An Adaptive Computational Intelligence Approach to Personalised Health and Immune Age Characterisation from Common Haematological Markers

• Main Authors: Zenil, Hector, Hernández-Quiroz, Francisco, Hernández-Orozco, Santiago, Uthamacumaran, Abicumaran, Saeb-Parsy, Kourosh
• Format: Journal Article
• Language: English
• Published: 02.03.2023
• Subjects: Quantitative Biology - Quantitative Methods
• DOI: 10.48550/arxiv.2303.01444

We introduce a simulated digital model that learns a person's optimal blood health over time. Using a learning adaptive algorithm, our model provides a risk assessment score that compares an individual's chronological age from birth to an estimation of a biological immune age derived from the score. We demonstrate its efficacy against real and synthetic data from medically relevant cases, extreme cases, and empirical blood cell count data from 100K data records in the Centers for Disease Control and Prevention's National Health and Nutrition Examination Survey (CDC NHANES) that spans 13 years. We find that the score is informative when distinguishing healthy individuals from those with diseases, both self-reported and abnormal blood tests manifested, providing an entry-level score for patient triaging. We show that, by analyzing an individual's Full Blood Count (FBC) or Complete Blood Count (CBC), test results over time allows us to calculate an immune age score that correlates with chronological age. The immune age score, derived solely from popular hematological markers, can be widely used to serve purposes of precise healthcare, and predictive medicine.