Search engine for discovering works of Art, research articles, and books related to Art and Culture
ShareThis
Javascript must be enabled to continue!

Prediction of the height of the longitudinal arch of the foot based on plantographic indicators by means of artificial intelligence

View through CrossRef
The height of the longitudinal arch of the foot is an indicator reflecting the smallest distance between the lower edge of the articulation of the navicular and medial cuneiform bones and the support. It is used to detect the lowering of the longitudinal arch of the foot in orthopedic foot diseases. An urgent task is to predict the height of the longitudinal arch based on plantographic and podometric indicators using artificial intelligence (AI) technologies to reduce radiation exposure during diagnosis and the selection of orthopedic products. To predict the height of the longitudinal arch of the foot, an artificial intelligence model based on plantographic indicators was developed and evaluated. The study included 37 people who underwent computer plantography and radiography of their feet under load. Correlation analysis was used to select significant features, and a comparative analysis of AI models was conducted to determine the optimal machine learning algorithm. According to the results of the correlation analysis, a significant (p≤0.05) relationship with the height of the longitudinal arch was identified, and the following indicators were selected for further AI model training: the length of the foot from the most prominent point of the heel rounding to the center of the base of the second toe, the linear index of arch height, the coefficient of spreading of the forefoot, the maximum width of the forefoot, and the angle of deviation of the first toe. The best performance in predicting the height of the longitudinal arch of the foot was demonstrated by the Random Forest model with a mean square error (MSE) of 6.4359, a mean absolute error (MAE) of 2.1674, a coefficient of determination (R2) of 0.6932, a mean absolute percentage error (MAPE) of 7.6152 %, and a root mean square error (RMSE) of 2.5369. The developed Random Forest model demonstrates a high predictive accuracy for the height of the longitudinal arch of the foot based on plantographic and podometric indicators, justifying its use for diagnosis, selection, and design of orthopedic products for the correction and compensation of foot deformities.
Title: Prediction of the height of the longitudinal arch of the foot based on plantographic indicators by means of artificial intelligence
Description:
The height of the longitudinal arch of the foot is an indicator reflecting the smallest distance between the lower edge of the articulation of the navicular and medial cuneiform bones and the support.
It is used to detect the lowering of the longitudinal arch of the foot in orthopedic foot diseases.
An urgent task is to predict the height of the longitudinal arch based on plantographic and podometric indicators using artificial intelligence (AI) technologies to reduce radiation exposure during diagnosis and the selection of orthopedic products.
To predict the height of the longitudinal arch of the foot, an artificial intelligence model based on plantographic indicators was developed and evaluated.
The study included 37 people who underwent computer plantography and radiography of their feet under load.
Correlation analysis was used to select significant features, and a comparative analysis of AI models was conducted to determine the optimal machine learning algorithm.
According to the results of the correlation analysis, a significant (p≤0.
05) relationship with the height of the longitudinal arch was identified, and the following indicators were selected for further AI model training: the length of the foot from the most prominent point of the heel rounding to the center of the base of the second toe, the linear index of arch height, the coefficient of spreading of the forefoot, the maximum width of the forefoot, and the angle of deviation of the first toe.
The best performance in predicting the height of the longitudinal arch of the foot was demonstrated by the Random Forest model with a mean square error (MSE) of 6.
4359, a mean absolute error (MAE) of 2.
1674, a coefficient of determination (R2) of 0.
6932, a mean absolute percentage error (MAPE) of 7.
6152 %, and a root mean square error (RMSE) of 2.
5369.
The developed Random Forest model demonstrates a high predictive accuracy for the height of the longitudinal arch of the foot based on plantographic and podometric indicators, justifying its use for diagnosis, selection, and design of orthopedic products for the correction and compensation of foot deformities.

Related Results

On Flores Island, do "ape-men" still exist? https://www.sapiens.org/biology/flores-island-ape-men/
On Flores Island, do "ape-men" still exist? https://www.sapiens.org/biology/flores-island-ape-men/
<span style="font-size:11pt"><span style="background:#f9f9f4"><span style="line-height:normal"><span style="font-family:Calibri,sans-serif"><b><spa...
Intervention of arch support: A quantitative study
Intervention of arch support: A quantitative study
Hallux valgus is a common foot deformity characterized by hypermobility of the first metatarsal ray. The lower longitudinal arch is an intrinsic factor related to the lateral drift...
In-plane bearing capacity analysis of concrete catenary arch with rigid skeleton: test and simulation
In-plane bearing capacity analysis of concrete catenary arch with rigid skeleton: test and simulation
Abstract Although the rigid skeleton concrete arch has been widely used in engineering, the research on the failure mode and bearing capacity of this kind of arch is very...
The Distribution of Foot Arch Types among Footballers in Bayelsa State, Nigeria
The Distribution of Foot Arch Types among Footballers in Bayelsa State, Nigeria
Background: The foot arch plays a vital role in human movement, acting as a shock absorber and stabilizer during physical activities. Aim: This study examines the distribution of...

Back to Top