一种用于检测颅内高压的深度学习方法的推导、外部验证及临床验证
Derivation, external and clinical validation of a deep learning approach for detecting intracranial hypertension.
作者信息
Gulamali Faris, Jayaraman Pushkala, Sawant Ashwin S, Desman Jacob, Fox Benjamin, Chang Annette, Soong Brian Y, Arivazagan Naveen, Reynolds Alexandra S, Duong Son Q, Vaid Akhil, Kovatch Patricia, Freeman Robert, Hofer Ira S, Sakhuja Ankit, Dangayach Neha S, Reich David S, Charney Alexander W, Nadkarni Girish N
机构信息
The Charles Bronfman Institute of Personalized Medicine, Icahn School of Medicine at Mount Sinai, New York, NY, USA.
The Division of Data Driven and Digital Medicine, Icahn School of Medicine at Mount Sinai, New York, NY, USA.
出版信息
NPJ Digit Med. 2024 Sep 5;7(1):233. doi: 10.1038/s41746-024-01227-0.
Increased intracranial pressure (ICP) ≥15 mmHg is associated with adverse neurological outcomes, but needs invasive intracranial monitoring. Using the publicly available MIMIC-III Waveform Database (2000-2013) from Boston, we developed an artificial intelligence-derived biomarker for elevated ICP (aICP) for adult patients. aICP uses routinely collected extracranial waveform data as input, reducing the need for invasive monitoring. We externally validated aICP with an independent dataset from the Mount Sinai Hospital (2020-2022) in New York City. The AUROC, accuracy, sensitivity, and specificity on the external validation dataset were 0.80 (95% CI, 0.80-0.80), 73.8% (95% CI, 72.0-75.6%), 73.5% (95% CI 72.5-74.5%), and 73.0% (95% CI, 72.0-74.0%), respectively. We also present an exploratory analysis showing aICP predictions are associated with clinical phenotypes. A ten-percentile increment was associated with brain malignancy (OR = 1.68; 95% CI, 1.09-2.60), intracerebral hemorrhage (OR = 1.18; 95% CI, 1.07-1.32), and craniotomy (OR = 1.43; 95% CI, 1.12-1.84; P < 0.05 for all).
颅内压（ICP）升高≥15mmHg与不良神经学预后相关，但需要进行有创颅内监测。利用来自波士顿的公开可用的MIMIC-III波形数据库（2000 - 2013年），我们为成年患者开发了一种用于检测ICP升高的人工智能衍生生物标志物（aICP）。aICP将常规收集的颅外波形数据用作输入，减少了对有创监测的需求。我们使用来自纽约市西奈山医院的独立数据集（2020 - 2022年）对aICP进行了外部验证。在外部验证数据集中，曲线下面积（AUROC）、准确率、敏感性和特异性分别为0.80（95%置信区间，0.80 - 0.80）、73.8%（95%置信区间，72.0 - 75.6%）、73.5%（95%置信区间，72.5 - 74.5%）和73.0%（95%置信区间，72.0 - 74.0%）。我们还进行了一项探索性分析，结果显示aICP预测与临床表型相关。aICP每增加十分位数与脑恶性肿瘤（比值比[OR]=1.68；95%置信区间，1.09 - 2.60）、脑出血（OR = 1.18；95%置信区间，1.07 - 1.32）和开颅手术（OR = 1.43；95%置信区间，1.12 - 1.84；所有P均<0.05）相关。
Zotero 插件