Diagnosis Of Complex Diseases Research Articles

A miniaturized microfluidic nanoplasmonic sensor with cavity reflection enhancement for ultrasensitive molecular interaction analysis

Molecular binding kinetics quantification is pivotal in the design of antibodies, small-molecule drugs, and early diagnosis of complex disease. This study presents a portable microfluidic system, featuring a nanoplasmonic sensor with cavity reflection enhancement (NSCRE), designed for the ultrasensitive detection and analysis of molecular interactions. This device comprises liquid flow paths, generic fiber spectrometers, a versatile NSCRE sensor chip, and a novel data analysis system. Furthermore, a neural network data processing system is developed based on a deep learning model to decrease significant data fluctuations caused by air segments. This “all-in-one” platform, integrating multifunctional, easy-to-use, and renewable NSCRE biosensors, boasts detection capabilities for both slow and rapid kinetics. It can automatically monitor interactions between molecules across a broad range of molecular weights (0.259–150 kDa), allowing for real-time, ultra-sensitive, and highly selective analysis. In addition, the platform with CRE effect facilitates a 7.2-fold increase in reflection intensity signals compared to that of a sensor without CRE. The immunoglobulin G detection with a limit of detection of 73 pM based on this device, showing a 50-fold increase in sensitivity compared to previously reported values. The miniaturized automatic detection system paves a new path for the use of molecular interaction analysis in life science research, drug discovery, early diagnosis, and other fields.

Pathformer: a biological pathway informed transformer for disease diagnosis and prognosis using multi-omics data.

Multi-omics data provide a comprehensive view of gene regulation at multiple levels, which is helpful in achieving accurate diagnosis of complex diseases like cancer. However, conventional integration methods rarely utilize prior biological knowledge and lack interpretability. To integrate various multi-omics data of tissue and liquid biopsies for disease diagnosis and prognosis, we developed a biological pathway informed Transformer, Pathformer. It embeds multi-omics input with a compacted multi-modal vector and a pathway-based sparse neural network. Pathformer also leverages criss-cross attention mechanism to capture the crosstalk between different pathways and modalities. We first benchmarked Pathformer with 18 comparable methods on multiple cancer datasets, where Pathformer outperformed all the other methods, with an average improvement of 6.3%-14.7% in F1 score for cancer survival prediction, 5.1%-12% for cancer stage prediction, and 8.1%-13.6% for cancer drug response prediction. Subsequently, for cancer prognosis prediction based on tissue multi-omics data, we used a case study to demonstrate the biological interpretability of Pathformer by identifying key pathways and their biological crosstalk. Then, for cancer early diagnosis based on liquid biopsy data, we used plasma and platelet datasets to demonstrate Pathformer's potential of clinical applications in cancer screening. Moreover, we revealed deregulation of interesting pathways (e.g. scavenger receptor pathway) and their crosstalk in cancer patients' blood, providing potential candidate targets for cancer microenvironment study. Pathformer is implemented and freely available at https://github.com/lulab/Pathformer.

Chelating ligand-bridged IO-Gd nanoparticles with enhanced contrast performance for dual-mode MRI

Magnetic resonance imaging (MRI) is a non-invasive medical imaging technique that has been widely applied in the clinical diagnosis of diseases across various fields. Currently, there is a dearth of high-performance dual-mode contrast agents that provide precise diagnostic information for complex diseases. In this study, iron oxide-gadolinium nanoparticles (IO-Gd NPs) bridged by hydrophilic ligand ethylenediamine tetramethylenephosphonic acid (EDTMP) are designed inspired by Solomon-Bloembergen–Morgan (SBM) theory, where T1 and T2 relaxivity increase with a reduction in Gd content. In particular, the NPs with minimum Gd content exhibit excellent dual-mode contrast performance (r1 = 94.42 mM−1 s−1, r2 = 343.62 mM−1 s−1). The underlying mechanism is that the bridged EDTMP coordinate limits Gd tumbling and forces Gd3+ to expose itself to the surface of the NPs. This provides more opportunities for water molecules to coordinate with Gd3+ and significantly enhances proton relaxivity. Moreover, the hydrophilicity of the ligand enhances the water dispersion stability of the NPs and increases the exchange rate of water protons near the NPs, further enhancing the dual-mode contrast effect. Finally, the biocompatibility and in vitro/vivo imaging performances of the IO@EDTMP-Gd NPs are systematically evaluated, and the results demonstrate their potential as dual-mode contrast agents. This study provides a new strategy for developing dual-mode MRI contrast agents that can further improve the accuracy of MRI in the diagnosis of complex diseases.

Machine learning assisted designing of Indacenodithiophene (IDT)-based polymers for future application of photoacoustic imaging

Non-invasive imaging tools are essential for diagnosis of complex disease. Photoacoustic (PA) imaging is a multiscale noninvasive imaging modality with high resolution and sensitivity for deep-seated pathologies. However, microenvironment of some pathologies produce PA signals compromising the optical resolution of PA imaging. This demands the construction of PA imaging agents to avoid the low signal to noise ratio with improved resolution and sensitivity. In this study, we use machine learning to design the IDT-based polymers with their absorption coefficient in NIR-I region. We used the database of polymer structures and properties to identify promising candidates for PAI. The models were then used to predict the properties of new IDT-based polymers with optimized absorption, biocompatibility and acoustic performance. Several promising candidates were identified and their in silico synthesis potential and PA imaging performance was predicted. The results demonstrates the potential of machine learning-guided polymers design for PA imaging agents and suggest that IDT-based polymers could be a valuable addition to the toolkit of PA imaging contrast agents.

Machine Learning Algorithms Applied to Predict Autism Spectrum Disorder Based on Gut Microbiome Composition.

The application of machine learning (ML) techniques stands as a reliable method for aiding in the diagnosis of complex diseases. Recent studies have related the composition of the gut microbiota to the presence of autism spectrum disorder (ASD), but until now, the results have been mostly contradictory. This work proposes using machine learning to study the gut microbiome composition and its role in the early diagnosis of ASD. We applied support vector machines (SVMs), artificial neural networks (ANNs), and random forest (RF) algorithms to classify subjects as neurotypical (NT) or having ASD, using published data on gut microbiome composition. Naive Bayes, k-nearest neighbors, ensemble learning, logistic regression, linear regression, and decision trees were also trained and validated; however, the ones presented showed the best performance and interpretability. All the ML methods were developed using the SAS Viya software platform. The microbiome's composition was determined using 16S rRNA sequencing technology. The application of ML yielded a classification accuracy as high as 90%, with a sensitivity of 96.97% and specificity reaching 85.29%. In the case of the ANN model, no errors occurred when classifying NT subjects from the first dataset, indicating a significant classification outcome compared to traditional tests and data-based approaches. This approach was repeated with two datasets, one from the USA and the other from China, resulting in similar findings. The main predictors in the obtained models differ between the analyzed datasets. The most important predictors identified from the analyzed datasets are Bacteroides, Lachnospira, Anaerobutyricum, and Ruminococcus torques. Notably, among the predictors in each model, there is the presence of bacteria that are usually considered insignificant in the microbiome's composition due to their low relative abundance. This outcome reinforces the conventional understanding of the microbiome's influence on ASD development, where an imbalance in the composition of the microbiota can lead to disrupted host-microbiota homeostasis. Considering that several previous studies focused on the most abundant genera and neglected smaller (and frequently not statistically significant) microbial communities, the impact of such communities has been poorly analyzed. The ML-based models suggest that more research should focus on these less abundant microbes. A novel hypothesis explains the contradictory results in this field and advocates for more in-depth research to be conducted on variables that may not exhibit statistical significance. The obtained results seem to contribute to an explanation of the contradictory findings regarding ASD and its relation with gut microbiota composition. While some research correlates higher ratios of Bacillota/Bacteroidota, others find the opposite. These discrepancies are closely linked to the minority organisms in the microbiome's composition, which may differ between populations but share similar metabolic functions. Therefore, the ratios of Bacillota/Bacteroidota regarding ASD may not be determinants in the manifestation of ASD.

Combining K Nearest Neighbor With Nonnegative Matrix Factorization for Predicting Circrna-Disease Associations.

Accumulating evidences show that circular RNAs (circRNAs) play an important role in regulating gene expression, and involve in many complex human diseases. Identifying associations of circRNA with disease helps to understand the pathogenesis, treatment and diagnosis of complex diseases. Since inferring circRNA-disease associations by biological experiments is costly and time-consuming, there is an urgently need to develop a computational model to identify the association between them. In this paper, we proposed a novel method named KNN-NMF, which combines K nearest neighbors with nonnegative matrix factorization to infer associations between circRNA and disease (KNN-NMF). Frist, we compute the Gaussian Interaction Profile (GIP) kernel similarity of circRNA and disease, the semantic similarity of disease, respectively. Then, the circRNA-disease new interaction profiles are established using weight K nearest neighbors to reduce the false negative association impact on prediction performance. Finally, Nonnegative Matrix Factorization is implemented to predict associations of circRNA with disease. The experiment results indicate that the prediction performance of KNN-NMF outperforms the competing methods under five-fold cross-validation. Moreover, case studies of two common diseases further show that KNN-NMF can identify potential circRNA-disease associations effectively.

Single-Cell Spatial MIST for Versatile, Scalable Detection of Protein Markers.

High-multiplex detection of protein biomarkers across tissue regions has been an attractive spatial biology approach due to significant advantages over traditional immunohistochemistry (IHC) methods. Different from most methods, spatial multiplex in situ tagging (MIST) transfers the spatial protein expression information to an ultrahigh-density, large-scale MIST array. This technique has been optimized to reach single-cell resolution by adoption of smaller array units and 30% 8-arm PEG polymer as transfer medium. Tissue cell nuclei stained with lamin B have been clearly visualized on the MIST arrays and are colocalized with detection of nine mouse brain markers. Pseudocells defined at 10 μm in size have been used to fully profile tissue regions including cells and the intercellular space. We showcased the versatility of our technology by successfully detecting 20 marker proteins in kidney samples with the addition of five minutes atop the duration of standard immunohistochemistry protocols. Spatial MIST is amenable to iterative staining and detection on the same tissue samples. When 25 proteins were co-detected on 1 mouse brain section for each round and 5 rounds were executed, an ultrahigh multiplexity of 125 proteins was obtained for each pseudocell. With its unique abilities, this single-cell spatial MIST technology has the potential to become an important method in advanced diagnosis of complex diseases.

Generative Adversarial Matrix Completion Network based on Multi-Source Data Fusion for miRNA-Disease Associations Prediction.

Numerous biological studies have shown that considering disease-associated micro RNAs (miRNAs) as potential biomarkers or therapeutic targets offers new avenues for the diagnosis of complex diseases. Computational methods have gradually been introduced to reveal disease-related miRNAs. Considering that previous models have not fused sufficiently diverse similarities, that their inappropriate fusion methods may lead to poor quality of the comprehensive similarity network and that their results are often limited by insufficiently known associations, we propose a computational model called Generative Adversarial Matrix Completion Network based on Multi-source Data Fusion (GAMCNMDF) for miRNA-disease association prediction. We create a diverse network connecting miRNAs and diseases, which is then represented using a matrix. The main task of GAMCNMDF is to complete the matrix and obtain the predicted results. The main innovations of GAMCNMDF are reflected in two aspects: GAMCNMDF integrates diverse data sources and employs a nonlinear fusion approach to update the similarity networks of miRNAs and diseases. Also, some additional information is provided to GAMCNMDF in the form of a 'hint' so that GAMCNMDF can work successfully even when complete data are not available. Compared with other methods, the outcomes of 10-fold cross-validation on two distinct databases validate the superior performance of GAMCNMDF with statistically significant results. It is worth mentioning that we apply GAMCNMDF in the identification of underlying small molecule-related miRNAs, yielding outstanding performance results in this specific domain. In addition, two case studies about two important neoplasms show that GAMCNMDF is a promising prediction method.

Kinetic characterization of SPR-based biomarker assays enables quality control, calibration free measurements and robust optimization for clinical application

ABSTRACT: Biomarker measurements are essential for the early diagnosis of complex diseases. However, many current biomarker assays lack sensitivity and multiplexing capacity, work in a narrow detection range and importantly lack real time quality control opportunities, which hampers clinical translation. In this paper, we demonstrate a toolbox to kinetically characterize a biomarker measurement assay using Surface Plasmon Resonance imaging (SPRi) with ample opportunities for real time quality control by exploiting quantitative descriptions of the various biomolecular interactions. We show an accurate prediction of SPRi measurements at both low and high concentrations of various analytes with deviations <5% between actual measurements and predicted measurement. The biphasic binding sites model was accurate for fitting the experimental curves and enables optimal detection of heterophilic antibodies, cross-reactivity, spotting irregularities and/or other confounders. The toolbox can also be used to create a (simulated) calibration curve, enabling calibration-free measurements with good recovery, it allows for easy assay optimizations, and could help bridge the gap to bring new biomarker assays to the clinic.

The Emerging Roles of Long Non-Coding RNAs in Intellectual Disability and Related Neurodevelopmental Disorders.

In the human brain, long non-coding RNAs (lncRNAs) are widely expressed in an exquisitely temporally and spatially regulated manner, thus suggesting their contribution to normal brain development and their probable involvement in the molecular pathology of neurodevelopmental disorders (NDD). Bypassing the classic protein-centric conception of disease mechanisms, some studies have been conducted to identify and characterize the putative roles of non-coding sequences in the genetic pathogenesis and diagnosis of complex diseases. However, their involvement in NDD, and more specifically in intellectual disability (ID), is still poorly documented and only a few genomic alterations affecting the lncRNAs function and/or expression have been causally linked to the disease endophenotype. Considering that a significant fraction of patients still lacks a genetic or molecular explanation, we expect that a deeper investigation of the non-coding genome will unravel novel pathogenic mechanisms, opening new translational opportunities. Here, we present evidence of the possible involvement of many lncRNAs in the etiology of different forms of ID and NDD, grouping the candidate disease-genes in the most frequently affected cellular processes in which ID-risk genes were previously collected. We also illustrate new approaches for the identification and prioritization of NDD-risk lncRNAs, together with the current strategies to exploit them in diagnosis.

ILncDA-LTR: Identification of lncRNA-disease associations by learning to rank

Identifying the associations between lncRNAs and diseases is helpful for the treatment and diagnosis of complex diseases. The existing computational methods mainly focus on the identification of associations between known lncRNAs and known diseases. However, with the application of high-throughput sequencing in lncRNA research, more and more lncRNAs have been detected. Predicting diseases related with newly detected lncRNAs has not been fully explored. Therefore, there is an urgent need for developing powerful computational methods to predict diseases related with newly detected lncRNAs. In this paper, we propose a Learning to Rank (LTR)-based method called iLncDA-LTR to predict diseases related with newly detected lncRNAs. iLncDA-LTR treats this task as an information retrieval task. The newly detected lncRNAs and diseases are considered as queries and documents, respectively. For a given newly detected lncRNA (query), iLncDA-LTR integrates multiple relevant information into LTR for predicting candidate diseases associated with query lncRNA. Experimental results show that iLncDA-LTR outperforms the other exiting state-of-the-art predictors on independent dataset. The corresponding web server of iLncDA-LTR has been constructed as well (http://bliulab.net/iLncDA-LTR/).

SGII: Systematic Identification of Essential lncRNAs in Mouse and Human Genome With lncRNA-Protein-Protein Heterogeneous Interaction Network.

Long noncoding RNAs (lncRNAs) play important roles in a variety of biological processes. Knocking out or knocking down some lncRNA genes can lead to death or infertility. These lncRNAs are called essential lncRNAs. Identifying the essential lncRNA is of importance for complex disease diagnosis and treatments. However, experimental methods for identifying essential lncRNAs are always costly and time consuming. Therefore, computational methods can be considered as an alternative approach. We propose a method to identify essential lncRNAs by combining network centrality measures and lncRNA sequence information. By constructing a lncRNA-protein-protein interaction network, we measure the essentiality of lncRNAs from their role in the network and their sequence together. We name our method as the systematic gene importance index (SGII). As far as we can tell, this is the first attempt to identify essential lncRNAs by combining sequence and network information together. The results of our method indicated that essential lncRNAs have similar roles in the LPPI network as the essential coding genes in the PPI network. Another encouraging observation is that the network information can significantly boost the predictive performance of sequence-based method. All source code and dataset of SGII have been deposited in a GitHub repository (https://github.com/ninglolo/SGII).

MsRepDB: a comprehensive repetitive sequence database of over 80 000 species.

Repeats are prevalent in the genomes of all bacteria, plants and animals, and they cover nearly half of the Human genome, which play indispensable roles in the evolution, inheritance, variation and genomic instability, and serve as substrates for chromosomal rearrangements that include disease-causing deletions, inversions, and translocations. Comprehensive identification, classification and annotation of repeats in genomes can provide accurate and targeted solutions towards understanding and diagnosis of complex diseases, optimization of plant properties and development of new drugs. RepBase and Dfam are two most frequently used repeat databases, but they are not sufficiently complete. Due to the lack of a comprehensive repeat database of multiple species, the current research in this field is far from being satisfactory. LongRepMarker is a new framework developed recently by our group for comprehensive identification of genomic repeats. We here propose msRepDB based on LongRepMarker, which is currently the most comprehensive multi-species repeat database, covering >80 000 species. Comprehensive evaluations show that msRepDB contains more species, and more complete repeats and families than RepBase and Dfam databases. (https://msrepdb.cbrc.kaust.edu.sa/pages/msRepDB/index.html).

Prediction of lncRNA-disease Associations Based on Robust Multi-label Learning

Background: Long non-coding RNAs (lncRNAs) are nonprotein-coding transcripts of more than 200 nucleotides in length. In recent years, studies have shown that long non-coding RNAs (lncRNA) play a vital role in various biological processes, complex disease diagnosis, prognosis, and treatment. Objective: Analysis of known lncRNA-disease associations and the prediction of potential lncRNA-disease associations are necessary to provide the most probable candidates for subsequent experimental validation. Methods: : In this paper, we present a novel robust computational framework for lncRNA-disease association prediction by combining the ℓ1-norm graph with multi-label learning. Specifically, we first construct a set of similarity matrices for lncRNAs and diseases using known associations. Then, both lncRNA and disease similarity matrices are adaptively re-weighted to enhance the robustness via the ℓ1- norm graph. Lastly, the association matrix is updated with a graph-based multi-label learning framework to uncover the underlying consistency between the lncRNA space and the disease space. Results: : We compared the proposed method with the four latest methods on five widely used data sets. The experimental results show that our method can achieve comparable performance in both five-fold cross-validation and leave-one-disease-out cross-validation prediction tasks. The case study of prostate cancer further confirms the practicability of our approach in identifying lncRNAs as potential prognostic biomarkers. Conclusion: Our method can serve as a useful tool for the prediction of novel lncRNA-disease associations.

Identification of a Rare Case With Nagashima-Type Palmoplantar Keratoderma and 18q Deletion Syndrome via Exome Sequencing and Low-Coverage Whole-Genome Sequencing.

Nagashima-type palmoplantar keratoderma (NPPK) is characterized by non-progressive, diffuse, and cross-gradient hyperkeratosis caused by mutations in the SERPINB7 gene on chromosome 18q21.33. Chromosome 18q deletion syndrome (18q- syndrome) is a terminal deletion or microdeletion syndrome characterized by intellectual disability and congenital malformations. This paper describes an 18-year-old man with palmoplantar keratoderma and diffuse white matter abnormalities in the brain. Trio-based exome sequencing (ES) revealed a suspected mosaic compound heterozygous mutation for c.796C>T (p.Arg266∗) in exon 8 inherited from the mother and a de novo exons 4–6 deletion of SERPINB7. Additional copy number variant (CNV) analysis of the ES data indicated a heterozygous gross deletion of 18q22.3-q23. The two SERPINB7 gene variants were verified by Sanger sequencing and quantitative real-time polymerase chain reaction (qRT-PCR). Finally, low-coverage whole-genome sequencing (WGS) confirmed the 18q22.3-q23 deletion and additionally detected a mosaic 18q21.33-q22.3 deletion, together explaining NPPK and the neurological phenotypes of the proband. The gross deletion of all exons of SERPINB7 was revealed for the first time. More rarely, c.796C>T (p.Arg266∗) was likely to be mosaic, while the exon deletion was mosaic. In conclusion, the combination of multiple molecular genetic testing methods provides comprehensive informative molecular findings and promotes the diagnosis of complex diseases, as in this case.

On Biomedical Computations in Cluster and Cloud Environment

Introduction. This publication summarizes the experience of the use of applied containerized software tools in cloud environment, which the authors gained during the project “Development of methods, algorithms and intellectual analytical system for processing and analysis of heterogeneous clinical and biomedical data in order to improve the diagnosis of complex diseases”, accomplished by the team from the United Institute of Informatics Problems of the NAS of Belarus and V.M. Glushkov Institute of Cybernetics of the NAS of Ukraine. In parallel, the features of biomedical data and the main approaches to their processing and classification, implemented within the framework of an intelligent analytical system, and the possibility of their implementation as part of a container application are described. The purpose of the paper is to describe modern technologies that ensure the reproducibility of numerical experiments in this field and the tools aimed to integrate several sources of biomedical information in order to improve the diagnostics and prognosis of complex diseases. Special attention is also paid to the methods of handling data received from different sources of biomedical information. Particular attention is paid to methods of processing data obtained from various sources of biomedical information and included to the intelligent analytical system. Results. The experience of the use of applied containerized biomedical software tools in cloud environment is summarized. The reproducibility of scientific computing in relation with modern technologies of scientific calculations is discussed. The main approaches to biomedical data preprocessing and integration in the framework of the intelligent analytical system are described. The developed hybrid classification model presents the basis of the intelligent analytical system and aims to integrate several sources of biomedical information. Conclusions. The experience of using the developed classification module NonSmoothSVC, which is part of the developed intelligent analytical system, gained during its testing on artificial and real data, allows us to conclude about several advantages provided by the containerized form of the created application. Namely: • It permits to provide access to real data located in cloud environment, • It is possible to perform calculations to solve research problems on cloud resources both with the help of developed tools and with the help of cloud services, • Such a form of research organization makes numerical experiments reproducible, i.e. any other researcher can compare the results of their developments on specific data that have already been studied by others, in order to verify the conclusions and technical feasibility of new results, • There exists a universal opportunity to use the developed tools on technical devices of various classes from a personal computer to powerful cluster. The hybrid classification model as a core of the intelligent system will make it possible to integrate multidimensional, heterogeneous biomedical data with the aim to better understand the molecular courses of disease origin and development, to improve the identification of disease subtypes and disease prognosis. Keywords: classifier, cloud service, containerized application, heterogeneous biomedical data

Value of medical imaging artificial intelligence in the diagnosis and treatment of new coronavirus pneumonia

AbstractThe development of computer technology is becoming more and more mature. The application of artificial intelligence to the medical field has made important contributions to medical diagnosis and auxiliary detection. Using the powerful computing power of computers to replace humans in the automatic diagnosis of complex diseases has been enthusiastic by the majority of scientific researchers. In the current medical imaging diagnosis system, the location of the lesion is mainly found by observing the two‐dimensional medical image sequence, and the signs of biological information cannot be accurately displayed. Through medical image analysis technology, two‐dimensional images will be divided into three‐dimensional models after image segmentation, image recognition, and three‐dimensional imaging. In this way, it seems that the doctor can “hold the image volume data,” which can greatly improve the scientific and accurate diagnosis. Sex—this article applies artificial intelligence to medical imaging, combined with embedded technology, RFID technology and signal processing technology, and applies the new coronavirus pneumonia image to the artificial intelligence environment after processing, assisting doctors in diagnosis of the disease, and providing relevant information about patients record and manage the diagnosis and diagnosis, save and accumulate the experience and knowledge of famous doctors through the expert system, and then perform corresponding operations and analysis. Through the medical image intelligent analysis system, the safety risk of medical imaging artificial intelligence diagnosis is reduced from 81% to 11%, which greatly reduces the hidden safety hazards for doctors and patients, reduces the workload of doctors, and also reduces the cost of medical care by 79% It is reduced to 20%, which reduces the waiting time of patients and achieves the purpose of improving the accuracy of diagnosis.

Artificial Intelligence (AI)-Empowered Echocardiography Interpretation: A State-of-the-Art Review.

Echocardiography (Echo), a widely available, noninvasive, and portable bedside imaging tool, is the most frequently used imaging modality in assessing cardiac anatomy and function in clinical practice. On the other hand, its operator dependability introduces variability in image acquisition, measurements, and interpretation. To reduce these variabilities, there is an increasing demand for an operator- and interpreter-independent Echo system empowered with artificial intelligence (AI), which has been incorporated into diverse areas of clinical medicine. Recent advances in AI applications in computer vision have enabled us to identify conceptual and complex imaging features with the self-learning ability of AI models and efficient parallel computing power. This has resulted in vast opportunities such as providing AI models that are robust to variations with generalizability for instantaneous image quality control, aiding in the acquisition of optimal images and diagnosis of complex diseases, and improving the clinical workflow of cardiac ultrasound. In this review, we provide a state-of-the art overview of AI-empowered Echo applications in cardiology and future trends for AI-powered Echo technology that standardize measurements, aid physicians in diagnosing cardiac diseases, optimize Echo workflow in clinics, and ultimately, reduce healthcare costs.

Hollow MnFe2O4@C@APBA Nanospheres with Size Exclusion and pH Response for Efficient Enrichment of Endogenous Glycopeptides

Enrichment and detection of glycopeptides are an important clinical measure for the diagnosis of complex diseases. Enrichment materials play a key role in this process; they must have an effective sample-screening ability to eliminate the interference of nonglycopeptides. In this work, novel hollow MnFe2O4@C@APBA nanospheres (HMCAs) with magnetic and pH responsiveness were prepared for glycopeptide enrichment. The as-prepared composites have a suitable hollow structure and large specific surface area, and the boron hydroxyl group in their cavities can fix or disconnect the hydrophilic groups of the glycopeptides at different pH, so the glycopeptides can be adsorbed or desorbed in a controllable way. Enrichment results showed that the HMCAs exhibited an excellent enrichment performance: ultralow limit of detection (approximately 0.5 fmol μL-1), perfect size-exclusion effect (HRP/BSA, 1:800, w/w), favorable universality (HRP, IgG, and RNase B), and high binding capacity (150 mg/g). In order to verify the application of materials in practice, the HMCAs were used for the analysis of complex samples and it was found that 474 glycopeptides were identified from 210 glycoproteins in three replicate analyses of 2 μL of human serum. The results showed that the HMCAs could be used as a promising enrichment material for glycopeptide characterization in MS-based glycoproteomics and related fields.

Multimodal AI System for the Rapid Diagnosis and Surgical Prediction of Necrotizing Enterocolitis

The rapid diagnosis and surgical prediction of necrotizing enterocolitis (NEC) remain a challenge because its complex pathogenesis has not been completely elucidated, and no single medical examination is specific for diagnosing NEC. Artificial intelligence (AI) has proven the robustness of multivariate analysis and been widely used in the diagnosis of complex diseases in the past decade. In this paper, a new multimodal AI system including feature engineering, machine learning (ML), and deep learning (DL) was constructed based on abdominal radiographs (ARs) and clinical data. A total of 4,535 ARs from 1,823 suspected NEC patients were analyzed by transfer learning, and then medical images and clinical parameters from 827 suspected NEC patients were used to train, validate, and test the AI system. Our results demonstrated that the system was effective in diagnosing NEC. In addition, the clinical datasets obtained one week before surgery from 379 NEC patients were studied by the multimodal AI system, and the results showed that it was capable of predicting which NEC patients required surgery. We compared the results in external test sets with those made by clinicians and found that the diagnostic and surgical predictive ability of the AI system was equivalent to that of experienced clinicians. This multimodal AI system can help clinicians improve diagnostic efficiency, reduce the number of missed diagnoses, and facilitate early diagnosis and treatment to prevent disease progression or even death.