Scholarlink

Purpose <p>Adolescent idiopathic scoliosis (AIS) has a large impact on health-related quality of life (HRQoL) including poor psychosocial functioning, body image, and psychological distress. Surgical management for AIS is common; however, there is limited consensus on preoperative and intraoperative strategies to optimize HRQoL outcomes. Accurate prediction of postoperative outcomes can help inform preoperative counselling and shared decision-making. This study aimed to generate machine learning models (MLMs) using preoperative and intraoperative variables to predict the difference in HRQoL outcomes from preoperative assessment to two years following AIS surgery.</p> Methods <p>A prospective, longitudinal, multicenter database was queried for AIS patients of Lenke 1 or 5 classification with two-year follow-up. MLMs were generated using preoperative and intraoperative variables to predict the difference in Scoliosis Research Society-22 (ΔSRS-22) questionnaire scores from preoperative assessment to two-year follow-up. MLMs were compared to a model that estimates the mean score by evaluating the mean squared error (MSE) and the fraction of times the prediction was within a predesignated value of the actual score (i.e., buffer accuracy).</p> Results <p>A total of 1,477 patients (84.6% female, 75.0% White) were included. The lowest MSE for each ΔSRS-22 outcome ranged from 0.18–0.48, while the highest 0.25-buffer, 0.5-buffer, 0.75-buffer, and 1-buffer accuracies for each ΔSRS-22 outcome ranged from 34.8%–53.4%, 56.8%–83.1%, 75.0%–94.6%, and 87.2%–97.3%, respectively. These MSEs and buffer accuracies outperformed mean estimates.</p> Conclusion <p>MLMs built using preoperative and intraoperative variables enabled prediction of the difference in HRQoL outcomes from preoperative assessment to two years following AIS surgery. Findings provide key insights into the feasibility of implementing MLMs as prognostic tools to counsel patients on expected outcomes of surgical management. Future work should implement additional surgeon, institution, and patient factors as model predictors to increase predictive accuracy of HRQoL outcomes and ultimately improve individualized patient care through data-driven patient counselling.</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

Using artificial intelligence to predict health-related quality of life for adolescent idiopathic scoliosis

  • 期刊论文

  • 发表日期：

    2026年7月22日

查看全文
  • Dusan Kovacevic,
  • Aazad Abbas,
  • Gurjovan Sahi,
  • Johnathan R. Lex,
  • Amer F. Samdani,
  • Suken A. Shah,
  • David Clements,
  • Peter O. Newton,
  • Michael P. Kelly,
  • Jay Toor,
  • Firoz Miyanji

摘要

Purpose

Adolescent idiopathic scoliosis (AIS) has a large impact on health-related quality of life (HRQoL) including poor psychosocial functioning, body image, and psychological distress. Surgical management for AIS is common; however, there is limited consensus on preoperative and intraoperative strategies to optimize HRQoL outcomes. Accurate prediction of postoperative outcomes can help inform preoperative counselling and shared decision-making. This study aimed to generate machine learning models (MLMs) using preoperative and intraoperative variables to predict the difference in HRQoL outcomes from preoperative assessment to two years following AIS surgery.

Methods

A prospective, longitudinal, multicenter database was queried for AIS patients of Lenke 1 or 5 classification with two-year follow-up. MLMs were generated using preoperative and intraoperative variables to predict the difference in Scoliosis Research Society-22 (ΔSRS-22) questionnaire scores from preoperative assessment to two-year follow-up. MLMs were compared to a model that estimates the mean score by evaluating the mean squared error (MSE) and the fraction of times the prediction was within a predesignated value of the actual score (i.e., buffer accuracy).

Results

A total of 1,477 patients (84.6% female, 75.0% White) were included. The lowest MSE for each ΔSRS-22 outcome ranged from 0.18–0.48, while the highest 0.25-buffer, 0.5-buffer, 0.75-buffer, and 1-buffer accuracies for each ΔSRS-22 outcome ranged from 34.8%–53.4%, 56.8%–83.1%, 75.0%–94.6%, and 87.2%–97.3%, respectively. These MSEs and buffer accuracies outperformed mean estimates.

Conclusion

MLMs built using preoperative and intraoperative variables enabled prediction of the difference in HRQoL outcomes from preoperative assessment to two years following AIS surgery. Findings provide key insights into the feasibility of implementing MLMs as prognostic tools to counsel patients on expected outcomes of surgical management. Future work should implement additional surgeon, institution, and patient factors as model predictors to increase predictive accuracy of HRQoL outcomes and ultimately improve individualized patient care through data-driven patient counselling.