RESUMO
BACKGROUND: Early detection of balance-related pathologies in adults using Posturography, anthropometric and personal data is limited. Our goal is to address this issue. It will enable us to identify adults in early stages of balance disorders using easily accessible and measurable data. METHODS: Open-source data of 163 subjects (47 males and 116 females) is used to train and test classification algorithms. Features include mean and standard deviation of the center of pressure displacement, obtained through posturography, the anthropometric and personal variables (age, sex, body mass index, foot length), and Trail Making Test scores. 75% of the data is employed for training and 25% of the data is used for testing. It is then validated using an indigenously collected dataset of healthy individuals. FINDINGS: Accuracy and Sensitivity, both, increases when anthropometric and personal variables are included alongside center of pressure features for classification. Specificity decreases slightly with the addition of anthropometric and personal variables with center of pressure displacement feature, which also affects the classification algorithms' performance. Standard deviation of the center of pressure displacement is found to be more effective than the mean value. A similar trend of the increased performance is observed during validation, except when neural networks were used for the classification. INTERPRETATION: Posturography data, Anthropometric measurements, personal data and self-assessment scales can identify balance issues in adults, making it suitable for community health centers with limited resources. Early detection prompts timely medical care, improving the management of disorders and thus enhancing the quality of life through rehabilitation.
