2013/12/06 by Balázs Szalkai, Szalkai, Balazs, Vince Kornél Grolmusz +5
Biochemistry, Genetics and Molecular Biology · Computer Science · #Applications (stat.AP) #Biomedical Text Mining and Ontologies #Data Mining Algorithms and Applications #FOS: Biological sciences #FOS: Computer and information sciences #Neurons and Cognition (q-bio.NC)
paper · pdf · doi:10.48550/arxiv.1312.1876
openalex publication_date 2013/12/06 · openalex created_date 2022/10/02 · openalex updated_date 2026/07/28
Background: The concept of combinatorial biomarkers was conceived around\n2010: it was noticed that simple biomarkers are often inadequate for\nrecognizing and characterizing complex diseases.\n Methods: Here we present an algorithmic search method for complex biomarkers\nwhich may predict or indicate Alzheimer's disease (AD) and other kinds of\ndementia. We applied data mining techniques that are capable to uncover\nimplication-like logical schemes with detailed quality scoring. Our program\nSCARF is capable of finding multi-factor relevant association rules\nautomatically. The new SCARF program was applied for the Tucson, Arizona based\nCritical Path Institute's CAMD database, containing laboratory and cognitive\ntest data for more than 6000 patients from the placebo arm of clinical trials\nof large pharmaceutical companies, and consequently, the data is much more\nreliable than numerous other databases for dementia.\n Results: The results suggest connections between liver enzyme-, B12 vitamin-,\nsodium- and cholesterol levels and dementia, and also some hematologic\nparameter-levels and dementia.\n