Development and validation of interpretable machine learning models for predicting the risk of necrosis after finger replantation: A retrospective multicenter study

INTRODUCTION: Digital necrosis (DN) is a critical postoperative complication following finger replantation surgery. This can necessitate additional surgical interventions that can adversely affect the patient's hand functionality, psychological well-being, and financial standing. The timely identification and management of the risk of post-replantation DN are thus crucial for enhancing patient outcomes. The objective of this study was to create and validate an easily understandable machine learning (ML) model for predicting the risk of DN following finger replantation surgery. PATIENTS AND METHODS: Data from 1579 patients who underwent finger replantation surgery at Suzhou Ruihua Orthopaedic Hospital between September 2018 and September 2023 were collected and divided into training and internal validation sets. Additionally, 293 data points from two other institutions were employed as independent external validation sets. Ten machine-learning methods, including Gradient Boosting Machine (GBM), were utilized for modeling. The performance of the model was assessed using the area under the receiver operating characteristic curve (AUC) and decision curve analysis (DCA). SHapley Additive exPlanation (SHAP) was utilized to provide both global and local interpretations of the final model. RESULTS: Nine indices, including the seniority of the doctor and the neutrophil count, were identified as independent predictors of DN. The GBM model showed optimal model with high predictive accuracy for DN risk in both the training set (AUC: 0.995) and the internal validation set (AUC: 0.978), which was confirmed using external validation (AUC: 0.983). The reliability and utility of the GBM model and the web-based computing platform were confirmed by DCA, calibration curve, accuracy, and sensitivity analyses. CONCLUSION: An interpretable machine-learning model based on complete blood counts and related inflammatory marker levels was constructed and validated to predict the likelihood of developing DN following finger replantation. This model can assist clinicians in the prompt identification of high-risk patients post-replantation, enabling timely intervention.

Resumen tomado de PubMed (NCBI) para el registro citado, en el idioma original. La versión de referencia es la de la publicación original.

El resumen se deja sin traducir para conservar la redacción original de los autores.

Using data from 1579 finger replantation patients with external validation on 293 cases from other institutions, a gradient boosting machine model predicted postoperative digital necrosis with area under the curve of 0.995 (training) and 0.983 (external validation) using blood counts and inflammatory markers.

Explore cómo esta investigación se conecta con la práctica clínica

Más estudios revisados por pares en la categoría «Seguridad y control de infecciones».

• Leech-Assisted Flap Salvage — Systematic Review of 277 Cases — Whitaker et al. (2012)
• Effects of hirudotherapy on liver functions, lipid profile, and insulin sensitivity in rats with metabolic syndrome — Bilden A et al. (2026)
• Efficacy and Safety of Hirudotherapy for Improving Sperm Quality Parameters in Male Infertility: A Randomized Controlled Trial — Abtahi-Forooshani M et al. (2026)
• Improvement of patient care through hirudotherapy and the management of leeches from their reception to their disposal in France — Vaesken C et al. (2023)
• Hirudotherapy in Medicine and Dentistry — Jha K et al. (2015)
• Management of Chronic Non-healing Wounds by Hirudotherapy — Iqbal A et al. (2017)
• La hirudoterapia atenúa el dolor artrítico en pacientes con diversos síndromes de dolor crónico: un análisis retrospectivo — Loeser J et al. (2020)
• Hirudotherapy (medicinal leeches) for treatment of upper airway obstruction in a dog — Trenholme H, Masseau I, Reinero C (2021)
• Análisis de infecciones resistentes a antibióticos asociadas a la hirudoterapia — Brauer P et al. (2024)
• ¡Déjame en paz, sanguijuela! Hemartrosis atraumática tras hirudoterapia — Curcio J, Lloyd C (2020)

Ver toda la investigación analizada por la ASH →