Related Experiment Video
Updated: Jul 16, 2025
06:37
Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
Published on: December 15, 2023
3.8K
Evaluation of height prediction models: from traditional methods to artificial intelligence
Ana G Chávez-Vázquez1, Miguel Klünder-Klünder2, Nayely G Garibay-Nieto3
1Unit of Epidemiological Research in Endocrinology and Nutrition, Hospital Infantil de México Federico Gómez, Mexico City, Mexico.
Pediatric Research
|September 21, 2023
Summary
Automated bone age readings using BoneXpert offer a more reliable method for predicting adult height compared to traditional manual methods. This AI-driven approach reduces variability and improves accuracy for predicting adult height in children.
Area of Science:
- Pediatric endocrinology
- Medical imaging analysis
- Artificial intelligence in healthcare
Background:
- Traditional adult height prediction (AHP) relies on manual bone age (BA) assessments.
- Artificial intelligence (AI) is enhancing the accuracy of BA readings and AHP models.
Purpose of the Study:
- To identify the most accurate adult height prediction (AHP) model for the current Mexican population.
- To compare the performance of traditional manual BA readings versus automated methods (BoneXpert) in AHP.
Main Methods:
- Cross-sectional study of 1173 participants aged 5-18 years.
- Bone age (BA) readings performed manually by two experts and automatically using BoneXpert.
- Adult height prediction (AHP) models evaluated based on proximity to the population mean height.
Main Results:
- All tested AHP models overestimated the population mean height.
- BoneXpert showed the smallest difference for males; Bayley & Pinneau for females.
- Manual BA readings exhibited significant interobserver variability (up to 43% difference >5cm).
Conclusions:
- Manual BA readings in traditional AHP models introduce high interobserver variability.
- The automated BoneXpert method is the most reliable for AHP, reducing variability.
- BoneXpert provides consistent AHP results close to the population mean height.
Related Concept Videos
01:19Survival Tree
105
Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
Building a Survival Tree
Constructing a...
Building a Survival Tree
Constructing a...
105
01:29Measures of Intelligence
7.6K
Psychologists measure intelligence by using standardized tests that produce a score known as the intelligence quotient or IQ. To understand IQ tests, it's important to recognize the key principles behind their construction: validity, reliability, and standardization.
Validity refers to how well a test measures what it claims to measure. An intelligence test should accurately assess intelligence rather than another characteristic, like anxiety. Criterion validity is one way to evaluate this;...
Validity refers to how well a test measures what it claims to measure. An intelligence test should accurately assess intelligence rather than another characteristic, like anxiety. Criterion validity is one way to evaluate this;...
7.6K
01:03Prediction Intervals
2.3K
The interval estimate of any variable is known as the prediction interval. It helps decide if a point estimate is dependable.
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y.
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y.
2.3K