@inproceedings{e5a99326910649328d919ed12e6c269a,
title = "Bigger Isn{\textquoteright}t Always Better: Data Considerations for Latent Class Analysis",
abstract = "Increasingly large datasets of clinical information present a significant opportunity to stratify patients for a more personalised approach to care. However, these data can be sparse and noisy, requiring processing of this data to be carefully considered. Here, we apply different minimum prevalence thresholds to diagnosis codes in a cohort of Multiple Sclerosis patients. We use this data to stratify patients using latent class analysis and examine the effect of different prevalence thresholds on the classes generated. We also examine computation efficiency using several disease-specific datasets.",
keywords = "Big Data, ICD10, Latent Class Analysis, Multiple Sclerosis",
author = "Stafford, \{Imogen S.\} and Nophar Geifman",
note = "Publisher Copyright: {\textcopyright} 2025 The Authors.; 35th Medical Informatics Europe Conference, MIE 2025 ; Conference date: 19-05-2025 Through 21-05-2025",
year = "2025",
month = may,
day = "15",
doi = "10.3233/SHTI250377",
language = "English",
series = "Studies in Health Technology and Informatics",
publisher = "IOS Press BV",
pages = "447--451",
editor = "Elisavet Andrikopoulou and Parisis Gallos and Arvanitis, \{Theodoros N.\} and Rosalynn Austin and Arriel Benis and Ronald Cornet and Panagiotis Chatzistergos and Alexander Dejaco and Linda Dusseljee-Peute and Alaa Mohasseb and Pantelis Natsiavas and Haythem Nakkas and Philip Scott",
booktitle = "Intelligent Health Systems - From Technology to Data and Knowledge, Proceedings of MIE 2025",
address = "Netherlands",
}