An explainable machine learning framework for accurate prediction of postoperative anterior chamber depth in…

AI / informaticsFrontiers in cell and developmental biology· 2026

An explainable machine learning framework for accurate prediction of postoperative anterior chamber depth in highly myopic cataract surgery.

Yuyang Yang, Haoqiang Cui, Jiajia Gao … Li Li

Cataract & RefractiveAI / informaticsQ1IF 4.5

Machine learning model accurately predicted postoperative eye chamber depth after myopic cataract surgery

An explainable machine learning framework for accurate prediction of postoperative anterior chamber depth in highly myopic cataract surgery.

Yuyang Yang … Li Li

Frontiers in cell and developmental biology · 2026

Purpose

To develop and validate machine learning models for predicting postoperative anterior chamber depth (anterior chamber depth) in highly myopic cataract patients based on preoperative biometric parameters.

Methods

This prospective study enrolled 203 eyes of 127 highly myopic patients who underwent phacoemulsification and intraocular lens (intraocular lens) implantation between January 2024 and December 2025.

n = 203 eyes

0.8259

Results

0.8259

the model's chamber-depth predictions closely matched actual post-surgery measurements

n = 203 eyes

More results

Six predictors were identified for model construction: axial length anterior chamber depth/lens thickness ratio (anterior chamber depth/LT), white-to-white distance (WTW), anterior chamber depth at 90° (ACD90), horizontal position angle, and anterior chamber depth + LT/2.

The accuracy within ±0.1 mm reached 80.49%, and within ±0.2 mm reached 100%.

More results

SHAP analysis revealed that anterior chamber depth + LT/2 was the most important predictor, followed by WTW, ACD90, and horizontal position angle.

“

Conclusion

This study successfully developed and validated an explainable RF-based machine learning model for the prediction of postoperative anterior chamber depth in highly myopic cataract patients, which supports more reliable intraocular lens power calculation and offers a practical tool for optimizing surgical planning in highly myopic eyes.

An explainable machine learning framework for accurate prediction of postoperative anterior chamber depth in highly myopic cataract surgery.

An explainable machine learning framework for accurate prediction of postoperative anterior chamber depth in highly myopic cataract surgery.

Related papers