Machine learning and quantitative computed tomography radiomics prediction of postoperative functional recovery in paraplegic dogs.

IF 1.3 2区农林科学 Q2 VETERINARY SCIENCES

Veterinary Surgery Pub Date : 2025-10-02 DOI:10.1111/vsu.70016

Daniel Low, Scott Rutherford

{"title":"Machine learning and quantitative computed tomography radiomics prediction of postoperative functional recovery in paraplegic dogs.","authors":"Daniel Low, Scott Rutherford","doi":"10.1111/vsu.70016","DOIUrl":null,"url":null,"abstract":"Objective: To develop a computed tomography (CT)-radiomics-based machine-learning algorithm for prediction of functional recovery in paraplegic dogs with acute intervertebral disc extrusion (IVDE).Study design: Multivariable prediction model development.Sample population: Paraplegic dogs with acute IVDE: 128 deep-pain positive and 86 deep-pain negative (DPN).Methods: Radiomics features from noncontrast CT were combined with deep-pain perception in an extreme gradient algorithm using an 80:20 train-test split. Model performance was assessed on the independent test set (Testfull) and on the test set of DPN dogs (TestDPN). Deep-pain perception alone served as the control.Results: Recovery of ambulation was recorded in 165/214 dogs (77.1%) after decompressive surgery. The model had an area under the receiver operating characteristic curve (AUC) of .9118 (95% CI: .8366-.9872), accuracy of 86.1% (95% CI: 74.4%-95.4%), sensitivity of 82.4% (95% CI: 68.6%-93.9%), and specificity of 100.0% (95% CI: 100.0%-100.0%) on Testfull, and an AUC of .7692 (95% CI: .6250-.9000), accuracy of 72.7% (95% CI: 50.0%-90.9%), sensitivity of 53.8% (95% CI: 25.0%-80.0%), and specificity of 100.0% (95% CI: 100.0%-100.0%) on TestDPN. Deep-pain perception had an AUC of .8088 (95% CI: .7273-.8871), accuracy of 69.8% (95% CI: 55.8%-83.7%), sensitivity of 61.8% (95% CI: 45.5%-77.4%), and specificity of 100.0% (95% CI: 100.0%-100.0%), which was different from that of the model (p = .02).Conclusion: Noncontrast CT-based radiomics provided prognostic information in dogs with severe spinal cord injury secondary to acute intervertebral disc extrusion. The model outperformed deep-pain perception alone in identifying dogs that recovered ambulation following decompressive surgery.Clinical significance: Radiomics features from noncontrast CT, when integrated into a multimodal machine-learning algorithm, may be useful as an assistive tool for surgical decision making.","PeriodicalId":23667,"journal":{"name":"Veterinary Surgery","volume":" ","pages":""},"PeriodicalIF":1.3000,"publicationDate":"2025-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Veterinary Surgery","FirstCategoryId":"97","ListUrlMain":"https://doi.org/10.1111/vsu.70016","RegionNum":2,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"VETERINARY SCIENCES","Score":null,"Total":0}

引用次数: 0

Abstract

Objective: To develop a computed tomography (CT)-radiomics-based machine-learning algorithm for prediction of functional recovery in paraplegic dogs with acute intervertebral disc extrusion (IVDE).

Study design: Multivariable prediction model development.

Sample population: Paraplegic dogs with acute IVDE: 128 deep-pain positive and 86 deep-pain negative (DPN).

Methods: Radiomics features from noncontrast CT were combined with deep-pain perception in an extreme gradient algorithm using an 80:20 train-test split. Model performance was assessed on the independent test set (Test_full) and on the test set of DPN dogs (Test_DPN). Deep-pain perception alone served as the control.

Results: Recovery of ambulation was recorded in 165/214 dogs (77.1%) after decompressive surgery. The model had an area under the receiver operating characteristic curve (AUC) of .9118 (95% CI: .8366-.9872), accuracy of 86.1% (95% CI: 74.4%-95.4%), sensitivity of 82.4% (95% CI: 68.6%-93.9%), and specificity of 100.0% (95% CI: 100.0%-100.0%) on Test_full, and an AUC of .7692 (95% CI: .6250-.9000), accuracy of 72.7% (95% CI: 50.0%-90.9%), sensitivity of 53.8% (95% CI: 25.0%-80.0%), and specificity of 100.0% (95% CI: 100.0%-100.0%) on Test_DPN. Deep-pain perception had an AUC of .8088 (95% CI: .7273-.8871), accuracy of 69.8% (95% CI: 55.8%-83.7%), sensitivity of 61.8% (95% CI: 45.5%-77.4%), and specificity of 100.0% (95% CI: 100.0%-100.0%), which was different from that of the model (p = .02).

Conclusion: Noncontrast CT-based radiomics provided prognostic information in dogs with severe spinal cord injury secondary to acute intervertebral disc extrusion. The model outperformed deep-pain perception alone in identifying dogs that recovered ambulation following decompressive surgery.

Clinical significance: Radiomics features from noncontrast CT, when integrated into a multimodal machine-learning algorithm, may be useful as an assistive tool for surgical decision making.

查看原文本刊更多论文

机器学习和定量计算机断层放射组学预测截瘫犬术后功能恢复。

目的：建立一种基于计算机断层扫描(CT)-放射组学的机器学习算法，用于预测急性椎间盘突出症（IVDE）截瘫犬的功能恢复。研究设计：建立多变量预测模型。样本人群：急性IVDE截瘫犬：128只深痛阳性，86只深痛阴性（DPN）。方法：采用80:20训练测试分割的极端梯度算法，将非对比CT放射组学特征与深度疼痛感知相结合。在独立测试集（Testfull）和DPN狗测试集（TestDPN）上评估模型的性能。仅深痛知觉作为对照。结果：214只犬中有165只（77.1%）在减压术后恢复活动能力。该模型的受者工作特性曲线（AUC）下面积为。在Testfull上，准确率为86.1% (95% CI: 74.4% ~ 95.4%)，灵敏度为82.4% (95% CI: 68.6% ~ 93.9%)，特异性为100.0% (95% CI: 100.0% ~ 100.0%)， AUC为。TestDPN检测的准确率为72.7% (95% CI: 50.0% ~ 90.9%)，灵敏度为53.8% (95% CI: 25.0% ~ 80.0%)，特异性为100.0% （95% CI: 100.0% ~ 100.0%）。深痛知觉的AUC为。准确性为69.8% (95% CI: 55.8% ~ 83.7%)，敏感性为61.8% (95% CI: 45.5% ~ 77.4%)，特异性为100.0% (95% CI: 100.0% ~ 100.0%)，与模型差异有统计学意义（p = 0.02）。结论：基于非对比ct的放射组学可为急性椎间盘突出致严重脊髓损伤犬提供预后信息。该模型在识别减压手术后恢复行走的狗方面优于单独的深度疼痛感知。临床意义：来自非对比CT的放射组学特征，当整合到多模态机器学习算法时，可能会作为手术决策的辅助工具。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Veterinary Surgery 农林科学-兽医学

CiteScore

3.40

自引率

22.20%

发文量

162

审稿时长

8-16 weeks

期刊介绍： Veterinary Surgery, the official publication of the American College of Veterinary Surgeons and European College of Veterinary Surgeons, is a source of up-to-date coverage of surgical and anesthetic management of animals, addressing significant problems in veterinary surgery with relevant case histories and observations. It contains original, peer-reviewed articles that cover developments in veterinary surgery, and presents the most current review of the field, with timely articles on surgical techniques, diagnostic aims, care of infections, and advances in knowledge of metabolism as it affects the surgical patient. The journal places new developments in perspective, encompassing new concepts and peer commentary to help better understand and evaluate the surgical patient.