Scholarlink

Purpose <p>We aimed to develop and internally validate prediction models for one-month postoperative performance status (PS) after surgery for spinal metastases and to identify patients likely to achieve PS 0–2 at one month.</p> Methods <p>We performed a retrospective analysis of a prospectively collected spine surgery registry. We compared three tree-based models (Random Forest, XGBoost, and CatBoost) with two regularized logistic regression models (ridge-regularized logistic regression and a sparse elastic-net logistic regression model constrained to ≤ 15 predictors). Model development and hyperparameter tuning were performed using nested cross-validation. Missing data were handled using model-specific strategies within the cross-validation pipeline, and a sensitivity analysis excluded the predictor with the highest missingness. Performance was assessed using discrimination and calibration metrics, including the area under the receiver operating characteristic curve (AUC-ROC), accuracy, precision, recall, F1 score, Brier score, calibration intercept, and calibration slope.</p> Results <p>The primary analysis included 375 patients with available one-month PS out of 413 enrolled patients. Random Forest achieved the highest discrimination (AUC-ROC 0.811 ± 0.079) and showed calibration measures closest to the ideal among the evaluated models (Brier score 0.168; calibration intercept − 0.024; slope 1.121). The sparse elastic-net model showed good discrimination (AUC-ROC 0.796 ± 0.081) with a limited set of predictors, although its calibration metrics suggested less reliable absolute probability estimates (Brier score 0.217; intercept 0.612; slope 3.228). Excluding the predictor with the highest missingness yielded similar performance for the main models.</p> Conclusion <p>Tree-based models, particularly Random Forest, provided the most favorable overall predictive performance for one-month postoperative PS after surgery for spinal metastases, whereas a sparse elastic-net logistic regression model preserved reasonable discrimination with a small predictor set and coefficient-based interpretability. These findings support clinically oriented prediction of early postoperative functional status while highlighting the need to assess calibration before clinical implementation.</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

Tree-based and sparse logistic models for predicting one-month postoperative performance status after surgery for spinal metastases

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年5月28日

查看全文
  • Satoshi Maki,
  • Yuki Shiratani,
  • Sumihisa Orita,
  • Akinobu Suzuki,
  • Koji Tamai,
  • Takaki Shimizu,
  • Kenichiro Kakutani,
  • Yutaro Kanda,
  • Hiroyuki Tominaga,
  • Ichiro Kawamura,
  • Masayuki Ishihara,
  • Masaaki Paku,
  • Yohei Takahashi,
  • Toru Funayama,
  • Kousei Miura,
  • Eiki Shirasawa,
  • Hirokazu Inoue,
  • Atsushi Kimura,
  • Takuya Iimura,
  • Hiroshi Moridaira,
  • Hideaki Nakajima,
  • Shuji Watanabe,
  • Koji Akeda,
  • Norihiko Takegami,
  • Kazuo Nakanishi,
  • Hirokatsu Sawada,
  • Koji Matsumoto,
  • Masahiro Funaba,
  • Hidenori Suzuki,
  • Haruki Funao,
  • Tsutomu Oshigiri,
  • Takashi Hirai,
  • Bungo Otsuki,
  • Kazu Kobayakawa,
  • Koji Uotani,
  • Hiroaki Manabe,
  • Shinji Tanishima,
  • Ko Hashimoto,
  • Chizuo Iwai,
  • Daisuke Yamabe,
  • Akihiko Hiyama,
  • Shoji Seki,
  • Kenji Kato,
  • Masashi Miyazaki,
  • Kazuyuki Watanabe,
  • Toshio Nakamae,
  • Takashi Kaito,
  • Hiroaki Nakashima,
  • Narihito Nagoshi,
  • Gen Inoue,
  • Shiro Imagama,
  • Kota Watanabe,
  • Satoshi Kato,
  • Seiji Ohtori,
  • Takeo Furuya

摘要

Purpose

We aimed to develop and internally validate prediction models for one-month postoperative performance status (PS) after surgery for spinal metastases and to identify patients likely to achieve PS 0–2 at one month.

Methods

We performed a retrospective analysis of a prospectively collected spine surgery registry. We compared three tree-based models (Random Forest, XGBoost, and CatBoost) with two regularized logistic regression models (ridge-regularized logistic regression and a sparse elastic-net logistic regression model constrained to ≤ 15 predictors). Model development and hyperparameter tuning were performed using nested cross-validation. Missing data were handled using model-specific strategies within the cross-validation pipeline, and a sensitivity analysis excluded the predictor with the highest missingness. Performance was assessed using discrimination and calibration metrics, including the area under the receiver operating characteristic curve (AUC-ROC), accuracy, precision, recall, F1 score, Brier score, calibration intercept, and calibration slope.

Results

The primary analysis included 375 patients with available one-month PS out of 413 enrolled patients. Random Forest achieved the highest discrimination (AUC-ROC 0.811 ± 0.079) and showed calibration measures closest to the ideal among the evaluated models (Brier score 0.168; calibration intercept − 0.024; slope 1.121). The sparse elastic-net model showed good discrimination (AUC-ROC 0.796 ± 0.081) with a limited set of predictors, although its calibration metrics suggested less reliable absolute probability estimates (Brier score 0.217; intercept 0.612; slope 3.228). Excluding the predictor with the highest missingness yielded similar performance for the main models.

Conclusion

Tree-based models, particularly Random Forest, provided the most favorable overall predictive performance for one-month postoperative PS after surgery for spinal metastases, whereas a sparse elastic-net logistic regression model preserved reasonable discrimination with a small predictor set and coefficient-based interpretability. These findings support clinically oriented prediction of early postoperative functional status while highlighting the need to assess calibration before clinical implementation.