Ryan Hoffman

Factors That Affect Radiofrequency Heat Lesion Size

OBJECTIVE This study aims to compare radiofrequency (RF) heat lesion size across electrodes and generator settings available for interventional pain management. METHODS Monopolar lesions are generated ex vivo in animal tissue using sharp cannulae with tip diameters 23, 22, 20, 18, 16 gauge; tip lengths 5, 6, 10, 15 mm; set temperatures 60, 70, 80, 90°C; set times 1, 1.5, 2, 3, 5, 10 minutes. Lesions are generated using the RRE electrode, cooled RF, and parallel-tip bipolar RF for comparison. Lesion sizes are assessed by automated photographic temperature inference from over 400 lesions, using multiple lesions per configuration. RESULTS Monopolar lesion width and length increase with each factor (P < 0.001). Increasing cannula diameter from 22 to 16 gauge increases average lesion width 58-65% (3-4 mm) at 80°C and 2 minutes. Increasing temperature from 60°C to 90°C increases lesion width 108-152% at 2 minutes. Although dimensions grow most rapidly over the first minute, average lesion width is 11-20% larger at 2 minutes, and 23-32% larger at 3 minutes, compared with 1 minute. Lesion length extends distal and proximal to the tip, and exceeds tip length by 1-5 mm at 80°C and 2 minutes. Conventional 16 gauge cannulae at 80-90°C for 2-3 minutes generate lesions of average width similar to that produced by the cooled RF configuration proposed for sacroiliac joint denervation. Bipolar RF between parallel cannulae produces a rounded brick-shaped lesion of comparable shape to three sequential monopolar lesions generated using the same cannulae and generator settings. CONCLUSIONS Tip gauge, tip length, temperature, and time substantially affect RF lesion size.

Omic and Electronic Health Record Big Data Analytics for Precision Medicine

<italic>Objective:</italic> Rapid advances of high-throughput technologies and wide adoption of electronic health records (EHRs) have led to fast accumulation of –omic and EHR data. These voluminous complex data contain abundant information for precision medicine, and big data analytics can extract such knowledge to improve the quality of healthcare. <italic>Methods:</italic> In this paper, we present –omic and EHR data characteristics, associated challenges, and data analytics including data preprocessing, mining, and modeling. <italic>Results:</italic> To demonstrate how big data analytics enables precision medicine, we provide two case studies, including identifying disease biomarkers from multi-omic data and incorporating –omic information into EHR. <italic>Conclusion: </italic> Big data analytics is able to address –omic and EHR data challenges for paradigm shift toward precision medicine. <italic>Significance:</italic> Big data analytics makes sense of –omic and EHR data to improve healthcare outcome. It has long lasting societal impact.OBJECTIVE Rapid advances of high-throughput technologies and wide adoption of electronic health records (EHRs) have led to fast accumulation of -omic and EHR data. These voluminous complex data contain abundant information for precision medicine, and big data analytics can extract such knowledge to improve the quality of health care. METHODS In this article, we present -omic and EHR data characteristics, associated challenges, and data analytics including data pre-processing, mining, and modeling. RESULTS To demonstrate how big data analytics enables precision medicine, we provide two case studies, including identifying disease biomarkers from multi-omic data and incorporating -omic information into EHR. CONCLUSION Big data analytics is able to address -omic and EHR data challenges for paradigm shift towards precision medicine. SIGNIFICANCE Big data analytics makes sense of -omic and EHR data to improve healthcare outcome. It has long lasting societal impact.

Intelligent mortality reporting with FHIR

One pressing need in the area of public health is timely, accurate, and complete reporting of deaths and the conditions leading up to them. Fast Healthcare Interoperability Resources (FHIR) is a new HL7 interoperability standard for electronic health record (EHR), while Sustainable Medical Applications and Reusable Technologies (SMART)-on-FHIR enables third-party app development that can work “out of the box”. This research demonstrates the feasibility of developing SMART-on-FHIR applications to enable medical professionals to perform timely and accurate death reporting within multiple different jurisdictions of US. We explored how the information on a standard certificate of death can be mapped to resources defined in the FHIR standard (DSTU2). We also demonstrated analytics for potentially improving the accuracy and completeness of mortality reporting data.

Integration of multi-modal biomedical data to predict cancer grade and patient survival

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.

Improving Validity of Cause of Death on Death Certificates

Accurate reporting of causes of death on death certificates is essential to formulate appropriate disease control, prevention and emergency response by national health-protection institutions such as Center for disease prevention and control (CDC). In this study, we utilize knowledge from publicly available expert-formulated rules for the cause of death to determine the extent of discordance in the death certificates in national mortality data with the expert knowledge base. We also report the most commonly occurring invalid causal pairs which physicians put in the death certificates. We use sequence rule mining to find patterns that are most frequent on death certificates and compare them with the rules from the expert knowledge based. Based on our results, 20.1% of the common patterns derived from entries into death certificates were discordant. The most probable causes of these discordance or invalid rules are missing steps and non-specific ICD-10 codes on the death certificates.

Predicting heart rejection using histopathological whole-slide imaging and deep neural network with dropout

Cardiac allograft rejection is one major limitation for long-term survival for patients with heart transplants. The endomyocardial biopsy is one gold standard to screen heart rejection for patients that have heart transplantation. However, manual identification of heart rejection is expensive and time-consuming. With the development of imaging processing techniques and machine learning tools, automatic prediction of heart rejection using whole-slide images is one promising approach to improve the care of patients with heart transplants. In this paper, we first develop a histopathological whole-slide image processing pipeline to extract features automatically. Then, we construct deep neural networks with and without regularization and dropout to classify the patients into non-rejection and rejection respectively. Our results show that neural networks with regularization and dropout can significantly reduce overfitting and achieve more stable accuracies.

Biomedical Imaging Informatics for Diagnostic Imaging Marker Selection

With the advent of digital imaging, thousands of medical images are captured and stored for future reference. In addition to recording medical history of a patient, these images are a rich source of information about disease-related markers. To extract robust and informative imaging markers, we need to regulate image quality, extract image features, select useful features, and validate them. Research and development of these computational methods fall under the science of biomedical imaging informatics. In this chapter, we discuss challenges and techniques of biomedical imaging informatics in the context of imaging marker extraction.