Rapid Computer‐Aided Diagnosis of Stroke by Serum Metabolic Fingerprint Based Multi‐Modal Recognition

Abstract

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.

Objectively Measured Sleep Characteristics and Incidence of Ischemic Stroke: The Sleep Heart Health Study

“…1 The stroke burden is expected to rise from approximately 38 million disability-adjusted life-years globally in 1990 to 61 million disability-adjusted lifeyears in 2020. 2 Ischemic stroke is the most prevalent type of stroke, accounting for nearly 88% of all types. 3 There are many common risk factors for ischemic stroke, including aging, smoking, tobacco use, and high blood pressure.…”

Sustainable Carbon Materials toward Emerging Applications

“…[ 148 ] Fe 3 O 4 was found with property of peroxidase‐mimicking in 2007, [ 149 ] leading to its broad range of biomedical applications. [ 150–152 ] The successful development of Fe 3 O 4 also triggers the developing transition metal‐based nanozymes and noble metal based nanozymes as well as their biomedical applications, such as Co, [ 153 ] Zr, [ 154 ] V, [ 155 ] Pt, [ 156 ] and Au. [ 157 ] Notably, the well‐designed carbon nanomaterials are considered as ideal candidates for nanozyme and have exhibited with enhanced biocatalytic performance as peroxidase mimics, superoxide dismutase (SOD) mimics and hydrolase mimics.…”

Nanomaterial‐Based Electrochemical Sensors: Mechanism, Preparation, and Application in Biomedicine

“…Health management relies on mining big health care data produced in real‐time subject monitoring [84d,97] . The noninvasive and cost‐effective wearable devices based on electrochemical biosensors have made substantial progress in providing accessibility and field analysis of human health conditions.…”