Scholarlink

Background &amp; aim <p>Horizontal strabismus affects ≈ 1.9% of the global population. Traditional “1&#xa0;mm ≈ 2 Δ” nomograms disregard patient heterogeneity, leaving re-operation rates at 7–8% even after primary horizontal surgery. We aimed to develop a single prescriptive model that simultaneously predicts which horizontal extra-ocular muscles require surgery and the precise recession/resection dose for each, following the TRIPOD + AI reporting checklist.</p> Methods <p>In this retrospective single-centre study, 634 consecutive patients (2019–2024) undergoing primary horizontal-muscle surgery were analysed. Fourteen routinely recorded pre-operative variables—including age, prism-cover deviation, axial-length metrics, refractive error and visual acuity—fed a fully connected multi-task neural network with a shared trunk and two heads: (i) 8-label classification for muscle-procedure selection and (ii) 8-output regression for surgical dose. Model development exceeded recommended sample-size heuristics for an expected AUC ≥ 0.90 and was internally validated with multilabel-stratified 10-fold cross-validation.</p> Results <p>The model achieved excellent discrimination for muscle selection (macro-AUC 0.97 ± 0.01; macro-MCC 0.83) with near-perfect calibration (ECE 0.008). Dose predictions were highly accurate (MAE 0.42 ± 0.04&#xa0;mm; RMSE 0.54 ± 0.07&#xa0;mm; R² 0.86 ± 0.04); 95% of estimates lay within ± 0.30&#xa0;mm of the surgeon’s plan. Exact match of the entire surgical plan reached 55%, far surpassing the majority baseline of 17%. These figures markedly outperform earlier regression-only approaches that reported MAE 0.5–0.8&#xa0;mm and indication-level AUC 0.82.</p> Conclusions <p>A transparent multi-task learning model can replicate expert, patient-specific surgical plans for horizontal strabismus with sub-millimetre precision. The tool could standardise planning and reduce inter-surgeon variability; multi-centre external validation remains essential.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Development and internal validation of a prescriptive multi-task learning model for horizontal strabismus surgery planning

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年1月21日

查看全文
  • Jieyue Wang,
  • Xiaoying Wu,
  • Sheng Ou

摘要

Background & aim

Horizontal strabismus affects ≈ 1.9% of the global population. Traditional “1 mm ≈ 2 Δ” nomograms disregard patient heterogeneity, leaving re-operation rates at 7–8% even after primary horizontal surgery. We aimed to develop a single prescriptive model that simultaneously predicts which horizontal extra-ocular muscles require surgery and the precise recession/resection dose for each, following the TRIPOD + AI reporting checklist.

Methods

In this retrospective single-centre study, 634 consecutive patients (2019–2024) undergoing primary horizontal-muscle surgery were analysed. Fourteen routinely recorded pre-operative variables—including age, prism-cover deviation, axial-length metrics, refractive error and visual acuity—fed a fully connected multi-task neural network with a shared trunk and two heads: (i) 8-label classification for muscle-procedure selection and (ii) 8-output regression for surgical dose. Model development exceeded recommended sample-size heuristics for an expected AUC ≥ 0.90 and was internally validated with multilabel-stratified 10-fold cross-validation.

Results

The model achieved excellent discrimination for muscle selection (macro-AUC 0.97 ± 0.01; macro-MCC 0.83) with near-perfect calibration (ECE 0.008). Dose predictions were highly accurate (MAE 0.42 ± 0.04 mm; RMSE 0.54 ± 0.07 mm; R² 0.86 ± 0.04); 95% of estimates lay within ± 0.30 mm of the surgeon’s plan. Exact match of the entire surgical plan reached 55%, far surpassing the majority baseline of 17%. These figures markedly outperform earlier regression-only approaches that reported MAE 0.5–0.8 mm and indication-level AUC 0.82.

Conclusions

A transparent multi-task learning model can replicate expert, patient-specific surgical plans for horizontal strabismus with sub-millimetre precision. The tool could standardise planning and reduce inter-surgeon variability; multi-centre external validation remains essential.