AI Article Synopsis

  • Deep vein thromboembolism (DVT) is a serious complication after spinal surgery, prompting the need for effective prevention strategies, particularly using machine learning (ML) for predicting DVT risk.
  • This study analyzed records from 500 patients undergoing elective spinal surgery to identify key risk factors for DVT and created five ML models, with the random forest classifier performing the best in predicting outcomes.
  • The research identified seven significant variables (like age, BMI, and anesthesia time) that contribute to DVT risk, highlighting the potential of ML in improving patient care after spinal procedures.

Article Abstract

Background: Deep vein thromboembolism (DVT) is a common postoperative complication with high morbidity and mortality rates. However, the safety and effectiveness of using prophylactic anticoagulants for preventing DVT after spinal surgery remain controversial. Hence, it is crucial to predict whether DVT occurs in advance following spinal surgery. The present study aimed to establish a machine learning (ML)-based prediction model of DVT formation following spinal surgery.

Methods: We reviewed the medical records of patients who underwent elective spinal surgery at the Third Affiliated Hospital of Zunyi Medical University (TAHZMU) from January 2020 to December 2022. We ultimately selected the clinical data of 500 patients who met the criteria for elective spinal surgery. The Boruta-SHAP algorithm was used for feature selection, and the SMOTE algorithm was used for data balance. The related risk factors for DVT after spinal surgery were screened and analyzed. Five ML algorithm models were established. The data of 150 patients treated at the Affiliated Hospital of Zunyi Medical University (AHZMU) from July 2023 to October 2023 were used for external verification of the model. The area under the curve (AUC), geometric mean (G-mean), sensitivity, accuracy, specificity, and F1 score were used to evaluate the performance of the models.

Results: The results revealed that activated partial thromboplastin time (APTT), age, body mass index (BMI), preoperative serum creatinine (Crea), anesthesia time, rocuronium dose, and propofol dose were the seven important characteristic variables for predicting DVT after spinal surgery. Among the five ML models established in this study, the random forest classifier (RF) showed superior performance to the other models in the internal validation set.

Conclusion: Seven preoperative and intraoperative variables were included in our study to develop an ML-based predictive model for DVT formation following spinal surgery, and this model can be used to assist in clinical evaluation and decision-making.

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.ijmedinf.2024.105609DOI Listing

Publication Analysis

Top Keywords

spinal surgery
32
formation spinal
12
dvt spinal
12
spinal
9
prediction model
8
deep vein
8
surgery
8
model dvt
8
dvt formation
8
elective spinal
8

Similar Publications

Purpose: Brachial plexus traction injuries have conventionally been categorized as involving the C5-C6, C5-C7, C5-T1, and C8-T1 roots. In this article, we report a distinct clinical presentation of brachial plexus injury characterized by intact finger flexion with signs of complete brachial plexus injury.

Methods: From 2010 to 2022, 989 patients who sustained brachial plexus injuries were examined and underwent surgery.

View Article and Find Full Text PDF

Evaluating Body Image Disturbance and Its Influencing Factors in Breast Cancer Patients Following Unilateral Mastectomy.

Psychiatry Clin Psychopharmacol

December 2024

Department of Operating Room, the Fifth Affiliated Hospital of Wenzhou Medical University, Lishui Central Hospital, Lishui, China.

Background: Patients with unilateral breast loss after single mastectomy for breast cancer may have body image disorders such as surgical lymphedema, flap ischemia, and spinal deformity, resulting in negative emotions such as depression, inferiority, and social dysfunction. This study mainly investigated and analyzed the status quo and influencing factors of body image disorder in breast cancer patients after single mastectomy.

Methods: This study is a cross-sectional study.

View Article and Find Full Text PDF

Design and Evaluation of Augmented Reality-Enhanced Robotic System for Epidural Interventions.

Sensors (Basel)

December 2024

Surgical Performance Enhancement and Robotics (SuPER) Centre, Department of Surgery, McGill University, Montreal, QC H3A 0G4, Canada.

The epidural injection is a medical intervention to inject therapeutics directly into the vicinity of the spinal cord for pain management. Because of its proximity to the spinal cord, imprecise insertion of the needle may result in irreversible damage to the nerves or spinal cord. This study explores enhancing procedural accuracy by integrating a telerobotic system and augmented reality (AR) assistance.

View Article and Find Full Text PDF

Spinal cord trauma leads to the destruction of the highly organized cytoarchitecture that carries information along the axis of the spinal column. Currently, there are no clinically accepted strategies that can help regenerate severed axons after spinal cord injury (SCI). Hydrogels are soft biomaterials with high water content that are widely used as scaffolds to interface with the central nervous system (CNS).

View Article and Find Full Text PDF

Background: Morphine analgesic tolerance (MAT) limits the clinical application of morphine in the management of chronic pain. IIK7 is a melatonin type 2 (MT2) receptor agonist known to have antioxidant properties. Oxidative stress is recognized as a critical factor in MAT.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!