Related Experiment Video
Updated: Aug 5, 2026
09:10
Precision of In Vivo Quantitative Tooth Wear Measurement Using Intra-Oral Scans
Published on: July 12, 2022
Interpretable Machine Learning for Population-Level Tooth Loss Prediction
Q T Lam1,2,3, F-Y Fan4, Y-L Wang1
1School of Dentistry, College of Oral Medicine, Taipei Medical University, Taipei, Taiwan.
Journal of Dental Research
|July 30, 2026
Summary
This study introduces an interpretable machine learning model for predicting severe tooth loss risk in US adults. The MICE-EBM framework offers transparent risk stratification for public health planning.
Area of Science:
- Dental Public Health
- Machine Learning
- Epidemiology
Background:
- Machine learning aids severe tooth loss (STL) risk stratification, but calibration issues, lack of interpretability, and complex survey designs hinder public health use.
- Existing models often function as 'black boxes,' limiting trust and implementation in real-world scenarios.
Purpose of the Study:
- To implement and evaluate an interpretable, survey-weighted Multiple Imputation by Chained Equations-Explainable Boosting Machine (MICE-EBM) framework for predicting population-level STL risk.
- To assess the model's performance, calibration, and interpretability across different US adult datasets, including validation under domain shift.
Main Methods:
- Utilized representative US adult datasets (BRFSS 2022, BRFSS 2024, NHANES 2015-2018) for model derivation, temporal validation, and cross-survey evaluation.
- Employed an antileakage HistGradientBoosting-driven pipeline for missing data imputation to preserve epidemiological variance.
- Implemented a survey-weighted MICE-EBM framework, incorporating sociobehavioral and systemic health determinants, and evaluated performance using AUC and Brier scores, with recalibration for cross-survey application.
Main Results:
- The MICE-EBM demonstrated strong temporal stability (BRFSS 2024 AUC: 0.863) and robust performance on derivation data (BRFSS 2022 AUC: 0.865).
- Cross-survey transfer to NHANES showed lower discrimination (AUC: 0.754) but improved calibration post-recalibration (Brier: 0.136).
- The interpretable EBM outperformed a black-box model in calibration after recalibration, while retaining transparency.
Conclusions:
- The MICE-EBM framework supports population-level STL risk stratification for US survey data with transparency and calibrated performance within the same survey.
- This TRIPOD+AI-compliant approach can aid dental public health planning.
- Cross-survey or international application necessitates local validation and recalibration for reliable implementation.
Related Concept Videos
01:15Teeth
The formation of teeth, also known as odontogenesis, is a complex process that begins in utero, around the sixth week of embryonic development. There are three stages to this process: the bud stage, the cap stage, and the bell stage.
In the bud stage, the tooth germ (an aggregation of cells) starts to form in the developing jawbone. During the cap stage, the tooth germ differentiates into enamel organ, dental papilla, and dental sac, which will later develop into the tooth's enamel, dentin and...
In the bud stage, the tooth germ (an aggregation of cells) starts to form in the developing jawbone. During the cap stage, the tooth germ differentiates into enamel organ, dental papilla, and dental sac, which will later develop into the tooth's enamel, dentin and...
01:21Tooth Anatomy
The human tooth enables us to eat a variety of foods, speak clearly, and even aid in shaping our faces. Teeth are composed of various elements that work together. Here's a detailed look at the anatomy of a human tooth.
The Crown, Neck, and Root
The visible part of the tooth is referred to as the crown. It's covered by enamel, the hardest substance in the human body. The crown is uniquely shaped for each type of tooth, allowing for different functions such as cutting, tearing, or grinding food.
The Crown, Neck, and Root
The visible part of the tooth is referred to as the crown. It's covered by enamel, the hardest substance in the human body. The crown is uniquely shaped for each type of tooth, allowing for different functions such as cutting, tearing, or grinding food.