Pulse.

a daily field guide to health research that matters

◆ Console

‹ Sun · 5 Jul 2026
Near-term implementable finding

Artificial neural network modelling using complete blood count for the early detection of black lung disease among Indonesian coal miners: A retrospective longitudinal study

Blood cell counts alone can flag early lung disease in coal miners, offering a simple screening tool to protect workers before symptoms develop.

A retrospective longitudinal study developed and internally validated an ANN using routine CBC parameters to predict early pneumoconiosis in 807 Indonesian coal miners over 8 years. Eosinophil and monocyte counts were the most influential predictors, supporting integration of CBC-based ML screening into occupational health surveillance for high-risk populations.

What the study was

Study design
Retrospective longitudinal ML study with ANN (n=807 coal miners, 2013-2021)
Population
807 Indonesian coal miners, 8-year longitudinal follow-up
Sample size
807
Category
Diagnostics
Maturity
Validated
Journal
J Infect Public Health

Why it surfaced

CBC-based ANN for occupational lung disease early detection; n=807 longitudinal dataset; demonstrates practical utility of routine hematology data for ML-driven disease prediction in underserved occupational population.

A plain-language summary of published research — not medical advice. Talk to a clinician about your own care.