It is extremely important to identify patients with acute pancreatitis who are at high risk for developing persistent organ failures early in the course of the disease. Due to the irregularity of longitudinal data and the poor interpretability of complex models, many models used to identify acute pancreatitis patients with a high risk of organ failure tended to rely on simple statistical models and limited their application to the early stages of patient admission. With the success of recurrent neural networks in modeling longitudinal medical data and the development of interpretable algorithms, these problems can be well addressed. In this study, we developed a novel model named Multi-task and Time-aware Gated Recurrent Unit RNN (MT-GRU) to directly predict organ failure in patients with acute pancreatitis based on irregular medical EMR data. Our proposed end-to-end multi-task model achieved significantly better performance compared to two-stage models. In addition, our model not only provided an accurate early warning of organ failure for patients throughout their hospital stay, but also demonstrated individual and population-level important variables, allowing physicians to understand the scientific basis of the model for decision-making. By providing early warning of the risk of organ failure, our proposed model is expected to assist physicians in improving outcomes for patients with acute pancreatitis.

An accurate and detailed account of patient medications, including medication changes within the patient timeline, is essential for healthcare providers to provide appropriate patient care. Healthcare providers or the patients themselves may initiate changes to patient medication. Medication changes take many forms, including prescribed medication and associated dosage modification. These changes provide information about the overall health of the patient and the rationale that led to the current care. Future care can then build on the resulting state of the patient. This work explores the automatic extraction of medication change information from free-text clinical notes. The Contextual Medication Event Dataset (CMED) is a corpus of clinical notes with annotations that characterize medication changes through multiple change-related attributes, including the type of change (start, stop, increase, etc.), initiator of the change, temporality, change likelihood, and negation. Using CMED, we identify medication mentions in clinical text and propose three novel high-performing BERT-based systems that resolve the annotated medication change characteristics. We demonstrate that our proposed systems improve medication change classification performance over the initial work exploring CMED.

Medicine recommendation aims to provide a combination of medicine based on the patient's electronic health record (EHR), which is an essential task in healthcare. Existing methods either base recommendations on EHRs or provide models with knowledge of drug-drug interactions (DDIs) to achieve DDI reduction. However, the former models the patient's health history but ignores undesirable DDIs, while the latter lacks mining of patient health records and gets low recommendation accuracy. Therefore, this study contributes to research on personalized medication recommendations that consider drug interaction effects and models the patient's past medical history. In this paper, the Distance-wise and Graph Contrastive Learning (DGCL) framework is proposed. Specifically, we develop a two-stage neural network module for clinical record learning. We propose the distance detection loss to model the difference between the output distribution of current cases and historical records. In the DDI recognition and control task, DGCL proposes a graph contrastive learning method to jointly train the DDI knowledge graph and the electronic record graph, thereby effectively controlling the level of DDI for recommended medications. By comparing the performance on the MIMIC-III dataset with several baselines, DGCL outperforms other models in terms of efficacy and safety.

BACKGROUND: Various formalisms have been developed to represent clinical practice guideline recommendations in a computer-interpretable way. However, none of the existing formalisms leverage the structured and computable information that emerge from the evidence-based guideline development process. Thus, we here propose a FHIR-based format that uses computer-interpretable representations of the knowledge artifacts that emerge during the process of evidence-based guideline development to directly serve as the basis of evidence-based recommendations. METHODS: We identified the information required to represent evidence-based clinical practice guideline recommendations and reviewed the knowledge artifacts emerging during the evidence-based guideline development process. We then conducted a consensus-based design process with domain experts to develop an information model for guideline recommendation representation that is structurally aligned to the evidence-based guideline recommendation development process and a corresponding representation based on FHIR resources developed for evidence-based medicine (EBMonFHIR). The resulting recommendations were modelled and represented in conformance with the FHIR Clinical Guidelines (CPG-on-FHIR) implementation guide. RESULTS: The information model of evidence-based clinical guideline recommendations and its EBMonFHIR-/CPG-on-FHIR-based representation contain the clinical contents of individual guideline recommendations, a set of metadata for the recommendations, the ratings for the recommendations (e.g., strength of recommendation, certainty of overall evidence), the ratings of certainty of evidence for individual outcomes (e.g., risk of bias) and links to the underlying evidence (systematic reviews based on primary studies). We created profiles and an implementation guide for all FHIR resources required to represent the knowledge artifacts generated during evidence-based guideline development and their re-use as the basis for recommendations and used the profiles to implement an exemplary clinical guideline recommendation. CONCLUSIONS: The FHIR implementation guide presented here can be used to directly link the evidence assessment process of evidence-based guideline recommendation development, i.e. systematic reviews and evidence grading, and the underlying evidence from primary studies to the resulting guideline recommendations. This not only allows the evidence on which recommendations are based on to be evaluated transparently and critically, but also enables guideline developers to leverage computable evidence in a more direct way to facilitate the generation of computer-interpretable guideline recommendations.

Characterizing disease relationships is essential to biomedical research to understand disease etiology and improve clinical decision-making. Measurements of distance between disease pairs enables valuable research tasks, such as subgrouping patients and identifying common time courses of disease onset. Distance metrics developed in prior work focused on smaller, targeted disease sets, while distance metrics covering all diseases have not yet been defined, which limits the applications to a broader disease spectrum. Our current study defines disease distances for all disease pairs within the International Classification of Diseases, version 10 (ICD-10), the diagnostic classification system universally used in electronic health records. Our proposed distance is computed based on a biomedical ontology, SNOMED CT (Systemized Nomenclature of Medicine, Clinical Terms), which can also be viewed as a structured knowledge graph. We compared the knowledge graph-based metric to three other distance metrics based on the hierarchical structure of ICD, clinical comorbidity, and genetic correlation, to evaluate how each may capture similar or unique aspects of disease relationships. We show that our knowledge graph-based distance metric captures known phenotypic, clinical, and molecular characteristics at a finer granularity than the other three. With the continued growth of using Electronic Health Records data for research, we believe that our distance metric will play an important role in patient subgrouping in precision health, enabling individualized disease prevention and treatments.

BACKGROUND: In electronic health records, patterns of missing laboratory test results could capture patients' course of disease as well as ​​reflect clinician's concerns or worries for possible conditions. These patterns are often understudied and overlooked. This study aims to identify informative patterns of missingness among laboratory data collected across 15 healthcare system sites in three countries for COVID-19 inpatients. METHODS: We collected and analyzed demographic, diagnosis, and laboratory data for 69,939 patients with positive COVID-19 PCR tests across three countries from 1 January 2020 through 30 September 2021. We analyzed missing laboratory measurements across sites, missingness stratification by demographic variables, temporal trends of missingness, correlations between labs based on missingness indicators over time, and clustering of groups of labs based on their missingness/ordering pattern. RESULTS: With these analyses, we identified mapping issues faced in seven out of 15 sites. We also identified nuances in data collection and variable definition for the various sites. Temporal trend analyses may support the use of laboratory test result missingness patterns in identifying severe COVID-19 patients. Lastly, using missingness patterns, we determined relationships between various labs that reflect clinical behaviors. CONCLUSION: In this work, we use computational approaches to relate missingness patterns to hospital treatment capacity and highlight the heterogeneity of looking at COVID-19 over time and at multiple sites, where there might be different phases, policies, etc. Changes in missingness could suggest a change in a patient's condition, and patterns of missingness among laboratory measurements could potentially identify clinical outcomes. This allows sites to consider missing data as informative to analyses and help researchers identify which sites are better poised to study particular questions.

Diabetes Mellitus (DM) is a group of metabolic disorders characterized by hyperglycaemia in the absence of treatment. Classification of DM is essential as it corresponds to the respective diagnosis and treatment. In this paper, we propose a new coupling network with hierarchical dual-attention that utilizes heterogeneous data, including Flash Glucose Monitoring (FGM) data and biomarkers in electronic medical records. The long short-term memory-based FGM sub-network extracts the time-dependent features of dynamic FGM sequences, while the biomarkers sub-network learns the features of static biomarkers. The convolutional block attention module (CBAM) for dispersing the feature weights of the spatial and channel dimensions is implemented into the FGM sub-network to endure the variability of FGM and allows us to extract high-level discriminative features more accurately. To better adjust the importance weights of the characteristics of the two sub-networks, self-attention is introduced to integrate the characteristics of heterogeneous data. Based on the dataset provided by Peking University People's Hospital, the proposed method is evaluated through factorial experiments of multi-source heterogeneous data, ablation studies of various attention strategies, time consumption evaluation and quantitative evaluation. The benchmark tests reveal the proposed network achieves a type 1 and 2 diabetes classification accuracy of 95.835% and the comprehensive performance metrics, including Matthews correlation coefficient, F1-score and G-mean, are 91.333%, 94.939% and 94.937% respectively. In the factorial experiments, the proposed method reaches the maximum area under the receiver operating characteristic curve of 0.9428, which indicates the effectiveness of the coupling between the nominated sub-networks. The coupling network with a dual-attention strategy performs better than the one without or only with a single-attention strategy in the ablation study as well. In addition, the model is also tested on another data set, and the accuracy of the test reaches 94.286%, reflecting that the model is robust when it is transferred to untrained diabetes data. The experimental results show that the proposed method is feasible in the classification of diabetes types. The code is available at https://github.com/bitDalei/Diabetes-Classification-with-Heterogeneous-Data.

Expert microscopic analysis of cells obtained from frequent heart biopsies is vital for early detection of pediatric heart transplant rejection to prevent heart failure. Detection of this rare condition is prone to low levels of expert agreement due to the difficulty of identifying subtle rejection signs within biopsy samples. The rarity of pediatric heart transplant rejection also means that very few gold-standard images are available for developing machine learning models. To solve this urgent clinical challenge, we developed a deep learning model to automatically quantify rejection risk within digital images of biopsied tissue using an explainable synthetic data augmentation approach. We developed this explainable AI framework to illustrate how our progressive and inspirational generative adversarial network models distinguish between normal tissue images and those containing cellular rejection signs. To quantify biopsy-level rejection risk, we first detect local rejection features using a binary image classifier trained with expert-annotated and synthetic examples. We converted these local predictions into a biopsy-wide rejection score via an interpretable histogram-based approach. Our model significantly improves upon prior works with the same dataset with an area under the receiver operating curve (AUROC) of 98.84% for the local rejection detection task and 95.56% for the biopsy-rejection prediction task. A biopsy-level sensitivity of 83.33% makes our approach suitable for early screening of biopsies to prioritize expert analysis. Our framework provides a solution to rare medical imaging challenges currently limited by small datasets.

The classification of different organisms into subtypes is one of the most important tools of organism studies, and among them, the classification of viruses itself has been the focus of many studies due to their use in virology and epidemiology. Many methods have been proposed to classify viruses, some of which are designed for a specific family of organisms and some of which are more general. But still, especially for certain categories such as Influenza and HIV, classification is facing performance challenges as well as processing and memory bottlenecks. In this way, we designed an automated classifier, called PC-mer, that is based on k-mer and physicochemical characteristics of nucleotides, which reduces the number of features about 2k times compared to the alternative methods based on k-mer, and compared to integer and one-hot encoding methods, it is possible to keep the number of features constant despite the growth of the sequence length. In this way, it also increases the training speed by an average of 17.93 times. This improvement in processing complexity is provided while PC-mer can also improve the classifying performance for a variety of virus families.

Causal relation extraction of biomedical entities is one of the most complex tasks in biomedical text mining, which involves two kinds of information: entity relations and entity functions. One feasible approach is to take relation extraction and function detection as two independent sub-tasks. However, this separate learning method ignores the intrinsic correlation between them and leads to unsatisfactory performance. In this paper, we propose a joint learning model, which combines entity relation extraction and entity function detection to exploit their commonality and capture their inter-relationship, so as to improve the performance of biomedical causal relation extraction. Experimental results on the BioCreative-V Track 4 corpus show that our joint learning model outperforms the separate models in BEL statement extraction, achieving the F1 scores of 57.0% and 37.3% on the test set in Stage 2 and Stage 1 evaluations, respectively. This demonstrates that our joint learning system reaches the state-of-the-art performance in Stage 2 compared with other systems.

Given a cardiac-arrest patient being monitored in the ICU (intensive care unit) for brain activity, how can we predict their health outcomes as early as possible? Early decision-making is critical in many applications, e.g. monitoring patients may assist in early intervention and improved care. On the other hand, early prediction on EEG data poses several challenges: (i) earliness-accuracy trade-off; observing more data often increases accuracy but sacrifices earliness, (ii) large-scale (for training) and streaming (online decision-making) data processing, and (iii) multi-variate (due to multiple electrodes) and multi-length (due to varying length of stay of patients) time series. Motivated by this real-world application, we present BeneFitter that infuses the incurred savings from an early prediction as well as the cost from misclassification into a unified domain-specific target called benefit. Unifying these two quantities allows us to directly estimate a single target (i.e. benefit), and importantly, (a) is efficient and fast, with training time linear in the number of input sequences, and can operate in real-time for decision-making, (b) can handle multi-variate and variable-length time-series, suitable for patient data, and (c) is effective, providing up to 2× time-savings with equal or better accuracy as compared to competitors.

SNOMED CT postcoordination is an underused mechanism that can help to implement advanced systems for the automatic extraction and encoding of clinical information from text. It allows defining non-existing SNOMED CT concepts by their relationships with existing ones. Manually building postcoordinated expressions is a difficult task. It requires a deep knowledge of the terminology and the support of specialized tools that barely exist. In order to support the building of postcoordinated expressions, we have implemented KGE4SCT: a method that suggests the corresponding SNOMED CT postcoordinated expression for a given clinical term. We leverage on the SNOMED CT ontology and its graph-like structure and use knowledge graph embeddings (KGEs). The objective of such embeddings is to represent in a vector space knowledge graph components (e.g. entities and relations) in a way that captures the structure of the graph. Then, we use vector similarity and analogies for obtaining the postcoordinated expression of a given clinical term. We obtained a semantic type accuracy of 98%, relationship accuracy of 90%, and analogy accuracy of 60%, with an overall completeness of postcoordination of 52% for the Spanish SNOMED CT version. We have also applied it to the English SNOMED CT version and outperformed state of the art methods in both, corpus generation for language model training for this task (improvement of 6% for analogy accuracy), and automatic postcoordination of SNOMED CT expressions, with an increase of 17% for partial conversion rate.