Axes of a revolution: challenges and promises of big data in healthcare

High resolution data modifies intensive care unit dialysis outcome predictions as compared with low resolution administrative data set

High resolution clinical databases from electronic health records are increasingly being used in the field of health data science. Compared to traditional administrative databases and disease registries, these newer highly granular clinical datasets offer several advantages, including availability of detailed clinical information for machine learning and the ability to adjust for potential confounders in statistical models. The purpose of this study is to compare the analysis of the same clinical research question using an administrative database and an electronic health record database. The Nationwide Inpatient Sample (NIS) was used for the low-resolution model, and the eICU Collaborative Research Database (eICU) was used for the high-resolution model. A parallel cohort of patients admitted to the intensive care unit (ICU) with sepsis and requiring mechanical ventilation was extracted from each database. The primary outcome was mortality and the exposure of interest was the use of dialysis. In the low resolution model, after controlling for the covariates that are available, dialysis use was associated with an increased mortality (eICU: OR 2.07, 95% CI 1.75-2.44, p<0.01; NIS: OR 1.40, 95% CI 1.36-1.45, p<0.01). In the high-resolution model, after the addition of the clinical covariates, the harmful effect of dialysis on mortality was no longer significant (OR 1.04, 95% 0.85-1.28, p = 0.64). The results of this experiment show that the addition of high resolution clinical variables to statistical models significantly improves the ability to control for important confounders that are not available in administrative datasets. This suggests that the results from prior studies using low resolution data may be inaccurate and may need to be repeated using detailed clinical data.

Real World-Big Data Analytics in Healthcare

The term Big Data is used to describe extremely large datasets that are complex, multi-dimensional, unstructured, and heterogeneous and that are accumulating rapidly and may be analyzed with appropriate informatic and statistical methodologies to reveal patterns, trends, and associations [...].

"Note Bloat" impacts deep learning-based NLP models for clinical prediction tasks

One unintended consequence of the Electronic Health Records (EHR) implementation is the overuse of content-importing technology, such as copy-and-paste, that creates "bloated" notes containing large amounts of textual redundancy. Despite the rising interest in applying machine learning models to learn from real-patient data, it is unclear how the phenomenon of note bloat might affect the Natural Language Processing (NLP) models derived from these notes. Therefore, in this work we examine the impact of redundancy on deep learning-based NLP models, considering four clinical prediction tasks using a publicly available EHR database. We applied two deduplication methods to the hospital notes, identifying large quantities of redundancy, and found that removing the redundancy usually has little negative impact on downstream performances, and can in certain circumstances assist models to achieve significantly better results. We also showed it is possible to attack model predictions by simply adding note duplicates, causing changes of correct predictions made by trained models into wrong predictions. In conclusion, we demonstrated that EHR text redundancy substantively affects NLP models for clinical prediction tasks, showing that the awareness of clinical contexts and robust modeling methods are important to create effective and reliable NLP systems in healthcare contexts.

A "smart" Imputation Approach for Effective Quality Control Across Complex Clinical Data Structures

The overwhelming need to improve the quality of complex data structures in healthcare is more important than ever. Although data quality has been the point of interest in many studies, none of them has focused on the development of quantitative and explainable methods for data imputation. In this work, we propose a "smart" imputation workflow to address missing data across complex data structures in the context of in silico clinical trials. AI algorithms were utilized to produce high-quality virtual patient profiles. A search algorithm was then developed to extract the best virtual patient profiles through the definition of a profile matching score (PMS). A case study was conducted, where the real dataset was randomly contaminated with multiple missing values (e.g., 10 to 50%). In total, 10000 virtual patient profiles with less than 0.02 Kullback-Leibler (KL) divergence were produced to estimate the PMS distribution. The best generator achieved the lowest average squared absolute difference (0.4) and average correlation difference (0.02) with the real dataset highlighting its increased effectiveness for data imputation across complex clinical data structures.

Introduction to supervised machine learning in clinical epidemiology

Machine learning refers to a series of processes in which a computer finds rules from a vast amount of data. With recent advances in computer technology and the availability of a wide variety of health data, machine learning has rapidly developed and been applied in medical research. Currently, there are three types of machine learning: supervised, unsupervised, and reinforcement learning. In medical research, supervised learning is commonly used for diagnoses and prognoses, while unsupervised learning is used for phenotyping a disease, and reinforcement learning for maximizing favorable results, such as optimization of total patients' waiting time in the emergency department. The present article focuses on the concept and application of supervised learning in medicine, the most commonly used machine learning approach in medicine, and provides a brief explanation of four algorithms widely used for prediction (random forests, gradient-boosted decision tree, support vector machine, and neural network). Among these algorithms, the neural network has further developed into deep learning algorithms to solve more complex tasks. Along with simple classification problems, deep learning is commonly used to process medical imaging, such as retinal fundus photographs for diabetic retinopathy diagnosis. Although machine learning can bring new insights into medicine by processing a vast amount of data that are often beyond human capacity, algorithms can also fail when domain knowledge is neglected. The combination of algorithms and human cognitive ability is a key to the successful application of machine learning in medicine.

Neural Network Training with Highly Incomplete Medical Datasets

Neural network training and validation rely on the availability of large high-quality datasets. However, in many cases only incomplete datasets are available, particularly in health care applications, where each patient typically undergoes different clinical procedures or can drop out of a study. Since the data to train the neural networks need to be complete, most studies discard the incomplete datapoints, which reduces the size of the training data, or impute the missing features, which can lead to artefacts. Alas, both approaches are inadequate when a large portion of the data is missing. Here, we introduce GapNet, an alternative deep-learning training approach that can use highly incomplete datasets without overfitting or introducing artefacts. First, the dataset is split into subsets of samples containing all values for a certain cluster of features. Then, these subsets are used to train individual neural networks. Finally, this ensemble of neural networks is combined into a single neural network whose training is fine-tuned using all complete datapoints. Using two highly incomplete real-world medical datasets, we show that GapNet improves the identification of patients with underlying Alzheimer’s disease pathology and of patients at risk of hospitalization due to Covid-19. Compared to commonly used imputation methods, this improvement suggests that GapNet can become a general tool to handle incomplete medical datasets.

Nature-inspired metaheuristics model for gene selection and classification of biomedical microarray data

Identifying a small subset of informative genes from a gene expression dataset is an important process for sample classification in the fields of bioinformatics and machine learning. In this process, there are two objectives: first, to minimize the number of selected genes, and second, to maximize the classification accuracy of the used classifier. In this paper, a hybrid machine learning framework based on a nature-inspired cuckoo search (CS) algorithm has been proposed to resolve this problem. The proposed framework is obtained by incorporating the cuckoo search (CS) algorithm with an artificial bee colony (ABC) in the exploitation and exploration of the genetic algorithm (GA). These strategies are used to maintain an appropriate balance between the exploitation and exploration phases of the ABC and GA algorithms in the search process. In preprocessing, the independent component analysis (ICA) method extracts the important genes from the dataset. Then, the proposed gene selection algorithms along with the Naive Bayes (NB) classifier and leave-one-out cross-validation (LOOCV) have been applied to find a small set of informative genes that maximize the classification accuracy. To conduct a comprehensive performance study, proposed algorithms have been applied on six benchmark datasets of gene expression. The experimental comparison shows that the proposed framework (ICA and CS-based hybrid algorithm with NB classifier) performs a deeper search in the iterative process, which can avoid premature convergence and produce better results compared to the previously published feature selection algorithm for the NB classifier.

The evolving roles and impacts of 5G enabled technologies in healthcare: The world epidemic COVID-19 issues

The latest 5G technology is being introduced the Internet of Things (IoT) Era. The study aims to focus the 5G technology and the current healthcare challenges as well as to highlight 5G based solutions that can handle the COVID-19 issues in different arenas. This paper provides a comprehensive review of 5G technology with the integration of other digital technologies (like AI and machine learning, IoT objects, big data analytics, cloud computing, robotic technology, and other digital platforms) in emerging healthcare applications. From the literature, it is clear that the promising aspects of 5G (such as super-high speed, high throughput, low latency) have a prospect in healthcare advancement. Now healthcare is being adopted 5G-based technologies to aid improved health services, more effective medical research, enhanced quality of life, better experiences of medical professionals and patients in anywhere–anytime. This paper emphasizes the evolving roles of 5G technology for handling the epidemiological challenges. The study also discusses various technological challenges and prospective for developing 5G powered healthcare solutions. Further works will incorporate more studies on how to expand 5G-based digital society as well as to resolve the issues of safety–security–privacy and availability–accessibility–integrity in future health crises.

The promising role of new molecular biomarkers in prostate cancer: from coding and non-coding genes to artificial intelligence approaches

Background

Risk stratification or progression in prostate cancer is performed with the support of clinical-pathological data such as the sum of the Gleason score and serum levels PSA. For several decades, methods aimed at the early detection of prostate cancer have included the determination of PSA serum levels. The aim of this systematic review is to provide an overview about recent advances in the discovery of new molecular biomarkers through transcriptomics, genomics and artificial intelligence that are expected to improve clinical management of the prostate cancer patient.

Methods

An exhaustive search was conducted by Pubmed, Google Scholar and Connected Papers using keywords relating to the genetics, genomics and artificial intelligence in prostate cancer, it includes “biomarkers”, “non-coding RNAs”, “lncRNAs”, “microRNAs”, “repetitive sequence”, “prognosis”, “prediction”, “whole-genome sequencing”, “RNA-Seq”, “transcriptome”, “machine learning”, and “deep learning”.

Results

New advances, including the search for changes in novel biomarkers such as mRNAs, microRNAs, lncRNAs, and repetitive sequences, are expected to contribute to an earlier and accurate diagnosis for each patient in the context of precision medicine, thus improving the prognosis and quality of life of patients. We analyze several aspects that are relevant for prostate cancer including its new molecular markers associated with diagnosis, prognosis, and prediction to therapy and how bioinformatic approaches such as machine learning and deep learning can contribute to clinic. Furthermore, we also include current techniques that will allow an earlier diagnosis, such as Spatial Transcriptomics, Exome Sequencing, and Whole-Genome Sequencing.

Conclusion

Transcriptomic and genomic analysis have contributed to generate knowledge in the field of prostate carcinogenesis, new information about coding and non-coding genes as biomarkers has emerged. Synergies created by the implementation of artificial intelligence to analyze and understand sequencing data have allowed the development of clinical strategies that facilitate decision-making and improve personalized management in prostate cancer.

The impact of medical cyber–physical systems on healthcare service delivery

Purpose

The pandemic has reinforced the need for revamping the healthcare service delivery systems around the world to meet the increased challenges of modern-day illnesses. The use of medical cyber–physical system (MCPS) in the healthcare is one of the means of transforming the landscape of the traditional healthcare service delivery system. The purpose of this study is to critically examine the impact of MCPS on the quality of healthcare service delivery.

Design/methodology/approach

This paper uses an evidence-based approach, the authors have conducted a systematic literature review to study the impact of MCPS on healthcare service delivery. Fifty-four articles were thematically examined to study the impact of MCPS on eight characteristics of the healthcare service delivery proposed by the world health organisation.

Findings

The study proposes support that MCPS will positively impact (1) comprehensiveness, (2) accessibility, (3) coverage, (4) continuity, (5) quality, (6) person-centredness, (7) coordination, (8) accountability and (9) efficiency dimension of the healthcare service delivery. The study further draws nine propositions to support the impact of MCPS on the healthcare service delivery.

Practical implications

This study can be used by stakeholders as a guide point while using MCPS in healthcare service delivery systems. Besides, healthcare managers can use this study to understand the performance of their healthcare system. This study can further be used for designing effective strategies for deploying MCPS to be effective and efficient in each of the dimensions of healthcare service delivery.

Originality/value

The previous studies have focussed on technology aspects of MCPS and none of them critically analysed the impact on healthcare service delivery. This is the first literature review carried out to understand the impact of MCPS on the nine dimensions of healthcare service delivery proposed by WHO. This study provides improved thematic awareness of the resulting body of knowledge, allowing the field of MCPS and healthcare service delivery to progress in a more informed and multidisciplinary manner.

AlzEye: longitudinal record-level linkage of ophthalmic imaging and hospital admissions of 353 157 patients in London, UK

PURPOSE

Retinal signatures of systemic disease ('oculomics') are increasingly being revealed through a combination of high-resolution ophthalmic imaging and sophisticated modelling strategies. Progress is currently limited not mainly by technical issues, but by the lack of large labelled datasets, a sine qua non for deep learning. Such data are derived from prospective epidemiological studies, in which retinal imaging is typically unimodal, cross-sectional, of modest number and relates to cohorts, which are not enriched with subpopulations of interest, such as those with systemic disease. We thus linked longitudinal multimodal retinal imaging from routinely collected National Health Service (NHS) data with systemic disease data from hospital admissions using a privacy-by-design third-party linkage approach.

PARTICIPANTS

Between 1 January 2008 and 1 April 2018, 353 157 participants aged 40 years or older, who attended Moorfields Eye Hospital NHS Foundation Trust, a tertiary ophthalmic institution incorporating a principal central site, four district hubs and five satellite clinics in and around London, UK serving a catchment population of approximately six million people.

FINDINGS TO DATE

Among the 353 157 individuals, 186 651 had a total of 1 337 711 Hospital Episode Statistics admitted patient care episodes. Systemic diagnoses recorded at these episodes include 12 022 patients with myocardial infarction, 11 735 with all-cause stroke and 13 363 with all-cause dementia. A total of 6 261 931 retinal images of seven different modalities and across three manufacturers were acquired from 1 54 830 patients. The majority of retinal images were retinal photographs (n=1 874 175) followed by optical coherence tomography (n=1 567 358).

FUTURE PLANS

AlzEye combines the world's largest single institution retinal imaging database with nationally collected systemic data to create an exceptional large-scale, enriched cohort that reflects the diversity of the population served. First analyses will address cardiovascular diseases and dementia, with a view to identifying hidden retinal signatures that may lead to earlier detection and risk management of these life-threatening conditions.

Epicardial and pericardial fat analysis on CT images and artificial intelligence: a literature review

The present review summarizes the available evidence on artificial intelligence (AI) algorithms aimed to the segmentation of epicardial and pericardial adipose tissues on computed tomography (CT) images. Body composition imaging is a novel concept based on quantitative analysis of body tissues. Manual segmentation of medical images allows to obtain quantitative and qualitative data on several tissues including epicardial and pericardial fat. However, since manual segmentation requires a considerable amount of time, the analysis of adipose tissue compartments based on AI has been proposed as an automatic, reliable, accurate and fast tool. The literature research was performed on March 2021 using MEDLINE PubMed Central and "adipose tissue artificial intelligence", "adipose tissue deep learning" or "adipose tissue machine learning" as keywords for articles search. Relevant articles concerning epicardial adipose tissue, pericardial adipose tissue and AI were selected. The evaluation of adipose tissue compartments can provide additional information on the pathogenesis and prognosis of several diseases, including cardiovascular. AI can assist physicians to obtain important information, possibly improving the patient's quality of life and identifying patients at risk of developing variable disorders.

An Optimized Machine Learning Model Accurately Predicts In-Hospital Outcomes at Admission to a Cardiac Unit

Risk stratification at the time of hospital admission is of paramount significance in triaging the patients and providing timely care. In the present study, we aim at predicting multiple clinical outcomes using the data recorded during admission to a cardiac care unit via an optimized machine learning method. This study involves a total of 11,498 patients admitted to a cardiac care unit over two years. Patient demographics, admission type (emergency or outpatient), patient history, lab tests, and comorbidities were used to predict various outcomes. We employed a fully connected neural network architecture and optimized the models for various subsets of input features. Using 10-fold cross-validation, our optimized machine learning model predicted mortality with a mean area under the receiver operating characteristic curve (AUC) of 0.967 (95% confidence interval (CI): 0.963–0.972), heart failure AUC of 0.838 (CI: 0.825–0.851), ST-segment elevation myocardial infarction AUC of 0.832 (CI: 0.821–0.842), pulmonary embolism AUC of 0.802 (CI: 0.764–0.84), and estimated the duration of stay (DOS) with a mean absolute error of 2.543 days (CI: 2.499–2.586) of data with a mean and median DOS of 6.35 and 5.0 days, respectively. Further, we objectively quantified the importance of each feature and its correlation with the clinical assessment of the corresponding outcome. The proposed method accurately predicts various cardiac outcomes and can be used as a clinical decision support system to provide timely care and optimize hospital resources.

Sleep apnea phenotyping and relationship to disease in a large clinical biobank

Objective

Sleep apnea is associated with a broad range of pathophysiology. While electronic health record (EHR) information has the potential for revealing relationships between sleep apnea and associated risk factors and outcomes, practical challenges hinder its use. Our objectives were to develop a sleep apnea phenotyping algorithm that improves the precision of EHR case/control information using natural language processing (NLP); identify novel associations between sleep apnea and comorbidities in a large clinical biobank; and investigate the relationship between polysomnography statistics and comorbid disease using NLP phenotyping.

Materials and Methods

We performed clinical chart reviews on 300 participants putatively diagnosed with sleep apnea and applied International Classification of Sleep Disorders criteria to classify true cases and noncases. We evaluated 2 NLP and diagnosis code-only methods for their abilities to maximize phenotyping precision. The lead algorithm was used to identify incident and cross-sectional associations between sleep apnea and common comorbidities using 4876 NLP-defined sleep apnea cases and 3× matched controls.

Results

The optimal NLP phenotyping strategy had improved model precision (≥0.943) compared to the use of one diagnosis code (≤0.733). Of the tested diseases, 170 disorders had significant incidence odds ratios (ORs) between cases and controls, 8 of which were confirmed using polysomnography (n = 4544), and 281 disorders had significant prevalence OR between sleep apnea cases versus controls, 41 of which were confirmed using polysomnography data.

Discussion and Conclusion

An NLP-informed algorithm can improve the accuracy of case-control sleep apnea ascertainment and thus improve the performance of phenome-wide, genetic, and other EHR analyses of a highly prevalent disorder.

Sleep apnea is a common disease in which breathing partially or completely pauses during sleep, leading to less oxygen in the blood, repeated awakenings, and increased risk of developing multiple diseases. Current studies of sleep apnea often have relatively few participants due to the challenge of performing overnight sleep recordings. Electronic health record (EHR) billing code diagnoses of sleep apnea could be repurposed to increase the size of research studies, but the accuracy of the diagnoses is reduced. We developed a reusable algorithm that improves the accuracy of EHR sleep apnea diagnoses using natural language processing to extract information from clinical notes. As a proof of concept, we used the algorithm to identify hundreds of diseases that are increased among participants with sleep apnea compared to similar patients without sleep apnea. Many of these disease relationships with sleep apnea have not been previously recognized. This improved algorithm will help to accelerate future large-scale investigations of the causes and consequences of sleep apnea.

Infectious diseases among elderly persons: Results from a population-based observational study in Shandong province, China, 2013-2017

Background

The health of the elderly is one of the major challenges in today's ageing society. However, research on infectious diseases among the elderly is limited. This study aimed to describe the epidemiological characteristics and dynamics of infectious diseases among the elderly population aged ≥60 years in Shandong province, China.

Methods

Incidence data for infectious diseases were collected from the Shandong Multi-Center Healthcare Big Data Platform from January 2013 to June 2017, which involved 550 432 elderly persons. We compared the incidence of each infectious disease and disease category, stratified by age, gender, and region. Annual percentage change (APC) was estimated using logarithmic linear regression to examine the incidence trends. Poisson regression was conducted to identify the effect of demographic factors on incidence, with incidence rate ratio (IRR) and their 95% confidence intervals (CIs) estimated.

Results

A total of 27 595 cases of 102 infectious diseases were reported during the study period, with an overall incidence of 1425.51/100 000 person-years. The most common infectious diseases were respiratory and mucocutaneous diseases among the elderly persons, with annual increases of 17.45% and 20.44%, respectively (both P<0.05). In rural areas, the incidence of respiratory, gastrointestinal, blood- and sex-transmitted, and mucocutaneous infections increased significantly, with APCs of 178.52%, 204.66%, 28.24%, 63.01%, respectively (all P<0.05). Elderly males had a higher risk of infections than that of females, with the highest IRRa of 2.94 (95% confidence interval (CI) = 2.89, 3.00) in respiratory diseases. The elderly aged 85-89 years had a much higher risk of respiratory diseases than those aged 60-64 years (IRRa = 9.85, 95%CI: 9.39, 10.33); however, the risk of blood- and sex-transmitted diseases was highest among the elderly aged 65-69 years (IRRa = 1.24, 95% CI = 1.06, 1.45).

Conclusions

Ageing population are facing a substantial challenge on infectious diseases. More attention should be paid to infections with significant growth. Targeted strategies and measures on elderly persons in different regions and subgroups are urgently needed.

A Smart Healthcare Knowledge Service Framework for Hierarchical Medical Treatment System

This paper reveals the research hotspots and development directions of case-based reasoning in the field of health care, and proposes the framework and key technologies of medical knowledge service systems based on case-based reasoning (CBR) in the big data environment. The 2124 articles on medical CBR in the Web of Science were visualized and analyzed using a bibliometrics method, and a CBR-based knowledge service system framework was constructed in the medical Internet of all people, things and data resources environment. An intelligent construction method for the clinical medical case base and the gray case knowledge reasoning model were proposed. A cloud-edge collaboration knowledge service system was developed and applied in a pilot project. Compared with other diagnostic tools, the system provides case-based explanations for its predicted results, making it easier for physicians to understand and accept, so that they can make better decisions. The results show that the system has good interpretability, has better acceptance than the common intelligent decision support system, and strongly supports physician auxiliary diagnosis and treatment as well as clinical teaching.

Multi-omic analysis in injured humans: Patterns align with outcomes and treatment responses

Trauma is a leading cause of death and morbidity worldwide. Here, we present the analysis of a longitudinal multi-omic dataset comprising clinical, cytokine, endotheliopathy biomarker, lipidome, metabolome, and proteome data from severely injured humans. A "systemic storm" pattern with release of 1,061 markers, together with a pattern suggestive of the "massive consumption" of 892 constitutive circulating markers, is identified in the acute phase post-trauma. Data integration reveals two human injury response endotypes, which align with clinical trajectory. Prehospital thawed plasma rescues only endotype 2 patients with traumatic brain injury (30-day mortality: 30.3 versus 75.0%; p = 0.0015). Ubiquitin carboxy-terminal hydrolase L1 (UCHL1) was identified as the most predictive circulating biomarker to identify endotype 2-traumatic brain injury (TBI) patients. These response patterns refine the paradigm for human injury, while the datasets provide a resource for the study of critical illness, trauma, and human stress responses.

Estimating heritability of glycaemic response to metformin using nationwide electronic health records and population-sized pedigree

Background

Variability of response to medication is a well-known phenomenon, determined by both environmental and genetic factors. Understanding the heritable component of the response to medication is of great interest but challenging due to several reasons, including small study cohorts and computational limitations.

Methods

Here, we study the heritability of variation in the glycaemic response to metformin, first-line therapeutic agent for type 2 diabetes (T2D), by leveraging 18 years of electronic health records (EHR) data from Israel’s largest healthcare service provider, consisting of over five million patients of diverse ethnicities and socio-economic background. Our cohort consists of 80,788 T2D patients treated with metformin, with an accumulated number of 1,611,591 HbA1C measurements and 4,581,097 metformin prescriptions. We estimate the explained variance of glycated hemoglobin (HbA1c%) reduction due to inheritance by constructing a six-generation population-size pedigree from national registries and linking it to medical health records.

Results

Using Linear Mixed Model-based framework, a common-practice method for heritability estimation, we calculate a heritability measure of \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${h}^{2}=12.6 \%$$\end{document}h2=12.6% (95% CI, \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$6.1 \%\! -\!19.1 \%$$\end{document}6.1%−19.1%) for absolute reduction of HbA1c% after metformin treatment in the entire cohort, \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${h}^{2}=21.0 \%$$\end{document}h2=21.0% (95% CI, \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$7.8 \%\! -\!34.4 \%$$\end{document}7.8%−34.4%) for males and \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${h}^{2}=22.9 \%$$\end{document}h2=22.9% (95% CI, \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$10.0 \%\! -\!35.7 \%$$\end{document}10.0%−35.7%) in females. Results remain unchanged after adjusting for pre-treatment HbA1c%, and in proportional reduction of HbA1c%.

Conclusions

To the best of our knowledge, our work is the first to estimate heritability of drug response using solely EHR data combining a pedigree-based kinship matrix. We demonstrate that while response to metformin treatment has a heritable component, most of the variation is likely due to other factors, further motivating non-genetic analyses aimed at unraveling metformin’s action mechanism.

Individuals in a population might respond differently to the same medication and this phenomenon is commonly attributed to either genes or the environment. Here, we studied the familial aspects of the response to metformin, a medication used in the treatment of type 2 diabetes. We combined information from 18 years of medical records identifying newly treated patients with type 2 diabetes with information about how the trait was inherited within their families. We calculated a metric that tells us how well differences in people’s genes account for differences in their traits, and demonstrate that although the difference in response to metformin is in part explained by the genes people with type 2 diabetes inherit, most of it is not explained by genes. This finding contributes to a better understanding of differences in metformin response and might help inform treatment in future.

Kalka and Gavrieli et al. assessed the heritability of variation in the glycaemic response to metformin by leveraging electronic health records data gathered from a large cohort of patients with diabetes and combining it with pedigree information. The authors show that although the variability in this response has a heritable component, most of it is likely non-genetic.

How can we discover the most valuable types of big data and artificial intelligence-based solutions? A methodology for the efficient development of the underlying analytics that improve care

BACKGROUND

Much has been invested in big data and artificial intelligence-based solutions for healthcare. However, few applications have been implemented in clinical practice. Early economic evaluations can help to improve decision-making by developers of analytics underlying these solutions aiming to increase the likelihood of successful implementation, but recommendations about their use are lacking. The aim of this study was to develop and apply a framework that positions best practice methods for economic evaluations alongside development of analytics, thereby enabling developers to identify barriers to success and to select analytics worth further investments.

METHODS

The framework was developed using literature, recommendations for economic evaluations and by applying the framework to use cases (chronic lymphocytic leukaemia (CLL), intensive care, diabetes). First, the feasibility of developing clinically relevant analytics was assessed and critical barriers to successful development and implementation identified. Economic evaluations were then used to determine critical thresholds and guide investment decisions.

RESULTS

When using the framework to assist decision-making of developers of analytics, continuing development was not always feasible or worthwhile. Developing analytics for progressive CLL and diabetes was clinically relevant but not feasible with the data available. Alternatively, developing analytics for newly diagnosed CLL patients was feasible but continuing development was not considered worthwhile because the high drug costs made it economically unattractive for potential users. Alternatively, in the intensive care unit, analytics reduced mortality and per-patient costs when used to identify infections (- 0.5%, - €886) and to improve patient-ventilator interaction (- 3%, - €264). Both analytics have the potential to save money but the potential benefits of analytics that identify infections strongly depend on infection rate; a higher rate implies greater cost-savings.

CONCLUSIONS

We present a framework that stimulates efficiency of development of analytics for big data and artificial intelligence-based solutions by selecting those applications of analytics for which development is feasible and worthwhile. For these applications, results from early economic evaluations can be used to guide investment decisions and identify critical requirements.

A Versatile, Secure, and Sustainable All-in-One Biobank-Registry Data Solution: The A3BC REDCap Model

Introduction: A key element in the big data revolution is large-scale biobanking and the associated development of high-quality data collections and supporting informatics solutions. As such, in establishing the Australian Arthritis and Autoimmune Biobank Collaborative (A3BC), we sought to establish a low-cost, nation-scale data management system capable of managing a multisite biobank registry with complex longitudinal sample and data requirements. Materials and Methods: We assessed several international commercial and nonprofit software platforms using standardized system requirement criteria and follow-up interviews. Vendor compliance scoring was prioritized to meet our project-critical requirements. Consumer/end-user codesign was integral to refining our system requirements for optimized adoption. Customization of the selected software solution was performed to optimize field auto-population between participant timepoints and forms, using modules that are transferable and that do not impact core code. Institutional and independent testing was used to ensure data security. Results: We selected the widely used research web application Research Electronic Data Capture (REDCap), which is "free" (under nonprofit license agreement terms), highly configurable, and customizable to a variety of biobank and registry needs and can be developed/maintained by biobank users with modest IT skill, time, and cost. We created a secure, comprehensive participant-centric biobank-registry database that includes: (1) best practice data security measures (incl. multisite access login using institutional user credentials), (2) permission-to-contact and dynamic itemized electronic consent, (3) a complete chain of custody from consent to longitudinal biospecimen data collection to publication, (4) complex longitudinal patient-reported surveys, (5) integration of record-level extracted/linked participant data, (6) significant form auto-population for streamlined data capture, and (7) native dashboards for operational visualizations. Conclusion: We recommend the versatile, reusable, and sustainable informatics model we have developed in REDCap for prospective chronic disease biobanks or registry biobanks (of local to national complexity) supporting holistic research into disease prediction, precision medicine, and prevention strategies.

The Role of Machine Learning in Cardiovascular Pathology

Machine learning has seen slow but steady uptake in diagnostic pathology over the past decade to assess digital whole-slide images. Machine learning tools have incredible potential to standardise, and likely even improve, histopathologic diagnoses, but they are not yet widely used in clinical practice. We describe the principles of these tools and technologies and some successful preclinical and pretranslational efforts in cardiovascular pathology, as well as a roadmap for moving forward. In nonhuman animal models, one proof-of-principle application is in rodent progressive cardiomyopathy, which is of particular significance to drug toxicity studies. Basic science successes include screening the quality of differentiated stem cells and characterising cardiomyocyte developmental stages, with potential applications for research and toxicology/drug safety screening using derived or native human pluripotent stem cells differentiated into cardiomyocytes. Translational studies of particular note include those with success in diagnosing the various forms of heart allograft rejection. For fully realising the value of these tools in clinical cardiovascular pathology, we identify 3 essential challenges. First is image quality standardisation to ensure that algorithms can be developed and implemented on robust, consistent data. The second is consensus diagnosis; experts don't always agree, and thus "truth" may be difficult to establish, but the algorithms themselves may provide a solution. The third is the need for large-enough data sets to facilitate robust algorithm development, necessitating large cross-institutional shared image databases. The power of histopathology-based machine learning technologies is tremendous, and we outline the next steps needed to capitalise on this power.

Dynamic prediction of renal survival among deeply phenotyped kidney transplant recipients using artificial intelligence: an observational, international, multicohort study

BACKGROUND

Kidney allograft failure is a common cause of end-stage renal disease. We aimed to develop a dynamic artificial intelligence approach to enhance risk stratification for kidney transplant recipients by generating continuously refined predictions of survival using updates of clinical data.

METHODS

In this observational study, we used data from adult recipients of kidney transplants from 18 academic transplant centres in Europe, the USA, and South America, and a cohort of patients from six randomised controlled trials. The development cohort comprised patients from four centres in France, with all other patients included in external validation cohorts. To build deeply phenotyped cohorts of transplant recipients, the following data were collected in the development cohort: clinical, histological, immunological variables, and repeated measurements of estimated glomerular filtration rate (eGFR) and proteinuria (measured using the proteinuria to creatininuria ratio). To develop a dynamic prediction system based on these clinical assessments and repeated measurements, we used a Bayesian joint models-an artificial intelligence approach. The prediction performances of the model were assessed via discrimination, through calculation of the area under the receiver operator curve (AUC), and calibration. This study is registered with ClinicalTrials.gov, NCT04258891.

FINDINGS

13 608 patients were included (3774 in the development cohort and 9834 in the external validation cohorts) and contributed 89 328 patient-years of data, and 416 510 eGFR and proteinuria measurements. Bayesian joint models showed that recipient immunological profile, allograft interstitial fibrosis and tubular atrophy, allograft inflammation, and repeated measurements of eGFR and proteinuria were independent risk factors for allograft survival. The final model showed accurate calibration and very high discrimination in the development cohort (overall dynamic AUC 0·857 [95% CI 0·847-0·866]) with a persistent improvement in AUCs for each new repeated measurement (from 0·780 [0·768-0·794] to 0·926 [0·917-0·932]; p<0·0001). The predictive performance was confirmed in the external validation cohorts from Europe (overall AUC 0·845 [0·837-0·854]), the USA (overall AUC 0·820 [0·808-0·831]), South America (overall AUC 0·868 [0·856-0·880]), and the cohort of patients from randomised controlled trials (overall AUC 0·857 [0·840-0·875]).

INTERPRETATION

Because of its dynamic design, this model can be continuously updated and holds value as a bedside tool that could refine the prognostic judgements of clinicians in everyday practice, hence enhancing precision medicine in the transplant setting.

FUNDING

MSD Avenir, French National Institute for Health and Medical Research, and Bettencourt Schueller Foundation.

Computational approaches leveraging integrated connections of multi-omic data toward clinical applications

In line with the advances in high-throughput technologies, multiple omic datasets have accumulated to study biological systems and diseases coherently. No single omics data type is capable of fully representing cellular activity. The complexity of the biological processes arises from the interactions between omic entities such as genes, proteins, and metabolites. Therefore, multi-omic data integration is crucial but challenging. The impact of the molecular alterations in multi-omic data is not local in the neighborhood of the altered gene or protein; rather, the impact diffuses in the network and changes the functionality of multiple signaling pathways and regulation of the gene expression. Additionally, multi-omic data is high-dimensional and has background noise. Several integrative approaches have been developed to accurately interpret the multi-omic datasets, including machine learning, network-based methods, and their combination. In this review, we overview the most recent integrative approaches and tools with a focus on network-based methods. We then discuss these approaches according to their specific applications, from disease-network and biomarker identification to patient stratification, drug discovery, and repurposing.

Retrospective analysis and time series forecasting with automated machine learning of ascariasis, enterobiasis and cystic echinococcosis in Romania

The epidemiology of neglected tropical diseases (NTD) is persistently underprioritized, despite NTD being widespread among the poorest populations and in the least developed countries on earth. This situation necessitates thorough and efficient public health intervention. Romania is at the brink of becoming a developed country. However, this South-Eastern European country appears to be a region that is susceptible to an underestimated burden of parasitic diseases despite recent public health reforms. Moreover, there is an evident lack of new epidemiologic data on NTD after Romania's accession to the European Union (EU) in 2007. Using the national ICD-10 dataset for hospitalized patients in Romania, we generated time series datasets for 2008-2018. The objective was to gain deep understanding of the epidemiological distribution of three selected and highly endemic parasitic diseases, namely, ascariasis, enterobiasis and cystic echinococcosis (CE), during this period and forecast their courses for the ensuing two years. Through descriptive and inferential analysis, we observed a decline in case numbers for all three NTD. Several distributional particularities at regional level emerged. Furthermore, we performed predictions using a novel automated time series (AutoTS) machine learning tool and could interestingly show a stable course for these parasitic NTD. Such predictions can help public health officials and medical organizations to implement targeted disease prevention and control. To our knowledge, this is the first study involving a retrospective analysis of ascariasis, enterobiasis and CE on a nationwide scale in Romania. It is also the first to use AutoTS technology for parasitic NTD.

Multiple additive regression trees with hybrid loss for classification tasks across heterogeneous clinical data in distributed environments: a case study

Multiple additive regression trees (MART) have been widely used in the literature for various classification tasks. However, the overfitting effects of MART across heterogeneous and highly imbalanced big data structures within distributed environments has not yet been investigated. In this work, we utilize distributed MART with hybrid loss to resolve overfitting effects during the training of disease classification models in a case study with 10 heterogeneous and distributed clinical datasets. Lexical and semantic analysis methods were utilized to match heterogeneous terminologies with 80% overlap. Data augmentation was used to resolve class imbalance yielding virtual data with goodness of fit 0.01 and correlation difference 0.02. Our results highlight the favorable performance of the proposed distributed MART on the augmented data with an average increase by 7.3% in the accuracy, 6.8% in sensitivity, 10.4% in specificity, for a specific loss function topology.

Unraveling the Immunopathogenesis and Genetic Variants in Vasculitis Toward Development of Personalized Medicine

Leukocytoclastic vasculitis (LCV) is a systemic autoimmune disease characterized by the inflammation of the vascular endothelium. Cutaneous small vessel vasculitis (CSVV) and anti-neutrophil cytoplasmic antibodies (ANCA)-associated vasculitis (AAV) are two examples of LCV. Advancements in genomic technologies have identified risk haplotypes, genetic variants, susceptibility loci and pathways that are associated with vasculitis immunopathogenesis. The discovery of these genetic factors and their corresponding cellular signaling aberrations have enabled the development and use of novel therapeutic strategies for vasculitis. Personalized medicine aims to provide targeted therapies to individuals who show poor response to conventional interventions. For example, monoclonal antibody therapies have shown remarkable efficacy in achieving disease remission. Here, we discuss pathways involved in disease pathogenesis and the underlying genetic associations in different populations worldwide. Understanding the immunopathogenic pathways in vasculitis and identifying associated genetic variations will facilitate the development of novel and targeted personalized therapies for patients.

Machine learning models for decision support in epilepsy management: A critical review

PURPOSE

There remain major challenges for the clinician in managing patients with epilepsy effectively. Choosing anti-seizure medications (ASMs) is subject to trial and error. About one-third of patients have drug-resistant epilepsy (DRE). Surgery may be considered for selected patients, but time from diagnosis to surgery averages 20 years. We reviewed the potential use of machine learning (ML) predictive models as clinical decision support tools to help address some of these issues.

METHODS

We conducted a comprehensive search of Medline and Embase of studies that investigated the application of ML in epilepsy management in terms of predicting ASM responsiveness, predicting DRE, identifying surgical candidates, and predicting epilepsy surgery outcomes. Original articles addressing these 4 areas published in English between 2000 and 2020 were included.

RESULTS

We identified 24 relevant articles: 6 on ASM responsiveness, 3 on DRE prediction, 2 on identifying surgical candidates, and 13 on predicting surgical outcomes. A variety of potential predictors were used including clinical, neuropsychological, imaging, electroencephalography, and health system claims data. A number of different ML algorithms and approaches were used for prediction, but only one study utilized deep learning methods. Some models show promising performance with areas under the curve above 0.9. However, most were single setting studies (18 of 24) with small sample sizes (median number of patients 55), with the exception of 3 studies that utilized large databases and 3 studies that performed external validation. There was a lack of standardization in reporting model performance. None of the models reviewed have been prospectively evaluated for their clinical benefits.

CONCLUSION

The utility of ML models for clinical decision support in epilepsy management remains to be determined. Future research should be directed toward conducting larger studies with external validation, standardization of reporting, and prospective evaluation of the ML model on patient outcomes.

Big Data in Nephrology

A huge array of data in nephrology is collected through patient registries, large epidemiological studies, electronic health records, administrative claims, clinical trial repositories, mobile health devices and molecular databases. Application of these big data, particularly using machine-learning algorithms, provides a unique opportunity to obtain novel insights into kidney diseases, facilitate personalized medicine and improve patient care. Efforts to make large volumes of data freely accessible to the scientific community, increased awareness of the importance of data sharing and the availability of advanced computing algorithms will facilitate the use of big data in nephrology. However, challenges exist in accessing, harmonizing and integrating datasets in different formats from disparate sources, improving data quality and ensuring that data are secure and the rights and privacy of patients and research participants are protected. In addition, the optimism for data-driven breakthroughs in medicine is tempered by scepticism about the accuracy of calibration and prediction from in silico techniques. Machine-learning algorithms designed to study kidney health and diseases must be able to handle the nuances of this specialty, must adapt as medical practice continually evolves, and must have global and prospective applicability for external and future datasets.

Federated learning for predicting clinical outcomes in patients with COVID-19

Federated learning (FL) is a method used for training artificial intelligence models with data from multiple sources while maintaining data anonymity, thus removing many barriers to data sharing. Here we used data from 20 institutes across the globe to train a FL model, called EXAM (electronic medical record (EMR) chest X-ray AI model), that predicts the future oxygen requirements of symptomatic patients with COVID-19 using inputs of vital signs, laboratory data and chest X-rays. EXAM achieved an average area under the curve (AUC) >0.92 for predicting outcomes at 24 and 72 h from the time of initial presentation to the emergency room, and it provided 16% improvement in average AUC measured across all participating sites and an average increase in generalizability of 38% when compared with models trained at a single site using that site's data. For prediction of mechanical ventilation treatment or death at 24 h at the largest independent test site, EXAM achieved a sensitivity of 0.950 and specificity of 0.882. In this study, FL facilitated rapid data science collaboration without data exchange and generated a model that generalized across heterogeneous, unharmonized datasets for prediction of clinical outcomes in patients with COVID-19, setting the stage for the broader use of FL in healthcare.

Gut Microbiota and Neuroplasticity

The accumulating evidence linking bacteria in the gut and neurons in the brain (the microbiota-gut-brain axis) has led to a paradigm shift in the neurosciences. Understanding the neurobiological mechanisms supporting the relevance of actions mediated by the gut microbiota for brain physiology and neuronal functioning is a key research area. In this review, we discuss the literature showing how the microbiota is emerging as a key regulator of the brain's function and behavior, as increasing amounts of evidence on the importance of the bidirectional communication between the intestinal bacteria and the brain have accumulated. Based on recent discoveries, we suggest that the interaction between diet and the gut microbiota, which might ultimately affect the brain, represents an unprecedented stimulus for conducting new research that links food and mood. We also review the limited work in the clinical arena to date, and we propose novel approaches for deciphering the gut microbiota-brain axis and, eventually, for manipulating this relationship to boost mental wellness.

NICEdrug.ch, a workflow for rational drug design and systems-level analysis of drug metabolism

The discovery of a drug requires over a decade of intensive research and financial investments - and still has a high risk of failure. To reduce this burden, we developed the NICEdrug.ch resource, which incorporates 250,000 bioactive molecules, and studied their enzymatic metabolic targets, fate, and toxicity. NICEdrug.ch includes a unique fingerprint that identifies reactive similarities between drug-drug and drug-metabolite pairs. We validated the application, scope, and performance of NICEdrug.ch over similar methods in the field on golden standard datasets describing drugs and metabolites sharing reactivity, drug toxicities, and drug targets. We use NICEdrug.ch to evaluate inhibition and toxicity by the anticancer drug 5-fluorouracil, and suggest avenues to alleviate its side effects. We propose shikimate 3-phosphate for targeting liver-stage malaria with minimal impact on the human host cell. Finally, NICEdrug.ch suggests over 1300 candidate drugs and food molecules to target COVID-19 and explains their inhibitory mechanism for further experimental screening. The NICEdrug.ch database is accessible online to systematically identify the reactivity of small molecules and druggable enzymes with practical applications in lead discovery and drug repurposing.

Remove obstacles to sharing health data with researchers outside of the European Union

COVID-19 has shown that international collaborations and global data sharing are essential for health research, but legal obstacles are preventing data sharing for non–pandemic-related research among public researchers across the world, with potentially damaging effects for citizens and patients.

Cloud Computing Enabled Big Multi-Omics Data Analytics

High-throughput experiments enable researchers to explore complex multifactorial diseases through large-scale analysis of omics data. Challenges for such high-dimensional data sets include storage, analyses, and sharing. Recent innovations in computational technologies and approaches, especially in cloud computing, offer a promising, low-cost, and highly flexible solution in the bioinformatics domain. Cloud computing is rapidly proving increasingly useful in molecular modeling, omics data analytics (eg, RNA sequencing, metabolomics, or proteomics data sets), and for the integration, analysis, and interpretation of phenotypic data. We review the adoption of advanced cloud-based and big data technologies for processing and analyzing omics data and provide insights into state-of-the-art cloud bioinformatics applications.

Deep learning methods for biomedical named entity recognition: a survey and qualitative comparison

The biomedical literature is growing rapidly, and the extraction of meaningful information from the large amount of literature is increasingly important. Biomedical named entity (BioNE) identification is one of the critical and fundamental tasks in biomedical text mining. Accurate identification of entities in the literature facilitates the performance of other tasks. Given that an end-to-end neural network can automatically extract features, several deep learning-based methods have been proposed for BioNE recognition (BioNER), yielding state-of-the-art performance. In this review, we comprehensively summarize deep learning-based methods for BioNER and datasets used in training and testing. The deep learning methods are classified into four categories: single neural network-based, multitask learning-based, transfer learning-based and hybrid model-based methods. They can be applied to BioNER in multiple domains, and the results are determined by the dataset size and type. Lastly, we discuss the future development and opportunities of BioNER methods.

Artificial intelligence and the medical physics profession - A Swedish perspective

BACKGROUND

There is a continuous and dynamic discussion on artificial intelligence (AI) in present-day society. AI is expected to impact on healthcare processes and could contribute to a more sustainable use of resources allocated to healthcare in the future. The aim for this work was to establish a foundation for a Swedish perspective on the potential effect of AI on the medical physics profession.

MATERIALS AND METHODS

We designed a survey to gauge viewpoints regarding AI in the Swedish medical physics community. Based on the survey results and present-day situation in Sweden, a SWOT analysis was performed on the implications of AI for the medical physics profession.

RESULTS

Out of 411 survey recipients, 163 responded (40%). The Swedish medical physicists with a professional license believed (90%) that AI would change the practice of medical physics but did not foresee (81%) that AI would pose a risk to their practice and career. The respondents were largely positive to the inclusion of AI in educational programmes. According to self-assessment, the respondents' knowledge of and workplace preparedness for AI was generally low.

CONCLUSIONS

From the survey and SWOT analysis we conclude that AI will change the medical physics profession and that there are opportunities for the profession associated with the adoption of AI in healthcare. To overcome the weakness of limited AI knowledge, potentially threatening the role of medical physicists, and build upon the strong position in Swedish healthcare, medical physics education and training should include learning objectives on AI.

The Role of FER rs4957796 in the Risk of Developing and Dying from a Bloodstream Infection: A 23-Year Follow-up of the Population-based Nord-Trøndelag Health Study

BACKGROUND

Bloodstream infection and sepsis are major causes of health loss worldwide, and it is important to identify patients at risk of developing and dying from these conditions. The single-nucleotide polymorphism most strongly associated with sepsis mortality is FER rs4957796. However, it is not known how this variant is associated with bloodstream infection incidence and mortality.

METHODS

We used prospective data from 1995-2017 from the population-based HUNT Study. Genotypes were ascertained from blood samples, and additional genotypes were imputed. Information on bloodstream infection and diagnosis codes at hospitalization were collected through record linkage with all hospitals in the area.

RESULTS

A total of 69 294 patients were included. Patients with the rs4957796 CC genotype had an increased risk of developing a bloodstream infection compared with the TT genotype (hazard ratio [HR], 1.20; 95% confidence interval [CI], 1.00-1.43). However, there was a protective additive effect of the C allele in terms of mortality in the total study population (HR, 0.77; 95% CI, .64-.92 per copy of the C allele) and among bloodstream infection patients (odds ratio, 0.70; 95% CI, .58-.85 per copy of the C allele). The results did not appear to be affected by selection bias.

CONCLUSIONS

The rs4957796 CC genotype was associated with an increased risk of contracting a bloodstream infection but with a reduced risk of dying from one. The latter finding is in line with studies of sepsis case fatality, while the former expands our understanding of the immunoregulatory role of this polymorphism.

Development and validation of prediction models for mechanical ventilation, renal replacement therapy, and readmission in COVID-19 patients

OBJECTIVE

Coronavirus disease 2019 (COVID-19) patients are at risk for resource-intensive outcomes including mechanical ventilation (MV), renal replacement therapy (RRT), and readmission. Accurate outcome prognostication could facilitate hospital resource allocation. We develop and validate predictive models for each outcome using retrospective electronic health record data for COVID-19 patients treated between March 2 and May 6, 2020.

MATERIALS AND METHODS

For each outcome, we trained 3 classes of prediction models using clinical data for a cohort of SARS-CoV-2 (severe acute respiratory syndrome coronavirus 2)-positive patients (n = 2256). Cross-validation was used to select the best-performing models per the areas under the receiver-operating characteristic and precision-recall curves. Models were validated using a held-out cohort (n = 855). We measured each model's calibration and evaluated feature importances to interpret model output.

RESULTS

The predictive performance for our selected models on the held-out cohort was as follows: area under the receiver-operating characteristic curve-MV 0.743 (95% CI, 0.682-0.812), RRT 0.847 (95% CI, 0.772-0.936), readmission 0.871 (95% CI, 0.830-0.917); area under the precision-recall curve-MV 0.137 (95% CI, 0.047-0.175), RRT 0.325 (95% CI, 0.117-0.497), readmission 0.504 (95% CI, 0.388-0.604). Predictions were well calibrated, and the most important features within each model were consistent with clinical intuition.

DISCUSSION

Our models produce performant, well-calibrated, and interpretable predictions for COVID-19 patients at risk for the target outcomes. They demonstrate the potential to accurately estimate outcome prognosis in resource-constrained care sites managing COVID-19 patients.

CONCLUSIONS

We develop and validate prognostic models targeting MV, RRT, and readmission for hospitalized COVID-19 patients which produce accurate, interpretable predictions. Additional external validation studies are needed to further verify the generalizability of our results.

Improving early diagnosis of rare diseases using Natural Language Processing in unstructured medical records: an illustration from Dravet syndrome

Background

The growing use of Electronic Health Records (EHRs) is promoting the application of data mining in health-care. A promising use of big data in this field is to develop models to support early diagnosis and to establish natural history. Dravet Syndrome (DS) is a rare developmental and epileptic encephalopathy that commonly initiates in the first year of life with febrile seizures (FS). Age at diagnosis is often delayed after 2 years, as it is difficult to differentiate DS at onset from FS. We aimed to explore if some clinical terms (concepts) are significantly more used in the electronic narrative medical reports of individuals with DS before the age of 2 years compared to those of individuals with FS. These concepts would allow an earlier detection of patients with DS resulting in an earlier orientation toward expert centers that can provide early diagnosis and care.

Methods

Data were collected from the Necker Enfants Malades Hospital using a document-based data warehouse, Dr Warehouse, which employs Natural Language Processing, a computer technology consisting in processing written information. Using Unified Medical Language System Meta-thesaurus, phenotype concepts can be recognized in medical reports. We selected individuals with DS (DS Cohort) and individuals with FS (FS Cohort) with confirmed diagnosis after the age of 4 years. A phenome-wide analysis was performed evaluating the statistical associations between the phenotypes of DS and FS, based on concepts found in the reports produced before 2 years and using a series of logistic regressions.

Results

We found significative higher representation of concepts related to seizures’ phenotypes distinguishing DS from FS in the first phases, namely the major recurrence of complex febrile convulsions (long-lasting and/or with focal signs) and other seizure-types. Some typical early onset non-seizure concepts also emerged, in relation to neurodevelopment and gait disorders.

Conclusions

Narrative medical reports of individuals younger than 2 years with FS contain specific concepts linked to DS diagnosis, which can be automatically detected by software exploiting NLP. This approach could represent an innovative and sustainable methodology to decrease time of diagnosis of DS and could be transposed to other rare diseases.

Digital Technology-Based Telemedicine for the COVID-19 Pandemic

In the year 2020, the coronavirus disease 2019 (COVID-19) crisis intersected with the development and maturation of several digital technologies including the internet of things (IoT) with next-generation 5G networks, artificial intelligence (AI) that uses deep learning, big data analytics, and blockchain and robotic technology, which has resulted in an unprecedented opportunity for the progress of telemedicine. Digital technology-based telemedicine platform has currently been established in many countries, incorporated into clinical workflow with four modes, including "many to one" mode, "one to many" mode, "consultation" mode, and "practical operation" mode, and has shown to be feasible, effective, and efficient in sharing epidemiological data, enabling direct interactions among healthcare providers or patients across distance, minimizing the risk of disease infection, improving the quality of patient care, and preserving healthcare resources. In this state-of-the-art review, we gain insight into the potential benefits of demonstrating telemedicine in the context of a huge health crisis by summarizing the literature related to the use of digital technologies in telemedicine applications. We also outline several new strategies for supporting the use of telemedicine at scale.

A machine learning based exploration of COVID-19 mortality risk

Early prediction of patient mortality risks during a pandemic can decrease mortality by assuring efficient resource allocation and treatment planning. This study aimed to develop and compare prognosis prediction machine learning models based on invasive laboratory and noninvasive clinical and demographic data from patients' day of admission. Three Support Vector Machine (SVM) models were developed and compared using invasive, non-invasive, and both groups. The results suggested that non-invasive features could provide mortality predictions that are similar to the invasive and roughly on par with the joint model. Feature inspection results from SVM-RFE and sparsity analysis displayed that, compared with the invasive model, the non-invasive model can provide better performances with a fewer number of features, pointing to the presence of high predictive information contents in several non-invasive features, including SPO2, age, and cardiovascular disorders. Furthermore, while the invasive model was able to provide better mortality predictions for the imminent future, non-invasive features displayed better performance for more distant expiration intervals. Early mortality prediction using non-invasive models can give us insights as to where and with whom to intervene. Combined with novel technologies, such as wireless wearable devices, these models can create powerful frameworks for various medical assignments and patient triage.