文献速递消化、代谢与肾脏急症

MPL-ANN与PLS-DA模型预测急性胰腺炎患者严重程度的比较:一项探索性研究

Comparison of MPL-ANN and PLS-DA models for predicting the severity of patients with acute pancreatitis: An exploratory study.
PubMed 文献 · Am J Emerg Med · 2021-01-22
一句话结论基于血常规和血清生化指标的MPL-ANN模型在区分轻症与重症急性胰腺炎方面表现优于PLS-DA模型(AUC 0.984 vs 0.912)。

本研究纳入133例轻症急性胰腺炎(MAP)患者、167例重症急性胰腺炎(SAP,含88例中度SAP)患者和69例健康对照,利用15项血常规参数和5项血清生化指标建立MPL-ANN与PLS-DA模型,以AUC评价其区分AP严重程度的诊断效能。结果显示,20项参数中中性粒细胞与淋巴细胞比值(NLR)筛查AP患者最有价值(AUC=0.990,95%CI:0.984-0.997,灵敏度94.3%,特异度98.6%)。基于6个最优参数的MPL-ANN模型在区分MAP与SAP时表现优于基于5个最优参数的PLS-DA模型(AUC=0.984 vs 0.912)。作者认为,基于常规血和血清生化指标的MPL-ANN模型为日常临床实践提供了可靠且简便可行的预测AP严重程度的工具。

要点

  • 在20项参数中,NLR筛查AP患者最有价值:AUC=0.990(95%CI:0.984-0.997),灵敏度94.3%,特异度98.6%。
  • MPL-ANN模型基于6个最优参数区分MAP与SAP:AUC=0.984(95%CI:0.960-1.00),灵敏度92.7%,特异度93.3%,准确率93.0%。
  • PLS-DA模型基于5个最优参数区分MAP与SAP:AUC=0.912(95%CI:0.853-0.971),灵敏度87.8%,特异度84.4%,准确率84.8%。
  • MPL-ANN模型在区分MAP与SAP时诊断和预测性能优于PLS-DA模型。
  • 作者认为,基于常规血和血清生化指标的MPL-ANN模型为日常临床实践提供了可靠且简便可行的预测AP严重程度的工具。

适用人群与场景

  • 纳入133例轻症急性胰腺炎(MAP)患者、167例重症急性胰腺炎(SAP,含88例中度SAP)患者和69例健康对照。

研究设计与关键结果

  • 研究为探索性研究,纳入133例MAP、167例SAP(含88例中度SAP)和69例健康对照,利用15项血常规参数和5项血清生化指标建立MPL-ANN与PLS-DA模型。
  • NLR在20项参数中筛查AP患者最有价值:AUC=0.990(95%CI:0.984-0.997),灵敏度94.3%,特异度98.6%。
  • MPL-ANN模型基于6个最优参数区分MAP与SAP:AUC=0.984(95%CI:0.960-1.00),灵敏度92.7%,特异度93.3%,准确率93.0%。
  • PLS-DA模型基于5个最优参数区分MAP与SAP:AUC=0.912(95%CI:0.853-0.971),灵敏度87.8%,特异度84.4%,准确率84.8%。
  • MPL-ANN模型在区分MAP与SAP时诊断和预测性能优于PLS-DA模型。

证据类型、等级与局限

  • 证据类型:探索性研究。
  • 局限:原文未报告局限性。

对床旁实践的改变

  • 作者认为,基于常规血和血清生化指标的MPL-ANN模型为日常临床实践提供了可靠且简便可行的预测AP严重程度的工具。

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

OBJECTIVE: Acute pancreatitis (AP) is a common inflammatory disorder that may develop into severe AP (SAP), resulting in life-threatening complications and even death. The purpose of this study was to explore two different machine learning models of multilayer perception-artificial neural network (MPL-ANN) and partial least squares-discrimination (PLS-DA) to diagnose and predict AP patients' severity.

METHODS: The MPL-ANN and PLS-DA models were established using candidate markers from 15 blood routine parameters and five serum biochemical indexes of 133 mild acute pancreatitis (MAP) patients, 167 SAP (including 88 moderately SAP) patients, and 69 healthy controls (HCs). The independent parameters and combined model's diagnostic efficiency in AP severity differentiation were analyzed using the area under the receiver operating characteristic curve (AUC).

RESULTS: The neutrophil to lymphocyte ratio (NLR) is the most useful marker in 20 parameters for screening AP patients [AUC = 0.990, 95% confidence interval (CI): 0.984-0.997, sensitivity 94.3%, specificity 98.6%]. The MPL-ANN model based on six optimal parameters exhibited better diagnostic and predict performance (AUC = 0.984, 95% CI: 0.960-1.00, sensitivity 92.7%, specificity 93.3%, accuracy 93.0%) than the PLS-DA model based on five optimal parameters (AUC = 0.912, 95% CI: 0.853-0.971, sensitivity 87.8%, specificity 84.4%, accuracy 84.8%) in discriminating MAP patients from SAP patients.

CONCLUSION: The results demonstrated that the MPL-ANN model based on routine blood and serum biochemical indexes provides a reliable and straightforward daily clinical practice tool to predict AP patients' severity.

来源:Am J Emerg Med,查看原文。版权归原作者所有。

参考来源

  1. Jin X, Ding Z, Li T, et al. Comparison of MPL-ANN and PLS-DA models for predicting the severity of patients with acute pancreatitis: An exploratory study. Am J Emerg Med. 2021. PMID: 33582613. doi:10.1016/j.ajem.2021.01.044

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。