Rise of Deep Learning for Genomic, Proteomic, and Metabolomic Data Integration in Precision Medicine

Deciphering Ferroptosis: From Molecular Pathways to Machine Learning-Guided Therapeutic Innovation

Ferroptosis is a unique form of cell death reliant on iron and lipid peroxidation. It disrupts redox balance, causing cell death by damaging the plasma membrane, with inducers acting through enzymatic pathways or transport systems. In cancer treatment, suppressing ferroptosis or circumventing it holds significant promise. Beyond cancer, ferroptosis affects aging, organs, metabolism, and nervous system. Understanding ferroptosis mechanisms holds promise for uncovering novel therapeutic strategies across a spectrum of diseases. However, detection and regulation of this regulated cell death are still mired with challenges. The dearth of cell, tissue, or organ-specific biomarkers muted the pharmacological use of ferroptosis. This review covers recent studies on ferroptosis, detailing its properties, key genes, metabolic pathways, and regulatory networks, emphasizing the interaction between cellular signaling and ferroptotic cell death. It also summarizes recent findings on ferroptosis inducers, inhibitors, and regulators, highlighting their potential therapeutic applications across diseases. The review addresses challenges in utilizing ferroptosis therapeutically and explores the use of machine learning to uncover complex patterns in ferroptosis-related data, aiding in the discovery of biomarkers, predictive models, and therapeutic targets. Finally, it discusses emerging research areas and the importance of continued investigation to harness the full therapeutic potential of targeting ferroptosis.

A comprehensive review of machine learning techniques for multi-omics data integration: challenges and applications in precision oncology

Multi-omics data play a crucial role in precision medicine, mainly to understand the diverse biological interaction between different omics. Machine learning approaches have been extensively employed in this context over the years. This review aims to comprehensively summarize and categorize these advancements, focusing on the integration of multi-omics data, which includes genomics, transcriptomics, proteomics and metabolomics, alongside clinical data. We discuss various machine learning techniques and computational methodologies used for integrating distinct omics datasets and provide valuable insights into their application. The review emphasizes both the challenges and opportunities present in multi-omics data integration, precision medicine and patient stratification, offering practical recommendations for method selection in various scenarios. Recent advances in deep learning and network-based approaches are also explored, highlighting their potential to harmonize diverse biological information layers. Additionally, we present a roadmap for the integration of multi-omics data in precision oncology, outlining the advantages, challenges and implementation difficulties. Hence this review offers a thorough overview of current literature, providing researchers with insights into machine learning techniques for patient stratification, particularly in precision oncology. Contact:  anirban@klyuniv.ac.in.

Understanding gut microbiome-based machine learning platforms: A review on therapeutic approaches using deep learning

Human beings possess trillions of microbial cells in a symbiotic relationship. This relationship benefits both partners for a long time. The gut microbiota helps in many bodily functions from harvesting energy from digested food to strengthening biochemical barriers of the gut and intestine. But the changes in microbiota composition and bacteria that can enter the gastrointestinal tract can cause infection. Several approaches like culture-independent techniques such as high-throughput and meta-omics projects targeting 16S ribosomal RNA (rRNA) sequencing are popular methods to investigate the composition of the human gastrointestinal tract microbiota and taxonomically characterizing microbial communities. The microbiota conformation and diversity should be provided by whole-genome shotgun metagenomic sequencing of site-specific community DNA associating genome mapping, gene inventory, and metabolic remodelling and reformation, to ease the functional study of human microbiota. Preliminary examination of the therapeutic potency for dysbiosis-associated diseases permits investigation of pharmacokinetic-pharmacodynamic changes in microbial communities for escalation of treatment and dosage plan. Gut microbiome study is an integration of metagenomics which has influenced the field in the last two decades. And the incorporation of artificial intelligence and deep learning through "omics-based" methods and microfluidic evaluation enhanced the capability of identification of thousands of microbes.

Unveiling diagnostic and therapeutic strategies for cervical cancer: biomarker discovery through proteomics approaches and exploring the role of cervical cancer stem cells

Cervical cancer (CC) is a major global health problem and leading cause of cancer deaths among women worldwide. Early detection through screening programs has reduced mortality; however, screening compliance remains low. Identifying non-invasive biomarkers through proteomics for diagnosis and monitoring response to treatment could improve patient outcomes. Here we review recent proteomics studies which have uncovered biomarkers and potential drug targets for CC. Additionally, we explore into the role of cervical cancer stem cells and their potential implications in driving CC progression and therapy resistance. Although challenges remain, proteomics has the potential to revolutionize the field of cervical cancer research and improve patient outcomes.

Alternative splicing events as peripheral biomarkers for motor learning deficit caused by adverse prenatal environments

Severity of neurobehavioral deficits in children born from adverse pregnancies, such as maternal alcohol consumption and diabetes, does not always correlate with the adversity's duration and intensity. Therefore, biological signatures for accurate prediction of the severity of neurobehavioral deficits, and robust tools for reliable identification of such biomarkers, have an urgent clinical need. Here, we demonstrate that significant changes in the alternative splicing (AS) pattern of offspring lymphocyte RNA can function as accurate peripheral biomarkers for motor learning deficits in mouse models of prenatal alcohol exposure (PAE) and offspring of mother with diabetes (OMD). An aptly trained deep-learning model identified 29 AS events common to PAE and OMD as superior predictors of motor learning deficits than AS events specific to PAE or OMD. Shapley-value analysis, a game-theory algorithm, deciphered the trained deep-learning model's learnt associations between its input, AS events, and output, motor learning performance. Shapley values of the deep-learning model's input identified the relative contribution of the 29 common AS events to the motor learning deficit. Gene ontology and predictive structure-function analyses, using Alphafold2 algorithm, supported existing evidence on the critical roles of these molecules in early brain development and function. The direction of most AS events was opposite in PAE and OMD, potentially from differential expression of RNA binding proteins in PAE and OMD. Altogether, this study posits that AS of lymphocyte RNA is a rich resource, and deep-learning is an effective tool, for discovery of peripheral biomarkers of neurobehavioral deficits in children of diverse adverse pregnancies.

Artificial intelligence for neurodegenerative experimental models

INTRODUCTION

Experimental models are essential tools in neurodegenerative disease research. However, the translation of insights and drugs discovered in model systems has proven immensely challenging, marred by high failure rates in human clinical trials.

METHODS

Here we review the application of artificial intelligence (AI) and machine learning (ML) in experimental medicine for dementia research.

RESULTS

Considering the specific challenges of reproducibility and translation between other species or model systems and human biology in preclinical dementia research, we highlight best practices and resources that can be leveraged to quantify and evaluate translatability. We then evaluate how AI and ML approaches could be applied to enhance both cross-model reproducibility and translation to human biology, while sustaining biological interpretability.

DISCUSSION

AI and ML approaches in experimental medicine remain in their infancy. However, they have great potential to strengthen preclinical research and translation if based upon adequate, robust, and reproducible experimental data.

HIGHLIGHTS

There are increasing applications of AI in experimental medicine. We identified issues in reproducibility, cross-species translation, and data curation in the field. Our review highlights data resources and AI approaches as solutions. Multi-omics analysis with AI offers exciting future possibilities in drug discovery.

Deep learning for plant bioinformatics: an explainable gradient-based approach for disease detection

Emerging in the realm of bioinformatics, plant bioinformatics integrates computational and statistical methods to study plant genomes, transcriptomes, and proteomes. With the introduction of high-throughput sequencing technologies and other omics data, the demand for automated methods to analyze and interpret these data has increased. We propose a novel explainable gradient-based approach EG-CNN model for both omics data and hyperspectral images to predict the type of attack on plants in this study. We gathered gene expression, metabolite, and hyperspectral image data from plants afflicted with four prevalent diseases: powdery mildew, rust, leaf spot, and blight. Our proposed EG-CNN model employs a combination of these omics data to learn crucial plant disease detection characteristics. We trained our model with multiple hyperparameters, such as the learning rate, number of hidden layers, and dropout rate, and attained a test set accuracy of 95.5%. We also conducted a sensitivity analysis to determine the model's resistance to hyperparameter variations. Our analysis revealed that our model exhibited a notable degree of resilience in the face of these variations, resulting in only marginal changes in performance. Furthermore, we conducted a comparative examination of the time efficiency of our EG-CNN model in relation to baseline models, including SVM, Random Forest, and Logistic Regression. Although our model necessitates additional time for training and validation due to its intricate architecture, it demonstrates a faster testing time per sample, offering potential advantages in real-world scenarios where speed is paramount. To gain insights into the internal representations of our EG-CNN model, we employed saliency maps for a qualitative analysis. This visualization approach allowed us to ascertain that our model effectively captures crucial aspects of plant disease, encompassing alterations in gene expression, metabolite levels, and spectral discrepancies within plant tissues. Leveraging omics data and hyperspectral images, this study underscores the potential of deep learning methods in the realm of plant disease detection. The proposed EG-CNN model exhibited impressive accuracy and displayed a remarkable degree of insensitivity to hyperparameter variations, which holds promise for future plant bioinformatics applications.

Deep learning applications in single-cell genomics and transcriptomics data analysis

Traditional bulk sequencing methods are limited to measuring the average signal in a group of cells, potentially masking heterogeneity, and rare populations. The single-cell resolution, however, enhances our understanding of complex biological systems and diseases, such as cancer, the immune system, and chronic diseases. However, the single-cell technologies generate massive amounts of data that are often high-dimensional, sparse, and complex, thus making analysis with traditional computational approaches difficult and unfeasible. To tackle these challenges, many are turning to deep learning (DL) methods as potential alternatives to the conventional machine learning (ML) algorithms for single-cell studies. DL is a branch of ML capable of extracting high-level features from raw inputs in multiple stages. Compared to traditional ML, DL models have provided significant improvements across many domains and applications. In this work, we examine DL applications in genomics, transcriptomics, spatial transcriptomics, and multi-omics integration, and address whether DL techniques will prove to be advantageous or if the single-cell omics domain poses unique challenges. Through a systematic literature review, we have found that DL has not yet revolutionized the most pressing challenges of the single-cell omics field. However, using DL models for single-cell omics has shown promising results (in many cases outperforming the previous state-of-the-art models) in data preprocessing and downstream analysis. Although developments of DL algorithms for single-cell omics have generally been gradual, recent advances reveal that DL can offer valuable resources in fast-tracking and advancing research in single-cell.

Metabolomics of head and neck cancer in biofluids: an integrative systematic review

INTRODUCTION

Head and neck cancer (HNC) is the fifth most common cancer globally. Diagnosis at early stages are critical to reduce mortality and improve functional and esthetic outcomes associated with HNC. Metabolomics is a promising approach for discovery of biomarkers and metabolic pathways for risk assessment and early detection of HNC.

OBJECTIVES

To summarize and consolidate the available evidence on metabolomics and HNC in plasma/serum, saliva, and urine.

METHODS

A systematic search of experimental research was executed using PubMed and Web of Science. Available data on areas under the curve was extracted. Metabolic pathway enrichment analysis were performed to identify metabolic pathways altered in HNC. Fifty-four studies were eligible for data extraction (33 performed in plasma/serum, 15 in saliva and 6 in urine).

RESULTS

Metabolites with high discriminatory performance for detection of HNC included single metabolites and combination panels of several lysoPCs, pyroglutamate, glutamic acid, glucose, tartronic acid, arachidonic acid, norvaline, linoleic acid, propionate, acetone, acetate, choline, glutamate and others. The glucose-alanine cycle and the urea cycle were the most altered pathways in HNC, among other pathways (i.e. gluconeogenesis, glycine and serine metabolism, alanine metabolism, etc.). Specific metabolites that can potentially serve as complementary less- or non-invasive biomarkers, as well as metabolic pathways integrating the data from the available studies, are presented.

CONCLUSION

The present work highlights utility of metabolite-based biomarkers for risk assessment, early detection, and prognostication of HNC, as well as facilitates incorporation of available metabolomics studies into multi-omics data integration and big data analytics for personalized health.

Phenomics as an approach to Comparative Developmental Physiology

The dynamic nature of developing organisms and how they function presents both opportunity and challenge to researchers, with significant advances in understanding possible by adopting innovative approaches to their empirical study. The information content of the phenotype during organismal development is arguably greater than at any other life stage, incorporating change at a broad range of temporal, spatial and functional scales and is of broad relevance to a plethora of research questions. Yet, effectively measuring organismal development, and the ontogeny of physiological regulations and functions, and their responses to the environment, remains a significant challenge. "Phenomics", a global approach to the acquisition of phenotypic data at the scale of the whole organism, is uniquely suited as an approach. In this perspective, we explore the synergies between phenomics and Comparative Developmental Physiology (CDP), a discipline of increasing relevance to understanding sensitivity to drivers of global change. We then identify how organismal development itself provides an excellent model for pushing the boundaries of phenomics, given its inherent complexity, comparably smaller size, relative to adult stages, and the applicability of embryonic development to a broad suite of research questions using a diversity of species. Collection, analysis and interpretation of whole organismal phenotypic data are the largest obstacle to capitalising on phenomics for advancing our understanding of biological systems. We suggest that phenomics within the context of developing organismal form and function could provide an effective scaffold for addressing grand challenges in CDP and phenomics.

Perspective of artificial intelligence in healthcare data management: A journey towards precision medicine

Mounting evidence has highlighted the implementation of big data handling and management in the healthcare industry to improve the clinical services. Various private and public companies have generated, stored, and analyzed different types of big healthcare data, such as omics data, clinical data, electronic health records, personal health records, and sensing data with the aim to move in the direction of precision medicine. Additionally, with the advancement in technologies, researchers are curious to extract the potential involvement of artificial intelligence and machine learning on big healthcare data to enhance the quality of patient's lives. However, seeking solutions from big healthcare data requires proper management, storage, and analysis, which imposes hinderances associated with big data handling. Herein, we briefly discuss the implication of big data handling and the role of artificial intelligence in precision medicine. Further, we also highlighted the potential of artificial intelligence in integrating and analyzing the big data that offer personalized treatment. In addition, we briefly discuss the applications of artificial intelligence in personalized treatment, especially in neurological diseases. Lastly, we discuss the challenges and limitations imposed by artificial intelligence in big data management and analysis to hinder precision medicine.

Johann Gregor Mendel: the victory of statistics over human imagination

In 2022, we celebrated 200 years since the birth of Johann Gregor Mendel. Although his contributions to science went unrecognized during his lifetime, Mendel not only described the principles of monogenic inheritance but also pioneered the modern way of doing science based on precise experimental data acquisition and evaluation. Novel statistical and algorithmic approaches are now at the center of scientific work, showing that work that is considered marginal in one era can become a mainstream research approach in the next era. The onset of data-driven science caused a shift from hypothesis-testing to hypothesis-generating approaches in science. Mendel is remembered here as a promoter of this approach, and the benefits of big data and statistical approaches are discussed.

Accurate Classification and Prediction of Acute Myocardial Infarction through an ARMD Procedure

The risk stratification of acute myocardial infarction (AMI) patients is of prime importance for clinical management and prognosis assessment. Thus, we propose an ensemble machine learning analysis procedure named ADASYN-RFECV-MDA-DNN (ARMD) to address sample-unbalanced problems and enable stratification and prediction of AMI outcomes. The ARMD analysis procedure was applied to the NMR data of sera from 534 AMI-related subjects in four categories with an extremely imbalanced sample proportion. Firstly, the adaptive synthetic sampling (ADASYN) algorithm was used to address the issue of the original sample imbalance. Secondly, the recursive feature elimination with cross-validation (RFECV) processing and random forest mean decrease accuracy (RF-MDA) algorithm was performed to identify the differential metabolites corresponding to each AMI outcome. Finally, the deep neural network (DNN) was employed to classify and predict AMI events, and its performance was evaluated by comparing the four traditional machine learning methods. Compared with the other four machine learning models, DNN presented consistent superiority in almost all of the model parameters including precision, f1-score, sensitivity, specificity, area under the receiver operating characteristic curve (AUC), and classification accuracy, highlighting the potential of deep learning in classification and stratification of clinical diseases. The ARMD analysis procedure was a practical analysis tool for supervised classification and regression modeling of clinical diseases.

Deep learning: A primer for dentists and dental researchers

OBJECTIVES

Despite deep learning's wide adoption in dental artificial intelligence (AI) research, researchers from other dental fields and, more so, dental professionals may find it challenging to understand and interpret deep learning studies, their employed methods, and outcomes. The objective of this primer is to explain the basic concept of deep learning. It will lay out the commonly used terms, and describe different deep learning approaches, their methods, and outcomes.

METHODS

Our research is based on the latest review studies, medical primers, as well as the state-of-the-art research on AI and deep learning, which have been gathered in the current study.

RESULTS

In this study, a basic understanding of deep learning models and various approaches to deep learning is presented. An overview of data management strategies for deep learning projects is presented, including data collection, data curation, data annotation, and data preprocessing. Additionally, we provided a step-by-step guide for completing a real-world project.

CONCLUSION

Researchers and clinicians can benefit from this study by gaining insight into deep learning. It can be used to critically appraise existing work or plan new deep learning projects.

CLINICAL SIGNIFICANCE

This study may be useful to dental researchers and professionals who are assessing and appraising deep learning studies within the field of dentistry.

Biomarkers of necrotizing enterocolitis in the era of machine learning and omics

Necrotizing enterocolitis (NEC) continues to be a major cause of morbidity and mortality in preterm infants. Despite decades of research in NEC, no reliable biomarkers can accurately diagnose NEC or predict patient prognosis. The recent emergence of multi-omics could potentially shift NEC biomarker discovery, particularly when evaluated using systems biology techniques. Furthermore, the use of machine learning and artificial intelligence in analyzing this 'big data' could enable novel interpretations of NEC subtypes, disease progression, and potential therapeutic targets, allowing for integration with personalized medicine approaches. In this review, we evaluate studies using omics technologies and machine learning in the diagnosis of NEC. Future implications and challenges inherent to the field are also discussed.

Deep learning facilitates multi-data type analysis and predictive biomarker discovery in cancer precision medicine

Cancer progression is linked to gene-environment interactions that alter cellular homeostasis. The use of biomarkers as early indicators of disease manifestation and progression can substantially improve diagnosis and treatment. Large omics datasets generated by high-throughput profiling technologies, such as microarrays, RNA sequencing, whole-genome shotgun sequencing, nuclear magnetic resonance, and mass spectrometry, have enabled data-driven biomarker discoveries. The identification of differentially expressed traits as molecular markers has traditionally relied on statistical techniques that are often limited to linear parametric modeling. The heterogeneity, epigenetic changes, and high degree of polymorphism observed in oncogenes demand biomarker-assisted personalized medication schemes. Deep learning (DL), a major subunit of machine learning (ML), has been increasingly utilized in recent years to investigate various diseases. The combination of ML/DL approaches for performance optimization across multi-omics datasets produces robust ensemble-learning prediction models, which are becoming useful in precision medicine. This review focuses on the recent development of ML/DL methods to provide integrative solutions in discovering cancer-related biomarkers, and their utilization in precision medicine.

A Machine Learning-Based Approach Using Multi-omics Data to Predict Metabolic Pathways

The integrative method approaches are continuously evolving to provide accurate insights from the data that is received through experimentation on various biological systems. Multi-omics data can be integrated with predictive machine learning algorithms in order to provide results with high accuracy. This protocol chapter defines the steps required for the ML-multi-omics integration methods that are applied on biological datasets for its analysis and the visual interpretation of the results thus obtained.

The performance of deep generative models for learning joint embeddings of single-cell multi-omics data

Recent extensions of single-cell studies to multiple data modalities raise new questions regarding experimental design. For example, the challenge of sparsity in single-omics data might be partly resolved by compensating for missing information across modalities. In particular, deep learning approaches, such as deep generative models (DGMs), can potentially uncover complex patterns via a joint embedding. Yet, this also raises the question of sample size requirements for identifying such patterns from single-cell multi-omics data. Here, we empirically examine the quality of DGM-based integrations for varying sample sizes. We first review the existing literature and give a short overview of deep learning methods for multi-omics integration. Next, we consider eight popular tools in more detail and examine their robustness to different cell numbers, covering two of the most common multi-omics types currently favored. Specifically, we use data featuring simultaneous gene expression measurements at the RNA level and protein abundance measurements for cell surface proteins (CITE-seq), as well as data where chromatin accessibility and RNA expression are measured in thousands of cells (10x Multiome). We examine the ability of the methods to learn joint embeddings based on biological and technical metrics. Finally, we provide recommendations for the design of multi-omics experiments and discuss potential future developments.

Interpretable machine learning methods for predictions in systems biology from omics data

Machine learning has become a powerful tool for systems biologists, from diagnosing cancer to optimizing kinetic models and predicting the state, growth dynamics, or type of a cell. Potential predictions from complex biological data sets obtained by “omics” experiments seem endless, but are often not the main objective of biological research. Often we want to understand the molecular mechanisms of a disease to develop new therapies, or we need to justify a crucial decision that is derived from a prediction. In order to gain such knowledge from data, machine learning models need to be extended. A recent trend to achieve this is to design “interpretable” models. However, the notions around interpretability are sometimes ambiguous, and a universal recipe for building well-interpretable models is missing. With this work, we want to familiarize systems biologists with the concept of model interpretability in machine learning. We consider data sets, data preparation, machine learning methods, and software tools relevant to omics research in systems biology. Finally, we try to answer the question: “What is interpretability?” We introduce views from the interpretable machine learning community and propose a scheme for categorizing studies on omics data. We then apply these tools to review and categorize recent studies where predictive machine learning models have been constructed from non-sequential omics data.

Omics Data and Data Representations for Deep Learning-Based Predictive Modeling

Medical discoveries mainly depend on the capability to process and analyze biological datasets, which inundate the scientific community and are still expanding as the cost of next-generation sequencing technologies is decreasing. Deep learning (DL) is a viable method to exploit this massive data stream since it has advanced quickly with there being successive innovations. However, an obstacle to scientific progress emerges: the difficulty of applying DL to biology, and this because both fields are evolving at a breakneck pace, thus making it hard for an individual to occupy the front lines of both of them. This paper aims to bridge the gap and help computer scientists bring their valuable expertise into the life sciences. This work provides an overview of the most common types of biological data and data representations that are used to train DL models, with additional information on the models themselves and the various tasks that are being tackled. This is the essential information a DL expert with no background in biology needs in order to participate in DL-based research projects in biomedicine, biotechnology, and drug discovery. Alternatively, this study could be also useful to researchers in biology to understand and utilize the power of DL to gain better insights into and extract important information from the omics data.

SYNPRED: prediction of drug combination effects in cancer using different synergy metrics and ensemble learning

Background

In cancer research, high-throughput screening technologies produce large amounts of multiomics data from different populations and cell types. However, analysis of such data encounters difficulties due to disease heterogeneity, further exacerbated by human biological complexity and genomic variability. The specific profile of cancer as a disease (or, more realistically, a set of diseases) urges the development of approaches that maximize the effect while minimizing the dosage of drugs. Now is the time to redefine the approach to drug discovery, bringing an artificial intelligence (AI)–powered informational view that integrates the relevant scientific fields and explores new territories.

Results

Here, we show SYNPRED, an interdisciplinary approach that leverages specifically designed ensembles of AI algorithms, as well as links omics and biophysical traits to predict anticancer drug synergy. It uses 5 reference models (Bliss, Highest Single Agent, Loewe, Zero Interaction Potency, and Combination Sensitivity Score), which, coupled with AI algorithms, allowed us to attain the ones with the best predictive performance and pinpoint the most appropriate reference model for synergy prediction, often overlooked in similar studies. By using an independent test set, SYNPRED exhibits state-of-the-art performance metrics either in the classification (accuracy, 0.85; precision, 0.91; recall, 0.90; area under the receiver operating characteristic, 0.80; and F1-score, 0.91) or in the regression models, mainly when using the Combination Sensitivity Score synergy reference model (root mean square error, 11.07; mean squared error, 122.61; Pearson, 0.86; mean absolute error, 7.43; Spearman, 0.87). Moreover, data interpretability was achieved by deploying the most current and robust feature importance approaches. A simple web-based application was constructed, allowing easy access by nonexpert researchers.

Conclusions

The performance of SYNPRED rivals that of the existing methods that tackle the same problem, yielding unbiased results trained with one of the most comprehensive datasets available (NCI ALMANAC). The leveraging of different reference models allowed deeper insights into which of them can be more appropriately used for synergy prediction. The Combination Sensitivity Score clearly stood out with improved performance among the full scope of surveyed approaches and synergy reference models. Furthermore, SYNPRED takes a particular focus on data interpretability, which has been in the spotlight lately when using the most advanced AI techniques.

Applications of Artificial Intelligence in Climate-Resilient Smart-Crop Breeding

Recently, Artificial intelligence (AI) has emerged as a revolutionary field, providing a great opportunity in shaping modern crop breeding, and is extensively used indoors for plant science. Advances in crop phenomics, enviromics, together with the other “omics” approaches are paving ways for elucidating the detailed complex biological mechanisms that motivate crop functions in response to environmental trepidations. These “omics” approaches have provided plant researchers with precise tools to evaluate the important agronomic traits for larger-sized germplasm at a reduced time interval in the early growth stages. However, the big data and the complex relationships within impede the understanding of the complex mechanisms behind genes driving the agronomic-trait formations. AI brings huge computational power and many new tools and strategies for future breeding. The present review will encompass how applications of AI technology, utilized for current breeding practice, assist to solve the problem in high-throughput phenotyping and gene functional analysis, and how advances in AI technologies bring new opportunities for future breeding, to make envirotyping data widely utilized in breeding. Furthermore, in the current breeding methods, linking genotype to phenotype remains a massive challenge and impedes the optimal application of high-throughput field phenotyping, genomics, and enviromics. In this review, we elaborate on how AI will be the preferred tool to increase the accuracy in high-throughput crop phenotyping, genotyping, and envirotyping data; moreover, we explore the developing approaches and challenges for multiomics big computing data integration. Therefore, the integration of AI with “omics” tools can allow rapid gene identification and eventually accelerate crop-improvement programs.

MLR-OOD: A Markov Chain Based Likelihood Ratio Method for Out-Of-Distribution Detection of Genomic Sequences

Machine learning or deep learning models have been widely used for taxonomic classification of metagenomic sequences and many studies reported high classification accuracy. Such models are usually trained based on sequences in several training classes in hope of accurately classifying unknown sequences into these classes. However, when deploying the classification models on real testing data sets, sequences that do not belong to any of the training classes may be present and are falsely assigned to one of the training classes with high confidence. Such sequences are referred to as out-of-distribution (OOD) sequences and are ubiquitous in metagenomic studies. To address this problem, we develop a deep generative model-based method, MLR-OOD, that measures the probability of a testing sequencing belonging to OOD by the likelihood ratio of the maximum of the in-distribution (ID) class conditional likelihoods and the Markov chain likelihood of the testing sequence measuring the sequence complexity. We compose three different microbial data sets consisting of bacterial, viral, and plasmid sequences for comprehensively benchmarking OOD detection methods. We show that MLR-OOD achieves the state-of-the-art performance demonstrating the generality of MLR-OOD to various types of microbial data sets. It is also shown that MLR-OOD is robust to the GC content, which is a major confounding effect for OOD detection of genomic sequences. In conclusion, MLR-OOD will greatly reduce false positives caused by OOD sequences in metagenomic sequence classification.

MetastaSite: Predicting metastasis to different sites using deep learning with gene expression data

Deep learning has massive potential in predicting phenotype from different omics profiles. However, deep neural networks are viewed as black boxes, providing predictions without explanation. Therefore, the requirements for these models to become interpretable are increasing, especially in the medical field. Here we propose a computational framework that takes the gene expression profile of any primary cancer sample and predicts whether patients’ samples are primary (localized) or metastasized to the brain, bone, lung, or liver based on deep learning architecture. Specifically, we first constructed an AutoEncoder framework to learn the non-linear relationship between genes, and then DeepLIFT was applied to calculate genes’ importance scores. Next, to mine the top essential genes that can distinguish the primary and metastasized tumors, we iteratively added ten top-ranked genes based upon their importance score to train a DNN model. Then we trained a final multi-class DNN that uses the output from the previous part as an input and predicts whether samples are primary or metastasized to the brain, bone, lung, or liver. The prediction performances ranged from AUC of 0.93–0.82. We further designed the model’s workflow to provide a second functionality beyond metastasis site prediction, i.e., to identify the biological functions that the DL model uses to perform the prediction. To our knowledge, this is the first multi-class DNN model developed for the generic prediction of metastasis to various sites.

Precision Oncology: Artificial Intelligence and DNA Methylation Analysis of Circulating Cell-Free DNA for Lung Cancer Detection

Background

Lung cancer (LC) is a leading cause of cancer-deaths globally. Its lethality is due in large part to the paucity of accurate screening markers. Precision Medicine includes the use of omics technology and novel analytic approaches for biomarker development. We combined Artificial Intelligence (AI) and DNA methylation analysis of circulating cell-free tumor DNA (ctDNA), to identify putative biomarkers for and to elucidate the pathogenesis of LC.

Methods

Illumina Infinium MethylationEPIC BeadChip array analysis was used to measure cytosine (CpG) methylation changes across the genome in LC. Six different AI platforms including support vector machine (SVM) and Deep Learning (DL) were used to identify CpG biomarkers and for LC detection. Training set and validation sets were generated, and 10-fold cross validation performed. Gene enrichment analysis using g:profiler and GREAT enrichment was used to elucidate the LC pathogenesis.

Results

Using a stringent GWAS significance threshold, p-value <5x10^-8, we identified 4389 CpGs (cytosine methylation loci) in coding genes and 1812 CpGs in non-protein coding DNA regions that were differentially methylated in LC. SVM and three other AI platforms achieved an AUC=1.00; 95% CI (0.90-1.00) for LC detection. DL achieved an AUC=1.00; 95% CI (0.95-1.00) and 100% sensitivity and specificity. High diagnostic accuracies were achieved with only intragenic or only intergenic CpG loci. Gene enrichment analysis found dysregulation of molecular pathways involved in the development of small cell and non-small cell LC.

Conclusion

Using AI and DNA methylation analysis of ctDNA, high LC detection rates were achieved. Further, many of the genes that were epigenetically altered are known to be involved in the biology of neoplasms in general and lung cancer in particular.

A systems genomics approach to uncover patient-specific pathogenic pathways and proteins in ulcerative colitis

We describe a precision medicine workflow, the integrated single nucleotide polymorphism network platform (iSNP), designed to determine the mechanisms by which SNPs affect cellular regulatory networks, and how SNP co-occurrences contribute to disease pathogenesis in ulcerative colitis (UC). Using SNP profiles of 378 UC patients we map the regulatory effects of the SNPs to a human signalling network containing protein-protein, miRNA-mRNA and transcription factor binding interactions. With unsupervised clustering algorithms we group these patient-specific networks into four distinct clusters driven by PRKCB, HLA, SNAI1/CEBPB/PTPN1 and VEGFA/XPO5/POLH hubs. The pathway analysis identifies calcium homeostasis, wound healing and cell motility as key processes in UC pathogenesis. Using transcriptomic data from an independent patient cohort, with three complementary validation approaches focusing on the SNP-affected genes, the patient specific modules and affected functions, we confirm the regulatory impact of non-coding SNPs. iSNP identified regulatory effects for disease-associated non-coding SNPs, and by predicting the patient-specific pathogenic processes, we propose a systems-level way to stratify patients.

Single Nucleotide Polymorphisms (SNPs) affect cellular regulatory networks, and SNP co-occurrences contribute to disease pathogenesis in ulcerative colitis (UC). Here the authors introduce iSNP, a precision medicine pipeline that combines genomics and network biology approaches to uncover patient specific pathways affected in complex diseases.

Network Approaches for Charting the Transcriptomic and Epigenetic Landscape of the Developmental Origins of Health and Disease

The early developmental phase is of critical importance for human health and disease later in life. To decipher the molecular mechanisms at play, current biomedical research is increasingly relying on large quantities of diverse omics data. The integration and interpretation of the different datasets pose a critical challenge towards the holistic understanding of the complex biological processes that are involved in early development. In this review, we outline the major transcriptomic and epigenetic processes and the respective datasets that are most relevant for studying the periconceptional period. We cover both basic data processing and analysis steps, as well as more advanced data integration methods. A particular focus is given to network-based methods. Finally, we review the medical applications of such integrative analyses.

Methods for Stratification and Validation Cohorts: A Scoping Review

Personalized medicine requires large cohorts for patient stratification and validation of patient clustering. However, standards and harmonized practices on the methods and tools to be used for the design and management of cohorts in personalized medicine remain to be defined. This study aims to describe the current state-of-the-art in this area. A scoping review was conducted searching in PubMed, EMBASE, Web of Science, Psycinfo and Cochrane Library for reviews about tools and methods related to cohorts used in personalized medicine. The search focused on cancer, stroke and Alzheimer’s disease and was limited to reports in English, French, German, Italian and Spanish published from 2005 to April 2020. The screening process was reported through a PRISMA flowchart. Fifty reviews were included, mostly including information about how data were generated (25/50) and about tools used for data management and analysis (24/50). No direct information was found about the quality of data and the requirements to monitor associated clinical data. A scarcity of information and standards was found in specific areas such as sample size calculation. With this information, comprehensive guidelines could be developed in the future to improve the reproducibility and robustness in the design and management of cohorts in personalized medicine studies.

Deep Neural Network Modeling Identifies Biomarkers of Response to Immune-checkpoint Therapy

Immunotherapy has shown significant promise as a treatment for cancer, such as lung cancer and melanoma. However, only 10%–30% of the patients respond to treatment with immune checkpoint blockers (ICBs), underscoring the need for biomarkers to predict response to immunotherapy. Here, we developed DeepGeneX, a computational framework that uses advanced deep neural network modeling and feature elimination to reduce single-cell RNA-seq data on ∼26,000 genes to six of the most important genes (CCR7, SELL, GZMB, WARS, GZMH, and LGALS1), that accurately predict response to immunotherapy. We also discovered that the high LGALS1 and WARS-expressing macrophage population represent a biomarker for ICB therapy nonresponders, suggesting that these macrophages may be a target for improving ICB response. Taken together, DeepGeneX enables biomarker discovery and provides an understanding of the molecular basis for the model’s predictions.

•

Predicting biomarkers for immunotherapy response remains a challenge

•

DeepGeneX combines neural networks with single-cell RNAseq to predict responders

•

LGALS1 and WARS-expressing macrophages in nonresponders impact T cell activation

•

DeepGeneX enables biomarker discovery and elucidates underlying molecular mechanism

Analyzing Precision Medicine Utilization with Real-World Data: A Scoping Review

Precision medicine (PM), specifically genetic-based testing, is currently used in over 140,000 individual tests to inform the clinical management of disease. Though several databases (e.g., the NIH Genetic Testing Registry) demonstrate the availability of these sequencing-based tests, we do not currently understand the extent to which these tests are used. There exists a need to synthesize the body of real-world data (RWD) describing the use of sequencing-based tests to inform their appropriate use. To accomplish this, we performed a scoping review to examine what RWD sources have been used in studies of PM utilization between January 2015 and August 2021 to characterize the use of genome sequencing (GS), exome sequencing (ES), tumor sequencing (TS), next-generation sequencing-based panels (NGS), gene expression profiling (GEP), and pharmacogenomics (PGx) panels. We abstracted variables describing the use of these types of tests and performed a descriptive statistical analysis. We identified 440 articles in our search and included 72 articles in our study. Publications based on registry databases were the most common, followed by studies based on private insurer administrative claims. Slightly more than one-third (38%) used integrated datasets. Two thirds (67%) of the studies focused on the use of tests for oncological clinical applications. We summarize the RWD sources used in peer-reviewed literature on the use of PM. Our findings will help improve future study design by encouraging the use of centralized databases and registries to track the implementation and use of PM.

NMR in Metabolomics: From Conventional Statistics to Machine Learning and Neural Network Approaches

NMR measurements combined with chemometrics allow achieving a great amount of information for the identification of potential biomarkers responsible for a precise metabolic pathway. These kinds of data are useful in different fields, ranging from food to biomedical fields, including health science. The investigation of the whole set of metabolites in a sample, representing its fingerprint in the considered condition, is known as metabolomics and may take advantage of different statistical tools. The new frontier is to adopt self-learning techniques to enhance clustering or classification actions that can improve the predictive power over large amounts of data. Although machine learning is already employed in metabolomics, deep learning and artificial neural networks approaches were only recently successfully applied. In this work, we give an overview of the statistical approaches underlying the wide range of opportunities that machine learning and neural networks allow to perform with accurate metabolites assignment and quantification.Various actual challenges are discussed, such as proper metabolomics, deep learning architectures and model accuracy.

Genomic Prediction Methods Accounting for Nonadditive Genetic Effects

The use of genomic information for prediction of future phenotypes or breeding values for the candidates to selection has become a standard over the last decade. However, most procedures for genomic prediction only consider the additive (or substitution) effects associated with polymorphic markers. Nevertheless, the implementation of models that consider nonadditive genetic variation may be interesting because they (1) may increase the ability of prediction, (2) can be used to define mate allocation procedures in plant and animal breeding schemes, and (3) can be used to benefit from nonadditive genetic variation in crossbreeding or purebred breeding schemes. This study reviews the available methods for incorporating nonadditive effects into genomic prediction procedures and their potential applications in predicting future phenotypic performance, mate allocation, and crossbred and purebred selection. Finally, a brief outline of some future research lines is also proposed.

Metabolomics of clinical samples reveal the treatment mechanism of lanthanum hydroxide on vascular calcification in chronic kidney disease

Previous studies showed that lanthanum hydroxide (LH) has a therapeutic effect on chronic kidney disease (CKD) and vascular calcification, which suggests that it might have clinical value. However, the target and mechanism of action of LH are unclear. Metabolomics of clinical samples can be used to predict the mechanism of drug action. In this study, metabolomic profiles in patients with end-stage renal disease (ESRD) were used to screen related signaling pathways, and we verified the influence of LH on the ROS-PI3K-AKT-mTOR-HIF-1α signaling pathway by western blotting and quantitative real-time RT-qPCR in vivo and in vitro. We found that ROS and SLC16A10 genes were activated in patients with ESRD. The SLC16A10 gene is associated with six significant metabolites (L-cysteine, L-cystine, L-isoleucine, L-arginine, L-aspartic acid, and L-phenylalanine) and the PI3K-AKT signaling pathway. The results showed that LH inhibits the ESRD process and its cardiovascular complications by inhibiting the ROS-PI3K-AKT-mTOR-HIF-1α signaling pathway. Collectively, LH may be a candidate phosphorus binder for the treatment of vascular calcification in ESRD.

Virtual Gene Concept and a Corresponding Pragmatic Research Program in Genetical Data Science

Mendel proposed an experimentally verifiable paradigm of particle-based heredity that has been influential for over 150 years. The historical arguments have been reflected in the near past as Mendel's concept has been diversified by new types of omics data. As an effect of the accumulation of omics data, a virtual gene concept forms, giving rise to genetical data science. The concept integrates genetical, functional, and molecular features of the Mendelian paradigm. I argue that the virtual gene concept should be deployed pragmatically. Indeed, the concept has already inspired a practical research program related to systems genetics. The program includes questions about functionality of structural and categorical gene variants, about regulation of gene expression, and about roles of epigenetic modifications. The methodology of the program includes bioinformatics, machine learning, and deep learning. Education, funding, careers, standards, benchmarks, and tools to monitor research progress should be provided to support the research program.

Machine Learning and Deep Learning for the Pharmacogenomics of Antidepressant Treatments

A growing body of evidence now proposes that machine learning and deep learning techniques can serve as a vital foundation for the pharmacogenomics of antidepressant treatments in patients with major depressive disorder (MDD). In this review, we focus on the latest developments for pharmacogenomics research using machine learning and deep learning approaches together with neuroimaging and multi-omics data. First, we review relevant pharmacogenomics studies that leverage numerous machine learning and deep learning techniques to determine treatment prediction and potential biomarkers for antidepressant treatments in MDD. In addition, we depict some neuroimaging pharmacogenomics studies that utilize various machine learning approaches to predict antidepressant treatment outcomes in MDD based on the integration of research on pharmacogenomics and neuroimaging. Moreover, we summarize the limitations in regard to the past pharmacogenomics studies of antidepressant treatments in MDD. Finally, we outline a discussion of challenges and directions for future research. In light of latest advancements in neuroimaging and multi-omics, various genomic variants and biomarkers associated with antidepressant treatments in MDD are being identified in pharmacogenomics research by employing machine learning and deep learning algorithms.

Predicting lupus membranous nephritis using reduced picolinic acid to tryptophan ratio as a urinary biomarker

The current gold standard for classifying lupus nephritis (LN) progression is a renal biopsy, which is an invasive procedure. Undergoing a series of biopsies for monitoring disease progression and treatments is unlikely suitable for patients with LN. Thus, there is an urgent need for non-invasive alternative biomarkers that can facilitate LN class diagnosis. Such biomarkers will be very useful in guiding intervention strategies to mitigate or treat patients with LN. Urine samples were collected from two independent cohorts. Patients with LN were classified into proliferative (class III/IV) and membranous (class V) by kidney histopathology. Metabolomics was performed to identify potential metabolites, which could be specific for the classification of membranous LN. The ratio of picolinic acid (Pic) to tryptophan (Trp) ([Pic/Trp] ratio) was found to be a promising candidate for LN diagnostic and membranous classification. It has high potential as an alternative biomarker for the non-invasive diagnosis of LN.

AI applications in functional genomics

We review the current applications of artificial intelligence (AI) in functional genomics. The recent explosion of AI follows the remarkable achievements made possible by "deep learning", along with a burst of "big data" that can meet its hunger. Biology is about to overthrow astronomy as the paradigmatic representative of big data producer. This has been made possible by huge advancements in the field of high throughput technologies, applied to determine how the individual components of a biological system work together to accomplish different processes. The disciplines contributing to this bulk of data are collectively known as functional genomics. They consist in studies of: i) the information contained in the DNA (genomics); ii) the modifications that DNA can reversibly undergo (epigenomics); iii) the RNA transcripts originated by a genome (transcriptomics); iv) the ensemble of chemical modifications decorating different types of RNA transcripts (epitranscriptomics); v) the products of protein-coding transcripts (proteomics); and vi) the small molecules produced from cell metabolism (metabolomics) present in an organism or system at a given time, in physiological or pathological conditions. After reviewing main applications of AI in functional genomics, we discuss important accompanying issues, including ethical, legal and economic issues and the importance of explainability.

Synthetic biomarkers: a twenty-first century path to early cancer detection

Detection of cancer at an early stage when it is still localized improves patient response to medical interventions for most cancer types. The success of screening tools such as cervical cytology to reduce mortality has spurred significant interest in new methods for early detection (for example, using non-invasive blood-based or biofluid-based biomarkers). Yet biomarkers shed from early lesions are limited by fundamental biological and mass transport barriers - such as short circulation times and blood dilution - that limit early detection. To address this issue, synthetic biomarkers are being developed. These represent an emerging class of diagnostics that deploy bioengineered sensors inside the body to query early-stage tumours and amplify disease signals to levels that could potentially exceed those of shed biomarkers. These strategies leverage design principles and advances from chemistry, synthetic biology and cell engineering. In this Review, we discuss the rationale for development of biofluid-based synthetic biomarkers. We examine how these strategies harness dysregulated features of tumours to amplify detection signals, use tumour-selective activation to increase specificity and leverage natural processing of bodily fluids (for example, blood, urine and proximal fluids) for easy detection. Finally, we highlight the challenges that exist for preclinical development and clinical translation of synthetic biomarker diagnostics.

Achieving Precision Medicine in Allergic Disease: Progress and Challenges

Allergic diseases (atopic dermatitis, food allergy, eosinophilic esophagitis, asthma and allergic rhinitis), perhaps more than many other traditionally grouped disorders, share several overlapping inflammatory pathways and risk factors, though we are still beginning to understand how the relevant patient and environmental factors uniquely shape each disease. Precision medicine is the concept of applying multiple levels of patient-specific data to tailor diagnoses and available treatments to the individual; ideally, a patient receives the right intervention at the right time, in order to maximize effectiveness but minimize morbidity, mortality and cost. While precision medicine in allergy is in its infancy, the recent success of biologics, development of tools focused on large data set integration and improved sampling methods are encouraging and demonstrates the utility of refining our understanding of allergic endotypes to improve therapies. Some of the biggest challenges to achieving precision medicine in allergy are characterizing allergic endotypes, understanding allergic multimorbidity relationships, contextualizing the impact of environmental exposures (the “exposome”) and ancestry/genetic risks, achieving actionable multi-omics integration, and using this information to develop adequately powered patient cohorts and refined clinical trials. In this paper, we highlight several recently developed tools and methods showing promise to realize the aspirational potential of precision medicine in allergic disease. We also outline current challenges, including exposome sampling and building the “knowledge network” with multi-omics integration.

Anticipation of Precision Diabetes and Promise of Integrative Multi-Omics

Precision diabetes is a concept of customizing delivery of health practices based on variability of diabetes. The authors reviewed recent research on type 2 diabetes heterogeneity and -omic biomarkers, including genomic, epigenomic, and metabolomic markers associated with type 2 diabetes. The emerging multiomics approach integrates complementary and interconnected molecular layers to provide systems level understanding of disease mechanisms and subtypes. Although the multiomic approach is not currently ready for routine clinical applications, future studies in the context of precision diabetes, particular in populations from diverse ethnic and demographic groups, may lead to improved diagnosis, treatment, and management of diabetes and diabetic complications.

Overview of omics biomarkers in pituitary neuroendocrine tumors to design future diagnosis and treatment strategies

Pituitary neuroendocrine tumors (PitNETs) are the second most common type of intracranial neoplasia. Since their manifestation usually causes hormone hypersecretion, effective management of PitNETs is indisputably necessary. Most of the non-functioning PitNETs pose a real challenge in diagnosis as they grow without giving any signs. Despite the good response of prolactinomas to dopamine agonist therapy, some of these tumors persist or recur; also, about 20% are resistant and 10% behave aggressively. The silent corticotropinomas may not cause symptoms until the tumor mass causes a complication. In somatotropinomas, the possibility of recurrence after transsphenoidal resection is more common in pediatric patients than in adult patients. Therefore, detection of tumors at early stages or identification of recurrence and remission after transsphenoidal surgery would allow wiser management of the disease. Extensive studies have been performed to uncover potential signatures that can be used for preventive diagnosis and/or prognosis of PitNETs as well as for targeted therapy. These molecular signatures at multiple biological levels hold promise for the convergence of preventive approaches and patient-centered disease management and offer potential therapeutic strategies. In this review, we provide an overview of the omics-based biomarker research and highlight the multi-omics signatures that have been proposed as pitNET biomarkers. In addition, understanding the multi-omics data integration of current biomarker discovery strategies was discussed in terms of preventive, predictive, and personalized medicine. The topics discussed in this review will help to develop broader visions for pitNET research, diagnosis, and therapy, particularly in the context of personalized medicine.

Artificial Intelligence for Alzheimer's Disease: Promise or Challenge?

Decades of experimental and clinical research have contributed to unraveling many mechanisms in the pathogenesis of Alzheimer's disease (AD), but the puzzle is still incomplete. Although we can suppose that there is no complete set of puzzle pieces, the recent growth of open data-sharing initiatives collecting lifestyle, clinical, and biological data from AD patients has provided a potentially unlimited amount of information about the disease, far exceeding the human ability to make sense of it. Moreover, integrating Big Data from multi-omics studies provides the potential to explore the pathophysiological mechanisms of the entire biological continuum of AD. In this context, Artificial Intelligence (AI) offers a wide variety of methods to analyze large and complex data in order to improve knowledge in the AD field. In this review, we focus on recent findings and future challenges for AI in AD research. In particular, we discuss the use of Computer-Aided Diagnosis tools for AD diagnosis and the use of AI to potentially support clinical practices for the prediction of individual risk of AD conversion as well as patient stratification in order to finally develop effective and personalized therapies.

A deep learning algorithm using CT images to screen for Corona virus disease (COVID-19)

OBJECTIVE

The outbreak of Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-COV-2) has caused more than 26 million cases of Corona virus disease (COVID-19) in the world so far. To control the spread of the disease, screening large numbers of suspected cases for appropriate quarantine and treatment are a priority. Pathogenic laboratory testing is typically the gold standard, but it bears the burden of significant false negativity, adding to the urgent need of alternative diagnostic methods to combat the disease. Based on COVID-19 radiographic changes in CT images, this study hypothesized that artificial intelligence methods might be able to extract specific graphical features of COVID-19 and provide a clinical diagnosis ahead of the pathogenic test, thus saving critical time for disease control.

METHODS

We collected 1065 CT images of pathogen-confirmed COVID-19 cases along with those previously diagnosed with typical viral pneumonia. We modified the inception transfer-learning model to establish the algorithm, followed by internal and external validation.

RESULTS

The internal validation achieved a total accuracy of 89.5% with a specificity of 0.88 and sensitivity of 0.87. The external testing dataset showed a total accuracy of 79.3% with a specificity of 0.83 and sensitivity of 0.67. In addition, in 54 COVID-19 images, the first two nucleic acid test results were negative, and 46 were predicted as COVID-19 positive by the algorithm, with an accuracy of 85.2%.

CONCLUSION

These results demonstrate the proof-of-principle for using artificial intelligence to extract radiological features for timely and accurate COVID-19 diagnosis.

KEY POINTS

• The study evaluated the diagnostic performance of a deep learning algorithm using CT images to screen for COVID-19 during the influenza season. • As a screening method, our model achieved a relatively high sensitivity on internal and external CT image datasets. • The model was used to distinguish between COVID-19 and other typical viral pneumonia, both of which have quite similar radiologic characteristics.

A deep learning algorithm using CT images to screen for Corona virus disease (COVID-19)

OBJECTIVE

The outbreak of Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-COV-2) has caused more than 26 million cases of Corona virus disease (COVID-19) in the world so far. To control the spread of the disease, screening large numbers of suspected cases for appropriate quarantine and treatment are a priority. Pathogenic laboratory testing is typically the gold standard, but it bears the burden of significant false negativity, adding to the urgent need of alternative diagnostic methods to combat the disease. Based on COVID-19 radiographic changes in CT images, this study hypothesized that artificial intelligence methods might be able to extract specific graphical features of COVID-19 and provide a clinical diagnosis ahead of the pathogenic test, thus saving critical time for disease control.

METHODS

We collected 1065 CT images of pathogen-confirmed COVID-19 cases along with those previously diagnosed with typical viral pneumonia. We modified the inception transfer-learning model to establish the algorithm, followed by internal and external validation.

RESULTS

The internal validation achieved a total accuracy of 89.5% with a specificity of 0.88 and sensitivity of 0.87. The external testing dataset showed a total accuracy of 79.3% with a specificity of 0.83 and sensitivity of 0.67. In addition, in 54 COVID-19 images, the first two nucleic acid test results were negative, and 46 were predicted as COVID-19 positive by the algorithm, with an accuracy of 85.2%.

CONCLUSION

These results demonstrate the proof-of-principle for using artificial intelligence to extract radiological features for timely and accurate COVID-19 diagnosis.

KEY POINTS

• The study evaluated the diagnostic performance of a deep learning algorithm using CT images to screen for COVID-19 during the influenza season. • As a screening method, our model achieved a relatively high sensitivity on internal and external CT image datasets. • The model was used to distinguish between COVID-19 and other typical viral pneumonia, both of which have quite similar radiologic characteristics.

[Machine learning in anesthesiology]

The application of artificial intelligence (AI) is currently changing very different areas of life. Artificial intelligence involves the emulation of human behavior with the aid of methods from mathematics and informatics. Machine learning (ML) represents a subdivision of AI. Algorithms for ML have the potential to optimize patient care, in that they can be utilized in a supportive way in personalized medicine, decision making and risk prediction. Although the majority of the applications in medicine are still limited to data analysis and research, it is certain that ML will become increasingly more important in scientific and clinical aspects in this supportive function. Therefore, it is necessary for clinicians to have at least a basic understanding of the functional principles, strengths and weaknesses of ML.