Abschlussarbeiten, Bachelor- und Masterarbeiten

20.08.2025, Abschlussarbeiten, Bachelor- und Masterarbeiten

Background:
Efficient hospital planning relies heavily on accurate estimates of surgery durations. Actual surgery times often vary due to patient characteristics, procedure types, and operational factors. This variability can lead to delays and complicate resource allocation. The goal of this Master’s thesis is to develop data-driven methods to estimate surgery durations based on relevant features and to create a reusable pipeline for predicting durations on future data.

Tasks:
The student will develop and evaluate predictive models for surgery durations. This includes data preprocessing, feature engineering, model development, and validation. By the end of the project, the student will deliver a list of surgeries with estimated durations along with a reproducible methodology that can support hospital scheduling.

Subtasks:

• Review literature on surgery duration estimation and predictive modeling in healthcare.
• Explore and preprocess the dataset, handle missing values, and standardize formats.
• Identify relevant features (e.g., procedure type, patient characteristics, surgeon, time of day).
• Transform categorical and numerical variables appropriately and assess feature importance.
• Implement statistical and machine learning models (e.g., linear regression, random forest, gradient boosting).
• Train models on historical data and optimize hyperparameters.
• Compare different models and select the best-performing approach.
• Develop a reusable prediction pipeline for new data.
• Document the workflow and methodology for reproducibility and future use.
• Produce a list of surgeries with estimated durations.
• Summarize findings, insights, and recommendations for hospital scheduling.

Requirements:

• Enrollment in Computer Science, Data Science, or a related field.
• Strong programming and data analysis skills (Python, R, SQL).
• Knowledge of machine learning models and their application.
• Interest in healthcare applications and predictive modeling.

Kontakt: sidra.rashid@tum.de

Mehr Information

https://www.pm.mh.tum.de/miti/startseite/