Deep Patient: An Unsupervised Representation to Predict the Future of Patients from the Electronic Health Records

From hype to reality: data science enabling personalized medicine

BACKGROUND

Personalized, precision, P4, or stratified medicine is understood as a medical approach in which patients are stratified based on their disease subtype, risk, prognosis, or treatment response using specialized diagnostic tests. The key idea is to base medical decisions on individual patient characteristics, including molecular and behavioral biomarkers, rather than on population averages. Personalized medicine is deeply connected to and dependent on data science, specifically machine learning (often named Artificial Intelligence in the mainstream media). While during recent years there has been a lot of enthusiasm about the potential of 'big data' and machine learning-based solutions, there exist only few examples that impact current clinical practice. The lack of impact on clinical practice can largely be attributed to insufficient performance of predictive models, difficulties to interpret complex model predictions, and lack of validation via prospective clinical trials that demonstrate a clear benefit compared to the standard of care. In this paper, we review the potential of state-of-the-art data science approaches for personalized medicine, discuss open challenges, and highlight directions that may help to overcome them in the future.

CONCLUSIONS

There is a need for an interdisciplinary effort, including data scientists, physicians, patient advocates, regulatory agencies, and health insurance organizations. Partially unrealistic expectations and concerns about data science-based solutions need to be better managed. In parallel, computational methods must advance more to provide direct benefit to clinical practice.

Deep Learning and Radiomics predict complete response after neo-adjuvant chemoradiation for locally advanced rectal cancer

Treatment of locally advanced rectal cancer involves chemoradiation, followed by total mesorectum excision. Complete response after chemoradiation is an accurate surrogate for long-term local control. Predicting complete response from pre-treatment features could represent a major step towards conservative treatment. Patients with a T2-4 N0-1 rectal adenocarcinoma treated between June 2010 and October 2016 with neo-adjuvant chemoradiation from three academic institutions were included. All clinical and treatment data was integrated in our clinical data warehouse, from which we extracted the features. Radiomics features were extracted from the tumor volume from the treatment planning CT Scan. A Deep Neural Network (DNN) was created to predict complete response, as a methodological proof-of-principle. The results were compared to a baseline Linear Regression model using only the TNM stage as a predictor and a second model created with Support Vector Machine on the same features used in the DNN. Ninety-five patients were included in the final analysis. There were 49 males (52%) and 46 females (48%). Median tumour size was 48 mm (15-130). Twenty-two patients (23%) had pathologic complete response after chemoradiation. One thousand six hundred eighty-three radiomics features were extracted. The DNN predicted complete response with an 80% accuracy, which was better than the Linear Regression model (69.5%) and the SVM model (71.58%). Our model correctly predicted complete response after neo-adjuvant rectal chemoradiotherapy in 80% of the patients of this multicenter cohort. Our results may help to identify patients who would benefit from a conservative treatment, rather than a radical resection.

Deep Learning in Biomedical Data Science

Since the 1980s, deep learning and biomedical data have been coevolving and feeding each other. The breadth, complexity, and rapidly expanding size of biomedical data have stimulated the development of novel deep learning methods, and application of these methods to biomedical data have led to scientific discoveries and practical solutions. This overview provides technical and historical pointers to the field, and surveys current applications of deep learning to biomedical data organized around five subareas, roughly of increasing spatial scale: chemoinformatics, proteomics, genomics and transcriptomics, biomedical imaging, and health care. The black box problem of deep learning methods is also briefly discussed.

Approaches to Medical Decision-Making Based on Big Clinical Data

The paper discusses different approaches to building a medical decision support system based on big data. The authors sought to abstain from any data reduction and apply universal teaching and big data processing methods independent of disease classification standards. The paper assesses and compares the accuracy of recommendations among three options: case-based reasoning, simple single-layer neural network, and probabilistic neural network. Further, the paper substantiates the assumption regarding the most efficient approach to solving the specified problem.

Patient representation learning and interpretable evaluation using clinical notes

We have three contributions in this work: 1. We explore the utility of a stacked denoising autoencoder and a paragraph vector model to learn task-independent dense patient representations directly from clinical notes. To analyze if these representations are transferable across tasks, we evaluate them in multiple supervised setups to predict patient mortality, primary diagnostic and procedural category, and gender. We compare their performance with sparse representations obtained from a bag-of-words model. We observe that the learned generalized representations significantly outperform the sparse representations when we have few positive instances to learn from, and there is an absence of strong lexical features. 2. We compare the model performance of the feature set constructed from a bag of words to that obtained from medical concepts. In the latter case, concepts represent problems, treatments, and tests. We find that concept identification does not improve the classification performance. 3. We propose novel techniques to facilitate model interpretability. To understand and interpret the representations, we explore the best encoded features within the patient representations obtained from the autoencoder model. Further, we calculate feature sensitivity across two networks to identify the most significant input features for different classification tasks when we use these pretrained representations as the supervised input. We successfully extract the most influential features for the pipeline using this technique.

Probabilistic Prognostic Estimates of Survival in Metastatic Cancer Patients (PPES-Met) Utilizing Free-Text Clinical Narratives

We propose a deep learning model - Probabilistic Prognostic Estimates of Survival in Metastatic Cancer Patients (PPES-Met) for estimating short-term life expectancy (>3 months) of the patients by analyzing free-text clinical notes in the electronic medical record, while maintaining the temporal visit sequence. In a single framework, we integrated semantic data mapping and neural embedding technique to produce a text processing method that extracts relevant information from heterogeneous types of clinical notes in an unsupervised manner, and we designed a recurrent neural network to model the temporal dependency of the patient visits. The model was trained on a large dataset (10,293 patients) and validated on a separated dataset (1818 patients). Our method achieved an area under the ROC curve (AUC) of 0.89. To provide explain-ability, we developed an interactive graphical tool that may improve physician understanding of the basis for the model's predictions. The high accuracy and explain-ability of the PPES-Met model may enable our model to be used as a decision support tool to personalize metastatic cancer treatment and provide valuable assistance to the physicians.

Landmark Models for Optimizing the Use of Repeated Measurements of Risk Factors in Electronic Health Records to Predict Future Disease Risk

The benefits of using electronic health records (EHRs) for disease risk screening and personalized health-care decisions are being increasingly recognized. Here we present a computationally feasible statistical approach with which to address the methodological challenges involved in utilizing historical repeat measures of multiple risk factors recorded in EHRs to systematically identify patients at high risk of future disease. The approach is principally based on a 2-stage dynamic landmark model. The first stage estimates current risk factor values from all available historical repeat risk factor measurements via landmark-age-specific multivariate linear mixed-effects models with correlated random intercepts, which account for sporadically recorded repeat measures, unobserved data, and measurement errors. The second stage predicts future disease risk from a sex-stratified Cox proportional hazards model, with estimated current risk factor values from the first stage. We exemplify these methods by developing and validating a dynamic 10-year cardiovascular disease risk prediction model using primary-care EHRs for age, diabetes status, hypertension treatment, smoking status, systolic blood pressure, total cholesterol, and high-density lipoprotein cholesterol in 41,373 persons from 10 primary-care practices in England and Wales contributing to The Health Improvement Network (1997-2016). Using cross-validation, the model was well-calibrated (Brier score = 0.041, 95% confidence interval: 0.039, 0.042) and had good discrimination (C-index = 0.768, 95% confidence interval: 0.759, 0.777).

Advances in Electronic Phenotyping: From Rule-Based Definitions to Machine Learning Models

With the widespread adoption of electronic health records (EHRs), large repositories of structured and unstructured patient data are becoming available to conduct observational studies. Finding patients with specific conditions or outcomes, known as phenotyping, is one of the most fundamental research problems encountered when using these new EHR data. Phenotyping forms the basis of translational research, comparative effectiveness studies, clinical decision support, and population health analyses using routinely collected EHR data. We review the evolution of electronic phenotyping, from the early rule-based methods to the cutting edge of supervised and unsupervised machine learning models. We aim to cover the most influential papers in commensurate detail, with a focus on both methodology and implementation. Finally, future research directions are explored.

Current Applications and Future Impact of Machine Learning in Radiology

Recent advances and future perspectives of machine learning techniques offer promising applications in medical imaging. Machine learning has the potential to improve different steps of the radiology workflow including order scheduling and triage, clinical decision support systems, detection and interpretation of findings, postprocessing and dose estimation, examination quality control, and radiology reporting. In this article, the authors review examples of current applications of machine learning and artificial intelligence techniques in diagnostic radiology. In addition, the future impact and natural extension of these techniques in radiology practice are discussed.

Using Neural Networks with Routine Health Records to Identify Suicide Risk: Feasibility Study

BACKGROUND

Each year, approximately 800,000 people die by suicide worldwide, accounting for 1-2 in every 100 deaths. It is always a tragic event with a huge impact on family, friends, the community and health professionals. Unfortunately, suicide prevention and the development of risk assessment tools have been hindered by the complexity of the underlying mechanisms and the dynamic nature of a person's motivation and intent. Many of those who die by suicide had contact with health services in the preceding year but identifying those most at risk remains a challenge.

OBJECTIVE

To explore the feasibility of using artificial neural networks with routinely collected electronic health records to support the identification of those at high risk of suicide when in contact with health services.

METHODS

Using the Secure Anonymised Information Linkage Databank UK, we extracted the data of those who died by suicide between 2001 and 2015 and paired controls. Looking at primary (general practice) and secondary (hospital admissions) electronic health records, we built a binary feature vector coding the presence of risk factors at different times prior to death. Risk factors included: general practice contact and hospital admission; diagnosis of mental health issues; injury and poisoning; substance misuse; maltreatment; sleep disorders; and the prescription of opiates and psychotropics. Basic artificial neural networks were trained to differentiate between the suicide cases and paired controls. We interpreted the output score as the estimated suicide risk. System performance was assessed with 10x10-fold repeated cross-validation, and its behavior was studied by representing the distribution of estimated risk across the cases and controls, and the distribution of factors across estimated risks.

RESULTS

We extracted a total of 2604 suicide cases and 20 paired controls per case. Our best system attained a mean error rate of 26.78% (SD 1.46; 64.57% of sensitivity and 81.86% of specificity). While the distribution of controls was concentrated around estimated risks < 0.5, cases were almost uniformly distributed between 0 and 1. Prescription of psychotropics, depression and anxiety, and self-harm increased the estimated risk by ~0.4. At least 95% of those presenting these factors were identified as suicide cases.

CONCLUSIONS

Despite the simplicity of the implemented system, the proposed methodology obtained an accuracy like other published methods based on specialized questionnaire generated data. Most of the errors came from the heterogeneity of patterns shown by suicide cases, some of which were identical to those of the paired controls. Prescription of psychotropics, depression and anxiety, and self-harm were strongly linked with higher estimated risk scores, followed by hospital admission and long-term drug and alcohol misuse. Other risk factors like sleep disorders and maltreatment had more complex effects.

Predictive Modeling of the Progression of Alzheimer's Disease with Recurrent Neural Networks

The number of service visits of Alzheimer's disease (AD) patients is different from each other and their visit time intervals are non-uniform. Although the literature has revealed many approaches in disease progression modeling, they fail to leverage these time-relevant part of patients' medical records in predicting disease's future status. This paper investigates how to predict the AD progression for a patient's next medical visit through leveraging heterogeneous medical data. Data provided by the National Alzheimer's Coordinating Center includes 5432 patients with probable AD from August 31, 2005 to May 25, 2017. Long short-term memory recurrent neural networks (RNN) are adopted. The approach relies on an enhanced "many-to-one" RNN architecture to support the shift of time steps. Hence, the approach can deal with patients' various numbers of visits and uneven time intervals. The results show that the proposed approach can be utilized to predict patients' AD progressions on their next visits with over 99% accuracy, significantly outperforming classic baseline methods. This study confirms that RNN can effectively solve the AD progression prediction problem by fully leveraging the inherent temporal and medical patterns derived from patients' historical visits. More promisingly, the approach can be customarily applied to other chronic disease progression problems.

Patient similarity for precision medicine: A systematic review

Evidence-based medicine is the most prevalent paradigm adopted by physicians. Clinical practice guidelines typically define a set of recommendations together with eligibility criteria that restrict their applicability to a specific group of patients. The ever-growing size and availability of health-related data is currently challenging the broad definitions of guideline-defined patient groups. Precision medicine leverages on genetic, phenotypic, or psychosocial characteristics to provide precise identification of patient subsets for treatment targeting. Defining a patient similarity measure is thus an essential step to allow stratification of patients into clinically-meaningful subgroups. The present review investigates the use of patient similarity as a tool to enable precision medicine. 279 articles were analyzed along four dimensions: data types considered, clinical domains of application, data analysis methods, and translational stage of findings. Cancer-related research employing molecular profiling and standard data analysis techniques such as clustering constitute the majority of the retrieved studies. Chronic and psychiatric diseases follow as the second most represented clinical domains. Interestingly, almost one quarter of the studies analyzed presented a novel methodology, with the most advanced employing data integration strategies and being portable to different clinical domains. Integration of such techniques into decision support systems constitutes and interesting trend for future research.

Survey on deep learning for radiotherapy

More than 50% of cancer patients are treated with radiotherapy, either exclusively or in combination with other methods. The planning and delivery of radiotherapy treatment is a complex process, but can now be greatly facilitated by artificial intelligence technology. Deep learning is the fastest-growing field in artificial intelligence and has been successfully used in recent years in many domains, including medicine. In this article, we first explain the concept of deep learning, addressing it in the broader context of machine learning. The most common network architectures are presented, with a more specific focus on convolutional neural networks. We then present a review of the published works on deep learning methods that can be applied to radiotherapy, which are classified into seven categories related to the patient workflow, and can provide some insights of potential future applications. We have attempted to make this paper accessible to both radiotherapy and deep learning communities, and hope that it will inspire new collaborations between these two communities to develop dedicated radiotherapy applications.

Predicting the Reasons of Customer Complaints: A First Step Toward Anticipating Quality Issues of In Vitro Diagnostics Assays with Machine Learning

Background

Vendors in the health care industry produce diagnostic systems that, through a secured connection, allow them to monitor performance almost in real time. However, challenges exist in analyzing and interpreting large volumes of noisy quality control (QC) data. As a result, some QC shifts may not be detected early enough by the vendor, but lead a customer to complain.

Objective

The aim of this study was to hypothesize that a more proactive response could be designed by utilizing the collected QC data more efficiently. Our aim is therefore to help prevent customer complaints by predicting them based on the QC data collected by in vitro diagnostic systems.

Methods

QC data from five select in vitro diagnostic assays were combined with the corresponding database of customer complaints over a period of 90 days. A subset of these data over the last 45 days was also analyzed to assess how the length of the training period affects predictions. We defined a set of features used to train two classifiers, one based on decision trees and the other based on adaptive boosting, and assessed model performance by cross-validation.

Results

The cross-validations showed classification error rates close to zero for some assays with adaptive boosting when predicting the potential cause of customer complaints. Performance was improved by shortening the training period when the volume of complaints increased. Denoising filters that reduced the number of categories to predict further improved performance, as their application simplified the prediction problem.

Conclusions

This novel approach to predicting customer complaints based on QC data may allow the diagnostic industry, the expected end user of our approach, to proactively identify potential product quality issues and fix these before receiving customer complaints. This represents a new step in the direction of using big data toward product quality improvement.

Advancing Predictive Hepatotoxicity at the Intersection of Experimental, in Silico, and Artificial Intelligence Technologies

Adverse drug reactions, particularly those that result in drug-induced liver injury (DILI), are a major cause of drug failure in clinical trials and drug withdrawals. Hepatotoxicity-mediated drug attrition occurs despite substantial investments of time and money in developing cellular assays, animal models, and computational models to predict its occurrence in humans. Underperformance in predicting hepatotoxicity associated with drugs and drug candidates has been attributed to existing gaps in our understanding of the mechanisms involved in driving hepatic injury after these compounds perfuse and are metabolized by the liver. Herein we assess in vitro, in vivo (animal), and in silico strategies used to develop predictive DILI models. We address the effectiveness of several two- and three-dimensional in vitro cellular methods that are frequently employed in hepatotoxicity screens and how they can be used to predict DILI in humans. We also explore how humanized animal models can recapitulate human drug metabolic profiles and associated liver injury. Finally, we highlight the maturation of computational methods for predicting hepatotoxicity, the untapped potential of artificial intelligence for improving in silico DILI screens, and how knowledge acquired from these predictions can shape the refinement of experimental methods.

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.

Scalable and accurate deep learning with electronic health records

Predictive modeling with electronic health record (EHR) data is anticipated to drive personalized medicine and improve healthcare quality. Constructing predictive statistical models typically requires extraction of curated predictor variables from normalized EHR data, a labor-intensive process that discards the vast majority of information in each patient's record. We propose a representation of patients' entire raw EHR records based on the Fast Healthcare Interoperability Resources (FHIR) format. We demonstrate that deep learning methods using this representation are capable of accurately predicting multiple medical events from multiple centers without site-specific data harmonization. We validated our approach using de-identified EHR data from two US academic medical centers with 216,221 adult patients hospitalized for at least 24 h. In the sequential format we propose, this volume of EHR data unrolled into a total of 46,864,534,945 data points, including clinical notes. Deep learning models achieved high accuracy for tasks such as predicting: in-hospital mortality (area under the receiver operator curve [AUROC] across sites 0.93-0.94), 30-day unplanned readmission (AUROC 0.75-0.76), prolonged length of stay (AUROC 0.85-0.86), and all of a patient's final discharge diagnoses (frequency-weighted AUROC 0.90). These models outperformed traditional, clinically-used predictive models in all cases. We believe that this approach can be used to create accurate and scalable predictions for a variety of clinical scenarios. In a case study of a particular prediction, we demonstrate that neural networks can be used to identify relevant information from the patient's chart.

Deep learning in pharmacogenomics: from gene regulation to patient stratification

This Perspective provides examples of current and future applications of deep learning in pharmacogenomics, including: identification of novel regulatory variants located in noncoding domains of the genome and their function as applied to pharmacoepigenomics; patient stratification from medical records; and the mechanistic prediction of drug response, targets and their interactions. Deep learning encapsulates a family of machine learning algorithms that has transformed many important subfields of artificial intelligence over the last decade, and has demonstrated breakthrough performance improvements on a wide range of tasks in biomedicine. We anticipate that in the future, deep learning will be widely used to predict personalized drug response and optimize medication selection and dosing, using knowledge extracted from large and complex molecular, epidemiological, clinical and demographic datasets.

Biomedical Informatics on the Cloud: A Treasure Hunt for Advancing Cardiovascular Medicine

In the digital age of cardiovascular medicine, the rate of biomedical discovery can be greatly accelerated by the guidance and resources required to unearth potential collections of knowledge. A unified computational platform leverages metadata to not only provide direction but also empower researchers to mine a wealth of biomedical information and forge novel mechanistic insights. This review takes the opportunity to present an overview of the cloud-based computational environment, including the functional roles of metadata, the architecture schema of indexing and search, and the practical scenarios of machine learning-supported molecular signature extraction. By introducing several established resources and state-of-the-art workflows, we share with our readers a broadly defined informatics framework to phenotype cardiovascular health and disease.

EMR-based medical knowledge representation and inference via Markov random fields and distributed representation learning

OBJECTIVE

Electronic medical records (EMRs) contain medical knowledge that can be used for clinical decision support (CDS). Our objective is to develop a general system that can extract and represent knowledge contained in EMRs to support three CDS tasks-test recommendation, initial diagnosis, and treatment plan recommendation-given the condition of a patient.

METHODS

We extracted four kinds of medical entities from records and constructed an EMR-based medical knowledge network (EMKN), in which nodes are entities and edges reflect their co-occurrence in a record. Three bipartite subgraphs (bigraphs) were extracted from the EMKN, one to support each task. One part of the bigraph was the given condition (e.g., symptoms), and the other was the condition to be inferred (e.g., diseases). Each bigraph was regarded as a Markov random field (MRF) to support the inference. We proposed three graph-based energy functions and three likelihood-based energy functions. Two of these functions are based on knowledge representation learning and can provide distributed representations of medical entities. Two EMR datasets and three metrics were utilized to evaluate the performance.

RESULTS

As a whole, the evaluation results indicate that the proposed system outperformed the baseline methods. The distributed representation of medical entities does reflect similarity relationships with respect to knowledge level.

CONCLUSION

Combining EMKN and MRF is an effective approach for general medical knowledge representation and inference. Different tasks, however, require individually designed energy functions.

Deep Learning Solutions for Classifying Patients on Opioid Use

Opioid analgesics, as commonly prescribed medications used for relieving pain in patients, are especially prevalent in US these years. However, an increasing amount of opioid misuse and abuse have caused lots of consequences. Researchers and clinicians have attempted to discover the factors leading to opioid long-term use, dependence, and abuse, but only limited incidents are understood from previous works. Motivated by recent successes of deep learning and the abundant amount of electronic health records, we apply state-of-the-art deep and recurrent neural network models on a dataset of more than one hundred thousand opioid users. Our models are shown to achieve robust and superior results on classifying opioid users, and are able to extract key factors for different opioid user groups. This work is also a good demonstration on adopting novel deep learning methods for real-world health care problems.

Opportunities and obstacles for deep learning in biology and medicine

Deep learning describes a class of machine learning algorithms that are capable of combining raw inputs into layers of intermediate features. These algorithms have recently shown impressive results across a variety of domains. Biology and medicine are data-rich disciplines, but the data are complex and often ill-understood. Hence, deep learning techniques may be particularly well suited to solve problems of these fields. We examine applications of deep learning to a variety of biomedical problems-patient classification, fundamental biological processes and treatment of patients-and discuss whether deep learning will be able to transform these tasks or if the biomedical sphere poses unique challenges. Following from an extensive literature review, we find that deep learning has yet to revolutionize biomedicine or definitively resolve any of the most pressing challenges in the field, but promising advances have been made on the prior state of the art. Even though improvements over previous baselines have been modest in general, the recent progress indicates that deep learning methods will provide valuable means for speeding up or aiding human investigation. Though progress has been made linking a specific neural network's prediction to input features, understanding how users should interpret these models to make testable hypotheses about the system under study remains an open challenge. Furthermore, the limited amount of labelled data for training presents problems in some domains, as do legal and privacy constraints on work with sensitive health records. Nonetheless, we foresee deep learning enabling changes at both bench and bedside with the potential to transform several areas of biology and medicine.

Deep Learning-Based Multi-Omics Integration Robustly Predicts Survival in Liver Cancer

Identifying robust survival subgroups of hepatocellular carcinoma (HCC) will significantly improve patient care. Currently, endeavor of integrating multi-omics data to explicitly predict HCC survival from multiple patient cohorts is lacking. To fill this gap, we present a deep learning (DL)-based model on HCC that robustly differentiates survival subpopulations of patients in six cohorts. We built the DL-based, survival-sensitive model on 360 HCC patients' data using RNA sequencing (RNA-Seq), miRNA sequencing (miRNA-Seq), and methylation data from The Cancer Genome Atlas (TCGA), which predicts prognosis as good as an alternative model where genomics and clinical data are both considered. This DL-based model provides two optimal subgroups of patients with significant survival differences (P = 7.13e-6) and good model fitness [concordance index (C-index) = 0.68]. More aggressive subtype is associated with frequent TP53 inactivation mutations, higher expression of stemness markers (KRT19 and EPCAM) and tumor marker BIRC5, and activated Wnt and Akt signaling pathways. We validated this multi-omics model on five external datasets of various omics types: LIRI-JP cohort (n = 230, C-index = 0.75), NCI cohort (n = 221, C-index = 0.67), Chinese cohort (n = 166, C-index = 0.69), E-TABM-36 cohort (n = 40, C-index = 0.77), and Hawaiian cohort (n = 27, C-index = 0.82). This is the first study to employ DL to identify multi-omics features linked to the differential survival of patients with HCC. Given its robustness over multiple cohorts, we expect this workflow to be useful at predicting HCC prognosis prediction. Clin Cancer Res; 24(6); 1248-59. ©2017 AACR.

High-fidelity phenotyping: richness and freedom from bias

Electronic health record phenotyping is the use of raw electronic health record data to assert characterizations about patients. Researchers have been doing it since the beginning of biomedical informatics, under different names. Phenotyping will benefit from an increasing focus on fidelity, both in the sense of increasing richness, such as measured levels, degree or severity, timing, probability, or conceptual relationships, and in the sense of reducing bias. Research agendas should shift from merely improving binary assignment to studying and improving richer representations. The field is actively researching new temporal directions and abstract representations, including deep learning. The field would benefit from research in nonlinear dynamics, in combining mechanistic models with empirical data, including data assimilation, and in topology. The health care process produces substantial bias, and studying that bias explicitly rather than treating it as merely another source of noise would facilitate addressing it.

A risk score including body mass index, glycated haemoglobin and triglycerides predicts future glycaemic control in people with type 2 diabetes

AIM

To identify, predict and validate distinct glycaemic trajectories among patients with newly diagnosed type 2 diabetes treated in primary care, as a first step towards more effective patient-centred care.

METHODS

We conducted a retrospective study in two cohorts, using routinely collected individual patient data from primary care practices obtained from two large Dutch diabetes patient registries. Participants included adult patients newly diagnosed with type 2 diabetes between January 2006 and December 2014 (development cohort, n = 10 528; validation cohort, n = 3777). Latent growth mixture modelling identified distinct glycaemic 5-year trajectories. Machine learning models were built to predict the trajectories using easily obtainable patient characteristics in daily clinical practice.

RESULTS

Three different glycaemic trajectories were identified: (1) stable, adequate glycaemic control (76.5% of patients); (2) improved glycaemic control (21.3% of patients); and (3) deteriorated glycaemic control (2.2% of patients). Similar trajectories could be discerned in the validation cohort. Body mass index and glycated haemoglobin and triglyceride levels were the most important predictors of trajectory membership. The predictive model, trained on the development cohort, had a receiver-operating characteristic area under the curve of 0.96 in the validation cohort, indicating excellent accuracy.

CONCLUSIONS

The developed model can effectively explain heterogeneity in future glycaemic response of patients with type 2 diabetes. It can therefore be used in clinical practice as a quick and easy tool to provide tailored diabetes care.

Big data and medical research in China

Luxia Zhang and colleagues discuss the development of big data in Chinese healthcare and the opportunities for its use in medical research

Machine Learning Approaches for Clinical Psychology and Psychiatry

Machine learning approaches for clinical psychology and psychiatry explicitly focus on learning statistical functions from multidimensional data sets to make generalizable predictions about individuals. The goal of this review is to provide an accessible understanding of why this approach is important for future practice given its potential to augment decisions associated with the diagnosis, prognosis, and treatment of people suffering from mental illness using clinical and biological data. To this end, the limitations of current statistical paradigms in mental health research are critiqued, and an introduction is provided to critical machine learning methods used in clinical studies. A selective literature review is then presented aiming to reinforce the usefulness of machine learning methods and provide evidence of their potential. In the context of promising initial results, the current limitations of machine learning approaches are addressed, and considerations for future clinical translation are outlined.

Evolutionary ARMS Race: Antimalarial Resistance Molecular Surveillance

Molecular surveillance of antimalarial drug resistance markers has become an important part of resistance detection and containment. In the current climate of multidrug resistance, including resistance to the global front-line drug artemisinin, there is a consensus to upscale molecular surveillance. The most salient limitation to current surveillance efforts is that skill and infrastructure requirements preclude many regions. This includes sub-Saharan Africa, where Plasmodium falciparum is responsible for most of the global malaria disease burden. New molecular and data technologies have emerged with an emphasis on accessibility. These may allow surveillance to be conducted in broad settings where it is most needed, including at the primary healthcare level in endemic countries, and extending to the village health worker.

[Not Available]

Zusammenfassung. Machine Learning (ML) ist ein aktives Forschungsgebiet in den Informationswissenschaften und hat unseren Alltag in den vergangenen Jahren bereits merklich verändert. Mit fortschreitender Entwicklung sind die neuesten Algorithmen imstande, immer komplexere Aufgaben zu übernehmen. Im vorliegenden Mini-Review beschreiben wir einige Grundlagen des ML und zeigen anhand praxisorienterter Beispiele, wie es in den nächsten Jahren Einzug in die klinische Routine halten könnte.

Automated disease cohort selection using word embeddings from Electronic Health Records

Accurate and robust cohort definition is critical to biomedical discovery using Electronic Health Records (EHR). Similar to prospective study designs, high quality EHR-based research requires rigorous selection criteria to designate case/control status particular to each disease. Electronic phenotyping algorithms, which are manually built and validated per disease, have been successful in filling this need. However, these approaches are time-consuming, leading to only a relatively small amount of algorithms for diseases developed. Methodologies that automatically learn features from EHRs have been used for cohort selection as well. To date, however, there has been no systematic analysis of how these methods perform against current gold standards. Accordingly, this paper compares the performance of a state-of-the-art automated feature learning method to extracting research-grade cohorts for five diseases against their established electronic phenotyping algorithms. In particular, we use word2vec to create unsupervised embeddings of the phenotype space within an EHR system. Using medical concepts as a query, we then rank patients by their proximity in the embedding space and automatically extract putative disease cohorts via a distance threshold. Experimental evaluation shows promising results with average F-score of 0.57 and AUC-ROC of 0.98. However, we noticed that results varied considerably between diseases, thus necessitating further investigation and/or phenotype-specific refinement of the approach before being readily deployed across all diseases.

Progress in non-invasive detection of liver fibrosis

Liver fibrosis is an important pathological precondition for hepatocellular carcinoma. The degree of hepatic fibrosis is positively correlated with liver cancer. Liver fibrosis is a series of pathological and physiological process related to liver cell necrosis and degeneration after chronic liver injury, which finally leads to extracellular matrix and collagen deposition. The early detection and precise staging of fibrosis and cirrhosis are very important for early diagnosis and timely initiation of appropriate therapeutic regimens. The risk of severe liver fibrosis finally progressing to liver carcinoma is >50%. It is known that biopsy is the gold standard for the diagnosis and staging of liver fibrosis. However, this method has some limitations, such as the potential for pain, sampling variability, and low patient acceptance. Furthermore, the necessity of obtaining a tissue diagnosis of liver fibrosis still remains controversial. An increasing number of reliable non-invasive approaches are now available that are widely applied in clinical practice, mostly in cases of viral hepatitis, resulting in a significantly decreased need for liver biopsy. In fact, the non-invasive detection and evaluation of liver cirrhosis now has good accuracy due to current serum markers, ultrasound imaging, and magnetic resonance imaging quantification techniques. A prominent advantage of the non-invasive detection and assessment of liver fibrosis is that liver fibrosis can be monitored repeatedly and easily in the same patient. Serum biomarkers have the advantages of high applicability (>95%) and good reproducibility. However, their results can be influenced by different patient conditions because none of these markers are liver-specific. The most promising techniques appear to be transient elastography and magnetic resonance elastography because they provide reliable results for the detection of fibrosis in the advanced stages, and future developments promise to increase the reliability and accuracy of the staging of hepatic fibrosis. This article aims to describe the recent progress in the development of non-invasive assessment methods for the staging of liver fibrosis, with a special emphasize on computer-aided quantitative and deep learning methods.

Leveraging uncertainty information from deep neural networks for disease detection

Deep learning (DL) has revolutionized the field of computer vision and image processing. In medical imaging, algorithmic solutions based on DL have been shown to achieve high performance on tasks that previously required medical experts. However, DL-based solutions for disease detection have been proposed without methods to quantify and control their uncertainty in a decision. In contrast, a physician knows whether she is uncertain about a case and will consult more experienced colleagues if needed. Here we evaluate drop-out based Bayesian uncertainty measures for DL in diagnosing diabetic retinopathy (DR) from fundus images and show that it captures uncertainty better than straightforward alternatives. Furthermore, we show that uncertainty informed decision referral can improve diagnostic performance. Experiments across different networks, tasks and datasets show robust generalization. Depending on network capacity and task/dataset difficulty, we surpass 85% sensitivity and 80% specificity as recommended by the NHS when referring 0−20% of the most uncertain decisions for further inspection. We analyse causes of uncertainty by relating intuitions from 2D visualizations to the high-dimensional image space. While uncertainty is sensitive to clinically relevant cases, sensitivity to unfamiliar data samples is task dependent, but can be rendered more robust.

Flexible, cluster-based analysis of the electronic medical record of sepsis with composite mixture models

The widespread adoption of electronic medical records (EMRs) in healthcare has provided vast new amounts of data for statistical machine learning researchers in their efforts to model and predict patient health status, potentially enabling novel advances in treatment. In the case of sepsis, a debilitating, dysregulated host response to infection, extracting subtle, uncataloged clinical phenotypes from the EMR with statistical machine learning methods has the potential to impact patient diagnosis and treatment early in the course of their hospitalization. However, there are significant barriers that must be overcome to extract these insights from EMR data. First, EMR datasets consist of both static and dynamic observations of discrete and continuous-valued variables, many of which may be missing, precluding the application of standard multivariate analysis techniques. Second, clinical populations observed via EMRs and relevant to the study and management of conditions like sepsis are often heterogeneous; properly accounting for this heterogeneity is critical. Here, we describe an unsupervised, probabilistic framework called a composite mixture model that can simultaneously accommodate the wide variety of observations frequently observed in EMR datasets, characterize heterogeneous clinical populations, and handle missing observations. We demonstrate the efficacy of our approach on a large-scale sepsis cohort, developing novel techniques built on our model-based clusters to track patient mortality risk over time and identify physiological trends and distinct subgroups of the dataset associated with elevated risk of mortality during hospitalization.

Predicting age by mining electronic medical records with deep learning characterizes differences between chronological and physiological age

Determining the discrepancy between chronological and physiological age of patients is central to preventative and personalized care. Electronic medical records (EMR) provide rich information about the patient physiological state, but it is unclear whether such information can be predictive of chronological age. Here we present a deep learning model that uses vital signs and lab tests contained within the EMR of Mount Sinai Health System (MSHS) to predict chronological age. The model is trained on 377,686 EMR from patients of ages 18-85 years old. The discrepancy between the predicted and real chronological age is then used as a proxy to estimate physiological age. Overall, the model can predict the chronological age of patients with a standard deviation error of ∼7 years. The ages of the youngest and oldest patients were more accurately predicted, while patients of ages ranging between 40 and 60 years were the least accurately predicted. Patients with the largest discrepancy between their physiological and chronological age were further inspected. The patients predicted to be significantly older than their chronological age have higher systolic blood pressure, higher cholesterol, damaged liver, and anemia. In contrast, patients predicted to be younger than their chronological age have lower blood pressure and shorter stature among other indicators; both groups display lower weight than the population average. Using information from ∼10,000 patients from the entire cohort who have been also profiled with SNP arrays, genome-wide association study (GWAS) uncovers several novel genetic variants associated with aging. In particular, significant variants were mapped to genes known to be associated with inflammation, hypertension, lipid metabolism, height, and increased lifespan in mice. Several genes with missense mutations were identified as novel candidate aging genes. In conclusion, we demonstrate how EMR data can be used to assess overall health via a scale that is based on deviation from the patient's predicted chronological age.

Electronic Health Record Driven Prediction for Gestational Diabetes Mellitus in Early Pregnancy

Gestational diabetes mellitus (GDM) is conventionally confirmed with oral glucose tolerance test (OGTT) in 24 to 28 weeks of gestation, but it is still uncertain whether it can be predicted with secondary use of electronic health records (EHRs) in early pregnancy. To this purpose, the cost-sensitive hybrid model (CSHM) and five conventional machine learning methods are used to construct the predictive models, capturing the future risks of GDM in the temporally aggregated EHRs. The experimental data sources from a nested case-control study cohort, containing 33,935 gestational women in West China Second Hospital. After data cleaning, 4,378 cases and 50 attributes are stored and collected for the data set. Through selecting the most feasible method, the cost parameter of CSHM is adapted to deal with imbalance of the dataset. In the experiment, 3940 samples are used for training and the rest 438 samples for testing. Although the accuracy of positive samples is barely acceptable (62.16%), the results suggest that the vast majority (98.4%) of those predicted positive instances are real positives. To our knowledge, this is the first study to apply machine learning models with EHRs to predict GDM, which will facilitate personalized medicine in maternal health management in the future.

Machine Learning in Radiology: Applications Beyond Image Interpretation

Much attention has been given to machine learning and its perceived impact in radiology, particularly in light of recent success with image classification in international competitions. However, machine learning is likely to impact radiology outside of image interpretation long before a fully functional "machine radiologist" is implemented in practice. Here, we describe an overview of machine learning, its application to radiology and other domains, and many cases of use that do not involve image interpretation. We hope that better understanding of these potential applications will help radiology practices prepare for the future and realize performance improvement and efficiency gains.

Computational biology: deep learning

Deep learning is the trendiest tool in a computational biologist's toolbox. This exciting class of methods, based on artificial neural networks, quickly became popular due to its competitive performance in prediction problems. In pioneering early work, applying simple network architectures to abundant data already provided gains over traditional counterparts in functional genomics, image analysis, and medical diagnostics. Now, ideas for constructing and training networks and even off-the-shelf models have been adapted from the rapidly developing machine learning subfield to improve performance in a range of computational biology tasks. Here, we review some of these advances in the last 2 years.

Radiomics: the bridge between medical imaging and personalized medicine

Radiomics, the high-throughput mining of quantitative image features from standard-of-care medical imaging that enables data to be extracted and applied within clinical-decision support systems to improve diagnostic, prognostic, and predictive accuracy, is gaining importance in cancer research. Radiomic analysis exploits sophisticated image analysis tools and the rapid development and validation of medical imaging data that uses image-based signatures for precision diagnosis and treatment, providing a powerful tool in modern medicine. Herein, we describe the process of radiomics, its pitfalls, challenges, opportunities, and its capacity to improve clinical decision making, emphasizing the utility for patients with cancer. Currently, the field of radiomics lacks standardized evaluation of both the scientific integrity and the clinical relevance of the numerous published radiomics investigations resulting from the rapid growth of this area. Rigorous evaluation criteria and reporting guidelines need to be established in order for radiomics to mature as a discipline. Herein, we provide guidance for investigations to meet this urgent need in the field of radiomics.

Artificial Intelligence versus Doctors' Intelligence: A Glance on Machine Learning Benefaction in Electrocardiography

Computational machine learning, especially self-enhancing algorithms, prove remarkable effectiveness in applications, including cardiovascular medicine. This review summarizes and cross-compares the current machine learning algorithms applied to electrocardiogram interpretation. In practice, continuous real-time monitoring of electrocardiograms is still difficult to realize. Furthermore, automated ECG interpretation by implementing specific artificial intelligence algorithms is even more challenging. By collecting large datasets from one individual, computational approaches can assure an efficient personalized treatment strategy, such as a correct prediction on patient-specific disease progression, therapeutic success rate and limitations of certain interventions, thus reducing the hospitalization costs and physicians’ workload. Clearly such aims can be achieved by a perfect symbiosis of a multidisciplinary team involving clinicians, researchers and computer scientists. Summarizing, continuous cross-examination between machine intelligence and human intelligence is a combination of precision, rationale and high-throughput scientific engine integrated into a challenging framework of big data science.

A glossary for big data in population and public health: discussion and commentary on terminology and research methods

The volume and velocity of data are growing rapidly and big data analytics are being applied to these data in many fields. Population and public health researchers may be unfamiliar with the terminology and statistical methods used in big data. This creates a barrier to the application of big data analytics. The purpose of this glossary is to define terms used in big data and big data analytics and to contextualise these terms. We define the five Vs of big data and provide definitions and distinctions for data mining, machine learning and deep learning, among other terms. We provide key distinctions between big data and statistical analysis methods applied to big data. We contextualise the glossary by providing examples where big data analysis methods have been applied to population and public health research problems and provide brief guidance on how to learn big data analysis methods.

Selecting relevant features from the electronic health record for clinical code prediction

A multitude of information sources is present in the electronic health record (EHR), each of which can contain clues to automatically assign diagnosis and procedure codes. These sources however show information overlap and quality differences, which complicates the retrieval of these clues. Through feature selection, a denser representation with a consistent quality and less information overlap can be obtained. We introduce and compare coverage-based feature selection methods, based on confidence and information gain. These approaches were evaluated over a range of medical specialties, with seven different medical specialties for ICD-9-CM code prediction (six at the Antwerp University Hospital and one in the MIMIC-III dataset) and two different medical specialties for ICD-10-CM code prediction. Using confidence coverage to integrate all sources in an EHR shows a consistent improvement in F-measure (49.83% for diagnosis codes on average), both compared with the baseline (44.25% for diagnosis codes on average) and with using the best standalone source (44.41% for diagnosis codes on average). Confidence coverage creates a concise patient stay representation independent of a rigid framework such as UMLS, and contains easily interpretable features. Confidence coverage has several advantages to a baseline setup. In our baseline setup, feature selection was limited to a filter removing features with less than five total occurrences in the trainingset. Prediction results improved consistently when using multiple heterogeneous sources to predict clinical codes, while reducing the number of features and the processing time.

Secondary Use of Patient Data: Review of the Literature Published in 2016

Objectives: To summarize recent research and emerging trends in the area of secondary use of healthcare data, and to present the best papers published in this field, selected to appear in the 2017 edition of the IMIA Yearbook. Methods: A literature review of articles published in 2016 and related to secondary use of healthcare data was performed using two bibliographic databases. From this search, 941 papers were identified. The section editors independently reviewed the papers for relevancy and impact, resulting in a consensus list of 14 candidate best papers. External reviewers examined each of the candidate best papers and the final selection was made by the editorial board of the Yearbook. Results: From the 941 retrieved papers, the selection process resulted in four best papers. These papers discuss data quality concerns, issues in preserving privacy of patients in shared datasets, and methods of decision support when consuming large amounts of raw electronic health record (EHR) data. Conclusion: In 2016, a significant effort was put into the development of new systems which aim to avoid significant human understanding and pre-processing of healthcare data, though this is still only an emerging area of research. The value of temporal relationships between data received significant study, as did effective information sharing while preserving patient privacy.