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

Overview of Deep Learning Models in Biomedical Domain with the Help of R Statistical Software

With the increase in volume of data and presence of structured and unstructured data in the biomedical filed, there is a need for building models which can handle complex & non-linear relations in the data and also predict and classify outcomes with higher accuracy. Deep learning models are one of such models which can handle complex and nonlinear data and are being increasingly used in the biomedical filed in the recent years. Deep learning methodology evolved from artificial neural networks which process the input data through multiple hidden layers with higher level of abstraction. Deep Learning networks are used in various fields such as image processing, speech recognition, fraud deduction, classification and prediction. Objectives of this paper is to provide an overview of Deep Learning Models and its application in the biomedical domain using R Statistical software Deep Learning concepts are illustrated by using the R statistical software package. X-ray Images from NIH datasets used to explain the prediction accuracy of the deep learning models. Deep Learning models helped to classify the outcomes under study with 91% accuracy. The paper provided an overview of Deep Learning Models, its types, its application in biomedical domain. - is paper has shown the effect of deep learning network in classifying images into normal and disease with 91% accuracy with help of the R statistical package.

A scoping review of ethics considerations in clinical natural language processing

Objectives

To review through an ethics lens the state of research in clinical natural language processing (NLP) for the study of bias and fairness, and to identify gaps in research.

Methods

We queried PubMed and Google Scholar for articles published between 2015 and 2021 concerning clinical NLP, bias, and fairness. We analyzed articles using a framework that combines the machine learning (ML) development process (ie, design, data, algorithm, and critique) and bioethical concepts of beneficence, nonmaleficence, autonomy, justice, as well as explicability. Our approach further differentiated between biases of clinical text (eg, systemic or personal biases in clinical documentation towards patients) and biases in NLP applications.

Results

Out of 1162 articles screened, 22 met criteria for full text review. We categorized articles based on the design (N = 2), data (N = 12), algorithm (N = 14), and critique (N = 17) phases of the ML development process.

Discussion

Clinical NLP can be used to study bias in applications reliant on clinical text data as well as explore biases in the healthcare setting. We identify 3 areas of active research that require unique ethical considerations about the potential for clinical NLP to address and/or perpetuate bias: (1) selecting metrics that interrogate bias in models; (2) opportunities and risks of identifying sensitive patient attributes; and (3) best practices in reconciling individual autonomy, leveraging patient data, and inferring and manipulating sensitive information of subgroups. Finally, we address the limitations of current ethical frameworks to fully address concerns of justice. Clinical NLP is a rapidly advancing field, and assessing current approaches against ethical considerations can help the discipline use clinical NLP to explore both healthcare biases and equitable NLP applications.

PercolationDF: A percolation-based medical diagnosis framework

Goal: With the continuing shortage and unequal distribution of medical resources, our objective is to develop a general diagnosis framework that utilizes a smaller amount of electronic medical records (EMRs) to alleviate the problem that the data volume requirement of prevailing models is too vast for medical institutions to afford. Methods: The framework proposed contains network construction, network expansion, and disease diagnosis methods. In the first two stages above, the knowledge extracted from EMRs is utilized to build and expense an EMR-based medical knowledge network (EMKN) to model and represent the medical knowledge. Then, percolation theory is modified to diagnose EMKN. Result: Facing the lack of data, our framework outperforms naïve Bayes networks, neural networks and logistic regression, especially in the top-10 recall. Out of 207 test cases, 51.7% achieved 100% in the top-10 recall, 21% better than what was achieved in one of our previous studies. Conclusion: The experimental results show that the proposed framework may be useful for medical knowledge representation and diagnosis. The framework effectively alleviates the lack of data volume by inferring the knowledge modeled in EMKN. Significance: The proposed framework not only has applications for diagnosis but also may be extended to other domains to represent and model the knowledge and inference on the representation.

An overview of artificial intelligence in oncology

Cancer is associated with significant morbimortality globally. Advances in screening, diagnosis, management and survivorship were substantial in the last decades, however, challenges in providing personalized and data-oriented care remain. Artificial intelligence (AI), a branch of computer science used for predictions and automation, has emerged as potential solution to improve the healthcare journey and to promote precision in healthcare. AI applications in oncology include, but are not limited to, optimization of cancer research, improvement of clinical practice (eg., prediction of the association of multiple parameters and outcomes - prognosis and response) and better understanding of tumor molecular biology. In this review, we examine the current state of AI in oncology, including fundamentals, current applications, limitations and future perspectives.

Annual Research Review: Translational machine learning for child and adolescent psychiatry

Children and adolescents could benefit from the use of predictive tools that facilitate personalized diagnoses, prognoses, and treatment selection. Such tools have not yet been deployed using traditional statistical methods, potentially due to the limitations of the paradigm and the need to leverage large amounts of digital data. This review will suggest that a machine learning approach could address these challenges and is designed to introduce new readers to the background, methods, and results in the field. A rationale is first introduced followed by an outline of fundamental elements of machine learning approaches. To provide an overview of the use of the techniques in child and adolescent literature, a scoping review of broad trends is then presented. Selected studies are also highlighted in order to draw attention to research areas that are closest to translation and studies that exhibit a high degree of experimental innovation. Limitations to the research, and machine learning approaches generally, are outlined in the penultimate section highlighting issues related to sample sizes, validation, clinical utility, and ethical challenges. Finally, future directions are discussed that could enhance the possibility of clinical implementation and address specific questions relevant to the child and adolescent psychiatry. The review gives a broad overview of the machine learning paradigm in order to highlight the benefits of a shift in perspective towards practically oriented statistical solutions that aim to improve clinical care of children and adolescents.

AI and Clinical Decision Making: The Limitations and Risks of Computational Reductionism in Bowel Cancer Screening

Advances in artificial intelligence in healthcare are frequently promoted as ‘solutions’ to improve the accuracy, safety, and quality of clinical decisions, treatments, and care. Despite some diagnostic success, however, AI systems rely on forms of reductive reasoning and computational determinism that embed problematic assumptions about clinical decision-making and clinical practice. Clinician autonomy, experience, and judgement are reduced to inputs and outputs framed as binary or multi-class classification problems benchmarked against a clinician’s capacity to identify or predict disease states. This paper examines this reductive reasoning in AI systems for colorectal cancer (CRC) to highlight their limitations and risks: (1) in AI systems themselves due to inherent biases in (a) retrospective training datasets and (b) embedded assumptions in underlying AI architectures and algorithms; (2) in the problematic and limited evaluations being conducted on AI systems prior to system integration in clinical practice; and (3) in marginalising socio-technical factors in the context-dependent interactions between clinicians, their patients, and the broader health system. The paper argues that to optimise benefits from AI systems and to avoid negative unintended consequences for clinical decision-making and patient care, there is a need for more nuanced and balanced approaches to AI system deployment and evaluation in CRC.

Scale-up of Digital Innovations in Health Care: Expert Commentary on Enablers and Barriers

Health care delivery is undergoing a rapid change from traditional processes toward the use of digital health interventions and personalized medicine. This movement has been accelerated by the COVID-19 crisis as a response to the need to guarantee access to health care services while reducing the risk of contagion. Digital health scale-up is now also vital to achieve population-wide impact: it will only accomplish sustainable effects if and when deployed into regular health care delivery services. The question of how sustainable digital health scale-up can be successfully achieved has, however, not yet been sufficiently resolved. This paper identifies and discusses enablers and barriers for scaling up digital health innovations. The results discussed in this paper were gathered by scientists and representatives of public bodies as well as patient organizations at an international workshop on scaling up digital health innovations. Results are explored in the context of prior research and implications for future work in achieving large-scale implementations that will benefit the population as a whole.

Scientific Exploration and Explainable Artificial Intelligence

Models developed using machine learning are increasingly prevalent in scientific research. At the same time, these models are notoriously opaque. Explainable AI aims to mitigate the impact of opacity by rendering opaque models transparent. More than being just the solution to a problem, however, Explainable AI can also play an invaluable role in scientific exploration. This paper describes how post-hoc analytic techniques from Explainable AI can be used to refine target phenomena in medical science, to identify starting points for future investigations of (potentially) causal relationships, and to generate possible explanations of target phenomena in cognitive science. In this way, this paper describes how Explainable AI—over and above machine learning itself—contributes to the efficiency and scope of data-driven scientific research.

Multimodal deep learning for biomedical data fusion: a review

Biomedical data are becoming increasingly multimodal and thereby capture the underlying complex relationships among biological processes. Deep learning (DL)-based data fusion strategies are a popular approach for modeling these nonlinear relationships. Therefore, we review the current state-of-the-art of such methods and propose a detailed taxonomy that facilitates more informed choices of fusion strategies for biomedical applications, as well as research on novel methods. By doing so, we find that deep fusion strategies often outperform unimodal and shallow approaches. Additionally, the proposed subcategories of fusion strategies show different advantages and drawbacks. The review of current methods has shown that, especially for intermediate fusion strategies, joint representation learning is the preferred approach as it effectively models the complex interactions of different levels of biological organization. Finally, we note that gradual fusion, based on prior biological knowledge or on search strategies, is a promising future research path. Similarly, utilizing transfer learning might overcome sample size limitations of multimodal data sets. As these data sets become increasingly available, multimodal DL approaches present the opportunity to train holistic models that can learn the complex regulatory dynamics behind health and disease.

MedGCN: Medication recommendation and lab test imputation via graph convolutional networks

Laboratory testing and medication prescription are two of the most important routines in daily clinical practice. Developing an artificial intelligence system that can automatically make lab test imputations and medication recommendations can save costs on potentially redundant lab tests and inform physicians of a more effective prescription. We present an intelligent medical system (named MedGCN) that can automatically recommend the patients' medications based on their incomplete lab tests, and can even accurately estimate the lab values that have not been taken. In our system, we integrate the complex relations between multiple types of medical entities with their inherent features in a heterogeneous graph. Then we model the graph to learn a distributed representation for each entity in the graph based on graph convolutional networks (GCN). By the propagation of graph convolutional networks, the entity representations can incorporate multiple types of medical information that can benefit multiple medical tasks. Moreover, we introduce a cross regularization strategy to reduce overfitting for multi-task training by the interaction between the multiple tasks. In this study, we construct a graph to associate 4 types of medical entities, i.e., patients, encounters, lab tests, and medications, and applied a graph neural network to learn node embeddings for medication recommendation and lab test imputation. we validate our MedGCN model on two real-world datasets: NMEDW and MIMIC-III. The experimental results on both datasets demonstrate that our model can outperform the state-of-the-art in both tasks. We believe that our innovative system can provide a promising and reliable way to assist physicians to make medication prescriptions and to save costs on potentially redundant lab tests.

Machine Learning and Smart Devices for Diabetes Management: Systematic Review

(1) Background: The use of smart devices to better manage diabetes has increased significantly in recent years. These technologies have been introduced in order to make life easier for patients with diabetes by allowing better control of the stability of blood sugar levels and anticipating the occurrence of dangerous events (hypo/hyperglycemia), etc. That being said, the main objectives of the self-management of diabetes is to improve the lifestyle and life quality of patients with diabetes; (2) Methods: We performed a systematic review based on articles that focus on the use of smart devices for the monitoring and better management of diabetes. The search was focused on keywords related to the topic, such as “Diabetes”, “Technology”, “Self-management”, “Artificial Intelligence”, etc. This was performed using databases, such as Scopus, Google Scholar, and PubMed; (3) Results: A total of 89 studies, published between 2011 and 2021, were included. The majority of the selected research aims to solve a diabetes management problem (e.g., blood glucose prediction, early detection of risk events, and the automatic adjustment of insulin doses, etc.). In these studies, wearable devices were used in combination with artificial intelligence (AI) techniques; (4) Conclusions: Wearable devices have attracted a great deal of scientific interest in the field of healthcare for people with chronic conditions, such as diabetes. They are capable of assisting in the management of diabetes, as well as preventing complications associated with this condition. Furthermore, the usage of these devices has improved illness management and quality of life.

Improving Performance of Outcome Prediction for In-patients with Acute Myocardial Infarction Based on Embedding Representation Learned from Electronic Medical Records: Development and Validation Study (Preprint)

Background

The widespread secondary use of electronic medical records (EMRs) promotes health care quality improvement. Representation learning that can automatically extract hidden information from EMR data has gained increasing attention.

Objective

We aimed to propose a patient representation with more feature associations and task-specific feature importance to improve the outcome prediction performance for inpatients with acute myocardial infarction (AMI).

Methods

Medical concepts, including patients’ age, gender, disease diagnoses, laboratory tests, structured radiological features, procedures, and medications, were first embedded into real-value vectors using the improved skip-gram algorithm, where concepts in the context windows were selected by feature association strengths measured by association rule confidence. Then, each patient was represented as the sum of the feature embeddings weighted by the task-specific feature importance, which was applied to facilitate predictive model prediction from global and local perspectives. We finally applied the proposed patient representation into mortality risk prediction for 3010 and 1671 AMI inpatients from a public data set and a private data set, respectively, and compared it with several reference representation methods in terms of the area under the receiver operating characteristic curve (AUROC), area under the precision-recall curve (AUPRC), and F1-score.

Results

Compared with the reference methods, the proposed embedding-based representation showed consistently superior predictive performance on the 2 data sets, achieving mean AUROCs of 0.878 and 0.973, AUPRCs of 0.220 and 0.505, and F1-scores of 0.376 and 0.674 for the public and private data sets, respectively, while the greatest AUROCs, AUPRCs, and F1-scores among the reference methods were 0.847 and 0.939, 0.196 and 0.283, and 0.344 and 0.361 for the public and private data sets, respectively. Feature importance integrated in patient representation reflected features that were also critical in prediction tasks and clinical practice.

Conclusions

The introduction of feature associations and feature importance facilitated an effective patient representation and contributed to prediction performance improvement and model interpretation.

Structure-Aware Siamese Graph Neural Networks for Encounter-Level Patient Similarity Learning

Patient similarity learning has attracted great research interest in biomedical informatics. Correctly identifying the similarity between a given patient and patient records in the database could contribute to clinical references for diagnosis and medication. The sparsity of underlying relationships between patients poses difficulties for similarity learning, which becomes more challenging when considering real-world Electronic Health Records (EHRs) with a large number of missing values. In the paper, we organize EHRs as a graph and propose a novel deep learning framework, Structure-aware Siamese Graph neural Networks (SSGNet), to perform robust encounter-level patient similarity learning while capturing the intrinsic graph structure and mitigating the influence from missing values. The proposed SSGNet regards each patient encounter as a node, and learns the node embeddings and the similarity between nodes simultaneously via Graph Neural Networks (GNNs) with siamese architecture. Further, SSGNet employs a low-rank and contrastive objective to optimize the structure of the patient graph and enhance model capacity. The extensive experiments were conducted on two publicly available datasets and a real-world dataset regarding IgA nephropathy from Peking University First Hospital, in comparison with multiple baseline and state-of-the-art methods. The significant improvement in Accuracy, Precision, Recall and F1 score on the patient encounter pairwise similarity classification task demonstrates the superiority of SSGNet. The mean average precision (mAP) of SSGNet on the similar encounter retrieval task is also better than other competitors. Furthermore, SSGNet's stable similarity classification accuracies at different missing rates of data validate the effectiveness and robustness of our proposal.

Improving Pain Assessment using Vital Signs and Pain Medication for patients with Sickle Cell Disease: Retrospective Study (Preprint)

Background

Sickle cell disease (SCD) is the most common inherited blood disorder affecting millions of people worldwide. Most patients with SCD experience repeated, unpredictable episodes of severe pain. These pain episodes are the leading cause of emergency department visits among patients with SCD and may last for several weeks. Arguably, the most challenging aspect of treating pain episodes in SCD is assessing and interpreting a patient’s pain intensity level.

Objective

This study aims to learn deep feature representations of subjective pain trajectories using objective physiological signals collected from electronic health records.

Methods

This study used electronic health record data collected from 496 Duke University Medical Center participants over 5 consecutive years. Each record contained measures for 6 vital signs and the patient’s self-reported pain score, with an ordinal range from 0 (no pain) to 10 (severe and unbearable pain). We also extracted 3 features related to medication: medication type, medication status (given or applied, or missed or removed or due), and total medication dosage (mg/mL). We used variational autoencoders for representation learning and designed machine learning classification algorithms to build pain prediction models. We evaluated our results using an accuracy and confusion matrix and visualized the qualitative data representations.

Results

We designed a classification model using raw data and deep representational learning to predict subjective pain scores with average accuracies of 82.8%, 70.6%, 49.3%, and 47.4% for 2-point, 4-point, 6-point, and 11-point pain ratings, respectively. We observed that random forest classification models trained on deep represented features outperformed models trained on unrepresented data for all pain rating scales. We observed that at varying Likert scales, our models performed better when provided with medication data along with vital signs data. We visualized the data representations to understand the underlying latent representations, indicating neighboring representations for similar pain scores with a higher resolution of pain ratings.

Conclusions

Our results demonstrate that medication information (the type of medication, total medication dosage, and whether the medication was given or missed) can significantly improve subjective pain prediction modeling compared with modeling with only vital signs. This study shows promise in data-driven estimated pain scores that will help clinicians with additional information about the patient’s condition, in addition to the patient’s self-reported pain scores.

Flexible-Window Predictions on Electronic Health Records

Various types of machine learning techniques are available for analyzing electronic health records (EHRs). For predictive tasks, most existing methods either explicitly or implicitly divide these time-series datasets into predetermined observation and prediction windows. Patients have different lengths of medical history and the desired predictions (for purposes such as diagnosis or treatment) are required at different times in the future. In this paper, we propose a method that uses a sequence-to-sequence generator model to transfer an input sequence of EHR data to a sequence of user-defined target labels, providing the end-users with "flexible" observation and prediction windows to define. We use adversarial and semi-supervised approaches in our design, where the sequence-to-sequence model acts as a generator and a discriminator distinguishes between the actual (observed) and generated labels. We evaluate our models through an extensive series of experiments using two large EHR datasets from adult and pediatric populations. In an obesity predicting case study, we show that our model can achieve superior results in flexible-window prediction tasks, after being trained once and even with large missing rates on the input EHR data. Moreover, using a number of attention analysis experiments, we show that the proposed model can effectively learn more relevant features in different prediction tasks.

Predictive structured-unstructured interactions in EHR models: A case study of suicide prediction

Clinical risk prediction models powered by electronic health records (EHRs) are becoming increasingly widespread in clinical practice. With suicide-related mortality rates rising in recent years, it is becoming increasingly urgent to understand, predict, and prevent suicidal behavior. Here, we compare the predictive value of structured and unstructured EHR data for predicting suicide risk. We find that Naive Bayes Classifier (NBC) and Random Forest (RF) models trained on structured EHR data perform better than those based on unstructured EHR data. An NBC model trained on both structured and unstructured data yields similar performance (AUC = 0.743) to an NBC model trained on structured data alone (0.742, p = 0.668), while an RF model trained on both data types yields significantly better results (AUC = 0.903) than an RF model trained on structured data alone (0.887, p < 0.001), likely due to the RF model’s ability to capture interactions between the two data types. To investigate these interactions, we propose and implement a general framework for identifying specific structured-unstructured feature pairs whose interactions differ between case and non-case cohorts, and thus have the potential to improve predictive performance and increase understanding of clinical risk. We find that such feature pairs tend to capture heterogeneous pairs of general concepts, rather than homogeneous pairs of specific concepts. These findings and this framework can be used to improve current and future EHR-based clinical modeling efforts.

Patient Representation Learning From Heterogeneous Data Sources and Knowledge Graphs Using Deep Collective Matrix Factorization: Evaluation Study

BACKGROUND

Patient representation learning aims to learn features, also called representations, from input sources automatically, often in an unsupervised manner, for use in predictive models. This obviates the need for cumbersome, time- and resource-intensive manual feature engineering, especially from unstructured data such as text, images, or graphs. Most previous techniques have used neural network-based autoencoders to learn patient representations, primarily from clinical notes in electronic medical records (EMRs). Knowledge graphs (KGs), with clinical entities as nodes and their relations as edges, can be extracted automatically from biomedical literature and provide complementary information to EMR data that have been found to provide valuable predictive signals.

OBJECTIVE

This study aims to evaluate the efficacy of collective matrix factorization (CMF), both the classical variant and a recent neural architecture called deep CMF (DCMF), in integrating heterogeneous data sources from EMR and KG to obtain patient representations for clinical decision support tasks.

METHODS

Using a recent formulation for obtaining graph representations through matrix factorization within the context of CMF, we infused auxiliary information during patient representation learning. We also extended the DCMF architecture to create a task-specific end-to-end model that learns to simultaneously find effective patient representations and predictions. We compared the efficacy of such a model to that of first learning unsupervised representations and then independently learning a predictive model. We evaluated patient representation learning using CMF-based methods and autoencoders for 2 clinical decision support tasks on a large EMR data set.

RESULTS

Our experiments show that DCMF provides a seamless way for integrating multiple sources of data to obtain patient representations, both in unsupervised and supervised settings. Its performance in single-source settings is comparable with that of previous autoencoder-based representation learning methods. When DCMF is used to obtain representations from a combination of EMR and KG, where most previous autoencoder-based methods cannot be used directly, its performance is superior to that of previous nonneural methods for CMF. Infusing information from KGs into patient representations using DCMF was found to improve downstream predictive performance.

CONCLUSIONS

Our experiments indicate that DCMF is a versatile model that can be used to obtain representations from single and multiple data sources and combine information from EMR data and KGs. Furthermore, DCMF can be used to learn representations in both supervised and unsupervised settings. Thus, DCMF offers an effective way of integrating heterogeneous data sources and infusing auxiliary knowledge into patient representations.

An explainable artificial intelligence approach for predicting cardiovascular outcomes using electronic health records

Understanding the conditionally-dependent clinical variables that drive cardiovascular health outcomes is a major challenge for precision medicine. Here, we deploy a recently developed massively scalable comorbidity discovery method called Poisson Binomial based Comorbidity discovery (PBC), to analyze Electronic Health Records (EHRs) from the University of Utah and Primary Children's Hospital (over 1.6 million patients and 77 million visits) for comorbid diagnoses, procedures, and medications. Using explainable Artificial Intelligence (AI) methodologies, we then tease apart the intertwined, conditionally-dependent impacts of comorbid conditions and demography upon cardiovascular health, focusing on the key areas of heart transplant, sinoatrial node dysfunction and various forms of congenital heart disease. The resulting multimorbidity networks make possible wide-ranging explorations of the comorbid and demographic landscapes surrounding these cardiovascular outcomes, and can be distributed as web-based tools for further community-based outcomes research. The ability to transform enormous collections of EHRs into compact, portable tools devoid of Protected Health Information solves many of the legal, technological, and data-scientific challenges associated with large-scale EHR analyses.

CODER: Knowledge-infused cross-lingual medical term embedding for term normalization

OBJECTIVE

This paper aims to propose knowledge-aware embedding, a critical tool for medical term normalization.

METHODS

We develop CODER (Cross-lingual knowledge-infused medical term embedding) via contrastive learning based on a medical knowledge graph (KG) named the Unified Medical Language System, and similarities are calculated utilizing both terms and relation triplets from the KG. Training with relations injects medical knowledge into embeddings and can potentially improve their performance as machine learning features.

RESULTS

We evaluate CODER based on zero-shot term normalization, semantic similarity, and relation classification benchmarks, and the results show that CODER outperforms various state-of-the-art biomedical word embeddings, concept embeddings, and contextual embeddings.

CONCLUSION

CODER embeddings excellently reflect semantic similarity and relatedness of medical concepts. One can use CODER for embedding-based medical term normalization or to provide features for machine learning. Similar to other pretrained language models, CODER can also be fine-tuned for specific tasks. Codes and models are available at https://github.com/GanjinZero/CODER.

Artificial intelligence in cancer diagnostics and therapy: current perspectives

Artificial intelligence (AI) has found its way into every sphere of human life including the field of medicine. Detection of cancer might be AI's most altruistic and convoluted challenge to date in the field of medicine. Embedding AI into various aspects of cancer diagnostics would be of immense use in dealing with the tedious, repetitive, time-consuming job of lesion detection, remove opportunities for human error, and cut costs and time. This would be of great value in cancer screening programs. By using AI algorithms, data from digital images from radiology and pathology that are imperceptible to the human eye can be identified (radiomics and pathomics). Correlating radiomics and pathomics with clinico-demographic-therapy-morbidity-mortality profiles will lead to a greater understanding of cancers. Specific imaging phenotypes have been found to be associated with specific gene-determined molecular pathways involved in cancer pathogenesis (radiogenomics). All these developments would not only help to personalize oncologic practice but also lead to the development of new imaging biomarkers. AI algorithms in oncoimaging and oncopathology will broadly have the following uses: cancer screening (detection of lesions), characterization and grading of tumors, and clinical decision-making and prognostication. However, AI cannot be a foolproof panacea nor can it supplant the role of humans. It can however be a powerful and useful complement to human insights and deeper understanding. Multiple issues like standardization, validity, ethics, privacy, finances, legal liability, training, accreditation, etc., need to be overcome before the vast potential of AI in diagnostic oncology can be fully harnessed.

Application of Artificial Intelligence on Psychological Interventions and Diagnosis: An Overview

BACKGROUND

Innovative technologies, such as machine learning, big data, and artificial intelligence (AI) are approaches adopted for personalized medicine, and psychological interventions and diagnosis are facing huge paradigm shifts. In this literature review, we aim to highlight potential applications of AI on psychological interventions and diagnosis.

METHODS

This literature review manifest studies that discuss how innovative technology as deep learning (DL) and AI is affecting psychological assessment and psychotherapy, we performed a search on PUBMED, and Web of Science using the terms "psychological interventions," "diagnosis on mental health disorders," "artificial intelligence," and "deep learning." Only studies considering patients' datasets are considered.

RESULTS

Nine studies met the inclusion criteria. Beneficial effects on clinical symptoms or prediction were shown in these studies, but future study is needed to determine the long-term effects.

LIMITATIONS

The major limitation for the current study is the small sample size, and lies in the lack of long-term follow-up-controlled studies for a certain symptom.

CONCLUSIONS

AI such as DL applications showed promising results on clinical practice, which could lead to profound impact on personalized medicine for mental health conditions. Future studies can improve furthermore by increasing sample sizes and focusing on ethical approvals and adherence for online-therapy.

VBridge: Connecting the Dots Between Features and Data to Explain Healthcare Models

Machine learning (ML) is increasingly applied to Electronic Health Records (EHRs) to solve clinical prediction tasks. Although many ML models perform promisingly, issues with model transparency and interpretability limit their adoption in clinical practice. Directly using existing explainable ML techniques in clinical settings can be challenging. Through literature surveys and collaborations with six clinicians with an average of 17 years of clinical experience, we identified three key challenges, including clinicians' unfamiliarity with ML features, lack of contextual information, and the need for cohort-level evidence. Following an iterative design process, we further designed and developed VBridge, a visual analytics tool that seamlessly incorporates ML explanations into clinicians' decision-making workflow. The system includes a novel hierarchical display of contribution-based feature explanations and enriched interactions that connect the dots between ML features, explanations, and data. We demonstrated the effectiveness of VBridge through two case studies and expert interviews with four clinicians, showing that visually associating model explanations with patients' situational records can help clinicians better interpret and use model predictions when making clinician decisions. We further derived a list of design implications for developing future explainable ML tools to support clinical decision-making.

Time-to-event prediction using survival analysis methods for Alzheimer's disease progression

INTRODUCTION

Many research studies have well investigated Alzheimer's disease (AD) detection and progression. However, the continuous-time survival prediction of AD is not yet fully explored to support medical practitioners with predictive analytics. In this study, we develop a survival analysis approach to examine interactions between patients' inherent temporal and medical patterns and predict the probability of the AD next stage progression during a time period. The likelihood of reaching the following AD stage is unique to a patient, helping the medical practitioner analyze the patient's condition and provide personalized treatment recommendations ahead of time.

METHODOLOGIES

We simulate the disease progression based on patient profiles using non-linear survival methods-non-linear Cox proportional hazard model (Cox-PH) and neural multi-task logistic regression (N-MTLR). In addition, we evaluate the concordance index (C-index) and Integrated Brier Score (IBS) to describe the evolution to the next stage of AD. For personalized forecasting of disease, we also developed deep neural network models using the dataset provided by the National Alzheimer's Coordinating Center with their multiple-visit details between 2005 and 2017.

RESULTS

The experiment results show that our N-MTLR based survival models outperform the CoxPH models, the best of which gives Concordance-Index of 0.79 and IBS of 0.09. We obtained 50 critical features out of 92 by applying recursive feature elimination and random forest techniques on the clinical data; the top ones include normal cognition and behavior, criteria for dementia, community affairs, etc. Our study demonstrates that selecting critical features can improve the effectiveness of probabilities at each time interval.

CONCLUSIONS

The proposed deep learning-based survival method and model can be used by medical practitioners to predict the patients' AD shift efficiently and recommend personalized treatment to mitigate or postpone the effects of AD. More generally, our proposed survival analysis approach for predicting disease stage shift can be used for other progressive diseases such as cancer, Huntington's disease, and scleroderma, just to mention a few, using the corresponding clinical data.

Identifying drug-related attributes to personalise antihypertensive agents: the outcome report of patients receiving metoprolol therapy

Background

Currently, numerous antihypertensive drugs from different pharmacological classes are available; however, blood pressure control is achieved in only less than a third of patients treated for hypertension. Moreover, providing optimal and personalised treatment for hypertension is challenging. Therefore, in this study, we propose a ‘drug-related attributes’ sensitive spectrum. This novel concept can assist clinicians in selecting an optimal antihypertensive drug and improve blood pressure control after examining the attributes of a patient.

Methods

We collected clinical data on attributes related to hypertension and its therapy of inpatients from West China Hospital who received metoprolol therapy and constructed the sensitive spectrum using data-visualisation tools.

Results

Our analysis revealed that haematocrit, haemoglobin, serum creatinine, serum cystatin C, serum urea, age, sex, systolic pressure, diastolic pressure, pulse pressure, and heart rate are metoprolol-related attributes.

Conclusion

Our study showed that all metoprolol-related attributes identified are reasonable and helpful in improving the personalisation of metoprolol therapy. The proposed drug-related attributes spectrum can help personalise antihypertensive medication. Moreover, data-visualisation tools can be effectively used to mine the drug-related attributes sensitive spectrum.

Machine learning and natural language processing to identify falls in electronic patient care records from ambulance attendances

We derived machine learning models utilizing features generated by natural language processing (NLP) of free-text data from an ambulance services provider to identify fall cases. The data comprised samples of electronic patient care records care records (ePCRs) from St John Western Australia (WA), the sole ambulance services provider in most of WA. We manually labeled fall cases by reviewing the free-text summary. The models used features including case characteristics (e.g., age) and text frequency-inverse document frequency (tf-idf) of each word of the free-text generated by NLP. Support vector machine (SVM) and random forest were used as classifiers. We compared the performance of the models against the manual identification of falls by recall, precision, and F-measure. A total of 9,447 cases (1%) were randomly sampled, of which 1,648 (17%) were labeled as fall. The best model was an SVM model using case characteristics and tf-idf's of the first 100 words of free-text, with recall of 0.84, precision of 0.86, and F-measure of 0.85. This performance was better than an SVM model with only case characteristics. Machine-learning models incorporated with features generated by NLP improved the performance of classifying fall cases compared with models without such features. Scope remains for further improvement.

Deep learning for temporal data representation in electronic health records: A systematic review of challenges and methodologies

OBJECTIVE

Temporal electronic health records (EHRs) contain a wealth of information for secondary uses, such as clinical events prediction and chronic disease management. However, challenges exist for temporal data representation. We therefore sought to identify these challenges and evaluate novel methodologies for addressing them through a systematic examination of deep learning solutions.

METHODS

We searched five databases (PubMed, Embase, the Institute of Electrical and Electronics Engineers [IEEE] Xplore Digital Library, the Association for Computing Machinery [ACM] Digital Library, and Web of Science) complemented with hand-searching in several prestigious computer science conference proceedings. We sought articles that reported deep learning methodologies on temporal data representation in structured EHR data from January 1, 2010, to August 30, 2020. We summarized and analyzed the selected articles from three perspectives: nature of time series, methodology, and model implementation.

RESULTS

We included 98 articles related to temporal data representation using deep learning. Four major challenges were identified, including data irregularity, heterogeneity, sparsity, and model opacity. We then studied how deep learning techniques were applied to address these challenges. Finally, we discuss some open challenges arising from deep learning.

CONCLUSION

Temporal EHR data present several major challenges for clinical prediction modeling and data utilization. To some extent, current deep learning solutions can address these challenges. Future studies may consider designing comprehensive and integrated solutions. Moreover, researchers should incorporate clinical domain knowledge into study designs and enhance model interpretability to facilitate clinical implementation.

The Use of Artificial Intelligence and Machine Learning in Surgery: A Comprehensive Literature Review

Interest in the use of artificial intelligence (AI) and machine learning (ML) in medicine has grown exponentially over the last few years. With its ability to enhance speed, precision, and efficiency, AI has immense potential, especially in the field of surgery. This article aims to provide a comprehensive literature review of artificial intelligence as it applies to surgery and discuss practical examples, current applications, and challenges to the adoption of this technology. Furthermore, we elaborate on the utility of natural language processing and computer vision in improving surgical outcomes, research, and patient care.

Measuring Patient Similarity on Multiple Diseases by Joint Learning via a Convolutional Neural Network

Patient similarity research is one of the most fundamental tasks in healthcare, helping to make decisions without incurring additional time and costs in clinical practices. Patient similarity can also apply to various medical fields, such as cohort analysis and personalized treatment recommendations. Because of this importance, patient similarity measurement studies are actively being conducted. However, medical data have complex, irregular, and sequential characteristics, making it challenging to measure similarity. Therefore, measuring accurate similarity is a significant problem. Existing similarity measurement studies use supervised learning to calculate the similarity between patients, with similarity measurement studies conducted only on one specific disease. However, it is not realistic to consider only one kind of disease, because other conditions usually accompany it; a study to measure similarity with multiple diseases is needed. This research proposes a convolution neural network-based model that jointly combines feature learning and similarity learning to define similarity in patients with multiple diseases. We used the cohort data from the National Health Insurance Sharing Service of Korea for the experiment. Experimental results verify that the proposed model has outstanding performance when compared to other existing models for measuring multiple-disease patient similarity.

Artificial Intelligence in Medicine: A Multinational Multi-Center Survey on the Medical and Dental Students' Perception

Background: The emerging field of artificial intelligence (AI) will probably affect the practice for the next generation of doctors. However, the students' views on AI have not been largely investigated. Methods: An anonymous electronic survey on AI was designed for medical and dental students to explore: (1) sources of information about AI, (2) AI applications and concerns, (3) AI status as a topic in medicine, and (4) students' feelings and attitudes. The questionnaire was advertised on social media platforms in 2020. Security measures were employed to prevent fraudulent responses. Mann-Whitney U-test was employed for all comparisons. A sensitivity analysis was also performed by binarizing responses to express disagreement and agreement using the Chi-squared test. Results: Three thousand one hundred thirty-three respondents from 63 countries from all continents were included. Most respondents reported having at least a moderate understanding of the technologies underpinning AI and of their current application, with higher agreement associated with being male (p < 0.0001), tech-savvy (p < 0.0001), pre-clinical student (p < 0.006), and from a developed country (p < 0.04). Students perceive AI as a partner rather than a competitor (72.2%) with a higher agreement for medical students (p = 0.002). The belief that AI will revolutionize medicine and dentistry (83.9%) with greater agreement for students from a developed country (p = 0.0004) was noted. Most students agree that the AI developments will make medicine and dentistry more exciting (69.9%), that AI shall be part of the medical training (85.6%) and they are eager to incorporate AI in their future practice (99%). Conclusion: Currently, AI is a hot topic in medicine and dentistry. Students have a basic understanding of AI principles, a positive attitude toward AI and would like to have it incorporated into their training.

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

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

Dynamic Functional Continuous Time Bayesian Networks for Prediction and Monitoring of the Impact of Patients' Modifiable Lifestyle Behaviors on the Emergence of Multiple Chronic Conditions

More than a quarter of all Americans are estimated to have multiple chronic conditions (MCC). It is known that shared modifiable lifestyle behaviors account for many common MCC. What is not precisely known is the dynamic effect of changes in lifestyle behaviors on the trajectories of MCC emergence. This paper proposes dynamic functional continuous time Bayesian networks to effectively formulate the dynamic effect of patients' modifiable lifestyle behaviors and their interaction with non-modifiable demographics and preexisting conditions on the emergence of MCC. The proposed method considers the parameters of the conditional dependencies of MCC as a nonlinear state-space model and develops an extended Kalman filter to capture the dynamics of the modifiable risk factors on the MCC evolution. It also develops a tensor-based control chart based on the integration of multilinear principal component analysis and multivariate exponentially weighted moving average chart to monitor the effect of changes in the modifiable risk factors on the risk of new MCC. We validate the proposed method based on a combination of simulation and a real dataset of 385 patients from the Cameron County Hispanic Cohort. The dataset examines the emergence of 5 chronic conditions (Diabetes, Obesity, Cognitive Impairment, Hyperlipidemia, Hypertension) based on 4 modifiable lifestyle behaviors representing (Diet, Exercise, Smoking Habits, Drinking Habits) and 3 non-modifiable demographic risk factors (Age, Gender, Education). For the simulated study, the proposed algorithm shows a run-length of 4 samples (4 months) to identify behavioral changes with significant impacts on the risk of new MCC. For the real data study, the proposed algorithm shows a run-length of one sample (one year) to identify behavioral changes with significant impacts on the risk of new MCC. The results demonstrate the sensitivity of the proposed methodology for dynamic prediction and monitoring of the risk of MCC emergence in individual patients.

The Dilemma of Analyzing Physical Activity and Sedentary Behavior with Wrist Accelerometer Data: Challenges and Opportunities

Physical behaviors (e.g., physical activity and sedentary behavior) have been the focus among many researchers in the biomedical and behavioral science fields. The recent shift from hip- to wrist-worn accelerometers in these fields has signaled the need to develop novel approaches to process raw acceleration data of physical activity and sedentary behavior. However, there is currently no consensus regarding the best practices for analyzing wrist-worn accelerometer data to accurately predict individuals' energy expenditure and the times spent in different intensities of free-living physical activity and sedentary behavior. To this end, accurately analyzing and interpreting wrist-worn accelerometer data has become a major challenge facing many clinicians and researchers. In response, this paper attempts to review different methodologies for analyzing wrist-worn accelerometer data and offer cutting edge, yet appropriate analysis plans for wrist-worn accelerometer data in the assessment of physical behavior. In this paper, we first discuss the fundamentals of wrist-worn accelerometer data, followed by various methods of processing these data (e.g., cut points, steps per minute, machine learning), and then we discuss the opportunities, challenges, and directions for future studies in this area of inquiry. This is the most comprehensive review paper to date regarding the analysis and interpretation of free-living physical activity data derived from wrist-worn accelerometers, aiming to help establish a blueprint for processing wrist-derived accelerometer data.

Different Data Mining Approaches Based Medical Text Data

The amount of medical text data is increasing dramatically. Medical text data record the progress of medicine and imply a large amount of medical knowledge. As a natural language, they are characterized by semistructured, high-dimensional, high data volume semantics and cannot participate in arithmetic operations. Therefore, how to extract useful knowledge or information from the total available data is very important task. Using various techniques of data mining can extract valuable knowledge or information from data. In the current study, we reviewed different approaches to apply for medical text data mining. The advantages and shortcomings for each technique compared to different processes of medical text data were analyzed. We also explored the applications of algorithms for providing insights to the users and enabling them to use the resources for the specific challenges in medical text data. Further, the main challenges in medical text data mining were discussed. Findings of this paper are benefit for helping the researchers to choose the reasonable techniques for mining medical text data and presenting the main challenges to them in medical text data mining.

Artificial Intelligence: A New Tool in Oncologist's Armamentarium

Artificial intelligence (AI) has become an essential tool in human life because of its pivotal role in communications, transportation, media, and social networking. Inspired by the complex neuronal network and its functions in human beings, AI, using computer-based algorithms and training, had been explored since the 1950s. To tackle the enormous amount of patients' clinical data, imaging, histopathological data, and the increasing pace of research on new treatments and clinical trials, and ever-changing guidelines for treatment with the advent of novel drugs and evidence, AI is the need of the hour. There are numerous publications and active work on AI's role in the field of oncology. In this review, we discuss the fundamental terminology of AI, its applications in oncology on the whole, and its limitations. There is an inter-relationship between AI, machine learning and, deep learning. The virtual branch of AI deals with machine learning. While the physical branch of AI deals with the delivery of different forms of treatment—surgery, targeted drug delivery, and elderly care. The applications of AI in oncology include cancer screening, diagnosis (clinical, imaging, and histopathological), radiation therapy (image acquisition, tumor and organs at risk segmentation, image registration, planning, and delivery), prediction of treatment outcomes and toxicities, prediction of cancer cell sensitivity to therapeutics and clinical decision-making. A specific area of interest is in the development of effective drug combinations tailored to every patient and tumor with the help of AI. Radiomics, the new kid on the block, deals with the planning and administration of radiotherapy. As with any new invention, AI has its fallacies. The limitations include lack of external validation and proof of generalizability, difficulty in data access for rare diseases, ethical and legal issues, no precise logic behind the prediction, and last but not the least, lack of education and expertise among medical professionals. A collaboration between departments of clinical oncology, bioinformatics, and data sciences can help overcome these problems in the near future.

Predicting the Travel Distance of Patients to Access Healthcare Using Deep Neural Networks

OBJECTIVE

Improving geographical access remains a key issue in determining the sufficiency of regional medical resources during health policy design. However, patient choices can be the result of the complex interactivity of various factors. The aim of this study is to propose a deep neural network approach to model the complex decision of patient choice in travel distance to access care, which is an important indicator for policymaking in allocating resources.

METHOD

We used the 4-year nationwide insurance data of Taiwan and accumulated the possible features discussed in earlier literature. This study proposes the use of a convolutional neural network (CNN)-based framework to make predictions. The model performance was tested against other machine learning methods. The proposed framework was further interpreted using Integrated Gradients (IG) to analyze the feature weights.

RESULTS

We successfully demonstrated the effectiveness of using a CNN-based framework to predict the travel distance of patients, achieving an accuracy of 0.968, AUC of 0.969, sensitivity of 0.960, and specificity of 0.989. The CNN-based framework outperformed all other methods. In this research, the IG weights are potentially explainable; however, the relationship does not correspond to known indicators in public health.

CONCLUSIONS

Our results demonstrate the feasibility of the deep learning-based travel distance prediction model. It has the potential to guide policymaking in resource allocation. Clinical and Translational Impact Statement- Deep learning technology is feasible in investigating the distance that patients would travel while accessing care. It is a tool that integrates complex interactive variables with highly imbalanced data distributions.

The PSYchiatric clinical outcome prediction (PSYCOP) cohort: leveraging the potential of electronic health records in the treatment of mental disorders

BACKGROUND

The quality of life and lifespan are greatly reduced among individuals with mental illness. To improve prognosis, the nascent field of precision psychiatry aims to provide personalised predictions for the course of illness and response to treatment. Unfortunately, the results of precision psychiatry studies are rarely externally validated, almost never implemented in clinical practice, and tend to focus on a few selected outcomes. To overcome these challenges, we have established the PSYchiatric Clinical Outcome Prediction (PSYCOP) cohort, which will form the basis for extensive studies in the upcoming years.

METHODS

PSYCOP is a retrospective cohort study that includes all patients with at least one contact with the psychiatric services of the Central Denmark Region in the period from January 1, 2011, to October 28, 2020 (n = 119 291). All data from the electronic health records (EHR) are included, spanning diagnoses, information on treatments, clinical notes, discharge summaries, laboratory tests, etc. Based on these data, machine learning methods will be used to make prediction models for a range of clinical outcomes, such as diagnostic shifts, treatment response, medical comorbidity, and premature mortality, with an explicit focus on clinical feasibility and implementation.

DISCUSSIONS

We expect that studies based on the PSYCOP cohort will advance the field of precision psychiatry through the use of state-of-the-art machine learning methods on a large and representative data set. Implementation of prediction models in clinical psychiatry will likely improve treatment and, hopefully, increase the quality of life and lifespan of those with mental illness.

Complexity and data mining in dental research: A network medicine perspective on interceptive orthodontics

Procedures and models of computerized data analysis are becoming researchers' and practitioners' thinking partners by transforming the reasoning underlying biomedicine. Complexity theory, Network analysis and Artificial Intelligence are already approaching this discipline, intending to provide support for patient's diagnosis, prognosis and treatments. At the same time, due to the sparsity, noisiness and time-dependency of medical data, such procedures are raising many unprecedented problems related to the mismatch between the human mind's reasoning and the outputs of computational models. Thanks to these computational, non-anthropocentric models, a patient's clinical situation can be elucidated in the orthodontic discipline, and the growth outcome can be approximated. However, to have confidence in these procedures, orthodontists should be warned of the related benefits and risks. Here we want to present how these innovative approaches can derive better patients' characterization, also offering a different point of view about patient's classification, prognosis and treatment.

Communication Efficient Tensor Factorization for Decentralized Healthcare Networks

Tensor factorization has been proved as an efficient unsupervised learning approach for health data analysis, especially for computational phenotyping, where the high-dimensional Electronic Health Records (EHRs) with patients history of medical procedures, medications, diagnosis, lab tests, etc., are converted to meaningful and interpretable medical concepts. Federated tensor factorization distributes the tensor computation to multiple workers under the coordination of a central server, which enables jointly learning the phenotypes across multiple hospitals while preserving the privacy of the patient information. However, existing federated tensor factorization algorithms encounter the single-point-failure issue with the involvement of the central server, which is not only easily exposed to external attacks, but also limits the number of clients sharing information with the server under restricted uplink bandwidth. In this paper, we propose CiderTF, a communication-efficient decentralized generalized tensor factorization, which reduces the uplink communication cost by leveraging a four-level communication reduction strategy designed for a generalized tensor factorization, which has the flexibility of modeling different tensor distribution with multiple kinds of loss functions. Experiments on two real-world EHR datasets demonstrate that CiderTF achieves comparable convergence with the communication reduction up to 99.99%.

Estimating redundancy in clinical text

The current mode of use of Electronic Health Records (EHR) elicits text redundancy. Clinicians often populate new documents by duplicating existing notes, then updating accordingly. Data duplication can lead to propagation of errors, inconsistencies and misreporting of care. Therefore, measures to quantify information redundancy play an essential role in evaluating innovations that operate on clinical narratives. This work is a quantitative examination of information redundancy in EHR notes. We present and evaluate two methods to measure redundancy: an information-theoretic approach and a lexicosyntactic and semantic model. Our first measure trains large Transformer-based language models using clinical text from a large openly available US-based ICU dataset and a large multi-site UK based Hospital. By comparing the information-theoretic efficient encoding of clinical text against open-domain corpora, we find that clinical text is ∼1.5× to ∼3× less efficient than open-domain corpora at conveying information. Our second measure, evaluates automated summarisation metrics Rouge and BERTScore to evaluate successive note pairs demonstrating lexicosyntactic and semantic redundancy, with averages from ∼43 to ∼65%.

Transformer + GAN based Traditional Chinese Medicine inpatient prescription recommendation (Preprint)

Background

Traditional Chinese medicine (TCM) practitioners usually follow a 4-step evaluation process during patient diagnosis: observation, auscultation, olfaction, inquiry, pulse feeling, and palpation. The information gathered in this process, along with laboratory test results and other measurements such as vital signs, is recorded in the patient’s electronic health record (EHR). In fact, all the information needed to make a treatment plan is contained in the EHR; however, only a seasoned TCM physician could use this information well to make a good treatment plan as the reasoning process is very complicated, and it takes years of practice for a medical graduate to master the reasoning skill. In this digital medicine era, with a deluge of medical data, ever-increasing computing power, and more advanced artificial neural network models, it is not only desirable but also readily possible for a computerized system to mimic the decision-making process of a TCM physician.

Objective

This study aims to develop an assistive tool that can predict prescriptions for inpatients in a hospital based on patients’ clinical EHRs.

Methods

Clinical health records containing medical histories, as well as current symptoms and diagnosis information, were used to train a transformer-based neural network model using the corresponding physician’s prescriptions as the target. This was accomplished by extracting relevant information, such as the patient’s current illness, medicines taken, nursing care given, vital signs, examinations, and laboratory results from the patient’s EHRs. The obtained information was then sorted chronologically to produce a sequence of data for the patient. These time sequence data were then used as input to a modified transformer network, which was chosen as a prescription prediction model. The output of the model was the prescription for the patient. The ultimate goal is for this tool to generate a prescription that matches what an expert TCM physician would prescribe. To alleviate the issue of overfitting, a generative adversarial network was used to augment the training sample data set by generating noise-added samples from the original training samples.

Results

In total, 21,295 copies of inpatient electronic medical records from Guang’anmen Hospital were used in this study. These records were generated between January 2017 and December 2018, covering 6352 types of medicines. These medicines were sorted into 819 types of first-category medicines based on their class relationships. As shown by the test results, the performance of a fully trained transformer model can have an average precision rate of 80.58% and an average recall rate of 68.49%.

Conclusions

As shown by the preliminary test results, the transformer-based TCM prescription recommendation model outperformed the existing conventional methods. The extra training samples generated by the generative adversarial network help to overcome the overfitting issue, leading to further improved recall and precision rates.

Interpreting clinical latent representations using autoencoders and probabilistic models

Electronic health records (EHRs) are a valuable data source that, in conjunction with deep learning (DL) methods, have provided important outcomes in different domains, contributing to supporting decision-making. Owing to the remarkable advancements achieved by DL-based models, autoencoders (AE) are becoming extensively used in health care. Nevertheless, AE-based models are based on nonlinear transformations, resulting in black-box models leading to a lack of interpretability, which is vital in the clinical setting. To obtain insights from AE latent representations, we propose a methodology by combining probabilistic models based on Gaussian mixture models and hierarchical clustering supported by Kullback-Leibler divergence. To validate the methodology from a clinical viewpoint, we used real-world data extracted from EHRs of the University Hospital of Fuenlabrada (Spain). Records were associated with healthy and chronic hypertensive and diabetic patients. Experimental outcomes showed that our approach can find groups of patients with similar health conditions by identifying patterns associated with diagnosis and drug codes. This work opens up promising opportunities for interpreting representations obtained by the AE-based model, bringing some light to the decision-making process made by clinical experts in daily practice.