Hollow Cobalt Oxide/Carbon Hybrids Aid Metabolic Encoding for Active Systemic Lupus Erythematosus during Pregnancy

Machine learning techniques for prediction in pregnancy complicated by autoimmune rheumatic diseases: Applications and challenges

Autoimmune rheumatic diseases are chronic conditions affecting multiple systems and often occurring in young women of childbearing age. The diseases and the physiological characteristics of pregnancy significantly impact maternal-fetal health and pregnancy outcomes. Currently, the integration of big data with healthcare has led to the increasing popularity of using machine learning (ML) to mine clinical data for studying pregnancy complications. In this review, we introduce the basics of ML and the recent advances and trends of ML in different prediction applications for common pregnancy complications by autoimmune rheumatic diseases. Finally, the challenges and future for enhancing the accuracy, reliability, and clinical applicability of ML in prediction have been discussed. This review will provide insights into the utilization of ML in identifying and assisting clinical decision-making for pregnancy complications, while also establishing a foundation for exploring comprehensive management strategies for pregnancy and enhancing maternal and child health.

Vacancy-Driven High-Performance Metabolic Assay for Diagnosis and Therapeutic Evaluation of Depression

Depression is one of the most common mental illnesses and is a well-known risk factor for suicide, characterized by low overall efficacy (<50%) and high relapse rate (40%). A rapid and objective approach for screening and prognosis of depression is highly desirable but still awaits further development. Herein, a high-performance metabolite-based assay to aid the diagnosis and therapeutic evaluation of depression by developing a vacancy-engineered cobalt oxide (Vo-Co3O4) assisted laser desorption/ionization mass spectrometer platform is presented. The easy-prepared nanoparticles with optimal vacancy achieve a considerable signal enhancement, characterized by favorable charge transfer and increased photothermal conversion. The optimized Vo-Co3O4 allows for a direct and robust record of plasma metabolic fingerprints (PMFs). Through machine learning of PMFs, high-performance depression diagnosis is achieved, with the areas under the curve (AUC) of 0.941-0.980 and an accuracy of over 92%. Furthermore, a simplified diagnostic panel for depression is established, with a desirable AUC value of 0.933. Finally, proline levels are quantified in a follow-up cohort of depressive patients, highlighting the potential of metabolite quantification in the therapeutic evaluation of depression. This work promotes the progression of advanced matrixes and brings insights into the management of depression.

Systemic lupus in the era of machine learning medicine

Artificial intelligence and machine learning applications are emerging as transformative technologies in medicine. With greater access to a diverse range of big datasets, researchers are turning to these powerful techniques for data analysis. Machine learning can reveal patterns and interactions between variables in large and complex datasets more accurately and efficiently than traditional statistical methods. Machine learning approaches open new possibilities for studying SLE, a multifactorial, highly heterogeneous and complex disease. Here, we discuss how machine learning methods are rapidly being integrated into the field of SLE research. Recent reports have focused on building prediction models and/or identifying novel biomarkers using both supervised and unsupervised techniques for understanding disease pathogenesis, early diagnosis and prognosis of disease. In this review, we will provide an overview of machine learning techniques to discuss current gaps, challenges and opportunities for SLE studies. External validation of most prediction models is still needed before clinical adoption. Utilisation of deep learning models, access to alternative sources of health data and increased awareness of the ethics, governance and regulations surrounding the use of artificial intelligence in medicine will help propel this exciting field forward.

Urinary biomarkers associated with podocyte injury in lupus nephritis

The most prevalent and devastating form of organ damage in systemic lupus erythematosus (SLE) is lupus nephritis (LN). LN is characterized by glomerular injury, inflammation, cell proliferation, and necrosis, leading to podocyte injury and tubular epithelial cell damage. Assays for urine biomarkers have demonstrated significant promise in the early detection of LN, evaluation of disease activity, and tracking of reaction to therapy. This is because they are non-invasive, allow for frequent monitoring and easy self-collection, transport and storage. Podocyte injury is believed to be a essential factor in LN. The extent and type of podocyte injury could be connected to the severity of proteinuria, making podocyte-derived cellular debris and injury-related urinary proteins potential markers for the diagnosis and monitoring of LN. This article focuses on studies examining urinary biomarkers associated with podocyte injury in LN, offering fresh perspectives on the application of biomarkers in the early detection and management of LN.

Serum Metabolic Fingerprints Characterize Systemic Lupus Erythematosus

Metabolic fingerprints in serum characterize diverse diseases for diagnostics and biomarker discovery. The identification of systemic lupus erythematosus (SLE) by serum metabolic fingerprints (SMFs) will facilitate precision medicine in SLE in an early and designed manner. Here, a discovery cohort of 731 individuals including 357 SLE patients and 374 healthy controls (HCs), and a validation cohort of 184 individuals (SLE/HC, 91/93) are constructed. Each SMF is directly recorded by nano-assisted laser desorption/ionization mass spectrometry (LDI MS) within 1 minute using 1 µL of native serum, which contains 908 mass to charge features. Sparse learning of SMFs achieves the SLE identification with sensitivity/specificity and area-under-the-curve (AUC) up to 86.0%/92.0% and 0.950 for the discovery cohort. For the independent validation cohort, it exhibits no performance loss by affording the sensitivity/specificity and AUC of 89.0%/100.0% and 0.992. Notably, a metabolic biomarker panel is screened out from the SMFs, demonstrating the unique metabolic pattern of SLE patients different from both HCs and rheumatoid arthritis patients. In conclusion, SMFs characterize SLE by revealing its unique metabolic pattern. Different regulation of small molecule metabolites contributes to the precise diagnosis of autoimmune disease and further exploration of the pathogenic mechanisms.

Designed Nanomaterials-Assisted Proteomics and Metabolomics Analysis for In Vitro Diagnosis

In vitro diagnosis (IVD) is pivotal in modern medicine, enabling early disease detection and treatment optimization. Omics technologies, particularly proteomics and metabolomics, offer profound insights into IVD. Despite its significance, omics analyses for IVD face challenges, including low analyte concentrations and the complexity of biological environments. In addition, the direct omics analysis by mass spectrometry (MS) is often hampered by issues like large sample volume requirements and poor ionization efficiency. Through manipulating their size, surface charge, and functionalization, as well as the nanoparticle-fluid incubation conditions, nanomaterials have emerged as a promising solution to extract biomolecules and enhance the desorption/ionization efficiency in MS detection. This review delves into the last five years of nanomaterial applications in omics, focusing on their role in the enrichment, separation, and ionization analysis of proteins and metabolites for IVD. It aims to provide a comprehensive update on nanomaterial design and application in omics, highlighting their potential to revolutionize IVD.

Construction of Porous Perovskite Oxide Microrods with Au Nanoparticle Anchor for Precise Metabolic Diagnosis of Alzheimer's Disease

Alzheimer's disease (AD) is a progressive illness, and early diagnosis and treatment can help delay its progression. However, clinics still lack high-throughput, low-invasive, precise, and objective diagnostic strategies. Herein, the Au nanoparticles anchored porous perovskite oxide microrods (CTO@Au) with designed superior properties is developed to construct a high-throughput detection platform. Specifically, a single metabolic fingerprinting is obtained from only 30 nL of serum within seconds, enabling the rapid acquisition of 239 × 8 high-quality fingerprints in ≈ 2 h. AD is distinguish from health controls and Parkinson's disease with an area under the curve (AUC) of 1.000. Moreover, eight specific metabolites are identified as a biomarker panel, based on which precise diagnosis of AD is achieved, with an AUC of 1.000 in blind test. The possible relevant pathways and potential mechanism involved in these biomarkers are investigated and discussed. This work provides a high-performance platform for metabolic diagnostic analysis.

Hollow multishelled heterostructures with enhanced performance for laser desorption/ionization mass spectrometry based metabolic diagnosis

High-performance metabolic diagnosis-based laser desorption/ionization mass spectrometry (LDI-MS) improves the precision diagnosis of diseases and subsequent treatment. Inorganic matrices are promising for the detection of metabolites by LDI-MS, while the structure and component impacts of the matrices on the LDI process are still under investigation. Here, we designed a multiple-shelled ZnMn2O4/(Co, Mn)(Co, Mn)2O4 (ZMO/CMO) as the matrix from calcined MOF-on-MOF for detecting metabolites in LDI-MS and clarified the synergistic impacts of multiple-shells and the heterostructure on LDI efficiency. The ZMO/CMO heterostructure allowed 3-5 fold signal enhancement compared with ZMO and CMO with the same morphology. Furthermore, the ZMO/CMO heterostructure with a triple-shelled hollow structure displayed a 3-fold signal enhancement compared to its nanoparticle counterpart. Taken together, the triple-shelled hollow ZMO/CMO exhibits 102-fold signal enhancement compared to the commercial matrix products (e.g., DHB and DHAP), allowing for sensitive metabolic profiling in bio-detection. We directly extracted metabolic patterns by the optimized triple-shelled hollow ZMO/CMO particle-assisted LDI-MS within 1 s using 100 nL of serum and used machine learning as the readout to distinguish hepatocellular carcinoma from healthy controls with the area under the curve value of 0.984. Our approach guides us in matrix design for LDI-MS metabolic analysis and drives the development of a nanomaterial-based LDI-MS platform toward precision diagnosis.

Bovine Omasum-Inspired Interfacial Carbon-Based Nanocomposite for Saliva Metabolic Screening of Gastric Cancer

Gastric cancer is one of the most common malignant digestive cancers, and its diagnostic has still faced challenges based on metabolic analysis due to complex sample pretreatment and low metabolite abundance. In this study, inspired by the structure of bovine omasum, we in situ synthesized a novel interfacial carbon-based nanocomposite of graphene supported nickel nanoparticles-encapsulated in the nitrogen-doped carbon nanotube (Ni/N-CNT/rGO), which was served as a novel matrix with enhanced ionization efficiency for the matrix-assisted laser desorption/ionization time of flight mass spectrometry (MALDI-TOF MS) saliva metabolic analysis of gastric cancer. Benefiting from its high sp² graphitic degree, large surface area, strong UV absorption, and rich active sites, Ni/N-CNT/rGO matrix exhibited excellent performances of reproducibility, coverage, salt-tolerance, sensitivity, and adsorption ability in MALDI-TOF MS. The differential scanning calorimetry (DSC) and thermal conversion behaviors explained the highly efficient LDI mechanism. Based on saliva metabolic fingerprints, Ni/N-CNT/rGO assisted LDI MS with cross-validation analysis could successfully distinguish gastric cancer patients from healthy controls through the screening of four potential biomarkers with an accuracy of 92.50%, specificity of 88.03%, and sensitivity of 97.12%. This work provided a fast and sensitive MS sensing platform for the metabolomics characterization of gastric cancer and might have potential value for precision medicine in the future.

Designed Concave Octahedron Heterostructures Decode Distinct Metabolic Patterns of Epithelial Ovarian Tumors

Epithelial ovarian cancer (EOC) is a polyfactorial process associated with alterations in metabolic pathways. A high-performance screening tool for EOC is in high demand to improve prognostic outcome but is still missing. Here, a concave octahedron Mn₂ O₃ /(Co,Mn)(Co,Mn)₂ O₄ (MO/CMO) composite with a heterojunction, rough surface, hollow interior, and sharp corners is developed to record metabolic patterns of ovarian tumors by laser desorption/ionization mass spectrometry (LDI-MS). The MO/CMO composites with multiple physical effects induce enhanced light absorption, preferred charge transfer, increased photothermal conversion, and selective trapping of small molecules. The MO/CMO shows ≈2-5-fold signal enhancement compared to mono- or dual-enhancement counterparts, and ≈10-48-fold compared to the commercialized products. Subsequently, serum metabolic fingerprints of ovarian tumors are revealed by MO/CMO-assisted LDI-MS, achieving high reproducibility of direct serum detection without treatment. Furthermore, machine learning of the metabolic fingerprints distinguishes malignant ovarian tumors from benign controls with the area under the curve value of 0.987. Finally, seven metabolites associated with the progression of ovarian tumors are screened as potential biomarkers. The approach guides the future depiction of the state-of-the-art matrix for intensive MS detection and accelerates the growth of nanomaterials-based platforms toward precision diagnosis scenarios.

Construction of a ternary component chip with enhanced desorption efficiency for laser desorption/ionization mass spectrometry based metabolic fingerprinting

Introduction: In vitro metabolic fingerprinting encodes diverse diseases for clinical practice, while tedious sample pretreatment in bio-samples has largely hindered its universal application. Designed materials are highly demanded to construct diagnostic tools for high-throughput metabolic information extraction. Results: Herein, a ternary component chip composed of mesoporous silica substrate, plasmonic matrix, and perfluoroalkyl initiator is constructed for direct metabolic fingerprinting of biofluids by laser desorption/ionization mass spectrometry. Method: The performance of the designed chip is optimized in terms of silica pore size, gold sputtering time, and initiator loading parameter. The optimized chip can be coupled with microarrays to realize fast, high-throughput (∼second/sample), and microscaled (∼1 μL) sample analysis in human urine without any enrichment or purification. On-chip urine fingerprints further allow for differentiation between kidney stone patients and healthy controls. Discussion: Given the fast, high throughput, and easy operation, our approach brings a new dimension to designing nano-material-based chips for high-performance metabolic analysis and large-scale diagnostic use.