Scholarlink

Background <p>Necrotising soft tissue infections (NSTI) are life-threatening conditions caused by diverse bacteria. Treatment strategies have remained largely universal and unchanged, and only modest improvements in patient outcomes have been observed. Emerging insights into NSTI pathogenesis may enable more targeted approaches. Because microbial aetiology is central to guiding appropriate therapy, we aimed to develop and externally validate machine learning models capable of predicting microbial aetiology using only data available at an early stage. In parallel, we explored whether similar models could predict selected clinical endpoints related to surgical management, patient handling, and organ support.</p> Methods <p>We used data from the INFECT study, an international multicentre prospective cohort investigating NSTI characteristics and pathogenesis. A total of 409 adults with surgically confirmed NSTI were enrolled between February 2013 and June 2017 from five Scandinavian hospitals. More than 700 clinical variables were collected from hospital admission to intensive care unit entry. Machine learning models were developed to predict the presence of <i>Streptococcus pyogenes</i> (GAS, Group A <i>streptococcus</i>) and five clinical endpoints: risk of amputation, size of skin defect, maximum skin defect size, length of intensive care (ICU) stay, and need for renal replacement therapy. Unsupervised variable selection was implemented, and Shapley Additive explanations were used for model interpretability. External validation employed a retrospective multicentre cohort of 216 NSTI patients treated in 11 Dutch hospitals between January 2013 and December 2017.</p> Results <p>Eight presurgical variables (age, diabetes, affected area, prior surgical intervention, and blood creatinine and haemoglobin concentrations) were sufficient for predicting GAS aetiology with high discriminatory power. Performance was good in both the development cohort (ROC-AUC 0.828; 95% CI 0.763–0.883) and the external validation cohort (ROC-AUC 0.758; 95% CI 0.696–0.821). Prediction of clinical endpoints related to surgical management, ICU stay, and organ support was unsuccessful.</p> Conclusions <p>We developed and externally validated a model predicting GAS aetiology in NSTI using presurgical data alone. Early identification of GAS may improve clinical handling and support tailored decisions on treatment and infection control, including management of close contacts and reduction of hospital transmission risk.</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

A validated model for early prediction of group A streptococcal aetiology in necrotising soft tissue infections using minimal patient data

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年1月10日

查看全文
  • Sonja Katz,
  • Jaco Suijker,
  • Steinar Skrede,
  • Annebeth Meij-de Vries,
  • Anouk Pijpe,
  • Anna Norrby-Teglund,
  • Laura M. Palma Medina,
  • Jan K. Damås,
  • Ole Hyldegaard,
  • Erik Solligård,
  • Mattias Svensson,
  • Michael Nekludov,
  • Ylva Karlsson,
  • Per Arnell,
  • Muhammad Afzal,
  • Helena Bergsten,
  • Lydia Bosnak,
  • Bavya Chakrakodi,
  • Puran Chen,
  • Johanna Emgård,
  • Linda Johansson,
  • Julius Juarez,
  • Srikanth Mairpady Shambat,
  • Nikola Siemens,
  • Johanna Snäll,
  • Julia Uhlman,
  • Takeaki Wajima,
  • Martin B. Madsen,
  • Daniel Bidstrup,
  • Nina F. Bærnthsen,
  • Julie V. Clausen,
  • Anna Damgaard,
  • Gladis H. Frendø,
  • Martin Forchammer,
  • Marco Hansen,
  • Morten F. F. Hedetoft,
  • Karen L. Hilsted,
  • Diana Isaksen,
  • Erik C. Jansen,
  • Josefine Kofoed,
  • Anette Lilja,
  • Lærke B. Madsen,
  • Rasmus Müller,
  • Isabel S. Nielsen,
  • Emilie M. J. Pedersen,
  • Marie W. Petersen,
  • Anders Perner,
  • Peter V. Polzik,
  • Frederikke Ravn,
  • Folke Lind,
  • Anders Kjellberg,
  • Erik von Oelreich,
  • Peter Kronlund,
  • Sverre Kullberg,
  • Ola Friman,
  • Lisa Hellgren,
  • Anna Granström,
  • Anna Schenning,
  • Sandra Carlsson,
  • Trond Bruun,
  • Torbjørn Nedrebø,
  • Oddvar Oppegaard,
  • Eivind Rath,
  • Marianne Søvik,
  • Hanne Søyland,
  • Dag Benoni,
  • Hans Lycke,
  • Joakim Trogen,
  • Kerstin Ohlauson,
  • Dietmar H. Pieper,
  • Singh Chhatwal,
  • Andreas Itzek,
  • Anshu Babbar,
  • Robert Thänert,
  • Jörn Hoßmann,
  • Eva Medina,
  • Domenica Hamisch,
  • Israel Barrantes,
  • Patric Nitsche-Schmitz,
  • Astrid Dröge,
  • Katja Mummenbrauer,
  • Francois Vandenesh,
  • Sylvere Bastien,
  • Jessica Baude,
  • Anne Tristan,
  • Erno Lindfors,
  • Francois Bergey,
  • Christoph Reschreiter,
  • Bernhard Ronacher,
  • Matthias Pilecky,
  • Eytan Ruppin,
  • Matthew Oberhardt,
  • Raphy Zarecky,
  • Malak Kotb,
  • Karthickeyan Chellakrishnan,
  • Santhosh Mukundan,
  • Suba Nokala,
  • Doreen Marsden,
  • Kristoffer Strålin,
  • P. P. M. van Zuijlen,
  • Marco Anteghini,
  • Knut Anders Mosevoll,
  • Vitor A. P. Martins dos Santos,
  • Edoardo Saccenti

摘要

Background

Necrotising soft tissue infections (NSTI) are life-threatening conditions caused by diverse bacteria. Treatment strategies have remained largely universal and unchanged, and only modest improvements in patient outcomes have been observed. Emerging insights into NSTI pathogenesis may enable more targeted approaches. Because microbial aetiology is central to guiding appropriate therapy, we aimed to develop and externally validate machine learning models capable of predicting microbial aetiology using only data available at an early stage. In parallel, we explored whether similar models could predict selected clinical endpoints related to surgical management, patient handling, and organ support.

Methods

We used data from the INFECT study, an international multicentre prospective cohort investigating NSTI characteristics and pathogenesis. A total of 409 adults with surgically confirmed NSTI were enrolled between February 2013 and June 2017 from five Scandinavian hospitals. More than 700 clinical variables were collected from hospital admission to intensive care unit entry. Machine learning models were developed to predict the presence of Streptococcus pyogenes (GAS, Group A streptococcus) and five clinical endpoints: risk of amputation, size of skin defect, maximum skin defect size, length of intensive care (ICU) stay, and need for renal replacement therapy. Unsupervised variable selection was implemented, and Shapley Additive explanations were used for model interpretability. External validation employed a retrospective multicentre cohort of 216 NSTI patients treated in 11 Dutch hospitals between January 2013 and December 2017.

Results

Eight presurgical variables (age, diabetes, affected area, prior surgical intervention, and blood creatinine and haemoglobin concentrations) were sufficient for predicting GAS aetiology with high discriminatory power. Performance was good in both the development cohort (ROC-AUC 0.828; 95% CI 0.763–0.883) and the external validation cohort (ROC-AUC 0.758; 95% CI 0.696–0.821). Prediction of clinical endpoints related to surgical management, ICU stay, and organ support was unsuccessful.

Conclusions

We developed and externally validated a model predicting GAS aetiology in NSTI using presurgical data alone. Early identification of GAS may improve clinical handling and support tailored decisions on treatment and infection control, including management of close contacts and reduction of hospital transmission risk.