MACHINE LEARNING IN PEDIATRIC DISEASE DIAGNOSIS: EVIDENCE, APPLICATIONS, AND FUTURE DIRECTIONS
Keywords:
Pediatric medicine encompasses the diagnosis and management of diseases from birth through adolescence, a period characterized by rapid physiological development, evolving immunological competence, and age-specific pathophysiology [1, 4]. Globally, infectious diseases, nutritional deficiencies, congenital anomalies, and malignancies collectively account for the majority of childhood morbidity and mortality, with disproportionate impact in low- and middle-income countries [3]. Accurate and timely diagnosis in pediatric populations is essential for initiating appropriate therapy, preventing complications, and reducing unnecessary antibiotic and medication use, yet remains challenged by the nonspecific presentation of many childhood illnesses and constraints on invasive investigation [2, 5].Abstract
Pediatric diseases present unique diagnostic challenges due to age-dependent
symptom variability, limited verbal communication from patients, and the necessity of
avoiding invasive procedures. Machine learning (ML) and deep learning (DL)
technologies have increasingly demonstrated potential for transforming diagnostic
References
1. Beam, A.L., and Isaac S. Kohane. "Big data and machine learning in health
care." JAMA 319.13 (2018): 1317-1318.
2. Chadha, M., et al. "Towards the automatic detection of respiratory diseases
using machine learning." IEEE Access 9 (2021): 167986-167999.
3. GBD 2019 Under-5 Mortality Collaborators. "Global, regional, and
national causes of child mortality in 2019." Lancet 399.10341 (2022): 2151-2168.
4. Fleuren, L.M., et al. "Machine learning for the prediction of sepsis: A
systematic review and meta-analysis of diagnostic test accuracy." Intensive Care
Medicine 46.3 (2020): 383-400.
5. Kermany, D.S., et al. "Identifying medical diagnoses and treatable
diseases by image-based deep learning." Cell 172.5 (2018): 1122-1131.
6. Topol, E.J. "High-performance medicine: The convergence of human and
artificial intelligence." Nature Medicine 25.1 (2019): 44-56.
7. Mani, S., et al. "Medical decision support using machine learning for early
detection of neonatal sepsis." Journal of the American Medical Informatics
Association 21.e1 (2014): e119-e124.
8. Pneumonia Child Survival Taskforce. "An assessment of the causes of
deaths in children in sub-Saharan Africa." Archives of Disease in Childhood 93.10
(2008): 883-888.
