... IEEE-EMBS International Conference on Biomedical and Health Informatics. IEEE-EMBS International Conference on Biomedical and Health Informatics最新文献

The transformation of the American healthcare payment system from fee-for-service to value-based care increasingly makes it valuable to develop patient registries for specialized populations, to better assess healthcare quality and costs. Recent widespread adoption of Electronic Health Records (EHRs) in the U.S. now makes possible construction of EHR-based specialty registry data collection tools and reports, previously unfeasible using manual chart abstraction. But the complexities of specialty registry EHR tools and measures, along with the variety of stakeholders involved, can result in misunderstood requirements and frequent product change requests, as users first experience the tools in their actual clinical workflows. Such requirements churn could easily stall progress in specialty registry rollout. Modeling a system's requirements and solution design can be a powerful way to remove ambiguities, facilitate shared understanding, and help evolve a design to meet newly-discovered needs. "Agile Modeling" retains these values while avoiding excessive unused up-front modeling in favor of iterative incremental modeling. Using Agile Modeling principles and practices, in calendar year 2015 one institution developed 58 EHR-based specialty registries, with 111 new data collection tools, supporting 134 clinical process and outcome measures, and enrolling over 16,000 patients. The subset of UML and non-UML models found most consistently useful in designing, building, and iteratively evolving EHR-based specialty registries included User Stories, Domain Models, Use Case Diagrams, Decision Trees, Graphical User Interface Storyboards, Use Case text descriptions, and Solution Class Diagrams.

The Big Data era in Biomedical research has resulted in large-cohort data repositories such as The Cancer Genome Atlas (TCGA). These repositories routinely contain hundreds of matched patient samples for genomic, proteomic, imaging, and clinical data modalities, enabling holistic and multi-modal integrative analysis of human disease. Using TCGA renal and ovarian cancer data, we conducted a novel investigation of multi-modal data integration by combining histopathological image and RNA-seq data. We compared the performances of two integrative prediction methods: majority vote and stacked generalization. Results indicate that integration of multiple data modalities improves prediction of cancer grade and outcome. Specifically, stacked generalization, a method that integrates multiple data modalities to produce a single prediction result, outperforms both single-data-modality prediction and majority vote. Moreover, stacked generalization reveals the contribution of each data modality (and specific features within each data modality) to the final prediction result and may provide biological insights to explain prediction performance.

Infections occur among all clinical domains. The changing nature of microbes, viruses and infections poses a great threat to the overall well-being in medicine. Clinicians in the infectious disease (ID) domain deal with diagnostic as well as treatment uncertainty in their everyday practice. Our current health information technology (HIT) systems do not consider the level of clinician expertise into the system design process. Thus, information is presented to both novice and expert ID clinicians in identical ways. The purpose of this study was to identify the cognitive strategies novice ID clinicians use in managing complex cases to make better recommendations for system design. In the process, we interviewed 14 ID experts and asked them to give us a detailed description of how novice clinicians would have dealt with complex cases. From the interview transcripts, we identified four major themes that expert clinicians suggested about novices' cognitive strategies including: A) dealing with uncertainty, B) lack of higher macrocognition, C) oversimplification of problems through heuristics and D) dealing with peer pressure. Current and future innovative decision support tools embedded in the electronic health record that can match these cognitive strategies may hold the key to cognitively supporting novice clinicians. The results of this study may open up avenues for future research and suggest design directions for better healthcare systems.

This work presents an integrated system-on-chip (SoC) that forms the core of a long-term, fully implantable, battery assisted, passive continuous glucose monitor. It integrates an amperometric glucose sensor interface, a near field communication (NFC) wireless front-end and a fully digital switched mode power management unit for supply regulation and on board battery charging. It uses 13.56 MHz (ISM) band to harvest energy and backscatter data to an NFC reader. System was implemented in 14nm CMOS technology and validated with post layout simulations.

Biomedical in vivo imaging has been playing an essential role in diagnoses and treatment in modern medicine. However, compared with the fast development of medical imaging systems, the medical imaging informatics, especially automated prediction, has not been fully explored. In our paper, we compared different feature extraction and classification methods for prediction pipeline to analyze in vivo endomicroscopic images, obtained from patients who are at risks for the development of gastric disease, esophageal adenocarcionoma. Extensive experiment results show that the selected feature representation and prediction algorithms achieved high accuracy in both binary and multi-class prediction tasks.

This paper presents a system on chip for a fully implantable cochlear implant. It includes acoustic sensor front-end, 4-channel digital sound processing and auditory nerve stimulation circuitry. It also features a digital, switched mode, single inductor dual output power supply that generates two regulated voltages; 0.4 V used to supply on-chip digital blocks and 0.9 V to supply analog blocks and charge the battery when an external RF source is detected. All passives are integrated on-chip including the inductor. The system was implemented in 14nm CMOS and validated with post layout simulations.

As the volume of biomedical literature increases, it can be challenging for clinicians to stay up-to-date. Graphical summarization systems help by condensing knowledge into networks of entities and relations. However, existing systems present relations out of context, ignoring key details such as study population. To better support precision medicine, summarization systems should include such information to contextualize and tailor results to individual patients. This paper introduces "contextualized semantic maps" for patient-tailored graphical summarization of published literature. These efforts are demonstrated in the domain of driver mutations in non-small cell lung cancer (NSCLC). A representation for relations and study population context in NSCLC was developed. An annotated gold standard for this representation was created from a set of 135 abstracts; F1-score annotator agreement was 0.78 for context and 0.68 for relations. Visualizing the contextualized relations demonstrated that context facilitates the discovery of key findings that are relevant to patient-oriented queries.

In this paper we investigated whether the geographical variation of lung cancer incidence can be predicted through examining the spatiotemporal trend of particulate matter air pollution levels. Regional trends of air pollution levels were analyzed by a novel shapelet-based time series analysis technique. First, we identified U.S. counties with reportedly high and low lung cancer incidence between 2008 and 2012 via the State Cancer Profiles provided by the National Cancer Institute. Then, we collected particulate matter exposure levels (PM_2.5 and PM₁₀) of the counties for the previous decade (1998-2007) via the AirData dataset provided by the Environmental Protection Agency. Using shapelet-based time series pattern mining, regional environmental exposure profiles were examined to identify frequently occurring sequential exposure patterns. Finally, a binary classifier was designed to predict whether a U.S. region is expected to experience high lung cancer incidence based on the region's PM_2.5 and PM₁₀ exposure the decade prior. The study confirmed the association between prolonged PM exposure and lung cancer risk. In addition, the study findings suggest that not only cumulative exposure levels but also the temporal variability of PM exposure influence lung cancer risk.

Brain tumor analysis is moving towards volumetric assessment of magnetic resonance imaging (MRI), providing a more precise description of disease progression to better inform clinical decision-making and treatment planning. While a multitude of segmentation approaches exist, inherent variability in the results of these algorithms may incorrectly indicate changes in tumor volume. In this work, we present a systematic approach to characterize variability in tumor boundaries that utilizes equivalence tests as a means to determine whether a tumor volume has significantly changed over time. To demonstrate these concepts, 32 MRI studies from 8 patients were segmented using four different approaches (statistical classifier, region-based, edge-based, knowledge-based) to generate different regions of interest representing tumor extent. We showed that across all studies, the average Dice coefficient for the superset of the different methods was 0.754 (95% confidence interval 0.701-0.808) when compared to a reference standard. We illustrate how variability obtained by different segmentations can be used to identify significant changes in tumor volume between sequential time points. Our study demonstrates that variability is an inherent part of interpreting tumor segmentation results and should be considered as part of the interpretation process.

Sequencing errors are a major issue for several next-generation sequencing-based applications such as de novo assembly and single nucleotide polymorphism detection. Several error-correction methods have been developed to improve raw data quality. However, error-correction performance is hard to evaluate because of the lack of a ground truth. In this study, we propose a novel approach which using ERCC RNA spike-in controls as the ground truth to facilitate error-correction performance evaluation. After aligning raw and corrected RNA-seq data, we characterized the quality of reads by three metrics: mismatch patterns (i.e., the substitution rate of A to C) of reads aligned with one mismatch, mismatch patterns of reads aligned with two mismatches and the percentage increase of reads aligned to reference. We observed that the mismatch patterns for reads aligned with one mismatch are significantly correlated between ERCC spike-ins and real RNA samples. Based on such observations, we conclude that ERCC spike-ins can serve as ground truths for error correction beyond their previous applications for validation of dynamic range and fold-change response. Also, the mismatch patterns for ERCC reads aligned with one mismatch can serve as a novel and reliable metric to evaluate the performance of error-correction tools.