion data changes after surgery can vary from static parameters. In this project, we will analyze and interpret motion data in a meaningful way for surgeons and can inform clinical decision-making.
Motion analysis data are used for indications and intraoperative dosage in selected pediatric orthopedic surgeries. However, motion data changes after surgery can vary from static parameters. In this project, we will analyze and interpret motion data in a meaningful way for surgeons and can inform clinical decision-making.
- Use motion data to monitor behavior after surgery
- Potentially develop a predictive outcome model
- Write a scientific project report.
**Tasks**
- Literature review (10%)
- Data pre-processing (10%)
- Develop an automated filter to improve the motion signal quality (10%)
- Develop a multi-class machine learning method to differentiate motions before and after surgery (40%)
- Provide feedback to the clinicians (20%)
- Reporting and presentation (10%)
**Your Profile**
- Background in Electrical Engineering, Biomedical Engineering, Mechanical Engineering, Computer Science, or related fields
- Experience with data analysis, signal processing, and machine learning (using Matlab or Python) is desirable.
- Independent worker with critical thinking and problem-solving skills.
- Use motion data to monitor behavior after surgery - Potentially develop a predictive outcome model - Write a scientific project report.
**Tasks**
- Literature review (10%) - Data pre-processing (10%) - Develop an automated filter to improve the motion signal quality (10%) - Develop a multi-class machine learning method to differentiate motions before and after surgery (40%) - Provide feedback to the clinicians (20%) - Reporting and presentation (10%)
**Your Profile**
- Background in Electrical Engineering, Biomedical Engineering, Mechanical Engineering, Computer Science, or related fields - Experience with data analysis, signal processing, and machine learning (using Matlab or Python) is desirable. - Independent worker with critical thinking and problem-solving skills.
Dr Moe Elgendi (moe.elgendi@hest.ethz.ch) and Prof Thomas Dreher (Thomas.Dreher@kispi.uzh.ch) will supervise the student at the Biomedical and Mobile Health Technology Research Group in ETH Zurich’s D-HEST Department of Health Sciences and Technology at Balgrist Campus
Dr Moe Elgendi (moe.elgendi@hest.ethz.ch) and Prof Thomas Dreher (Thomas.Dreher@kispi.uzh.ch) will supervise the student at the Biomedical and Mobile Health Technology Research Group in ETH Zurich’s D-HEST Department of Health Sciences and Technology at Balgrist Campus
