Tensor Factorization for Precision Medicine in Heart Failure with Preserved Ejection Fraction

Labour monitoring and decision support: a machine-learning-based paradigm

Introduction

A machine-learning-based paradigm, combining unsupervised and supervised components, is proposed for the problem of real-time monitoring and decision support during labour, addressing the limitations of current state-of-the-art approaches, such as the partograph or purely supervised models.

Methods

The proposed approach is illustrated with World Health Organisation's Better Outcomes in Labour Difficulty (BOLD) prospective cohort study data, including 9,995 women admitted for labour in 2014-2015 in thirteen major regional health care facilities across Nigeria and Uganda. Unsupervised dimensionality reduction is used to map complex labour data to a visually intuitive space. In this space, an ongoing labour trajectory can be compared to those of a historical cohort of women with similar characteristics and known outcomes-this information can be used to estimate personalised "healthy" trajectory references (and alert the healthcare provider to significant deviations), as well as draw attention to high incidences of different interventions/adverse outcomes among similar labours. To evaluate the proposed approach, the predictive value of simple risk scores quantifying deviation from normal progress and incidence of complications among similar labours is assessed in a caesarean section prediction context and compared to that of the partograph and state-of-the-art supervised machine-learning models.

Results

Considering all women, our predictors yielded sensitivity and specificity of ∼0.70. It was observed that this predictive performance could increase or decrease when looking at different subgroups.

Discussion

With a simple implementation, our approach outperforms the partograph and matches the performance of state-of-the-art supervised models, while offering superior flexibility and interpretability as a real-time monitoring and decision-support solution.

Impact of tooth loss and patient characteristics on coronary artery calcium score classification and prediction

This study, for the first time, explores the integration of data science and machine learning for the classification and prediction of coronary artery calcium (CAC) scores. It focuses on tooth loss and patient characteristics as key input features to enhance the accuracy of classifying CAC scores into tertiles and predicting their values. Advanced analytical techniques were employed to assess the effectiveness of tooth loss and patient characteristics in the classification and prediction of CAC scores. The study utilized data science and machine learning methodologies to analyze the relationships between these input features and CAC scores. The research evaluated the individual and combined contributions of patient characteristics and tooth loss on the accuracy of identifying individuals at higher risk of cardiovascular issues related to CAC. The findings indicated that patient characteristics were particularly effective for tertile classification of CAC scores, achieving a classification accuracy of 75%. Tooth loss alone provided more accurate predicted CAC scores with the smallest average mean squared error of regression and with a classification accuracy of 71%. The combination of patient characteristics and tooth loss demonstrated improved accuracy in identifying individuals at higher risk with the best sensitivity rate of 92% over patient characteristics (85%) and tooth loss (88%). The results highlight the significance of both oral health indicators and patient characteristics in predictive modeling and classification tasks for CAC scores. By integrating data science and machine learning techniques, the research provides a foundation for further exploration of the connections between oral health, patient characteristics, and cardiovascular outcomes, emphasizing their importance in advancing the accuracy of CAC score classification and prediction.

Censored Least Squares for Imputing Missing Values in PARAFAC Tensor Factorization

Tensor factorization is a dimensionality reduction method applied to multidimensional arrays. These methods are useful for identifying patterns within a variety of biomedical datasets due to their ability to preserve the organizational structure of experiments and therefore aid in generating meaningful insights. However, missing data in the datasets being analyzed can impose challenges. Tensor factorization can be performed with some level of missing data and reconstruct a complete tensor. However, while tensor methods may impute these missing values, the choice of fitting algorithm may influence the fidelity of these imputations. Previous approaches, based on alternating least squares with prefilled values or direct optimization, suffer from introduced bias or slow computational performance. In this study, we propose that censored least squares can better handle missing values with data structured in tensor form. We ran censored least squares on four different biological datasets and compared its performance against alternating least squares with prefilled values and direct optimization. We used the error of imputation and the ability to infer masked values to benchmark their missing data performance. Censored least squares appeared best suited for the analysis of high-dimensional biological data by accuracy and convergence metrics across several studies.

A New Fuzzy-Based Classification Method for Use in Smart/Precision Medicine

The development of information technology has had a significant impact on various areas of human activity, including medicine. It has led to the emergence of the phenomenon of Industry 4.0, which, in turn, led to the development of the concept of Medicine 4.0. Medicine 4.0, or smart medicine, can be considered as a structural association of such areas as AI-based medicine, telemedicine, and precision medicine. Each of these areas has its own characteristic data, along with the specifics of their processing and analysis. Nevertheless, at present, all these types of data must be processed simultaneously, in order to provide the most complete picture of the health of each individual patient. In this paper, after a brief analysis of the topic of medical data, a new classification method is proposed that allows the processing of the maximum number of data types. The specificity of this method is its use of a fuzzy classifier. The effectiveness of this method is confirmed by an analysis of the results from the classification of various types of data for medical applications and health problems. In this paper, as an illustration of the proposed method, a fuzzy decision tree has been used as the fuzzy classifier. The accuracy of the classification in terms of the proposed method, based on a fuzzy classifier, gives the best performance in comparison with crisp classifiers.

Computational clustering reveals differentiated coronary artery calcium progression at prevalent levels of pulse wave velocity by classifying high-risk patients

Many studies found that increased arterial stiffness is significantly associated with the presence and progression of Coronary Calcium Score (CCS). However, none so far have used machine learning algorithms to improve their value. Therefore, this study aims to evaluate the association between carotid-femoral Pulse Wave Velocity (cfPWV) and CCS score through computational clustering. We conducted a retrospective cross-sectional study using data from a cardiovascular risk screening program that included 377 participants. We used an unsupervised clustering algorithm using age, weight, height, blood pressure, heart rate, and cfPWV as input variables. Differences between cluster groups were analyzed through Chi-square and T-student tests. The association between (i) cfPWV and age groups, (ii) log (CCS) and age groups, and (iii) cfPWV and log(CCS) were addressed through linear regression analysis. Clusters were labeled post hoc based on cardiovascular risk. A "higher-risk group" had significantly higher left (0.76 vs. 0.70 mm, P < 0.001) and right (0.71 vs. 0.66 mm, P = 0.003) intima-media thickness, CCS (42 vs. 4 Agatston units, P = 0.012), and ascending (3.40 vs. 3.20 cm, P < 0.001) and descending (2.60 vs. 2.37 cm, P < 0.001) aorta diameters. Association with age appeared linear for cfPWV and exponential for log (CCS). The progression of the log (CCS) and cfPWV through age groups was steeper in the "higher-risk group" than in the "lower-risk group". cfPWV strongly correlated with CCS, and CCS progression over cfPWV differed among clusters. This finding could improve PWV as a "gate-keeper" of CCS testing and potentially enhance cardiovascular risk stratification.

A cardiologist's guide to machine learning in cardiovascular disease prognosis prediction

A modern-day physician is faced with a vast abundance of clinical and scientific data, by far surpassing the capabilities of the human mind. Until the last decade, advances in data availability have not been accompanied by analytical approaches. The advent of machine learning (ML) algorithms might improve the interpretation of complex data and should help to translate the near endless amount of data into clinical decision-making. ML has become part of our everyday practice and might even further change modern-day medicine. It is important to acknowledge the role of ML in prognosis prediction of cardiovascular disease. The present review aims on preparing the modern physician and researcher for the challenges that ML might bring, explaining basic concepts but also caveats that might arise when using these methods. Further, a brief overview of current established classical and emerging concepts of ML disease prediction in the fields of omics, imaging and basic science is presented.

Tensor Decomposition of Largest Convolutional Eigenvalues Reveals Pathologic Predictive Power of RhoB in Rectal Cancer Biopsy

RhoB protein belongs to the Rho GTPase family, which plays an important role in governing cell signaling and tissue morphology. RhoB expression is known to have implications in pathologic processes of diseases. Investigation in the regulation and communication of this protein, detected by immunohistochemical staining on the microscope, is worth exploring to gain insightful information that may lead to identifying optimal disease treatment options. In particular, the role of RhoB in rectal cancer is not well discovered. Here, we report that methods of deep learning-based image analysis and the decomposition of multiway arrays discover the predictive factor of RhoB in two cohorts of patients with rectal cancer having survival rates of <5 and >5 years. The analysis results show distinctions between the tensor decomposition factors of the two cohorts.

A deep learning framework assisted echocardiography with diagnosis, lesion localization, phenogrouping heterogeneous disease, and anomaly detection

Echocardiography is the first-line diagnostic technique for heart diseases. Although artificial intelligence techniques have made great improvements in the analysis of echocardiography, the major limitations remain to be the built neural networks are normally adapted to a few diseases and specific equipment. Here, we present an end-to-end deep learning framework named AIEchoDx that differentiates four common cardiovascular diseases (Atrial Septal Defect, Dilated Cardiomyopathy, Hypertrophic Cardiomyopathy, prior Myocardial Infarction) from normal subjects with performance comparable to that of consensus of three senior cardiologists in AUCs (99.50% vs 99.26%, 98.75% vs 92.75%, 99.57% vs 97.21%, 98.52% vs 84.20%, and 98.70% vs 89.41%), respectively. Meanwhile, AIEchoDx accurately recognizes critical lesion regions of interest along with each disease by visualizing the decision-making process. Furthermore, our analysis indicates that heterogeneous diseases, like dilated cardiomyopathy, could be classified into two phenogroups with distinct clinical characteristics. Finally, AIEchoDx performs efficiently as an anomaly detection tool when applying handheld device-produced videos. Together, AIEchoDx provides a potential diagnostic assistant tool in either cart-based echocardiography equipment or handheld echocardiography device for primary and point-of-care medical personnel with high diagnostic performance, and the application of lesion region identification and heterogeneous disease phenogrouping, which may broaden the application of artificial intelligence in echocardiography.

Application of artificial intelligence in medical technologies: A systematic review of main trends

Objective

Artificial intelligence (AI) has been increasingly applied in various fields of science and technology. In line with the current research, medicine involves an increasing number of artificial intelligence technologies. The introduction of rapid AI can lead to positive and negative effects. This is a multilateral analytical literature review aimed at identifying the main branches and trends in the use of using artificial intelligence in medical technologies.

Methods

The total number of literature sources reviewed is n = 89, and they are analyzed based on the literature reporting evidence-based guideline PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) for a systematic review.

Results

As a result, from the initially selected 198 references, 155 references were obtained from the databases and the remaining 43 sources were found on open internet as direct links to publications. Finally, 89 literature sources were evaluated after exclusion of unsuitable references based on the duplicated and generalized information without focusing on the users.

Conclusions

This article is identifying the current state of artificial intelligence in medicine and prospects for future use. The findings of this review will be useful for healthcare and AI professionals for improving the circulation and use of medical AI from design to implementation stage.

Multimodal machine learning in precision health: A scoping review

Machine learning is frequently being leveraged to tackle problems in the health sector including utilization for clinical decision-support. Its use has historically been focused on single modal data. Attempts to improve prediction and mimic the multimodal nature of clinical expert decision-making has been met in the biomedical field of machine learning by fusing disparate data. This review was conducted to summarize the current studies in this field and identify topics ripe for future research. We conducted this review in accordance with the PRISMA extension for Scoping Reviews to characterize multi-modal data fusion in health. Search strings were established and used in databases: PubMed, Google Scholar, and IEEEXplore from 2011 to 2021. A final set of 128 articles were included in the analysis. The most common health areas utilizing multi-modal methods were neurology and oncology. Early fusion was the most common data merging strategy. Notably, there was an improvement in predictive performance when using data fusion. Lacking from the papers were clear clinical deployment strategies, FDA-approval, and analysis of how using multimodal approaches from diverse sub-populations may improve biases and healthcare disparities. These findings provide a summary on multimodal data fusion as applied to health diagnosis/prognosis problems. Few papers compared the outputs of a multimodal approach with a unimodal prediction. However, those that did achieved an average increase of 6.4% in predictive accuracy. Multi-modal machine learning, while more robust in its estimations over unimodal methods, has drawbacks in its scalability and the time-consuming nature of information concatenation.

The research of clinical temporal knowledge graph based on deep learning

Temporal knowledge base exists on various fields. Take medical medicine field as example, diabetes is a typical chronic disease which evolves slowly. This paper starts from actual EMR data of hospitals by combination of experience and knowledge of clinical doctors. Link prediction on clinical knowledge base such as diabetic complication requires the analysis on temporal characteristic of temporal knowledge base, which is a great challenge for traditional link prediction models. This paper proposes temporal knowledge graph link prediction model based on deep learning. This model selects the TransR transformation model suitable for big data and makes entity projection in relation space containing different semantic meanings, so as to vector the entities and complex semantic relations in graph. Then it adopts LSTM recursive neural network and adds the top-bottom relational information of the graph for sequential learning. Finally it constantly carries out deep learning through incremental calculation and LSTM recursive network to improve the accuracy of prediction. The incremental LSTM model highlights the hidden semantic and clinical temporal information and effectively utilizes sequential learning to mining forward-backward dependent information. It compensates the deficiency of lower prediction accuracy on timely knowledge graph caused by the traditional link prediction models. Finally, it is proved that the new model has better performance over temporal knowledge graph link prediction.

Advancing clinical genomics and precision medicine with GVViZ: FAIR bioinformatics platform for variable gene-disease annotation, visualization, and expression analysis

Background

Genetic disposition is considered critical for identifying subjects at high risk for disease development. Investigating disease-causing and high and low expressed genes can support finding the root causes of uncertainties in patient care. However, independent and timely high-throughput next-generation sequencing data analysis is still a challenge for non-computational biologists and geneticists.

Results

In this manuscript, we present a findable, accessible, interactive, and reusable (FAIR) bioinformatics platform, i.e., GVViZ (visualizing genes with disease-causing variants). GVViZ is a user-friendly, cross-platform, and database application for RNA-seq-driven variable and complex gene-disease data annotation and expression analysis with a dynamic heat map visualization. GVViZ has the potential to find patterns across millions of features and extract actionable information, which can support the early detection of complex disorders and the development of new therapies for personalized patient care. The execution of GVViZ is based on a set of simple instructions that users without a computational background can follow to design and perform customized data analysis. It can assimilate patients’ transcriptomics data with the public, proprietary, and our in-house developed gene-disease databases to query, easily explore, and access information on gene annotation and classified disease phenotypes with greater visibility and customization. To test its performance and understand the clinical and scientific impact of GVViZ, we present GVViZ analysis for different chronic diseases and conditions, including Alzheimer’s disease, arthritis, asthma, diabetes mellitus, heart failure, hypertension, obesity, osteoporosis, and multiple cancer disorders. The results are visualized using GVViZ and can be exported as image (PNF/TIFF) and text (CSV) files that include gene names, Ensembl (ENSG) IDs, quantified abundances, expressed transcript lengths, and annotated oncology and non-oncology diseases.

Conclusions

We emphasize that automated and interactive visualization should be an indispensable component of modern RNA-seq analysis, which is currently not the case. However, experts in clinics and researchers in life sciences can use GVViZ to visualize and interpret the transcriptomics data, making it a powerful tool to study the dynamics of gene expression and regulation. Furthermore, with successful deployment in clinical settings, GVViZ has the potential to enable high-throughput correlations between patient diagnoses based on clinical and transcriptomics data.

Supplementary Information

The online version contains supplementary material available at 10.1186/s40246-021-00336-1.

Tensor learning of pointwise mutual information from EHR data for early prediction of sepsis

Early detection of sepsis can facilitate early clinical intervention with effective treatment and may reduce sepsis mortality rates. In view of this, machine learning-based automated diagnosis of sepsis using easily recordable physiological data can be more promising as compared to the gold standard rule-based clinical criteria in current practice. This study aims to develop such a machine learning framework that demonstrates the quantification of heterogeneity within the tabular electronic health records (EHR) data of clinical covariates to capture both linear relationships and nonlinear correlation for the early prediction of sepsis. Here, the statistics of pairwise association for each hour-covariate pair within the EHR data for every 6-hours window-duration with selected 24 covariates is described using pointwise mutual information (PMI) matrix. This matrix gives the heterogeneity of data as a two-dimensional map. Such matrices are fused horizontally along the z-axis as vertical slices in the xy plane to form a 3-way tensor for each record with the corresponding Length of Stay (L). Tensor factorization of such fused tensor for every record is performed using Tucker decomposition, and only the core tensors are retained later, excluding the 3 unitary matrices to provide the latent feature set for the prediction of sepsis onset. A five-fold cross-validation scheme is employed wherein the obtained 120 latent features from the reshaped core tensor, are fed to Light Gradient Boosting Machine Learning models (LightGBM) for binary classification, further alleviating the involved class imbalance. The machine-learning framework is designed via Bayesian optimization, yielding an average normalized utility score of 0.4519 as defined by challenge organizers and area under the receiver operating characteristic curve (AUROC) of 0.8621 on publicly available PhysioNet/Computing in Cardiology Challenge 2019 training data. The proposed tensor decomposition of 3-way fused tensor formulated using PMI matrices leverages higher-order temporal interactions between the pairwise associations among the clinical values for early prediction of sepsis. This is validated with improved risk prediction power for every hour of admission to the ICU in terms of utility score, AUROC, and F1 score. The results obtained show a significant improvement particularly in terms of utility score of ~1.5-2% under a 5-fold cross-validation scheme on entire training data as compared to a top entrant research study that participated in the challenge.

Big Data, Extracting Insights, Comprehension, and Analytics in Cardiology: An Overview

Healthcare system facilitates the treatment of patients with the support of wearable, smart, and handheld devices, as well as many other devices. These devices are producing a huge bulk of data that need to be moulded for extracting meaningful insights from them for the useful use of researchers and practitioners. Various approaches, methods, and tools are in use for doing so and to extract meaningful information in the field of healthcare. This information is being used as evidence to further analyze the data for the early care of patient and to devise treatment. Early care and treatment can facilitate healthcare and the treatment of the patient and can have immense potentiality of dropping the care cost and quality refining of care and can decrease waste and chances of error. To facilitate healthcare in general and cardiology in specific, the proposed study presents an overview of the available literature associated with big data, its insights, and analytics. The presented report will help practitioners and researchers to devise new solutions for early care in healthcare and in cardiology.

Machine Learning and the Future of Cardiovascular Care: JACC State-of-the-Art Review

The role of physicians has always been to synthesize the data available to them to identify diagnostic patterns that guide treatment and follow response. Today, increasingly sophisticated machine learning algorithms may grow to support clinical experts in some of these tasks. Machine learning has the potential to benefit patients and cardiologists, but only if clinicians take an active role in bringing these new algorithms into practice. The aim of this review is to introduce clinicians who are not data science experts to key concepts in machine learning that will allow them to better understand the field and evaluate new literature and developments. The current published data in machine learning for cardiovascular disease is then summarized, using both a bibliometric survey, with code publicly available to enable similar analysis for any research topic of interest, and select case studies. Finally, several ways that clinicians can and must be involved in this emerging field are presented.

Practicing precision medicine with intelligently integrative clinical and multi-omics data analysis

Precision medicine aims to empower clinicians to predict the most appropriate course of action for patients with complex diseases like cancer, diabetes, cardiomyopathy, and COVID-19. With a progressive interpretation of the clinical, molecular, and genomic factors at play in diseases, more effective and personalized medical treatments are anticipated for many disorders. Understanding patient’s metabolomics and genetic make-up in conjunction with clinical data will significantly lead to determining predisposition, diagnostic, prognostic, and predictive biomarkers and paths ultimately providing optimal and personalized care for diverse, and targeted chronic and acute diseases. In clinical settings, we need to timely model clinical and multi-omics data to find statistical patterns across millions of features to identify underlying biologic pathways, modifiable risk factors, and actionable information that support early detection and prevention of complex disorders, and development of new therapies for better patient care. It is important to calculate quantitative phenotype measurements, evaluate variants in unique genes and interpret using ACMG guidelines, find frequency of pathogenic and likely pathogenic variants without disease indicators, and observe autosomal recessive carriers with a phenotype manifestation in metabolome. Next, ensuring security to reconcile noise, we need to build and train machine-learning prognostic models to meaningfully process multisource heterogeneous data to identify high-risk rare variants and make medically relevant predictions. The goal, today, is to facilitate implementation of mainstream precision medicine to improve the traditional symptom-driven practice of medicine, and allow earlier interventions using predictive diagnostics and tailoring better-personalized treatments. We strongly recommend automated implementation of cutting-edge technologies, utilizing machine learning (ML) and artificial intelligence (AI) approaches for the multimodal data aggregation, multifactor examination, development of knowledgebase of clinical predictors for decision support, and best strategies for dealing with relevant ethical issues.

Identifying Phenogroups in patients with subclinical diastolic dysfunction using unsupervised statistical learning

BACKGROUND

Subclinical diastolic dysfunction is a precursor for developing heart failure with preserved ejection fraction (HFpEF); yet not all patients progress to HFpEF. Our objective was to evaluate clinical and echocardiographic variables to identify patients who develop HFpEF.

METHODS

Clinical, laboratory, and echocardiographic data were retrospectively collected for 81 patients without HF and 81 matched patients with HFpEF at the time of first documentation of subclinical diastolic dysfunction. Density-based clustering or hierarchical clustering to group patients was based on 65 total variables including 19 categorical and 46 numerical variables. Logistic regression analysis was conducted on the entire study population as well as each individual cluster to identify independent predictors of HFpEF.

RESULTS

Unsupervised clustering identified 3 subgroups which differed in gender composition, severity of cardiac hypertrophy and aortic stenosis, NT-proBNP, percentage of patients who progressed to HFpEF, and timing of disease progression from diastolic dysfunction to HFpEF to death. Clusters that had higher percentages of women had progressively milder cardiac hypertrophy, less severe aortic stenosis, lower NT-proBNP, were diagnosed at an older age with HFpEF, and survived to an older age. Independent predictors of HFpEF for the entire cohort included diabetes, chronic kidney disease, atrial fibrillation, and diuretic use, with additional predictive variables found for each cluster.

CONCLUSIONS

Cluster analysis can identify phenotypically distinct subgroups of patients with diastolic dysfunction. Clusters differ in HFpEF and mortality outcome. In addition, the variables that correlate with and predict HFpEF outcome differ among clusters.

Artificial intelligence supported patient self-care in chronic heart failure: a paradigm shift from reactive to predictive, preventive and personalised care

Heart failure (HF) is one of the most complex chronic disorders with high prevalence, mainly due to the ageing population and better treatment of underlying diseases. Prevalence will continue to rise and is estimated to reach 3% of the population in Western countries by 2025. It is the most important cause of hospitalisation in subjects aged 65 years or more, resulting in high costs and major social impact. The current "one-size-fits-all" approach in the treatment of HF does not result in best outcome for all patients. These facts are an imminent threat to good quality management of patients with HF. An unorthodox approach from a new vision on care is required. We propose a novel predictive, preventive and personalised medicine approach where patients are truly leading their management, supported by an easily accessible online application that takes advantage of artificial intelligence. This strategy paper describes the needs in HF care, the needed paradigm shift and the elements that are required to achieve this shift. Through the inspiring collaboration of clinical and high-tech partners from North-West Europe combining state of the art HF care, artificial intelligence, serious gaming and patient coaching, a virtual doctor is being created. The results are expected to advance and personalise self-care, where standard care tasks are performed by the patients themselves, in principle without involvement of healthcare professionals, the latter being able to focus on complex conditions. This new vision on care will significantly reduce costs per patient while improving outcomes to enable long-term sustainability of top-level HF care.

Metabolomics technology and bioinformatics for precision medicine

Precision medicine is rapidly emerging as a strategy to tailor medical treatment to a small group or even individual patients based on their genetics, environment and lifestyle. Precision medicine relies heavily on developments in systems biology and omics disciplines, including metabolomics. Combination of metabolomics with sophisticated bioinformatics analysis and mathematical modeling has an extreme power to provide a metabolic snapshot of the patient over the course of disease and treatment or classifying patients into subpopulations and subgroups requiring individual medical treatment. Although a powerful approach, metabolomics have certain limitations in technology and bioinformatics. We will review various aspects of metabolomics technology and bioinformatics, from data generation, bioinformatics analysis, data fusion and mathematical modeling to data management, in the context of precision medicine.

Artificial Intelligence in Cardiology

Artificial intelligence and machine learning are poised to influence nearly every aspect of the human condition, and cardiology is not an exception to this trend. This paper provides a guide for clinicians on relevant aspects of artificial intelligence and machine learning, reviews selected applications of these methods in cardiology to date, and identifies how cardiovascular medicine could incorporate artificial intelligence in the future. In particular, the paper first reviews predictive modeling concepts relevant to cardiology such as feature selection and frequent pitfalls such as improper dichotomization. Second, it discusses common algorithms used in supervised learning and reviews selected applications in cardiology and related disciplines. Third, it describes the advent of deep learning and related methods collectively called unsupervised learning, provides contextual examples both in general medicine and in cardiovascular medicine, and then explains how these methods could be applied to enable precision cardiology and improve patient outcomes.

Cancer classification and pathway discovery using non-negative matrix factorization

OBJECTIVES

Extracting genetic information from a full range of sequencing data is important for understanding disease. We propose a novel method to effectively explore the landscape of genetic mutations and aggregate them to predict cancer type.

DESIGN

We applied non-smooth non-negative matrix factorization (nsNMF) and support vector machine (SVM) to utilize the full range of sequencing data, aiming to better aggregate genetic mutations and improve their power to predict disease type. More specifically, we introduce a novel classifier to distinguish cancer types using somatic mutations obtained from whole-exome sequencing data. Mutations were identified from multiple cancers and scored using SIFT, PP2, and CADD, and collapsed at the individual gene level. nsNMF was then applied to reduce dimensionality and obtain coefficient and basis matrices. A feature matrix was derived from the obtained matrices to train a classifier for cancer type classification with the SVM model.

RESULTS

We have demonstrated that the classifier was able to distinguish four cancer types with reasonable accuracy. In five-fold cross-validations using mutation counts as features, the average prediction accuracy was 80% (SEM = 0.1%), significantly outperforming baselines and outperforming models using mutation scores as features.

CONCLUSION

Using the factor matrices derived from the nsNMF, we identified multiple genes and pathways that are significantly associated with each cancer type. This study presents a generic and complete pipeline to study the associations between somatic mutations and cancers. The proposed method can be adapted to other studies for disease status classification and pathway discovery.

Supervised Nonnegative Matrix Factorization to Predict ICU Mortality Risk

ICU mortality risk prediction is a tough yet important task. On one hand, due to the complex temporal data collected, it is difficult to identify the effective features and interpret them easily; on the other hand, good prediction can help clinicians take timely actions to prevent the mortality. These correspond to the interpretability and accuracy problems. Most existing methods lack of the interpretability, but recently Subgraph Augmented Nonnegative Matrix Factorization (SANMF) has been successfully applied to time series data to provide a path to interpret the features well. Therefore, we adopted this approach as the backbone to analyze the patient data. One limitation of the original SANMF method is its poor prediction ability due to its unsupervised nature. To deal with this problem, we proposed a supervised SANMF algorithm by integrating the logistic regression loss function into the NMF framework and solved it with an alternating optimization procedure. We used the simulation data to verify the effectiveness of this method, and then we applied it to ICU mortality risk prediction and demonstrated its superiority over other conventional supervised NMF methods.

Recent Advances in Supervised Dimension Reduction: A Survey

Recently, we have witnessed an explosive growth in both the quantity and dimension of data generated, which aggravates the high dimensionality challenge in tasks such as predictive modeling and decision support. Up to now, a large amount of unsupervised dimension reduction methods have been proposed and studied. However, there is no specific review focusing on the supervised dimension reduction problem. Most studies performed classification or regression after unsupervised dimension reduction methods. However, we recognize the following advantages if learning the low-dimensional representation and the classification/regression model simultaneously: high accuracy and effective representation. Considering classification or regression as being the main goal of dimension reduction, the purpose of this paper is to summarize and organize the current developments in the field into three main classes: PCA-based, Non-negative Matrix Factorization (NMF)-based, and manifold-based supervised dimension reduction methods, as well as provide elaborated discussions on their advantages and disadvantages. Moreover, we outline a dozen open problems that can be further explored to advance the development of this topic.

Are My EHRs Private Enough? Event-Level Privacy Protection

Privacy is a major concern in sharing human subject data to researchers for secondary analyses. A simple binary consent (opt-in or not) may significantly reduce the amount of sharable data, since many patients might only be concerned about a few sensitive medical conditions rather than the entire medical records. We propose event-level privacy protection, and develop a feature ablation method to protect event-level privacy in electronic medical records. Using a list of 13 sensitive diagnoses, we evaluate the feasibility and the efficacy of the proposed method. As feature ablation progresses, the identifiability of a sensitive medical condition decreases with varying speeds on different diseases. We find that these sensitive diagnoses can be divided into three categories: (1) five diseases have fast declining identifiability (AUC below 0.6 with less than 400 features excluded); (2) seven diseases with progressively declining identifiability (AUC below 0.7 with between 200 and 700 features excluded); and (3) one disease with slowly declining identifiability (AUC above 0.7 with 1,000 features excluded). The fact that the majority (12 out of 13) of the sensitive diseases fall into the first two categories suggests the potential of the proposed feature ablation method as a solution for event-level record privacy protection.

Natural Language Processing for EHR-Based Computational Phenotyping

This article reviews recent advances in applying natural language processing (NLP) to Electronic Health Records (EHRs) for computational phenotyping. NLP-based computational phenotyping has numerous applications including diagnosis categorization, novel phenotype discovery, clinical trial screening, pharmacogenomics, drug-drug interaction (DDI), and adverse drug event (ADE) detection, as well as genome-wide and phenome-wide association studies. Significant progress has been made in algorithm development and resource construction for computational phenotyping. Among the surveyed methods, well-designed keyword search and rule-based systems often achieve good performance. However, the construction of keyword and rule lists requires significant manual effort, which is difficult to scale. Supervised machine learning models have been favored because they are capable of acquiring both classification patterns and structures from data. Recently, deep learning and unsupervised learning have received growing attention, with the former favored for its performance and the latter for its ability to find novel phenotypes. Integrating heterogeneous data sources have become increasingly important and have shown promise in improving model performance. Often, better performance is achieved by combining multiple modalities of information. Despite these many advances, challenges and opportunities remain for NLP-based computational phenotyping, including better model interpretability and generalizability, and proper characterization of feature relations in clinical narratives.

Big Data and Data Science in Critical Care

The digitalization of the health-care system has resulted in a deluge of clinical big data and has prompted the rapid growth of data science in medicine. Data science, which is the field of study dedicated to the principled extraction of knowledge from complex data, is particularly relevant in the critical care setting. The availability of large amounts of data in the ICU, the need for better evidence-based care, and the complexity of critical illness makes the use of data science techniques and data-driven research particularly appealing to intensivists. Despite the increasing number of studies and publications in the field, thus far there have been few examples of data science projects that have resulted in successful implementations of data-driven systems in the ICU. However, given the expected growth in the field, intensivists should be familiar with the opportunities and challenges of big data and data science. The present article reviews the definitions, types of algorithms, applications, challenges, and future of big data and data science in critical care.

Precision Medicine for Heart Failure with Preserved Ejection Fraction: An Overview

There are few proven therapies for heart failure with preserved ejection fraction (HFpEF). The lack of therapies, along with increased recognition of the disorder and its underlying pathophysiology, has led to the acknowledgement that HFpEF is heterogeneous and is not likely to respond to a one-size-fits-all approach. Thus, HFpEF is a prime candidate to benefit from a precision medicine approach. For this reason, we have assembled a compendium of papers on the topic of precision medicine in HFpEF in the Journal of Cardiovascular Translational Research. These papers cover a variety of topics relevant to precision medicine in HFpEF, including automated identification of HFpEF patients; machine learning, novel molecular approaches, genomics, and deep phenotyping of HFpEF; and clinical trial designs that can be used to advance precision medicine in HFpEF. In this introductory article, we provide an overview of precision medicine in HFpEF with the hope that the work described here and in the other papers in this special theme issue will stimulate investigators and clinicians to advance a more targeted approach to HFpEF classification and treatment.

Phenomapping for the Identification of Hypertensive Patients with the Myocardial Substrate for Heart Failure with Preserved Ejection Fraction

We sought to evaluate whether unbiased machine learning of dense phenotypic data ("phenomapping") could identify distinct hypertension subgroups that are associated with the myocardial substrate (i.e., abnormal cardiac mechanics) for heart failure with preserved ejection fraction (HFpEF). In the HyperGEN study, a population- and family-based study of hypertension, we studied 1273 hypertensive patients utilizing clinical, laboratory, and conventional echocardiographic phenotyping of the study participants. We used machine learning analysis of 47 continuous phenotypic variables to identify mutually exclusive groups constituting a novel classification of hypertension. The phenomapping analysis classified study participants into 2 distinct groups that differed markedly in clinical characteristics, cardiac structure/function, and indices of cardiac mechanics (e.g., phenogroup #2 had a decreased absolute longitudinal strain [12.8 ± 4.1 vs. 14.6 ± 3.5%] even after adjustment for traditional comorbidities [p < 0.001]). The 2 hypertension phenogroups may represent distinct subtypes that may benefit from targeted therapies for the prevention of HFpEF.