Scholarlink

Background <p>Elderly patients undergoing surgery for hip fractures are at high risk for perioperative Major Adverse Cardiac Events (MACE), which can markedly compromise postoperative outcomes. This study aims to develop a machine learning (ML) based, interpretable tool to predict MACE using clinical and ultrasound-based variables in this population.</p> Methods <p>We analyzed data from 877 patients in the multicenter LUSHIP study, incorporating demographics, Revised Cardiac Risk Index (RCRI), functional status, and preoperative lung ultrasound (LUS) scores. Multiple ML models were trained and validated using bootstrap resampling. The final ensemble meta-model combined GBM (Gradient Boosting Machine) and GLMNET (Elastic-Net Regularized Generalized Linear Models).</p> Results <p>The ensemble model achieved an AUROC of 0.86, with sensitivity and specificity of 0.72 and 0.83, respectively. These results significantly improve over traditional tools such as the Revised Cardiac Risk Index (RCRI), particularly when used alone. A significant contribution of this work is the integration of lung ultrasound (LUS) as a non-invasive, bedside biomarker, which notably improved risk prediction compared to the performance of the individual LUS marker alone (AUC = 0.78). Relevant predictors for the ML model are LUS score, RCRI score, and patient age. A web-based Shiny application was developed to enable real-time personalized risk estimation.</p> Conclusion <p>This interpretable ML model improves perioperative cardiac risk stratification and profiling in elderly hip fracture patients and may guide targeted preventive strategies and resource allocation.</p> Trial registration <p>CT04074876</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

An interpretable machine learning tool for predicting perioperative cardiac events in patients scheduled for hip fracture surgery: insights from the multicenter LUSHIP study

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年10月27日

查看全文
  • Danila Azzolina,
  • Gianmaria Cammarota,
  • Enrico Boero,
  • Paola Berchialla,
  • Savino Spadaro,
  • Federico Longhini,
  • Cristian Deana,
  • Daniele Guerino Biasucci,
  • Stefano D’Incà,
  • Irene Batticci,
  • Nicola Fasano,
  • Edoardo De Robertis,
  • Rachele Simonte,
  • Salvatore Maurizio Maggiore,
  • Valentina Bellini,
  • Elena Giovanna Bignami,
  • Luigi Vetrugno,
  • Vito Marco Ranieri,
  • Anna Pesamosca,
  • Agnese Cattarossi,
  • Saskia Granzotti,
  • Alessandro Cavarape,
  • Andrea Cortegiani,
  • Lisa Mattuzzi,
  • Luca Flaibani,
  • Nicola Federici,
  • Francesco Meroi,
  • Marco Tescione,
  • Andrea Bruni,
  • Eugenio Garofalo,
  • Mattia Bernardinetti,
  • Felice Urso,
  • Camilla Colombotto,
  • Francesco Forfori,
  • Sandro Pregnolato,
  • Francesco Corradi,
  • Federico Dazzi,
  • Sara Tempini,
  • Alessandro Isirdi,
  • Moro Federico,
  • Nicole Giovane,
  • Milo Vason,
  • Carlo Alberto Volta,
  • Fabio Gori,
  • Michela Neri,
  • Auro Caraffa,
  • Giovanni Cosco,
  • Eugenio Vadalà,
  • Demetrio Labate,
  • Nicola Polimeni,
  • Marilena Napolitano,
  • Sebastiano Macheda,
  • Angela Corea,
  • Lucia Lentin,
  • Michele Divella,
  • Daniele Orso,
  • Clara Zaghis,
  • Silvia Del Rio,
  • Serena Tomasino,
  • Alessandro Brussa,
  • Natascia D’Andrea,
  • Simone Bressan,
  • Giuseppe Neri,
  • Pietro Giammanco,
  • Alberto Nicolò Galvano,
  • Mariachiara Ippolito,
  • Fabrizio Ricci,
  • Francesca Stefani,
  • Lolita Fasoli,
  • Piergiorgio Bresil,
  • Federica Curto,
  • Lorenzo Pirazzoli,
  • Carlo Frangioni,
  • Mattia Puppo,
  • Sabrina Mussetta,
  • Michele Autelli,
  • Giuseppe Giglio,
  • Filippo Riccone,
  • Erika Taddei

摘要

Background

Elderly patients undergoing surgery for hip fractures are at high risk for perioperative Major Adverse Cardiac Events (MACE), which can markedly compromise postoperative outcomes. This study aims to develop a machine learning (ML) based, interpretable tool to predict MACE using clinical and ultrasound-based variables in this population.

Methods

We analyzed data from 877 patients in the multicenter LUSHIP study, incorporating demographics, Revised Cardiac Risk Index (RCRI), functional status, and preoperative lung ultrasound (LUS) scores. Multiple ML models were trained and validated using bootstrap resampling. The final ensemble meta-model combined GBM (Gradient Boosting Machine) and GLMNET (Elastic-Net Regularized Generalized Linear Models).

Results

The ensemble model achieved an AUROC of 0.86, with sensitivity and specificity of 0.72 and 0.83, respectively. These results significantly improve over traditional tools such as the Revised Cardiac Risk Index (RCRI), particularly when used alone. A significant contribution of this work is the integration of lung ultrasound (LUS) as a non-invasive, bedside biomarker, which notably improved risk prediction compared to the performance of the individual LUS marker alone (AUC = 0.78). Relevant predictors for the ML model are LUS score, RCRI score, and patient age. A web-based Shiny application was developed to enable real-time personalized risk estimation.

Conclusion

This interpretable ML model improves perioperative cardiac risk stratification and profiling in elderly hip fracture patients and may guide targeted preventive strategies and resource allocation.

Trial registration

CT04074876