Rapid Computer-Aided Diagnosis of Stroke by Serum Metabolic Fingerprint Based Multi-Modal Recognition.
Rapid Computer-Aided Diagnosis of Stroke by Serum Metabolic Fingerprint Based Multi-Modal Recognition.
复制标题
基于多模态识别的血清代谢指纹图谱的脑卒中快速计算机辅助诊断
DOI：
10.1002/advs.202002021
复制
发表时间：
2020-11
期刊：
影响因子：
--
通讯作者：
Qian K
中科院分区：
文献类型：
--
作者：
Xu W;Lin J;Gao M;Chen Y;Cao J;Pu J;Huang L;Zhao J;Qian K
中风是全球死亡和残疾的主要原因，预计到2020年将导致6100万残疾调整生命年。快速诊断是中风管理的核心，有助于早期预防和医疗。血清代谢指纹（SMF）反映了潜在的疾病进展，预测患者表型。深度学习（DL）编码具有临床指标的SMF优于单一生物标志物，同时带来了通过特征选择进行解释的预测较差的挑战。在此，通过DL使用基于SMF的多模态识别来执行中风的快速计算机辅助诊断，以将联合收割机自适应机器学习与新的特征选择方法相结合。通过纳米辅助激光解吸/电离质谱法（LDI MS）提取SMF，在几秒钟内消耗100 nL血清。通过整合SMF和临床指标构建多模态识别，与仅通过SMF或临床指标的单模态诊断相比，卒中筛查的曲线下面积（AUC）最高可达0.845。DL的预测是通过选择20个关键的代谢物特征，通过显着图方法进行差异调节，揭示中风的分子机制。该方法强调了DL在精准医学中的新兴作用，并建议在中风筛查中扩展SMF计算分析的实用性。使用纳米辅助激光解吸/电离质谱法实现血清代谢指纹（SMF）的快速提取，在几秒钟内消耗100 nL天然血清。通过深度学习将SMF与临床指标进一步整合，基于SMF的多模态识别实现了中风的无创诊断。作为一种平台方法，它可以在不久的将来适应许多医疗模式和疾病应用。
Stroke is a leading cause of mortality and disability worldwide, expected to result in 61 million disability‐adjusted life‐years in 2020. Rapid diagnostics is the core of stroke management for early prevention and medical treatment. Serum metabolic fingerprints (SMFs) reflect underlying disease progression, predictive of patient phenotypes. Deep learning (DL) encoding SMFs with clinical indexes outperforms single biomarkers, while posing challenges with poor prediction to interpret by feature selection. Herein, rapid computer‐aided diagnosis of stroke is performed using SMF based multi‐modal recognition by DL, to combine adaptive machine learning with a novel feature selection approach. SMFs are extracted by nano‐assisted laser desorption/ionization mass spectrometry (LDI MS), consuming 100 nL of serum in seconds. A multi‐modal recognition is constructed by integrating SMFs and clinical indexes with an enhanced area under curve (AUC) up to 0.845 for stroke screening, compared to single‐modal diagnosis by only SMFs or clinical indexes. The prediction of DL is addressed by selecting 20 key metabolite features with differential regulation through a saliency map approach, shedding light on the molecular mechanisms in stroke. The approach highlights the emerging role of DL in precision medicine and suggests an expanding utility for computational analysis of SMFs in stroke screening. Rapid extraction of serum metabolic fingerprints (SMFs) is achieved using nano‐assisted laser desorption/ionization mass spectrometry, consuming 100 nL of native serum in seconds. Further integrating SMFs with clinical indexes by deep learning, the SMF based multi‐modal recognition achieves noninvasive diagnosis of stroke. As a platform approach, it can be adapted to many medical modalities and disease applications in the near future.
登录
查看更多内容
影响因子：
14.8
作者：
Kohoutova, Lada;Heo, Juyeon;Cha, Sungmin;Lee, Sungwoo;Moon, Taesup;Wager, Tor D.;Woo, Choong-Wan
通讯作者：
Woo, Choong-Wan
DOI：
10.1038/nrg.2018.4
发表时间：
2018-05
期刊：
Nature reviews. Genetics
影响因子：
--
作者：
Karczewski KJ;Snyder MP
通讯作者：
Snyder MP
影响因子：
8.4
作者：
Li, Yao;Xie, Maowen;Sun, Xuping
通讯作者：
Sun, Xuping
影响因子：
2.8
作者：
An, Se-A;Kim, Jinkwon;Oh, Seung-Hun
通讯作者：
Oh, Seung-Hun
影响因子：
16.6
作者：
Goubran, Maged;Leuze, Christoph;Zeineh, Michael
通讯作者：
Zeineh, Michael