Direkt zum Inhalt springen
login.png Login join.png Register    |
Support subgroup
de | en
MyTUM-Portal
Technische Universität München

Technische Universität München

Sitemap > Schwarzes Brett > Abschlussarbeiten, Bachelor- und Masterarbeiten > Bachelor Thesis: Predicting No-Show Appointments in an Orthopedic Ambulatory Clinic Using Machine Learning
auf   Zurück zu  Nachrichten-Bereich      Browse in News  nächster    

Bachelor Thesis: Predicting No-Show Appointments in an Orthopedic Ambulatory Clinic Using Machine Learning

06.03.2025, Abschlussarbeiten, Bachelor- und Masterarbeiten

This thesis project aims to develop machine learning models to classify patients based on their likelihood of missing appointments at the orthopedic ambulatory clinic of a university hospital in Germany.

Background

Missed medical appointments, commonly referred to as no-shows, represent a significant and persistent challenge within ambulatory clinics, impacting both operational efficiency and patient care quality.

Objectives

This study seeks to analyze appointment attendance behavior among orthopedic patients and derive insights into factors influencing no-shows. Furthermore, by leveraging machine learning techniques, the project aims to develop predictive models to classify patients based on their no-show risk. The findings will support the development of targeted intervention strategies to reduce no-show rates and optimize scheduling efficiency. The project is based on a real-world clinical dataset from an orthopedic ambulatory clinic.

While the project framework is flexible and can be tailored based on research interests, the core tasks include:

  • Literature Review: Review existing predictive methodologies for appointment no-shows, with a focus on clinical applications.
  • Exploratory Data Analysis (EDA): Examine key dataset characteristics, variable distributions, and relationships between potential predictors. The raw data will require preprocessing and cleaning.
  • Machine Learning Model Development and Evaluation: Implement and evaluate two to three machine learning models, with the option to include ensemble methods, to predict the probability of no-shows for individual appointments.
  • Results Analysis and Presentation: Evaluate predictive accuracy, identify key risk factors associated with no-shows, and explore potential intervention strategies to reduce missed appointments.

    • What We Offer

  • Real-world clinical dataset spanning 20+ years
  • Opportunities for publication in academic journals
  • Interdisciplinary collaboration with medical and computer science experts
  • Regular feedback and mentorship from domain specialists
  • Top-level hardware for scientific computing
  • Flexible start dates (thesis opportunities available year-round)
  • ork environment in German or English, with the thesis conducted in English

    • Prerequisites

    Prior experience in data wrangling and advanced predictive modeling techniques.

    How to Apply

    Send an email to laura.amenda@tum.de with the following:

  • Your CV
  • A brief introduction outlining your background and motivation
  • Your preferred start date
  • Academic transcripts

    • We look forward to receiving your email!

    References

    Ding, Xiruo, et al. "Designing risk prediction models for ambulatory no-shows across different specialties and clinics." Journal of the American Medical Informatics Association 25.8 (2018): 924-930.https://doi.org/10.1093/jamia/ocy002

    Mun, Jeffrey S., et al. "Patient “No-Show” Prior to Elective Primary Total Hip Arthroplasty Increases Risk of Postoperative Anemia." Arthroplasty Today 31 (2025): 101602.https://www.sciencedirect.com/science/article/pii/S2352344124002875

    Robaina, Joey A., et al. "Predicting no-shows in paediatric orthopaedic clinics." BMJ Health & Care Informatics 27.1 (2020): e100047.https://doi.org/10.1136/bmjhci-2019-100047

    Srinivas, Sharan, and A. Ravi Ravindran. "Optimizing outpatient appointment system using machine learning algorithms and scheduling rules: A prescriptive analytics framework." Expert Systems with Applications 102 (2018): 245-261.https://doi.org/10.1016/j.eswa.2018.02.022

    Kontakt: laura.amenda@tum.de

    Aktuelles

    RSS Feed RSS