@misc{9242911,
  abstract     = {{Forensic pathology is a branch of medicine that aims to determine the manner and cause of unnatural, suspicious or unexpected deaths that require a legal investigation. An important part of determining the cause of death is the examination of the body through an autopsy. The purpose of this project is to evaluate whether machine learning algorithms can predict cause of death based on autopsy data. The dataset used contains autopsy variables and cause of death extracted from 23 000 autopsy reports. In order to see if there exists groups within the dataset that correspond with the causes of death, dimension reduction and clustering is performed with UMAP and hierarchical clustering. The classification is performed with four different models tasked with classifying heart failure. The four models are logistic regression, random forest, neural network and TabPFN. The classifiers performed quite similar to each other and all performed AUC scores between 0.75-0.79. Meaning all models performed better than randomly guessing. In conclusion, the project works as a proof of concept for classifying cause of death based on autopsy data. In order to increase the performance of the classifiers, other autopsy variables better capturing differences between the causes of death need to be extracted from the autopsy reports.}},
  author       = {{Svensson, Alexander}},
  issn         = {{1404-6342}},
  language     = {{eng}},
  note         = {{Student Paper}},
  series       = {{Master's Theses in Mathematical Sciences}},
  title        = {{From data to diagnosis in forensic pathology}},
  year         = {{2026}},
}