野外人工智能分诊工具的研发:对躯干枪伤患者休克、输血和确定性手术治疗的预测置信度
研究利用美国外科医师学会创伤质量改进计划(ACS TQIP)来源的躯干及交界区枪伤患者(16-60岁)数据库,纳入29,816例,训练一种信息感知的Dirichlet深度神经网络(野外人工智能分诊),以野外可获得的枪伤解剖部位、生命体征和患者信息预测休克、需行重大出血控制手术或早期大量输血(MT),并同步建立置信度模型输出真类概率(0-1)。结果显示休克、重大手术、早期MT分别占13.0%、22.4%、6.3%,在80/20训练-测试拆分、1000个epoch下,预测休克、早期MT、重大手术的平均受试者工作特征曲线下面积分别为0.89、0.86、0.82;错误预测与正确预测的平均真类概率分别为休克0.25对0.87、MT 0.30对0.81、重大手术0.24对0.69。作者认为该模型能准确识别躯干枪伤患者的潜在休克并预测其MT和重大手术需求且置信度高,是重要的概念验证,未来将通过扩展数据库来完善和验证模型。
要点
- 模型基于29,816例16-60岁躯干及交界区枪伤患者,休克、重大手术、早期MT分别占13.0%、22.4%、6.3%。
- 预测休克、早期MT、重大手术的平均AUC分别为0.89、0.86、0.82(80/20训练-测试拆分,1000个epoch)。
- 错误预测对正确预测的平均真类概率:休克0.25对0.87,MT 0.30对0.81,重大手术0.24对0.69。
- 作者认为该模型能准确识别躯干枪伤患者的潜在休克并预测MT和重大手术需求,且置信度高。
- 作者称其为重要的概念验证,未来将扩展数据库以完善和验证模型,并可能用于民用和军事场景的分诊。
适用人群与场景
- 美国外科医师学会创伤质量改进计划(ACS TQIP)来源数据库中躯干及交界区枪伤患者,年龄16-60岁。
研究设计与关键结果
- 研究类型:基于ACS TQIP来源数据库的机器学习模型开发与测试(预后性研究,证据等级III级)。
- 共29,816例患者符合全部纳入标准;休克、重大手术、早期MT分别占13.0%、22.4%、6.3%。
- 采用信息感知的Dirichlet深度神经网络(野外人工智能分诊),以枪伤解剖部位、生命体征和野外可获得的患者信息为输入,监督训练预测休克、需行重大出血控制手术或早期大量输血。
- 并行建立置信度模型,基于输入变量的取值和相互关联预测真类概率(0-1标度),表示所做预测正确的可能性。
- 80/20训练-测试拆分、1,000个epoch下,预测休克、早期MT、重大手术的平均受试者工作特征曲线下面积分别为0.89、0.86、0.82。
- 错误预测对正确预测的平均真类概率:休克0.25对0.87,MT 0.30对0.81,重大手术0.24对0.69。
证据类型、等级与局限
- 证据类型:基于ACS TQIP来源数据库的机器学习模型开发与测试;证据等级:预后性,III级。
- 局限:作者称该模型为重要的概念验证,未来迭代将扩展数据库以完善和验证模型。
对床旁实践的改变
- 作者认为野外人工智能分诊能准确识别躯干枪伤患者的潜在休克并预测其早期MT和重大手术需求,且置信度高。
- 作者认为该模型是重要的概念验证,未来将通过扩展数据库来完善和验证模型,进一步提升其在民用和军事场景野外分诊中的潜力。
提炼说明
- 本条依据论文摘要整理;摘要未涉及「诊断标准与关键阈值」「处置流程与药物剂量」「红旗征与不能漏的情况」「指南或共识出处」,故未列出这些栏目;全文请点「阅读原文」。
英文原文(摘要)· 点击展开
BACKGROUND: In-field triage tools for trauma patients are limited by availability of information, linear risk classification, and a lack of confidence reporting. We therefore set out to develop and test a machine learning algorithm that can overcome these limitations by accurately and confidently making predictions to support in-field triage in the first hours after traumatic injury.
METHODS: Using an American College of Surgeons Trauma Quality Improvement Program-derived database of truncal and junctional gunshot wound (GSW) patients (aged 16-60 years), we trained an information-aware Dirichlet deep neural network (field artificial intelligence triage). Using supervised training, field artificial intelligence triage was trained to predict shock and the need for major hemorrhage control procedures or early massive transfusion (MT) using GSW anatomical locations, vital signs, and patient information available in the field. In parallel, a confidence model was developed to predict the true-class probability (scale of 0-1), indicating the likelihood that the prediction made was correct, based on the values and interconnectivity of input variables.
RESULTS: A total of 29,816 patients met all the inclusion criteria. Shock, major surgery, and early MT were identified in 13.0%, 22.4%, and 6.3% of the included patients, respectively. Field artificial intelligence triage achieved mean areas under the receiver operating characteristic curve of 0.89, 0.86, and 0.82 for prediction of shock, early MT, and major surgery, respectively, for 80/20 train-test splits over 1,000 epochs. Mean predicted true-class probability for errors/correct predictions was 0.25/0.87 for shock, 0.30/0.81 for MT, and 0.24/0.69 for major surgery.
CONCLUSION: Field artificial intelligence triage accurately identifies potential shock in truncal GSW patients and predicts their need for MT and major surgery, with a high degree of certainty. The presented model is an important proof of concept. Future iterations will use an expansion of databases to refine and validate the model, further adding to its potential to improve triage in the field, both in civilian and military settings.
LEVEL OF EVIDENCE: Prognostic, Level III.
参考来源
- Nederpelt CJ, Mokhtari AK, Alser O, et al. Development of a field artificial intelligence triage tool: Confidence in the prediction of shock, transfusion, and definitive surgical therapy in patients with truncal gunshot wounds. J Trauma Acute Care Surg. 2021. PMID: 34016929. doi:10.1097/TA.0000000000003155
供执业医师抢救与诊疗参考,不替代临床判断;剂量请结合体重、肝肾功能和本院药品规格复核,以指南原文为准。