$\mathtt {Deepr}$: A Convolutional Net for Medical Records

Interpretable disease prediction using heterogeneous patient records with self-attentive fusion encoder

OBJECTIVE

We propose an interpretable disease prediction model that efficiently fuses multiple types of patient records using a self-attentive fusion encoder. We assessed the model performance in predicting cardiovascular disease events, given the records of a general patient population.

MATERIALS AND METHODS

We extracted 798111 ses and 67 623 controls from the sample cohort database and nationwide healthcare claims data of South Korea. Among the information provided, our model used the sequential records of medical codes and patient characteristics, such as demographic profiles and the most recent health examination results. These two types of patient records were combined in our self-attentive fusion module, whereas previously dominant methods aggregated them using a simple concatenation. The prediction performance was compared to state-of-the-art recurrent neural network-based approaches and other widely used machine learning approaches.

RESULTS

Our model outperformed all the other compared methods in predicting cardiovascular disease events. It achieved an area under the curve of 0.839, while the other compared methods achieved between 0.74111 d 0.830. Moreover, our model consistently outperformed the other methods in a more challenging setting in which we tested the model's ability to draw an inference from more nonobvious, diverse factors.

DISCUSSION

We also interpreted the attention weights provided by our model as the relative importance of each time step in the sequence. We showed that our model reveals the informative parts of the patients' history by measuring the attention weights.

CONCLUSION

We suggest an interpretable disease prediction model that efficiently fuses heterogeneous patient records and demonstrates superior disease prediction performance.

Numerical Feature Transformation-based Sequence Generation Model for Multi-disease Diagnosis

The goal of computer-aided diagnosis is to predict patient’s diseases based on patient’s clinical data. The development of deep learning technology provides new help for clinical diagnosis. In this paper, we propose a new sequence generation model for multi-disease diagnosis prediction based on numerical feature transformation. Our model simultaneously uses patient’s laboratory test results and clinical text as input to diagnose and predict the disease that the patient may have. According to medical knowledge, our model can transform numerical features into descriptive text features, thereby enriching the semantic information of clinical texts. Besides, our model uses attention-based sequence generation methods to achieve the diagnosis of multiple diseases and better utilizes the correlation information between multiple diseases. We evaluate our model’s performance on a dataset of respiratory diseases from the real world, and experimental results show that our model’s accuracy reaches 42.75%, and the [Formula: see text] score reaches 65.65%, which is better than many other methods. It is suitable for the accurate diagnosis of multiple diseases.

Patient Representation From Structured Electronic Medical Records Based on Embedding Technique: Development and Validation Study

Background

The secondary use of structured electronic medical record (sEMR) data has become a challenge due to the diversity, sparsity, and high dimensionality of the data representation. Constructing an effective representation for sEMR data is becoming more and more crucial for subsequent data applications.

Objective

We aimed to apply the embedding technique used in the natural language processing domain for the sEMR data representation and to explore the feasibility and superiority of the embedding-based feature and patient representations in clinical application.

Methods

The entire training corpus consisted of records of 104,752 hospitalized patients with 13,757 medical concepts of disease diagnoses, physical examinations and procedures, laboratory tests, medications, etc. Each medical concept was embedded into a 200-dimensional real number vector using the Skip-gram algorithm with some adaptive changes from shuffling the medical concepts in a record 20 times. The average of vectors for all medical concepts in a patient record represented the patient. For embedding-based feature representation evaluation, we used the cosine similarities among the medical concept vectors to capture the latent clinical associations among the medical concepts. We further conducted a clustering analysis on stroke patients to evaluate and compare the embedding-based patient representations. The Hopkins statistic, Silhouette index (SI), and Davies-Bouldin index were used for the unsupervised evaluation, and the precision, recall, and F1 score were used for the supervised evaluation.

Results

The dimension of patient representation was reduced from 13,757 to 200 using the embedding-based representation. The average cosine similarity of the selected disease (subarachnoid hemorrhage) and its 15 clinically relevant medical concepts was 0.973. Stroke patients were clustered into two clusters with the highest SI (0.852). Clustering analyses conducted on patients with the embedding representations showed higher applicability (Hopkins statistic 0.931), higher aggregation (SI 0.862), and lower dispersion (Davies-Bouldin index 0.551) than those conducted on patients with reference representation methods. The clustering solutions for patients with the embedding-based representation achieved the highest F1 scores of 0.944 and 0.717 for two clusters.

Conclusions

The feature-level embedding-based representations can reflect the potential clinical associations among medical concepts effectively. The patient-level embedding-based representation is easy to use as continuous input to standard machine learning algorithms and can bring performance improvements. It is expected that the embedding-based representation will be helpful in a wide range of secondary uses of sEMR data.

A Deep Recurrent Neural Network-Based Explainable Prediction Model for Progression from Atrophic Gastritis to Gastric Cancer

Gastric cancer is the fifth most common cancer type worldwide and one of the most frequently diagnosed cancers in South Korea. In this study, we propose DeepPrevention, which comprises a prediction module to predict the possibility of progression from atrophic gastritis to gastric cancer and an explanation module to identify risk factors for progression from atrophic gastritis to gastric cancer, to identify patients with atrophic gastritis who are at high risk of gastric cancer. The data set used in this study was South Korea National Health Insurance Service (NHIS) medical checkup data for atrophic gastritis patients from 2002 to 2013. Our experimental results showed that the most influential predictors of gastric cancer development were sex, smoking duration, and current smoking status. In addition, we found that the average age of gastric cancer diagnosis in a group of high-risk patients was 57, and income, BMI, regular exercise, and the number of endoscopic screenings did not show any significant difference between groups. At the individual level, we identified that there were relatively strong associations between gastric cancer and smoking duration and smoking status.

Analysis of the Impact of Medical Features and Risk Prediction of Acute Kidney Injury for Critical Patients Using Temporal Electronic Health Record Data With Attention-Based Neural Network

Acute kidney injury (AKI) is one of the most severe consequences of kidney injury, and it will also cause or aggravate the complications by the fast decline of kidney excretory function. Accurate AKI prediction, including the AKI case, AKI stage, and AKI onset time interval, can provide adequate support for effective interventions. Besides, discovering how the medical features affect the AKI result may also provide supporting information for disease treatment. An attention-based temporal neural network approach was employed in this study for AKI prediction and for the analysis of the impact of medical features from temporal electronic health record (EHR) data of patients before AKI diagnosis. We used the publicly available dataset provided by the Medical Information Mart for Intensive Care (MIMIC) for model training, validation, and testing, and then the model was applied in clinical practice. The improvement of AKI case prediction is around 5% AUC (area under the receiver operating characteristic curve), and the AUC value of AKI stage prediction on AKI stage 3 is over 82%. We also analyzed the data by two steps: the associations between the medical features and the AKI case (positive or inverse) and the extent of the impact of medical features on AKI prediction result. It shows that features, such as lactate, glucose, creatinine, blood urea nitrogen (BUN), prothrombin time (PT), and partial thromboplastin time (PTT), are positively associated with the AKI case, while there are inverse associations between the AKI case and features such as platelet, hemoglobin, hematocrit, urine, and international normalized ratio (INR). The laboratory test features such as urine, glucose, creatinine, sodium, and blood urea nitrogen and the medication features such as nonsteroidal anti-inflammatory drugs, agents acting on the renin–angiotensin system, and lipid-lowering medication were detected to have higher weights than other features in the proposed model, which may imply that these features have a great impact on the AKI case.

A Convolutional Neural Network-Based Triplet-Mining Metric Learning Schema for Measuring Patient Similarity Addressing Personalized Healthcare

Prediction of the development risk of some diseases is an important area of Health Care Research. When exploring the personalized care of the patients, precise identification and classification of similarity in patients from their past report is an important process. Electronically stored health information EHRs that has been sampled unevenly as well as which has variable appointment durations, is considered to be unsuitable for measuring the similarity among patients directly, as there is no proper representation that are fitting. In addition, a technique is required that is efficient to evaluate similarities in patient. We propose two new similarities learning environments using deep learning that learn simultaneously the representations of the patients as well as measurement of similarity in pairs. A Convolutional Neural Network (CNN) is used to understand EHRs that contains crucial information which are local thereby providing scholastic illumination in the triplet loss otherwise entropy loss. When the training is completed, distances are calculated as well as similarities scores. Using this similarity information, disease predictions along with patient grouping is performed. Experimentally the results gives an idea that CNN can represent the EHR sequences in a better way and the schema offered are more efficient than the modern metric distance learning.

Neural Clinical Event Sequence Prediction through Personalized Online Adaptive Learning

Clinical event sequences consist of thousands of clinical events that represent records of patient care in time. Developing accurate prediction models for such sequences is of a great importance for defining representations of a patient state and for improving patient care. One important challenge of learning a good predictive model of clinical sequences is patient-specific variability. Based on underlying clinical complications, each patient's sequence may consist of different sets of clinical events. However, population-based models learned from such sequences may not accurately predict patient-specific dynamics of event sequences. To address the problem, we develop a new adaptive event sequence prediction framework that learns to adjust its prediction for individual patients through an online model update.

Clinical decision-making framework against over-testing based on modeling implicit evaluation criteria

Different statistical methods include various subjective criteria that can prevent over-testing. However, no unified framework that defines generalized objective criteria for various diseases is available to determine the appropriateness of diagnostic tests recommended by doctors. We present the clinical decision-making framework against over-testing based on modeling the implicit evaluation criteria (CDFO-MIEC). The CDFO-MIEC quantifies the subjective evaluation process using statistics-based methods to identify over-testing. Furthermore, it determines the test's appropriateness with extracted entities obtained via named entity recognition and entity alignment. More specifically, implicit evaluation criteria are defined-namely, the correlation among the diagnostic tests, symptoms, and diseases, confirmation function, and exclusion function. Additionally, four evaluation strategies are implemented by applying statistical methods, including the multi-label k-nearest neighbor and the conditional probability algorithms, to model the implicit evaluation criteria. Finally, they are combined into a classification and regression tree to make the final decision. The CDFO-MIEC also provides interpretability by decision conditions for supporting each clinical decision of over-testing. We tested the CDFO-MIEC on 2,860 clinical texts obtained from a single respiratory medicine department in China with the appropriate confirmation by physicians. The dataset was supplemented with random inappropriate tests. The proposed framework excelled against the best competing text classification methods with a Mean_F₁ of 0.9167. This determined whether the appropriate and inappropriate tests were properly classified. The four evaluation strategies captured the features effectively, and they were imperative. Therefore, the proposed CDFO-MIEC is feasible because it exhibits high performance and can prevent over-testing.

Early Prediction of Organ Failures in Patients with Acute Pancreatitis Using Text Mining

It is of great significance to establish an assessment model for organ failures in the early stage of admission in acute pancreatitis (AP). And the clinical notes are underutilized. To predict organ failures for AP patients using early clinical notes in hospital, early text features obtained from the pretrained Chinese Bidirectional Encoder Representations from Transformers model and attention-based LSTM were combined with early structured features (laboratory tests, vital signs, and demographic characteristics) to predict organ failures (respiratory, cardiovascular, and renal) in 12,748 AP inpatients in West China Hospital, Sichuan University, from 2008 to 2018. The text plus structured features fusion model was used to predict organ failures, compared to the baseline model with only structured features. The performance of the model with text features added is superior to the model that only includes structured features.

High-Risk Prediction of Cardiovascular Diseases via Attention-Based Deep Neural Networks

High-risk prediction of cardiovascular disease is of great significance and impendency in medical fields with the increasing phenomenon of sub-health these years. Most existing pathological methods for the prognosis prediction are either costly or prone to misjudgement. Therefore, plenty of automated models based on machine learning have been proposed to predict the onset of cardiovascular disease with the premorbid information of patients extracted from their historical Electronic Health Records (EHRs). However, it is a tough job to select proper features from longitudinal and heterogeneous EHRs, and also a great challenge to obtain accurate and robust representations for patients. In this paper, we propose an entirely end-to-end model called DeepRisk based on attention mechanism and deep neural networks, which can not only learn high-quality features automatically from EHRs, but also efficiently integrate heterogeneous and time-ordered medical data, and finally predict patients' risk of cardiovascular diseases. Experiments are carried out on a real medical dataset and results show that DeepRisk can significantly improve the high-risk prediction accuracy for cardiovascular disease compared with state-of-the-art approaches.

Intelligent Health Care: Applications of Deep Learning in Computational Medicine

With the progress of medical technology, biomedical field ushered in the era of big data, based on which and driven by artificial intelligence technology, computational medicine has emerged. People need to extract the effective information contained in these big biomedical data to promote the development of precision medicine. Traditionally, the machine learning methods are used to dig out biomedical data to find the features from data, which generally rely on feature engineering and domain knowledge of experts, requiring tremendous time and human resources. Different from traditional approaches, deep learning, as a cutting-edge machine learning branch, can automatically learn complex and robust feature from raw data without the need for feature engineering. The applications of deep learning in medical image, electronic health record, genomics, and drug development are studied, where the suggestion is that deep learning has obvious advantage in making full use of biomedical data and improving medical health level. Deep learning plays an increasingly important role in the field of medical health and has a broad prospect of application. However, the problems and challenges of deep learning in computational medical health still exist, including insufficient data, interpretability, data privacy, and heterogeneity. Analysis and discussion on these problems provide a reference to improve the application of deep learning in medical health.

An Inception Convolutional Autoencoder Model for Chinese Healthcare Question Clustering

Healthcare question answering (HQA) system plays a vital role in encouraging patients to inquire for professional consultation. However, there are some challenging factors in learning and representing the question corpus of HQA datasets, such as high dimensionality, sparseness, noise, nonprofessional expression, etc. To address these issues, we propose an inception convolutional autoencoder model for Chinese healthcare question clustering (ICAHC). First, we select a set of kernels with different sizes using convolutional autoencoder networks to explore both the diversity and quality in the clustering ensemble. Thus, these kernels encourage to capture diverse representations. Second, we design four ensemble operators to merge representations based on whether they are independent, and input them into the encoder using different skip connections. Third, it maps features from the encoder into a lower-dimensional space, followed by clustering. We conduct comparative experiments against other clustering algorithms on a Chinese healthcare dataset. Experimental results show the effectiveness of ICAHC in discovering better clustering solutions. The results can be used in the prediction of patients' conditions and the development of an automatic HQA system.

StoCast: Stochastic Disease Forecasting With Progression Uncertainty

Forecasting patients' disease progressions with rich longitudinal clinical data has drawn much attention in recent years due to its impactful application in healthcare and the medical field. Researchers have tackled this problem by leveraging traditional machine learning, statistical techniques and deep learning based models. However, existing methods suffer from either deterministic internal structures or over-simplified stochastic components, failing to deal with complex uncertain scenarios such as progression uncertainty (i.e., multiple possible trajectories) and data uncertainty (i.e., imprecise observations and misdiagnosis). To overcome these major uncertainty issues, we propose a novel deep generative model, Stochastic Disease Forecasting Model (StoCast), along with an associated neural network architecture StoCastNet, that can be trained efficiently via stochastic optimization techniques. Our StoCast model uses internal stochastic components to deal with departures of observed data from patients' true health states, and more importantly, is able to produce a comprehensive estimate of future disease progression trajectories. Based on two public datasets related to Alzheimer's disease and Parkinson's disease, we demonstrate how our StoCast model achieves robust and superior performance than deterministic baseline approaches, and conveys richer information that can potentially assist doctors to make decisions with greater confidence in a complex uncertain scenario.

Multi-layer Representation Learning and Its Application to Electronic Health Records

Electronic Health Records (EHRs) are digital records associated with hospitalization, diagnosis, medications and so on. Secondary use of EHRs can promote the clinical informatics applications and the development of healthcare undertaking. EHRs have the unique characteristic where the patient visits are temporally ordered but the diagnosis codes within a visit are randomly ordered. The hierarchical structure requires a multi-layer network to explore the different relational information of EHRs. In this paper, we propose a Multi-Layer Representation Learning method (MLRL), which is capable of learning effective patient representation by hierarchically exploring the valuable information in both diagnosis codes and patient visits. Firstly, MLRL utilizes the multi-head attention mechanism to explore the potential connections in diagnosis codes, and a linear transformation is implemented to further map the code vectors to non-negative real-valued representations. The initial visit vectors are then obtained by summarizing all the code representations. Secondly, the proposed method combines Bidirectional Long Short-Term Memory with self-attention mechanism to learn the weighted visit vectors which are aggregated to form the patient representation. Finally, to evaluate the performance of MLRL, we apply it to patient's mortality prediction on real EHRs and the experimental results demonstrate that MLRL has a significant improvement in prediction performance. MLRL achieves around 0.915 in Area Under Curve which is superior to the results obtained by baseline methods. Furthermore, compared with raw data and other data representations, the learned representation with MLRL shows its outstanding results and availability on multiple different classifiers.

AI and Big Data in Healthcare: Towards a More Comprehensive Research Framework for Multimorbidity

Multimorbidity refers to the coexistence of two or more chronic diseases in one person. Therefore, patients with multimorbidity have multiple and special care needs. However, in practice it is difficult to meet these needs because the organizational processes of current healthcare systems tend to be tailored to a single disease. To improve clinical decision making and patient care in multimorbidity, a radical change in the problem-solving approach to medical research and treatment is needed. In addition to the traditional reductionist approach, we propose interactive research supported by artificial intelligence (AI) and advanced big data analytics. Such research approach, when applied to data routinely collected in healthcare settings, provides an integrated platform for research tasks related to multimorbidity. This may include, for example, prediction, correlation, and classification problems based on multiple interaction factors. However, to realize the idea of this paradigm shift in multimorbidity research, the optimization, standardization, and most importantly, the integration of electronic health data into a common national and international research infrastructure is needed. Ultimately, there is a need for the integration and implementation of efficient AI approaches, particularly deep learning, into clinical routine directly within the workflows of the medical professionals.

Predictive Maintenance in Building Facilities: A Machine Learning-Based Approach

The operation and maintenance of buildings has seen several advances in recent years. Multiple information and communication technology (ICT) solutions have been introduced to better manage building maintenance. However, maintenance practices in buildings remain less efficient and lead to significant energy waste. In this paper, a predictive maintenance framework based on machine learning techniques is proposed. This framework aims to provide guidelines to implement predictive maintenance for building installations. The framework is organised into five steps: data collection, data processing, model development, fault notification and model improvement. A sport facility was selected as a case study in this work to demonstrate the framework. Data were collected from different heating ventilation and air conditioning (HVAC) installations using Internet of Things (IoT) devices and a building automation system (BAS). Then, a deep learning model was used to predict failures. The case study showed the potential of this framework to predict failures. However, multiple obstacles and barriers were observed related to data availability and feedback collection. The overall results of this paper can help to provide guidelines for scientists and practitioners to implement predictive maintenance approaches in buildings.

Modeling multivariate clinical event time-series with recurrent temporal mechanisms

In this work, we propose a novel autoregressive event time-series model that can predict future occurrences of multivariate clinical events. Our model represents multivariate event time-series using different temporal mechanisms aimed to fit different temporal characteristics of the time-series. In particular, information about distant past is modeled through the hidden state space defined by an LSTM-based model, information on recently observed clinical events is modeled through discriminative projections, and information about periodic (repeated) events is modeled using a special recurrent mechanism based on probability distributions of inter-event gaps compiled from past data. We evaluate our proposed model on electronic health record (EHRs) data derived from MIMIC-III dataset. We show that our new model equipped with the above temporal mechanisms leads to improved prediction performance compared to multiple baselines.

Machine Learning for Clinical Outcome Prediction

Clinical decision-making in healthcare is already being influenced by predictions or recommendations made by data-driven machines. Numerous machine learning applications have appeared in the latest clinical literature, especially for outcome prediction models, with outcomes ranging from mortality and cardiac arrest to acute kidney injury and arrhythmia. In this review article, we summarize the state-of-the-art in related works covering data processing, inference, and model evaluation, in the context of outcome prediction models developed using data extracted from electronic health records. We also discuss limitations of prominent modeling assumptions and highlight opportunities for future research.

Language models are an effective representation learning technique for electronic health record data

Widespread adoption of electronic health records (EHRs) has fueled the development of using machine learning to build prediction models for various clinical outcomes. However, this process is often constrained by having a relatively small number of patient records for training the model. We demonstrate that using patient representation schemes inspired from techniques in natural language processing can increase the accuracy of clinical prediction models by transferring information learned from the entire patient population to the task of training a specific model, where only a subset of the population is relevant. Such patient representation schemes enable a 3.5% mean improvement in AUROC on five prediction tasks compared to standard baselines, with the average improvement rising to 19% when only a small number of patient records are available for training the clinical prediction model.

Detecting Miscoded Diabetes Diagnosis Codes in Electronic Health Records for Quality Improvement: Temporal Deep Learning Approach

BACKGROUND

Diabetes affects more than 30 million patients across the United States. With such a large disease burden, even a small error in classification can be significant. Currently billing codes, assigned at the time of a medical encounter, are the "gold standard" reflecting the actual diseases present in an individual, and thus in aggregate reflect disease prevalence in the population. These codes are generated by highly trained coders and by health care providers but are not always accurate.

OBJECTIVE

This work provides a scalable deep learning methodology to more accurately classify individuals with diabetes across multiple health care systems.

METHODS

We leveraged a long short-term memory-dense neural network (LSTM-DNN) model to identify patients with or without diabetes using data from 5 acute care facilities with 187,187 patients and 275,407 encounters, incorporating data elements including laboratory test results, diagnostic/procedure codes, medications, demographic data, and admission information. Furthermore, a blinded physician panel reviewed discordant cases, providing an estimate of the total impact on the population.

RESULTS

When predicting the documented diagnosis of diabetes, our model achieved an 84% F1 score, 96% area under the curve-receiver operating characteristic curve, and 91% average precision on a heterogeneous data set from 5 distinct health facilities. However, in 81% of cases where the model disagreed with the documented phenotype, a blinded physician panel agreed with the model. Taken together, this suggests that 4.3% of our studied population have either missing or improper diabetes diagnosis.

CONCLUSIONS

This study demonstrates that deep learning methods can improve clinical phenotyping even when patient data are noisy, sparse, and heterogeneous.

A review on deep learning approaches in healthcare systems: Taxonomies, challenges, and open issues

In the last few years, the application of Machine Learning approaches like Deep Neural Network (DNN) models have become more attractive in the healthcare system given the rising complexity of the healthcare data. Machine Learning (ML) algorithms provide efficient and effective data analysis models to uncover hidden patterns and other meaningful information from the considerable amount of health data that conventional analytics are not able to discover in a reasonable time. In particular, Deep Learning (DL) techniques have been shown as promising methods in pattern recognition in the healthcare systems. Motivated by this consideration, the contribution of this paper is to investigate the deep learning approaches applied to healthcare systems by reviewing the cutting-edge network architectures, applications, and industrial trends. The goal is first to provide extensive insight into the application of deep learning models in healthcare solutions to bridge deep learning techniques and human healthcare interpretability. And then, to present the existing open challenges and future directions.

TAPER: Time-Aware Patient EHR Representation

Effective representation learning of electronic health records is a challenging task and is becoming more important as the availability of such data is becoming pervasive. The data contained in these records are irregular and contain multiple modalities such as notes, and medical codes. They are preempted by medical conditions the patient may have, and are typically recorded by medical staff. Accompanying codes are notes containing valuable information about patients beyond the structured information contained in electronic health records. We use transformer networks and the recently proposed BERT language model to embed these data streams into a unified vector representation. The presented approach effectively encodes a patient's visit data into a single a distributed representation, which can be used for downstream tasks. Our model demonstrates superior performance and generalization on mortality, readmission and length of stay tasks using the publicly available MIMIC-III ICU dataset.

Learning multimorbidity patterns from electronic health records using Non-negative Matrix Factorisation

Multimorbidity, or the presence of several medical conditions in the same individual, has been increasing in the population - both in absolute and relative terms. Nevertheless, multimorbidity remains poorly understood, and the evidence from existing research to describe its burden, determinants and consequences has been limited. Previous studies attempting to understand multimorbidity patterns are often cross-sectional and do not explicitly account for multimorbidity patterns' evolution over time; some of them are based on small datasets and/or use arbitrary and narrow age ranges; and those that employed advanced models, usually lack appropriate benchmarking and validations. In this study, we (1) introduce a novel approach for using Non-negative Matrix Factorisation (NMF) for temporal phenotyping (i.e., simultaneously mining disease clusters and their trajectories); (2) provide quantitative metrics for the evaluation of these clusters and trajectories; and (3) demonstrate how the temporal characteristics of the disease clusters that result from our model can help mine multimorbidity networks and generate new hypotheses for the emergence of various multimorbidity patterns over time. We trained and evaluated our models on one of the world's largest electronic health records (EHR) datasets, containing more than 7 million patients, from which over 2 million where relevant to, and hence included in this study.

Natural Language Processing Model for Managing Maintenance Requests in Buildings

In recent years, facility management (FM) has adopted many computer technology solutions for building maintenance, such as building information modelling (BIM) and computerized maintenance management systems (CMMS). However, maintenance requests management in buildings remains a manual and a time-consuming process that depends on human management. In this paper, a machine-learning algorithm based on natural language processing (NLP) is proposed to classify maintenance requests. This algorithm aims to assist the FM teams in managing day-to-day maintenance activities. A healthcare facility is addressed as a case study in this work. Ten-year maintenance records from the facility contributed to the design and development of the algorithm. Multiple NLP methods were used in this study, and the results reveal that the NLP model can classify work requests with an average accuracy of 78%. Furthermore, NLP methods have proven to be effective for managing unstructured text data.

Exploiting complex medical data with interpretable deep learning for adverse drug event prediction

A variety of deep learning architectures have been developed for the goal of predictive modelling and knowledge extraction from medical records. Several models have placed strong emphasis on temporal attention mechanisms and decay factors as a means to include highly temporally relevant information regarding the recency of medical event occurrence while facilitating medical code-level interpretability. In this study we utilise such models with a large Electronic Patient Record (EPR) data set consisting of diagnoses, medication, and clinical text data for the purpose of adverse drug event (ADE) prediction. The first contribution of this work is an empirical evaluation of two state-of-the-art medical-code based models in terms of objective performance metrics for ADE prediction on diagnosis and medication data. Secondly, as an extension of previous work, we augment an interpretable deep learning architecture to permit numerical risk and clinical text features and demonstrate how this approach yields improved predictive performance compared to the other baselines. Finally, we assess the importance of attention mechanisms in regards to their usefulness for medical code-level and text-level interpretability, which may facilitate novel insights pertaining to the nature of ADE occurrence within the health care domain.

Investigation on the impacts of COVID-19 quarantine on society and environment: Preventive measures and supportive technologies

The present outbreak of the novel coronavirus SARS-CoV-2, epicentered in China in December 2019, has spread to many other countries. The entire humanity has a vital responsibility to tackle this pandemic and the technologies are being helpful to them to a greater extent. The purpose of the work is to precisely bring scientific and general awareness to the people all around the world who are currently fighting the war against COVID-19. It's visible that the number of people infected is increasing day by day and the medical community is tirelessly working to maintain the situation under control. Other than the negative effects caused by COVID-19, it is also equally important for the public to understand some of the positive impacts it has directly or indirectly given to society. This work emphasizes the various impacts that are created on society as well as the environment. As a special additive, some important key areas are highlighted namely, how the modernized technologies are aiding the people during the period of social distancing. Some effective technological implications carried out by both information technology and educational institutions are highlighted. There are also several steps taken by the state government and central government in each country in adopting the complete lockdown rule. These steps are taken primarily to prevent the people from COVID-19 impact. Moreover, the teachings we need to learn from the quarantine situation created to prevent further spread of this global pandemic is discussed in brief and the importance of carrying them to the future. Finally, the paper also elucidates the general preventive measures that have to be taken to prevent this deadly coronavirus, and the role of technology in this pandemic situation has also been discussed.

ZiMM: A deep learning model for long term and blurry relapses with non-clinical claims data

This paper considers the problems of modeling and predicting a long-term and "blurry" relapse that occurs after a medical act, such as a surgery. We do not consider a short-term complication related to the act itself, but a long-term relapse that clinicians cannot explain easily, since it depends on unknown sets or sequences of past events that occurred before the act. The relapse is observed only indirectly, in a "blurry" fashion, through longitudinal prescriptions of drugs over a long period of time after the medical act. We introduce a new model, called ZiMM (Zero-inflated Mixture of Multinomial distributions) in order to capture long-term and blurry relapses. On top of it, we build an end-to-end deep-learning architecture called ZiMM Encoder-Decoder (ZiMM ED) that can learn from the complex, irregular, highly heterogeneous and sparse patterns of health events that are observed through a claims-only database. ZiMM ED is applied on a "non-clinical" claims database, that contains only timestamped reimbursement codes for drug purchases, medical procedures and hospital diagnoses, the only available clinical feature being the age of the patient. This setting is more challenging than a setting where bedside clinical signals are available. Our motivation for using such a non-clinical claims database is its exhaustivity population-wise, compared to clinical electronic health records coming from a single or a small set of hospitals. Indeed, we consider a dataset containing the claims of almost all French citizens who had surgery for prostatic problems, with a history between 1.5 and 5 years. We consider a long-term (18 months) relapse (urination problems still occur despite surgery), which is blurry since it is observed only through the reimbursement of a specific set of drugs for urination problems. Our experiments show that ZiMM ED improves several baselines, including non-deep learning and deep-learning approaches, and that it allows working on such a dataset with minimal preprocessing work.

Prediction of Medical Concepts in Electronic Health Records: Similar Patient Analysis

Background

Medicine 2.0—the adoption of Web 2.0 technologies such as social networks in health care—creates the need for apps that can find other patients with similar experiences and health conditions based on a patient’s electronic health record (EHR). Concurrently, there is an increasing number of longitudinal EHR data sets with rich information, which are essential to fulfill this need.

Objective

This study aimed to evaluate the hypothesis that we can leverage similar EHRs to predict possible future medical concepts (eg, disorders) from a patient’s EHR.

Methods

We represented patients’ EHRs using time-based prefixes and suffixes, where each prefix or suffix is a set of medical concepts from a medical ontology. We compared the prefixes of other patients in the collection with the state of the current patient using various interpatient distance measures. The set of similar prefixes yields a set of suffixes, which we used to determine probable future concepts for the current patient’s EHR.

Results

We evaluated our methods on the Multiparameter Intelligent Monitoring in Intensive Care II data set of patients, where we achieved precision up to 56.1% and recall up to 69.5%. For a limited set of clinically interesting concepts, specifically a set of procedures, we found that 86.9% (353/406) of the true-positives are clinically useful, that is, these procedures were actually performed later on the patient, and only 4.7% (19/406) of true-positives were completely irrelevant.

Conclusions

These initial results indicate that predicting patients’ future medical concepts is feasible. Effectively predicting medical concepts can have several applications, such as managing resources in a hospital.

Deep representation learning of electronic health records to unlock patient stratification at scale

Deriving disease subtypes from electronic health records (EHRs) can guide next-generation personalized medicine. However, challenges in summarizing and representing patient data prevent widespread practice of scalable EHR-based stratification analysis. Here we present an unsupervised framework based on deep learning to process heterogeneous EHRs and derive patient representations that can efficiently and effectively enable patient stratification at scale. We considered EHRs of 1,608,741 patients from a diverse hospital cohort comprising a total of 57,464 clinical concepts. We introduce a representation learning model based on word embeddings, convolutional neural networks, and autoencoders (i.e., ConvAE) to transform patient trajectories into low-dimensional latent vectors. We evaluated these representations as broadly enabling patient stratification by applying hierarchical clustering to different multi-disease and disease-specific patient cohorts. ConvAE significantly outperformed several baselines in a clustering task to identify patients with different complex conditions, with 2.61 entropy and 0.31 purity average scores. When applied to stratify patients within a certain condition, ConvAE led to various clinically relevant subtypes for different disorders, including type 2 diabetes, Parkinson's disease, and Alzheimer's disease, largely related to comorbidities, disease progression, and symptom severity. With these results, we demonstrate that ConvAE can generate patient representations that lead to clinically meaningful insights. This scalable framework can help better understand varying etiologies in heterogeneous sub-populations and unlock patterns for EHR-based research in the realm of personalized medicine.

Assistant diagnosis with Chinese electronic medical records based on CNN and BiLSTM with phrase-level and word-level attentions

Background

Inferring diseases related to the patient’s electronic medical records (EMRs) is of great significance for assisting doctor diagnosis. Several recent prediction methods have shown that deep learning-based methods can learn the deep and complex information contained in EMRs. However, they do not consider the discriminative contributions of different phrases and words. Moreover, local information and context information of EMRs should be deeply integrated.

Results

A new method based on the fusion of a convolutional neural network (CNN) and bidirectional long short-term memory (BiLSTM) with attention mechanisms is proposed for predicting a disease related to a given EMR, and it is referred to as FCNBLA. FCNBLA deeply integrates local information, context information of the word sequence and more informative phrases and words. A novel framework based on deep learning is developed to learn the local representation, the context representation and the combination representation. The left side of the framework is constructed based on CNN to learn the local representation of adjacent words. The right side of the framework based on BiLSTM focuses on learning the context representation of the word sequence. Not all phrases and words contribute equally to the representation of an EMR meaning. Therefore, we establish the attention mechanisms at the phrase level and word level, and the middle module of the framework learns the combination representation of the enhanced phrases and words. The macro average f-score and accuracy of FCNBLA achieved 91.29 and 92.78%, respectively.

Conclusion

The experimental results indicate that FCNBLA yields superior performance compared with several state-of-the-art methods. The attention mechanisms and combination representations are also confirmed to be helpful for improving FCNBLA’s prediction performance. Our method is helpful for assisting doctors in diagnosing diseases in patients.

Inferring multimodal latent topics from electronic health records

Electronic health records (EHR) are rich heterogeneous collections of patient health information, whose broad adoption provides clinicians and researchers unprecedented opportunities for health informatics, disease-risk prediction, actionable clinical recommendations, and precision medicine. However, EHRs present several modeling challenges, including highly sparse data matrices, noisy irregular clinical notes, arbitrary biases in billing code assignment, diagnosis-driven lab tests, and heterogeneous data types. To address these challenges, we present MixEHR, a multi-view Bayesian topic model. We demonstrate MixEHR on MIMIC-III, Mayo Clinic Bipolar Disorder, and Quebec Congenital Heart Disease EHR datasets. Qualitatively, MixEHR disease topics reveal meaningful combinations of clinical features across heterogeneous data types. Quantitatively, we observe superior prediction accuracy of diagnostic codes and lab test imputations compared to the state-of-art methods. We leverage the inferred patient topic mixtures to classify target diseases and predict mortality of patients in critical conditions. In all comparison, MixEHR confers competitive performance and reveals meaningful disease-related topics.

Using case-level context to classify cancer pathology reports

Individual electronic health records (EHRs) and clinical reports are often part of a larger sequence-for example, a single patient may generate multiple reports over the trajectory of a disease. In applications such as cancer pathology reports, it is necessary not only to extract information from individual reports, but also to capture aggregate information regarding the entire cancer case based off case-level context from all reports in the sequence. In this paper, we introduce a simple modular add-on for capturing case-level context that is designed to be compatible with most existing deep learning architectures for text classification on individual reports. We test our approach on a corpus of 431,433 cancer pathology reports, and we show that incorporating case-level context significantly boosts classification accuracy across six classification tasks-site, subsite, laterality, histology, behavior, and grade. We expect that with minimal modifications, our add-on can be applied towards a wide range of other clinical text-based tasks.

BEHRT: Transformer for Electronic Health Records

Today, despite decades of developments in medicine and the growing interest in precision healthcare, vast majority of diagnoses happen once patients begin to show noticeable signs of illness. Early indication and detection of diseases, however, can provide patients and carers with the chance of early intervention, better disease management, and efficient allocation of healthcare resources. The latest developments in machine learning (including deep learning) provides a great opportunity to address this unmet need. In this study, we introduce BEHRT: A deep neural sequence transduction model for electronic health records (EHR), capable of simultaneously predicting the likelihood of 301 conditions in one's future visits. When trained and evaluated on the data from nearly 1.6 million individuals, BEHRT shows a striking improvement of 8.0-13.2% (in terms of average precision scores for different tasks), over the existing state-of-the-art deep EHR models. In addition to its scalability and superior accuracy, BEHRT enables personalised interpretation of its predictions; its flexible architecture enables it to incorporate multiple heterogeneous concepts (e.g., diagnosis, medication, measurements, and more) to further improve the accuracy of its predictions; its (pre-)training results in disease and patient representations can be useful for future studies (i.e., transfer learning).

Incorporating medical code descriptions for diagnosis prediction in healthcare

BACKGROUND

Diagnosis aims to predict the future health status of patients according to their historical electronic health records (EHR), which is an important yet challenging task in healthcare informatics. Existing diagnosis prediction approaches mainly employ recurrent neural networks (RNN) with attention mechanisms to make predictions. However, these approaches ignore the importance of code descriptions, i.e., the medical definitions of diagnosis codes. We believe that taking diagnosis code descriptions into account can help the state-of-the-art models not only to learn meaning code representations, but also to improve the predictive performance, especially when the EHR data are insufficient.

METHODS

We propose a simple, but general diagnosis prediction framework, which includes two basic components: diagnosis code embedding and predictive model. To learn the interpretable code embeddings, we apply convolutional neural networks (CNN) to model medical descriptions of diagnosis codes extracted from online medical websites. The learned medical embedding matrix is used to embed the input visits into vector representations, which are fed into the predictive models. Any existing diagnosis prediction approach (referred to as the base model) can be cast into the proposed framework as the predictive model (called the enhanced model).

RESULTS

We conduct experiments on two real medical datasets: the MIMIC-III dataset and the Heart Failure claim dataset. Experimental results show that the enhanced diagnosis prediction approaches significantly improve the prediction performance. Moreover, we validate the effectiveness of the proposed framework with insufficient EHR data. Finally, we visualize the learned medical code embeddings to show the interpretability of the proposed framework.

CONCLUSIONS

Given the historical visit records of a patient, the proposed framework is able to predict the next visit information by incorporating medical code descriptions.

Representation learning for clinical time series prediction tasks in electronic health records

Background

Electronic health records (EHRs) provide possibilities to improve patient care and facilitate clinical research. However, there are many challenges faced by the applications of EHRs, such as temporality, high dimensionality, sparseness, noise, random error and systematic bias. In particular, temporal information is difficult to effectively use by traditional machine learning methods while the sequential information of EHRs is very useful.

Method

In this paper, we propose a general-purpose patient representation learning approach to summarize sequential EHRs. Specifically, a recurrent neural network based denoising autoencoder (RNN-DAE) is employed to encode inhospital records of each patient into a low dimensional dense vector.

Results

Based on EHR data collected from Shuguang Hospital affiliated to Shanghai University of Traditional Chinese Medicine, we experimentally evaluate our proposed RNN-DAE method on both mortality prediction task and comorbidity prediction task. Extensive experimental results show that our proposed RNN-DAE method outperforms existing methods. In addition, we apply the “Deep Feature” represented by our proposed RNN-DAE method to track similar patients with t-SNE, which also achieves some interesting observations.

Conclusion

We propose an effective unsupervised RNN-DAE method to summarize patient sequential information in EHR data. Our proposed RNN-DAE method is useful on both mortality prediction task and comorbidity prediction task.

Multi-objective ensemble deep learning using electronic health records to predict outcomes after lung cancer radiotherapy

Accurately predicting treatment outcome is crucial for creating personalized treatment plans and follow-up schedules. Electronic health records (EHRs) contain valuable patient-specific information that can be leveraged to improve outcome prediction. We propose a reliable multi-objective ensemble deep learning (MoEDL) method that uses features extracted from EHRs to predict high risk of treatment failure after radiotherapy in patients with lung cancer. The dataset used in this study contains EHRs of 814 patients who had not achieved disease-free status and 193 patients who were disease-free with at least one year follow-up time after lung cancer radiation therapy. The proposed MoEDL consists of three phases: (1) training with dynamic ensemble deep learning; (2) model selection with adaptive multi-objective optimization; and (3) testing with evidential reasoning (ER) fusion. Specifically, in the training phase, we employ deep perceptron networks as base learners to handle various issues with EHR data. The architecture and key hyper-parameters of each base learner are dynamically adjusted to increase the diversity of learners while reducing the time spent tuning hyper-parameters. Furthermore, we integrate the snapshot ensembles (SE) restarting strategy, multi-objective optimization, and ER fusion to improve the prediction robustness and accuracy of individual networks. The SE restarting strategy can yield multiple candidate models at no additional training cost in the training stage. The multi-objective model simultaneously considers sensitivity, specificity, and AUC as objective functions, overcoming the limitations of single-objective-based model selection. For the testing stage, we utilized an analytic ER rule to fuse the output scores from each optimal model to obtain reliable and robust predictive results. Our experimental results demonstrate that MoEDL can perform better than other conventional methods.

A predictive analytics framework for identifying patients at risk of developing multiple medical complications caused by chronic diseases

Chronic diseases often cause several medical complications. This paper aims to predict multiple complications among patients with a chronic disease. The literature uses single-task learning algorithms to predict complications independently and assumes no correlation among complications of chronic diseases. We propose two methods (independent prediction of complications with single-task learning and concurrent prediction of complications with multi-task learning) and show that medical complications of chronic diseases can be correlated. We use a case study and compare the performance of these two methods by predicting complications of hypertrophic cardiomyopathy on 106 predictors in 1078 electronic medical records from April 2009-April 2017, inclusive. The methods are implemented using logistic regression, artificial neural networks, decision trees, and support vector machines. The results show multi-task learning with logistic regression improves the performance of predictions in terms of both discrimination and calibration.

Toward a clinical text encoder: pretraining for clinical natural language processing with applications to substance misuse

OBJECTIVE

Our objective is to develop algorithms for encoding clinical text into representations that can be used for a variety of phenotyping tasks.

MATERIALS AND METHODS

Obtaining large datasets to take advantage of highly expressive deep learning methods is difficult in clinical natural language processing (NLP). We address this difficulty by pretraining a clinical text encoder on billing code data, which is typically available in abundance. We explore several neural encoder architectures and deploy the text representations obtained from these encoders in the context of clinical text classification tasks. While our ultimate goal is learning a universal clinical text encoder, we also experiment with training a phenotype-specific encoder. A universal encoder would be more practical, but a phenotype-specific encoder could perform better for a specific task.

RESULTS

We successfully train several clinical text encoders, establish a new state-of-the-art on comorbidity data, and observe good performance gains on substance misuse data.

DISCUSSION

We find that pretraining using billing codes is a promising research direction. The representations generated by this type of pretraining have universal properties, as they are highly beneficial for many phenotyping tasks. Phenotype-specific pretraining is a viable route for trading the generality of the pretrained encoder for better performance on a specific phenotyping task.

CONCLUSIONS

We successfully applied our approach to many phenotyping tasks. We conclude by discussing potential limitations of our approach.

Artificial intelligence in reproductive medicine

Artificial intelligence (AI) has experienced rapid growth over the past few years, moving from the experimental to the implementation phase in various fields, including medicine. Advances in learning algorithms and theories, the availability of large datasets and improvements in computing power have contributed to breakthroughs in current AI applications. Machine learning (ML), a subset of AI, allows computers to detect patterns from large complex datasets automatically and uses these patterns to make predictions. AI is proving to be increasingly applicable to healthcare, and multiple machine learning techniques have been used to improve the performance of assisted reproductive technology (ART). Despite various challenges, the integration of AI and reproductive medicine is bound to give an essential direction to medical development in the future. In this review, we discuss the basic aspects of AI and machine learning, and we address the applications, potential limitations and challenges of AI. We also highlight the prospects and future directions in the context of reproductive medicine.

Development and Validation of a Deep Neural Network Model for Prediction of Postoperative In-hospital Mortality

WHAT WE ALREADY KNOW ABOUT THIS TOPIC

WHAT THIS ARTICLE TELLS US THAT IS NEW: BACKGROUND:: The authors tested the hypothesis that deep neural networks trained on intraoperative features can predict postoperative in-hospital mortality.

METHODS

The data used to train and validate the algorithm consists of 59,985 patients with 87 features extracted at the end of surgery. Feed-forward networks with a logistic output were trained using stochastic gradient descent with momentum. The deep neural networks were trained on 80% of the data, with 20% reserved for testing. The authors assessed improvement of the deep neural network by adding American Society of Anesthesiologists (ASA) Physical Status Classification and robustness of the deep neural network to a reduced feature set. The networks were then compared to ASA Physical Status, logistic regression, and other published clinical scores including the Surgical Apgar, Preoperative Score to Predict Postoperative Mortality, Risk Quantification Index, and the Risk Stratification Index.

RESULTS

In-hospital mortality in the training and test sets were 0.81% and 0.73%. The deep neural network with a reduced feature set and ASA Physical Status classification had the highest area under the receiver operating characteristics curve, 0.91 (95% CI, 0.88 to 0.93). The highest logistic regression area under the curve was found with a reduced feature set and ASA Physical Status (0.90, 95% CI, 0.87 to 0.93). The Risk Stratification Index had the highest area under the receiver operating characteristics curve, at 0.97 (95% CI, 0.94 to 0.99).

CONCLUSIONS

Deep neural networks can predict in-hospital mortality based on automatically extractable intraoperative data, but are not (yet) superior to existing methods.

Deep Learning Intervention for Health Care Challenges: Some Biomedical Domain Considerations

The use of deep learning (DL) for the analysis and diagnosis of biomedical and health care problems has received unprecedented attention in the last decade. The technique has recorded a number of achievements for unearthing meaningful features and accomplishing tasks that were hitherto difficult to solve by other methods and human experts. Currently, biological and medical devices, treatment, and applications are capable of generating large volumes of data in the form of images, sounds, text, graphs, and signals creating the concept of big data. The innovation of DL is a developing trend in the wake of big data for data representation and analysis. DL is a type of machine learning algorithm that has deeper (or more) hidden layers of similar function cascaded into the network and has the capability to make meaning from medical big data. Current transformation drivers to achieve personalized health care delivery will be possible with the use of mobile health (mHealth). DL can provide the analysis for the deluge of data generated from mHealth apps. This paper reviews the fundamentals of DL methods and presents a general view of the trends in DL by capturing literature from PubMed and the Institute of Electrical and Electronics Engineers database publications that implement different variants of DL. We highlight the implementation of DL in health care, which we categorize into biological system, electronic health record, medical image, and physiological signals. In addition, we discuss some inherent challenges of DL affecting biomedical and health domain, as well as prospective research directions that focus on improving health management by promoting the application of physiological signals and modern internet technology.

Readmission prediction using deep learning on electronic health records

Unscheduled 30-day readmissions are a hallmark of Congestive Heart Failure (CHF) patients that pose significant health risks and escalate care cost. In order to reduce readmissions and curb the cost of care, it is important to initiate targeted intervention programs for patients at risk of readmission. This requires identifying high-risk patients at the time of discharge from hospital. Here, using real data from over 7500 CHF patients hospitalized between 2012 and 2016 in Sweden, we built and tested a deep learning framework to predict 30-day unscheduled readmission. We present a cost-sensitive formulation of Long Short-Term Memory (LSTM) neural network using expert features and contextual embedding of clinical concepts. This study targets key elements of an Electronic Health Record (EHR) driven prediction model in a single framework: using both expert and machine derived features, incorporating sequential patterns and addressing the class imbalance problem. We evaluate the contribution of each element towards prediction performance (ROC-AUC, F1-measure) and cost-savings. We show that the model with all key elements achieves higher discrimination ability (AUC: 0.77; F1: 0.51; Cost: 22% of maximum possible savings) outperforming the reduced models in at least two evaluation metrics. Additionally, we present a simple financial analysis to estimate annual savings if targeted interventions are offered to high risk patients.

Automated Survival Prediction in Metastatic Cancer Patients Using High-Dimensional Electronic Medical Record Data

BACKGROUND

Oncologists use patients' life expectancy to guide decisions and may benefit from a tool that accurately predicts prognosis. Existing prognostic models generally use only a few predictor variables. We used an electronic medical record dataset to train a prognostic model for patients with metastatic cancer.

METHODS

The model was trained and tested using 12 588 patients treated for metastatic cancer in the Stanford Health Care system from 2008 to 2017. Data sources included provider note text, labs, vital signs, procedures, medication orders, and diagnosis codes. Patients were divided randomly into a training set used to fit the model coefficients and a test set used to evaluate model performance (80%/20% split). A regularized Cox model with 4126 predictor variables was used. A landmarking approach was used due to the multiple observations per patient, with t0 set to the time of metastatic cancer diagnosis. Performance was also evaluated using 399 palliative radiation courses in test set patients.

RESULTS

The C-index for overall survival was 0.786 in the test set (averaged across landmark times). For palliative radiation courses, the C-index was 0.745 (95% confidence interval [CI] = 0.715 to 0.775) compared with 0.635 (95% CI = 0.601 to 0.669) for a published model using performance status, primary tumor site, and treated site (two-sided P < .001). Our model's predictions were well-calibrated.

CONCLUSIONS

The model showed high predictive performance, which will need to be validated using external data. Because it is fully automated, the model can be used to examine providers' practice patterns and could be deployed in a decision support tool to help improve quality of care.