The Biomedical Informatics Program (BIP) aims to maximize the scientific impact of research proposals through four specific aims:
1) Developing interoperable applications and repositories to integrate multi-scale data across institutions.
2) Consulting with investigators to coordinate use of informatics tools.
3) Educating researchers on biomedical informatics principles and tools.
4) Developing novel informatics techniques for large data integration, semantic data extraction/transformation/loading, and testing data integrity in federated environments.
The BIP brings together researchers from Emory, Morehouse, and Georgia Tech to provide resources and training to enable collaborative, data-driven translational research across ACTSI institutions.
Review of Image Watermarking Technique for MediIJARIIT
In this article, we focus on the complementary role of watermarking with respect to medical information security (integrity, authenticity …) and management. We review sample cases where watermarking has been deployed. We conclude that watermarking has found a niche role in healthcare systems, as an instrument for protection of medical information, for secure sharing and handling of medical images. The concern of medical experts on the preservation of documents diagnostic integrity remains paramount. Medical image watermarking is an appropriate method used for enhancing security and authentication of medical data, which is crucial and used for further diagnosis and reference. This paper discusses the available medical image watermarking methods for protecting and authenticating medical data. The paper focuses on algorithms for application of watermarking technique on Region of Non Interest (RONI) of the medical image preserving Region of Interest (ROI).
Clinical Data Collaboration Across the Enterprise Carestream
In addition to the CARESTREAM Vue PACS installed in 2003, the hospital has implemented full electronic ADT and paperless Ancillaries, EMR Adoption, full electronic medication CPOE and a Structured and Document Clinical Repository (connected to regional EHR).
Despite the completeness of this IT infrastructure, the hospital was still searching for an optimal solution for an integrated clinical image repository and distribution system.
Slides presented at the Molecular Med Tri-Con 2018 Precision Medicine, "Emerging Role of Radiomics in Precision Medicine" (http://www.triconference.com/Precision-Medicine/)
Abstract
The goal of this talk is to discuss the role of data standards, and specifically the Digital Imaging and Communication in Medicine (DICOM) standard, in supporting radiomics research. From the clinical images, to the storage of image annotations and results of radiomics analysis, standardization can potentially have transformative effect by enabling discovery, reuse and mining of the data, and integration of the radiomics workflows into the healthcare enterprise.
Radiomics: Novel Paradigm of Deep Learning for Clinical Decision Support towa...Wookjin Choi
‘Radiomics’ is a novel process to identify ‘radiome’ in the field of imaging informatics when long-term clinical outcomes such as mortality are not immediately available, relying on first acquiring paired gene expression data and medical images at diagnosis from a study cohort, and then leveraging the public gene expression data containing clinical outcomes from a closely matched population into a personalized medicine (Stanford and Harvard University).
Review of Image Watermarking Technique for MediIJARIIT
In this article, we focus on the complementary role of watermarking with respect to medical information security (integrity, authenticity …) and management. We review sample cases where watermarking has been deployed. We conclude that watermarking has found a niche role in healthcare systems, as an instrument for protection of medical information, for secure sharing and handling of medical images. The concern of medical experts on the preservation of documents diagnostic integrity remains paramount. Medical image watermarking is an appropriate method used for enhancing security and authentication of medical data, which is crucial and used for further diagnosis and reference. This paper discusses the available medical image watermarking methods for protecting and authenticating medical data. The paper focuses on algorithms for application of watermarking technique on Region of Non Interest (RONI) of the medical image preserving Region of Interest (ROI).
Clinical Data Collaboration Across the Enterprise Carestream
In addition to the CARESTREAM Vue PACS installed in 2003, the hospital has implemented full electronic ADT and paperless Ancillaries, EMR Adoption, full electronic medication CPOE and a Structured and Document Clinical Repository (connected to regional EHR).
Despite the completeness of this IT infrastructure, the hospital was still searching for an optimal solution for an integrated clinical image repository and distribution system.
Slides presented at the Molecular Med Tri-Con 2018 Precision Medicine, "Emerging Role of Radiomics in Precision Medicine" (http://www.triconference.com/Precision-Medicine/)
Abstract
The goal of this talk is to discuss the role of data standards, and specifically the Digital Imaging and Communication in Medicine (DICOM) standard, in supporting radiomics research. From the clinical images, to the storage of image annotations and results of radiomics analysis, standardization can potentially have transformative effect by enabling discovery, reuse and mining of the data, and integration of the radiomics workflows into the healthcare enterprise.
Radiomics: Novel Paradigm of Deep Learning for Clinical Decision Support towa...Wookjin Choi
‘Radiomics’ is a novel process to identify ‘radiome’ in the field of imaging informatics when long-term clinical outcomes such as mortality are not immediately available, relying on first acquiring paired gene expression data and medical images at diagnosis from a study cohort, and then leveraging the public gene expression data containing clinical outcomes from a closely matched population into a personalized medicine (Stanford and Harvard University).
Review on automated follicle identification for polycystic ovarian syndromejournalBEEI
Polycystic Ovarian Syndrome (PCOS), is a condition of the ovary consisting numerous follicles. Accurate size and number of follicles detected are crucial for treatment. Hence the diagnosis of this condition is by measuring and calculating the size and number of follicles existed in the ovary. For diagnosis, ultrasound imaging has become an effective tool as it is non-invasive, inexpensive and portable. However, the presence of speckle noise in ultrasound imaging has caused an obstruction for manual diagnosis which are high time consumption and often produce errors. Thus, image segmentation for ultrasound imaging is critical to identify follicles for PCOS diagnosis and proper health treatment. This paper presents different methods proposed and applied in automated follicle identification for PCOS diagnosis by previous researchers. In this paper, the methods and performance evaluation are identified and compared. Finally, this paper also provided suggestions in developing methods for future research.
Intra Report- St. James' Hospital Medical Physics Muhammad Alli
The MPBE department (Medical Physics and Bioengineering) provides technical services to the hospital by taking care of medical equipment, the calibration of imaging equipment as well as services to ensuring the safe operation of equipment. The medical physicists also provide services in nuclear medicine. Radioiodine therapy is a service the hospital provides, one of my major goals setting out to work at St. James’s was to learn about radiotherapy, I had a role looking though research papers to try and find information which could help with the way the radioiodine therapy the hospital provides is given, that role was elegantly supported with other relevant work, such as contamination monitoring and experimental work which built an amazing knowledgebase for me. I took part in the NIMIS project and delivered a presentation on a new piece of dose tracking software to the MPBE department.
I carried out many other short term roles which served to develop me in many areas within and including science, IT and engineering as well as developing my people skills. I learned how to interact on a technical level with an interdisciplinary team. As well as gain an understanding of team dynamics, organizational and project management. The experience was very enriching all-around and I would gladly recommend it to future students as an INTRA placement.
Digital biomarkers for preventive personalised healthcarePaolo Missier
A talk given to the Alan Turing Institute, UK, Oct 2021, reporting on the preliminary results and ongoing research in our lab, on self-monitoring using accelerometers for healthcare applications
Machine Learning and Deep Contemplation of DataJoel Saltz
Spatio temporal data analytics - Generation of Features
1) Sanity Checking and Data Cleaning, 2) Qualitative Exploration, 3) Descriptive Statistics, 4) Classification, 5) Identification of Interesting Phenomena, 6) Prediction, 7) Control and 8)
Save Data for Later (Compression).
Detailed example from Precision Medicine; Pathomics, Radiomics.
AN EFFECTIVE AND EFFICIENT FEATURE SELECTION METHOD FOR LUNG CANCER DETECTIONijcsit
Medical image data is growing rapidly. Lung cancer considers to be the most common cause of death among people throughout the world. Early lung cancer detection can increase the chance of people survival. The 5 year survival rate for lung cancer patient increases from 14 to 49% if the disease is detected in time. Computed Tomography can be more efficient than X ray for detecting lung cancer in time. But the problem seemed to merge due to time constraint in detecting the presence of lung cancer.MAT LAB have been applied for the study of these techniques. Feature selection is a method to reduce the number of features in medical applications where the image has hundreds or thousands of features. In order to extract the accurate features of an image, an image need to be processed for its effective retreival.Image feature selection is an essential task for recognizing the image and it can be done for overcoming classification problems. However, the quality of the image recognition tasks can be improved with the help
of better classification accuracy for enhancing the retrieval performance.
June 2018 version
How deep learning reshapes medicine
- Brief deep learning
- Recent applications
- Specific researches
- Perspectives and future directions
지난주말에 있었던 제 4회 대한신경집중치료학회 편집위원회 워크샵에서 발표했던 내용중에 발췌한 것입니다. 원래 제목은 "인공지능 관련 연구: 논문 작성과 심사에 관한 요령" 입니다. 최근에 deep learning in medical imaging으로 2편의 리뷰와 논문 1편, CADD 논문, 앙상블 논문 1편이 되면서 요청이 온것 같습니다.부족한 제가 하기 어려운 주제를 맡았는데, 혹시 도움이 되실 분이 있으면 도움을 되시라고 올려드립니다. 결론은 인공지능 연구라고 특별히 다르지는 않지만, 공학 연구와 의학연구가 다르고, 인공지능 특성을 잘 이해해야 한다 정도 될것 같습니다. (상당부분 저희병원 박성호 교수님의 radiology 논문 Methodology for Evaluation of Clinical Performance and Impact of Artificial Intelligence Technology for Medical Diagnosis and Prediction을 참고했습니다.)
Twenty Years of Whole Slide Imaging - the Coming Phase ChangeJoel Saltz
I surveyed the development of Digital Pathology methodology beginning with the 1997 virtual microscope prototype at Hopkins (PMC2233368) to current tools, methods and algorithms designed to display, analyze and classify whole slide imaging data. I will describe the capabilities of current methods, describe how these methods are likely to evolve and how they will be likely to impact Pathology research and practice.
Thesis Proposal, as presented for dissertation proposal defenseHeather Piwowar
The slides I presented for my PhD proposal defense for my project, "Foundational studies for measuring the impact, prevalence, and patterns of publicly sharing biomedical research data." Dept of Biomedical Informatics, University of Pittsburgh.
Review on automated follicle identification for polycystic ovarian syndromejournalBEEI
Polycystic Ovarian Syndrome (PCOS), is a condition of the ovary consisting numerous follicles. Accurate size and number of follicles detected are crucial for treatment. Hence the diagnosis of this condition is by measuring and calculating the size and number of follicles existed in the ovary. For diagnosis, ultrasound imaging has become an effective tool as it is non-invasive, inexpensive and portable. However, the presence of speckle noise in ultrasound imaging has caused an obstruction for manual diagnosis which are high time consumption and often produce errors. Thus, image segmentation for ultrasound imaging is critical to identify follicles for PCOS diagnosis and proper health treatment. This paper presents different methods proposed and applied in automated follicle identification for PCOS diagnosis by previous researchers. In this paper, the methods and performance evaluation are identified and compared. Finally, this paper also provided suggestions in developing methods for future research.
Intra Report- St. James' Hospital Medical Physics Muhammad Alli
The MPBE department (Medical Physics and Bioengineering) provides technical services to the hospital by taking care of medical equipment, the calibration of imaging equipment as well as services to ensuring the safe operation of equipment. The medical physicists also provide services in nuclear medicine. Radioiodine therapy is a service the hospital provides, one of my major goals setting out to work at St. James’s was to learn about radiotherapy, I had a role looking though research papers to try and find information which could help with the way the radioiodine therapy the hospital provides is given, that role was elegantly supported with other relevant work, such as contamination monitoring and experimental work which built an amazing knowledgebase for me. I took part in the NIMIS project and delivered a presentation on a new piece of dose tracking software to the MPBE department.
I carried out many other short term roles which served to develop me in many areas within and including science, IT and engineering as well as developing my people skills. I learned how to interact on a technical level with an interdisciplinary team. As well as gain an understanding of team dynamics, organizational and project management. The experience was very enriching all-around and I would gladly recommend it to future students as an INTRA placement.
Digital biomarkers for preventive personalised healthcarePaolo Missier
A talk given to the Alan Turing Institute, UK, Oct 2021, reporting on the preliminary results and ongoing research in our lab, on self-monitoring using accelerometers for healthcare applications
Machine Learning and Deep Contemplation of DataJoel Saltz
Spatio temporal data analytics - Generation of Features
1) Sanity Checking and Data Cleaning, 2) Qualitative Exploration, 3) Descriptive Statistics, 4) Classification, 5) Identification of Interesting Phenomena, 6) Prediction, 7) Control and 8)
Save Data for Later (Compression).
Detailed example from Precision Medicine; Pathomics, Radiomics.
AN EFFECTIVE AND EFFICIENT FEATURE SELECTION METHOD FOR LUNG CANCER DETECTIONijcsit
Medical image data is growing rapidly. Lung cancer considers to be the most common cause of death among people throughout the world. Early lung cancer detection can increase the chance of people survival. The 5 year survival rate for lung cancer patient increases from 14 to 49% if the disease is detected in time. Computed Tomography can be more efficient than X ray for detecting lung cancer in time. But the problem seemed to merge due to time constraint in detecting the presence of lung cancer.MAT LAB have been applied for the study of these techniques. Feature selection is a method to reduce the number of features in medical applications where the image has hundreds or thousands of features. In order to extract the accurate features of an image, an image need to be processed for its effective retreival.Image feature selection is an essential task for recognizing the image and it can be done for overcoming classification problems. However, the quality of the image recognition tasks can be improved with the help
of better classification accuracy for enhancing the retrieval performance.
June 2018 version
How deep learning reshapes medicine
- Brief deep learning
- Recent applications
- Specific researches
- Perspectives and future directions
지난주말에 있었던 제 4회 대한신경집중치료학회 편집위원회 워크샵에서 발표했던 내용중에 발췌한 것입니다. 원래 제목은 "인공지능 관련 연구: 논문 작성과 심사에 관한 요령" 입니다. 최근에 deep learning in medical imaging으로 2편의 리뷰와 논문 1편, CADD 논문, 앙상블 논문 1편이 되면서 요청이 온것 같습니다.부족한 제가 하기 어려운 주제를 맡았는데, 혹시 도움이 되실 분이 있으면 도움을 되시라고 올려드립니다. 결론은 인공지능 연구라고 특별히 다르지는 않지만, 공학 연구와 의학연구가 다르고, 인공지능 특성을 잘 이해해야 한다 정도 될것 같습니다. (상당부분 저희병원 박성호 교수님의 radiology 논문 Methodology for Evaluation of Clinical Performance and Impact of Artificial Intelligence Technology for Medical Diagnosis and Prediction을 참고했습니다.)
Twenty Years of Whole Slide Imaging - the Coming Phase ChangeJoel Saltz
I surveyed the development of Digital Pathology methodology beginning with the 1997 virtual microscope prototype at Hopkins (PMC2233368) to current tools, methods and algorithms designed to display, analyze and classify whole slide imaging data. I will describe the capabilities of current methods, describe how these methods are likely to evolve and how they will be likely to impact Pathology research and practice.
Thesis Proposal, as presented for dissertation proposal defenseHeather Piwowar
The slides I presented for my PhD proposal defense for my project, "Foundational studies for measuring the impact, prevalence, and patterns of publicly sharing biomedical research data." Dept of Biomedical Informatics, University of Pittsburgh.
You are 15 years old. Imagine walking into a hip emporium that inspires you to be curious and energizes you to succeed at a career. You sit down and play games; learn how to build games, 3D worlds and simulations; or just chat with like-minded friends about the future. The entire experience is about helping you "visualize" your science and engineering career exploration. In a "design team setting" you "play" roles ranging from 3D modeler to aerospace engineer.
IncredibleMinds goes beyond college guidance and occupational information to address the entire process of STEM career assessment, exploration and action planning necessary to help minority youth find STEM careers that fit their skills, interests, personalities, and developmental needs. New educational solutions need to be relevant and valuable to industry as well as relevant and valuable to youth (National Association of Governors, 2006). The key to the future of education is leveraging current investments in entertainment software and industry technologies.
We use commercial video games as the conceptual bridge to “playing” with industry simulation and modeling tools. Modeling and simulation tools are the immersive environments that our next-generation engineers and scientists must master. These tools provide the means to design and build engineered systems as well as to investigate and visualize complex scientific phenomena. The modeling and simulation industry is a $6 billion U.S. industry that is central to innovation in high-growth industries and the advancement of scientific discovery. Today, Congressional and industry leaders consider the modeling and simulation industry a "national critical technology.” According to Dr. Edwin Crues, NASA Constellation Program Modeling and Simulation Architect, “We cannot have an active and vibrant space program without an active and vibrant modeling and simulation community to support it.”
From systems physiology to precision medicine
Frontiers in metabolism
EMBO Press EPFL
the pathogenesis and management of the metabolic syndrome as a major medical challenge.
30 talks/speakers given by worldwide leaders in the metabolism field
Cell biology, signaling, metabolomics, physiology, genetics genomics and aging
innovative ideas
Exponential technology - How do we make sure everyone benefits?Matthijs Pontier
Exponential technology - How do we make sure everyone benefits?
Democracy, democratic transhumanism, technoprogressivism, Exponential Technology How can we make sure everyone benefits? Dr. Matthijs Pontier
2. Content • Why should everyone benefit? • How do we make sure everyone benefits? • Democratic Transhumanism • Machine Ethics • When we succeed New ethical dilemma’s Matthijs Pontier, Leiden, 27-2-2016 Where is the boundary of the human? The new technological turn
3. Why should everyone benefit? Who is everyone? • Does life matter? Matthijs Pontier, Leiden, 27-2-2016Where is the boundary of the human? The new technological turn
4. Why should everyone benefit? Who is everyone? • What is life, anyway? Matthijs Pontier, Leiden, 27-2-2016
5. Why should everyone benefit? Who is everyone? • Does life matter? • What is life, anyway? • Does human life matter? Matthijs Pontier, Leiden, 27-2-2016
6. Why should everyone benefit? Who is everyone? • Does life matter? • What is life, anyway? • Does human life matter? • Do human individuals matter? Matthijs Pontier, Leiden, 27-2-2016
7. Why build technology? Matthijs Pontier, Leiden, 27-2-2016 Where is the boundary of the human? The new technological turn
8. Why build technology? Matthijs Pontier, Leiden, 27-2-2016 Where is the boundary of the human? The new technological turn
9. Why build technology?
10. Why build technology? Matthijs Pontier, Leiden, 27-2-2016 Where is the boundary of the human? The new technological turn
11. Why build technology? • Evolutionary progress • Preserve (human) life • To preserve human rights • To improve our well-being Matthijs Pontier, Leiden, 27-2-2016 Where is the boundary of the human? The new technological turn
12. Why build technology? • Evolutionary progress – Description of a process or goal in itself? • Preserve (human) life • To preserve human rights • To improve our well-being Matthijs Pontier, Leiden, 27-2-2016 Where is the boundary of the human? The new technological turn
13. Why build technology? • Evolutionary progress / Preserve humans • To preserve human rights • To improve our well-being • Hedonic utilitarianism? Matthijs Pontier, Leiden, 27-2-2016
14. Why build technology? • Evolutionary progress / Preserve humans • To preserve human rights • To improve our well-being • Hedonic utilitarianism? Matthijs Pontier, 15. Brave New World
17. How do we promote happiness?
18. Promoting happiness: Kill all unhappy people? 19. Promoting happiness: Improving autonomy? 20. How do we promote autonomy? • If everyone uses cognitive enhancers, do you still have a free choice to use it yourself?
1984, ai, autonomy, brave new world, democracy, democratic transhumanism, ethics, healthcare, human enhancement, huxley, ik ben alice, machine ethics, open source, orwell, philosophy, robots, science, tech, technology, technoprogressivism
A presentation by Dr. Swamy Venuturupalli, MD, FACR from Lupus LA's annual patient education conference at Cedars Sinai Medical Center in Los Angeles, CA.
Dr. Swamy Venuturupalli is a board-certified rheumatologist practicing in Los Angeles. He is Clinical Chief of the Division of Rheumatology at Cedars Sinai Medical Center and Associate Clinical Professor of Medicine at UCLA as well as being Editor-in-Chief of Current Rheumatology Reports.
Dr. Venuturupalli grew up in Bombay, India, the son of two physicians. In 1995, he received his medical degree from the prestigious Topiwala National Medical College in Bombay. Dr. Venuturupalli completed his residency in Internal Medicine, with distinction, at the Upstate Medical University in Syracuse, NY. Following his residency, he was appointed Chief Resident in the department of medicine at Syracuse University, where he was in charge of managing and training 65 residents.
In 1999, Dr. Venuturupalli moved to Los Angeles for a combined fellowship in health services research with UCLA's School of Medicine, the RAND Corporation, and the Greater Los Angeles Veteran's Administration Medical Center. Along with his cohort, he conducted research on complementary and alternative medicine, publishing studies on Ayurvedic medicine, dietary supplements, and mind-body medicine. Dr. Venuturupalli then completed a rheumatology fellowship at the UCLA-Olive View medical program in 2002.
Dr. Venuturupalli's role as research investigator includes over a hundred clinical trials involving conditions such as lupus, rheumatoid arthritis, inflammatory muscle diseases, ankylosing spondylitis, etc. He participates in ongoing rheumatology research with Dr. Daniel Wallace, a leading physician in the field, at the Cedars Sinai Division of Rheumatology. Dr. Venuturupalli lectures frequently to the general public and to the staff and faculty at Cedars Sinai Hospital on various topics in rheumatology, including alternative and complementary medicine. He was also recently invited to give grand rounds at Cedars on topics such as antiphospholipid syndrome and myositis. Dr. Venuturupalli has authored numerous text-book chapters, is published in peer-reviewed journals, and is currently the Editor-in-Chief of the journal Current Rheumatology Reviews.
For the past eight years, Dr. Venuturupalli has held a private practice in association with a group of 4 rheumatologists. Dr. Venuturupalli is highly regarded by his colleagues and is a sought-after teacher in his field of expertise. He has served as the past president of the Southern California Rheumatology Society, a non-profit professional organization of rheumatologists focusing on professional education.
Areas of expertise: Inflammatory Muscle disease, Systemic Lupus Erythematosus, Anti- Phospholipid syndrome, Sjogren's syndrome, Osteoporosis, Vasculitis.
Larry Smarr, Founding Director of the California Institute for Telecommunications and Information Technology (Calit2), shares his presentation delivered at Venture Summit Friday, July 12, 2013
How advances in Exponential Technology are enabling entrepreneurs to do in Healthcare what was once only possible by government and large corporations.
The Learning Health System: Thinking and Acting Across ScalesPhilip Payne
A Learning Health System (LHS) can be defined as an environment in which knowledge generation processes are embedded into daily clinical practice in order to continually improve the quality, safety, and outcomes of healthcare delivery. While still largely an aspirational goal, the promise of the LHS is a future in which every patient encounter is an opportunity to learn and improve that patient’s care, as well as the care their family and broader community receives. The foundation for building such an LHS can and should be the Electronic Health Record (EHR), which provides the basis for the comprehensive instrumentation and measurement of clinical phenotypes, as well as a means of delivering new evidence at the patient- and population levels. In this presentation, we will explore the ways in which such EHR-derived phenotypes can be combined with complementary data across a spectrum from biomolecules to population level trends, to both generate insights and deliver such knowledge in the right time, place, and format, ultimately improving clinical outcomes and value.
Presentation by Dr Adrian Burton, ARDC, to the 'Unlocking value from publicly funded Clinical Research Data' workshop, cohosted by ARDC and CSIRO at ANU on 6 March 2019.
Clinical trial data wants to be free: Lessons from the ImmPort Immunology Dat...Barry Smith
Presentation to the Clinical and Research Ethics Seminar, Clinical and Translational Science Center, Buffalo, January 21, 2014
https://immport.niaid.nih.gov/
http://youtu.be/booqxkpvJMg
Ontology-Driven Clinical Intelligence: A Path from the Biobank to Cross-Disea...Remedy Informatics
The discovery of clinical insights through effective management and reuse of data requires several conditions to be optimized: Data need to be digital, data need to be structured, and data need to be standardized in terms of metadata and ontology. This presentation describes a bioinformatics system that combines a next-generation biobank management model mapped to applicable international standards and guidelines with a master ontology that controls all input and output and is able to add unique properties to meet the specialized needs of clinicians for cross-disease research.
This module describes how missing data can be managed while maintaining data quality. It explains how to plan for missing data; defines different types of “missingness;” outlines the benefits of documenting missing data and illustrates how to document missing data; and describes procedures to minimize missing data. Upon completion of this module, students will be able to explain why data managers should strive to minimize missing data and develop a plan to record or code why data are missing.
Translational Biomedical Informatics 2010: Infrastructure and Scaling – Brian Athey,
PhD; Professor of Biomedical Informatics and Director for Academic Informatics,
University of Michigan Medical School; Chair Designate for Computational Medicine and Bioinformatics, University of Michigan; Associate Director, Michigan Institute for Clinical Health Research; Principal Investigator, National Center for Integrative Biomedical Informatics
International perspective for sharing publicly funded medical research dataARDC
Presentation by Olivier Salvado, CSIRO, to the 'Unlocking value from publicly funded Clinical Research Data' workshop, cohosted by ARDC and CSIRO at ANU on 6 March 2019.
Similar to Biomedical Informatics Program -- Atlanta CTSA (ACTSI) (20)
American Association for Cancer Research Annual Meeting 2022
Analysis of images of routinely acquired tissue specimens promise to provide biomarkers that can be used to predict disease outcome and steer treatment, improve diagnostic reproducibility, and reveal new insights to further advance current human understanding of disease. The advent of AI and ubiquitous high-end computing are making it possible to carry out accurate whole slide image morphological and molecular tissue analyses at cellular and subcellular resolutions. AI methods are can enable exploration and discovery of novel diagnostic biomarkers grounded in prognostically predictive spatial and molecular patterns as well as quantitative assessments of predictive value and reproducibility of traditional morphological patterns employed in anatomic pathology. AI methods may be adapted to help steer treatment through integrative analysis of clinical information along with Pathology, Radiology and molecular data.
Learning, Training, Classification, Common Sense and Exascale ComputingJoel Saltz
In this talk, I will describe work my group has carried out in development of deep learning methods that target semantic segmentation and object identification tasks in terapixel Pathology datasets and for satellite data. I will describe what we have been able to achieve, how this work can generalize to additional types of problems and will outline how exascale computing could be used to transform and integrate our methods and pipelines. I will then go on to outline broad research program in exascale computing and deep learning that promises to identify common deep learning methods for previously disparate large and extreme scale data tasks.
Integrative Everything, Deep Learning and Streaming DataJoel Saltz
Workshop on Clusters, Clouds, and Data for Scientific Computing, September 6, 2018
The need to create to label information and segment regions in individual sensor data sources and to create synthesizes from multiple disparate data sources span many areas of science, biomedicine and technology. The rapid evolution in sensor technologies – from digital microscopes to UAVs drive requirements in this area. I will describe a variety of use cases, describe technical challenges as well as tools, algorithms and techniques developed by our group and collaborators.
Digital Pathology: Precision Medicine, Deep Learning and Computer Aided Inter...Joel Saltz
In this presentation, I will survey the development of Digital Pathology methodology beginning with the 1997 virtual microscope prototype at Hopkins to current tools, methods and algorithms designed to display, analyze and classify whole slide imaging data. I will describe methods, tools and algorithms to extract information from Pathology images. These tools include ability to traverse whole slide images, segment nuclei, carry out deep learning region classification and characterize relationship between extracted features and morphological structures. I will also describe some of the research efforts that motivate development of these tools, the role Pathomics is playing in precision medicine research as well as the impact of Pathology Informatics on clinical practice and health care quality.
Presentation at the Department of Biomedical Informatics, University Pittsburgh Medical Center, April 27, 2018
Twenty Years of Whole Slide Imaging - the Coming Phase ChangeJoel Saltz
Presentation at Pathology Visions 2017 - https://digitalpathologyassociation.org/2017-pathology-visions-agenda
I will survey the development of Digital Pathology methodology beginning with the 1997 virtual microscope prototype at Hopkins (PMC2233368) to current tools, methods and algorithms designed to display, analyze and classify whole slide imaging data. I will describe the capabilities of current methods, describe how these methods are likely to evolve and how they will be likely to impact Pathology research and practice.
Pathomics Based Biomarkers and Precision MedicineJoel Saltz
Role of Digital Pathology Data Science (Pathomics) in precision medicine. Features from billions or trillions of objects segmented from digital Pathology data can be employed to predict patient outcome and steer treatment.
Presentation at Imaging 2020, Jackson Hole, WY September 2016
Tools to Analyze Morphology and Spatially Mapped Molecular Data - Informatio...Joel Saltz
Description of NCI Information Technology for Cancer Research Project dedicated to 1) development of development of Digital Pathology pipelines, databases, data modeling and visualization methods, 2) support for digital pathology/Radiology/"omics" based precision medicine
Presented at Spring 2015 Information Technology for Cancer Research PI Meeting
Generation and Use of Quantitative Pathology PhenotypeJoel Saltz
Motivation, tools and methods analysis of digital pathology imagery, integration with "omics" and Radiology, use in Precision Medicine. Presentation at the Early Detection Research Network meeting, April 2015, Atlanta GA
Spatio-‐temporal Sensor Integration, Analysis, Classification or Can Exascal...Joel Saltz
Presentation at Clusters, Clouds and Data for Scientific Computing 2014
Integrative analyses of large scale spatio-temporal datasets play increasingly important roles in many areas of science and engineering. Our recent work in this area is motivated by application scenarios involving complementary digital microscopy, radiology and “omic” analyses in cancer research. In these scenarios, the objective is to use a coordinated set of image analysis, feature extraction and machine learning methods to predict disease progression and to aid in targeting new therapies. I will describe tools and methods our group has developed for extraction, management, and analysis of features along with the systems software methods for optimizing execution on high end CPU/GPU platforms. Once having provided our current work as an introduction, I will then describe 1) related but much more ambitious exascale biomedical and non-biomedical use cases that also involve the complex interplay between multi-scale structure and molecular mechanism and 2) concepts and requirements for methods and tools that address these challenges.
Integrative
analyses of large scale spatio-temporal datasets play increasingly important roles in many areas of science and engineering. Our recent work in this area is motivated by application scenarios involving complementary digital microscopy, Radiology and "omic"
analyses in cancer research. In these scenarios, our objective is to use a coordinated set of image analysis, feature extraction and machine learning methods to predict disease progression and to aid in targeting new therapies.
We describe methods
we have developed for extraction, management and analysis of features along with the systems software methods for optimizing execution on high end CPU/GPU platforms. We will also describe biomedical results obtained from these studies and extensions of the
computational methods to broader application areas.
2. BIP Team
Emory Morehouse Georgia Tech
Joel Saltz Elizabeth Ofili Barbara Boyan
Tahsin Kurc Alex Quarshie Mary Jean Harrold
Tim Morris Adam Davis Alessandro Orso
Marc Overcash Doug Blough
Andrew Post Karsten Schwan
Sanjay Agravat Mustaque Ahamad
Circe Tsui
Tony Pan
Ashish Sharma
Fusheng Wang
Carlos Moreno
3. BIP Objectives
The overarching goal of the ACTSI Biomedical Informatics Program (BIP) is to
maximize the scientific impact of ACTSI investigator proposals and facilitate
novel translational research by 1) enabling management, linkage, analysis and
mining of multi-scale, multi-dimensional data across ACTSI institutions and 2)
training, consulting, and assisting ACTSI investigators for more effective
application of bioinformatics, biostatistics, and informatics in their projects.
4. BIP Aims
Specific Aim 1: Develop a suite of interoperable, linked applications and
repositories for management and integration of clinical, "omics", imaging,
laboratory, and tissue data.
Specific Aim 2: Engage ACTSI investigators via consultations to maximize the
impact of ACTSI investigator proposals through coordinated use of bioinformatics,
biostatistics, and informatics.
Specific Aim 3: Educate researchers and others in our academic community on the
principles and best practices of biomedical informatics and use of biomedical
informatics applications and tools. Closely coordinated with the Research
Education, Training, and Career Development program.
Specific Aim 4: Develop novel biomedical informatics techniques and tools for: 1)
synthesis of information from very large multi-scale, multi-dimensional data, 2)
tools to create patient data registries through a semantic extract-transform-load
process, and 3) methods and tools for testing data integrity and maintaining
security in federated environments.
5. Aim 1: Develop suite of interoperable, linked applications
Develop integrative, federated ACTSI virtual
information warehouse
Integrated clinical/imaging/”omic”/biomarker/tissue
information should always be available
A virtually centralized, Atlanta wide information
warehouse that has all relevant data
Index and federate information generated throughout
ACTSI -- information available from patients seen and
information gathered at any ACTSI site, specimens sent to
any affiliated core, imaging carried out at any affiliated site
Governance and technology to manage authentication,
authorization
6. Applications and Databases Deployed by BIP
Application Deployed Content and Usage Function and Benefits
CR-Assist Dec 2005 322 studies since deployment, 126 active Enables researchers to manage
studies, 4258 participants, and 439 users participants, schedule and track study
events (visits, laboratory tests), and print
labels for bio-specimen collection.
eBIRT Jul 2010 424 services from 57 cores Enables discovery of relevant laboratories,
expertise, and services.
PAIS Database Aug 2010 In silico brain tumor study database of Enables researches to store, index, and
image analysis results from 307 slides explore image markups and annotations on
micro-anatomic structures for correlative
studies.
REDCap Apr 2010 1057 data instruments created, used by 75 Provides support for researchers to easily
studies capture and manage clinical research data.
Nautilus LIMS Jul 2010 421 studies in LIMS and 94 users; number Facilitates structured and more efficient
of aliquots received in LIMS: 754,099 management of laboratory workflows and
bio-specimens via a common
infrastructure.
AIW Clinical Registry Mar 2011 5 years of data on 4061 Emory patients Provides semantically annotated, easy-to-
query databases of clinical data for clinical
research.
AIW-Readmissions May 2011 5 years of clinical and administrative data on Provides a semantically annotated dataset
149,814 Emory patients for analyzing hospital readmissions.
MSM i2b2 Oct 2010 Clinical information from 21,000 patients Easy to use interfaces for researchers to
access EHR data for cohort identification.
7. Example Translational Research Projects
In silico study of brain tumors
Integrative analysis of image, omics, and clinical outcome data
Cardiovascular Studies
Correlative analyses of integrated data from databases of clinical
information as well as genomic and phenotypic information
Minority-Health Grid (MH-GRID)
Advance genomic science and personalized medicine in minority
health research
Big Bethel AME Project
Uses principles of community engaged research and biomedical
informatics tools to assist diabetic congregants of the Big Bethel AME
church in Atlanta to improve diabetes self management skills.
8. Example Translational Research Projects
Glenn Project
Increasing rate of consent and research specimen collection at Emory
University Hospital, Emory Midtown Hospital and Grady Hospital
Early hospital readmission
Understand relationship between disease conditions, treatments and
environmental factors in predicting hospital readmissions within 30
days.
Clinical Interaction Network
Search and analysis of de-identified patient data to help investigators
plan studies
CIN obtains real time notification when study patient is hospitalized
and obtains real time EMR data
9. In Silico Brain Tumor Research Center
(ISBRTC)
A research center of excellence for in silico study of brain tumors
Systematically execute in silico analyses (experiments) using
complementary data types
Collaborative effort among four institutions
Emory University
Thomas Jefferson University
Henry Ford Hospital
Stanford University
Initial focus on gliomas
Better Classification
Study Biology of Progression
Development of Methods and Workflows
“Companion” National Library of Medicine R01 funded, additional
companion proposals in review and preparation
7/9/2012
9
10. Minority-Health Grid (MH-GRID)
PI: Gary Gibbons, multi-site project involving
Morehouse School of Medicine, Grady, Jackson Hinds
Clinic, and Kaiser
Health disparities research focusing on hypertension
in minority populations
Integration of de-identified clinical phenotypes,
social-environmental data elements, biospecimens,
laboratory data, and genomic information
Data sharing and federation infrastructure will build
on the BIP Architecture and the Enhanced Registries
system
11. Big Bethel AME Project
PI: Priscilla Igho-Pemu. A Pilot study involving CIN, BIP, and CER programs of the
ACTSI and Big Bethel AME Church.
Hypothesis: Diabetic patients who use ehealthystrides and its social networking
forum will demonstrate better diabetes self management skills.
Main outcome variable: attainment of at least 3/7 of the American Association of
Diabetes Educators (AADE7) diabetes self-care behavioral goals.
Uses principles of community engaged research and biomedical informatics tools
to assist consented diabetic congregants (Participants) of the Big Bethel AME
church in Atlanta under the guidance of a trained coach to improve diabetes self
management skills.
Supports consumers as drivers of health transformation.
Coaches and participants are trained on the use of the ehealthystrides
application, personal health record creation, AADE7 goals and use of the
structured behavioral goal setting tools.
A community access “kiosk” with internet access and web portal has been
provided at the Big Bethel AME church premises to enhance training and
utilization of informatics tools by participants.
110 participants have currently been enrolled.
12. GLENN Project
POC: Dan Brat, project to define streamlined processes and
systems for Breast Cancer bio-banking at Winship
Primary goal: Increasing rate of consent and research
specimen collection at Emory University Hospital, Emory
Midtown Hospital and Grady Hospital
Integration of identified and de-identified clinical phenotypes
with available specimens for use in research
Architecture will utilize ACTSI master study participant index,
enterprise LIMS implementation and Emory enterprise service
bus
Generic architecture for use to support bio-banking across
Emory/ACTSI
13. LIMS
Establish a ‘virtual’ biobank and specimen tracking
infrastructure across the ACTSI.
Labs at many of our Clinical Interaction Networks are
in deployment or close to deployment:
Emory University, Morehouse School of Medicine, Grady,
Midtown, and Children’s
In process for next phase laboratories:
Hope Clinic
Neurology
Children’s Research Laboratories
14. Topic-specific Clinical Registries
Created using AIW infrastructure
Novel semantic extract-transform-load (ETL) tool in AIW to
create disease specific, semantically annotated clinical
repositories
i2b2 is used as user-facing presentation layer
Multiple registries are in various stages of
development for cardiovascular disease, diabetes,
oncology, and analyses of re-admissions that draw
data from the Emory Healthcare CDW.
15. eBIRT
Integrating “Find an Expert” functionality
based off of existing technologies, such as the
VIVO project
Kicked off the v2, “Find a Collaborator”
functionality and exploring the different
requirements
16. R-CENTER Web Portal
Centralizes access to research resources at
Morehouse School of Medicine (MSM)
through the internet.
Launched in July 2011
Enables discovery of expertise and resources
for research at MSM, the ACTSI and RCMI
Translational Research Network (RTRN).
17. Aim 2. Engage ACTSI investigators via consultations
Goal: Maximize the impact of ACTSI investigator
studies and proposals through coordinated use of
bioinformatics, biostatistics, and informatics.
Carried out in close collaboration with BERD and CIN
18. Aim 2. Engage ACTSI investigators via consultations
Ad hoc interactions with investigators and research
groups by BIP, CIN, and BERD teams
Established Studio consultation program
Investigators request Studio consultation
a coordinated venue for a pre-review and requirements
evaluation of proposals/projects by a panel of experts to
enhance the impact of ACTSI proposals and projects
Requests for BIP assistance are captured through the
RAPID system, jointly developed by BIP and the ACTSI
Tracking & Evaluation program
19. Investigator Studios
(a joint operation with BERD, BIP, and CIN)
Studios started in July of 2010, designed to provide “one-stop
shopping” for pre-submission consultations
In 2011 there were nine Studios conducted involving the full
complement of BERD, BIP, and CIN faculty
Ongoing 2012 schedule slots for the first Friday of each month
Investigators are requested to submit research plans and goals
in advance of the Studio session
Junior researchers can include their senior faculty mentors in
any session
Advertising on ACTSI web site and in Weekly Roundup has
been beneficial
20. Aim 3: Informatics Training Program
Closely coordinated with RETCD
Clinical Informatics Academy. This Continuing Medical
Education (CME) activity is targeted at clinical researchers,
clinicians, public health researchers, physicians, nurses, and
medical technologists with computer science, engineering, or
biomedical background.
It focuses on practical aspects of employing biomedical informatics in
research projects and patient care. The course consists of 14 hours of
lecture and breakout sessions.
The first session was held on June 1-2, 2011 with 42 participants
enrolled. The next course is scheduled for March 2012.
21. Aim 3: Informatics Training Program
Biomedical informatics (BMI) track in MSCR. A biomedical
informatics track with one student currently enrolled and
another two students to be added in Fall 2011.
Introduction to Biomedical Informatics is a required course and will
provide an introduction to clinical information systems, bioinformatics,
medical imaging, and computational tools.
Students will carry out a required translational research rotation and
will take Ethics as another required course.
Two student slots in the MSCR BMI track will be sponsored with GT
ACTSI BIP matching funds.
22. Aim 3: Informatics Training Program
Biomedical Informatics PhD Program. In Fall 2010, Emory
obtained approval for a new BMI PhD program that is jointly
administered by Emory’s Departments of Biomedical
Informatics, Math & CS, Biostatistics and Bioinformatics, and
CCI.
It will engage students with computational and biomedical training within
teams of software system researchers and scientific investigators, addressing
translational bioinformatics and clinical research informatics focus areas.
Certificate Program in Biomedical Informatics. This program
is targeted at researchers and clinical professionals who would
like to take a set of short courses on the basics and principles
of biomedical informatics.
23. Aim 3: Informatics Training Program
Clinical and Translational Informatics Rounds (CTIR). CTIR is a
monthly meeting targeted at clinical and translational
researchers, clinicians, pharmacists, nurses and information
services support staff.
It provides a venue for participants to critically discuss a diverse set of
landmark and current informatics papers, present their work before or after
presentation at national meetings, and brainstorm about current or planned
informatics projects, databases, decision support systems in patient-related
research areas.
One of the objectives is to form a group of informaticians across the
institution in preparation for the American Medical Informatics Association
efforts to implement subspecialty board certification in Clinical Informatics.
24. Aim 4. Develop novel biomedical informatics
techniques and tools for
Next Generation Integrative Methods in Medicine. Develop high-performance
computing and data management tools that will make it feasible to systematically
carry out large-scale comparative analyses using high-resolution, high-throughput
datasets.
Semantic Extract-Transform-Load (ETL) for Data Registries. Develop a semantic
ETL tool that will support temporal concepts and data mappings to semantic
terms.
Integrity Testing: Biomedical Data Sources and Data Federation. Develop, in a
collaborative effort between GT and Emory, a framework of tools and techniques
designed to detect errors by combining domain knowledge, modeling, and
software testing techniques
Authentication and Access Control in Federated Environments. Develop a
standards-based security framework in a collaborative effort between GT and
Emory to enhance security capabilities in federated environments.
25. Next Generation Integrative Methods
(in collaboration with Georgia Tech)
Large volumes of data generated by state-of-the-art
next generation sequencing instruments and image
scanners
Integration of these data types is limited in research
and healthcare delivery because of challenges with
large scale data management and analysis
Development of fast methods and tools that take
advantage of
Large scale storage environments and deep memory
hierarchies
Clusters of CPU-GPU nodes
26. Semantic ETL Tools and Enhanced Registries
Linked Databases for Research
Leverages common data elements and models and
existing standards. Initially for cardiovascular disease,
diabetes and co-morbidities.
Derived data elements represent categories of data
and temporal patterns of interest.
Linked to source data – initially, the Emory
Healthcare Clinical Data Warehouse and the Grady
Health System Diabetes Patient Tracking System.
Supports end-user researcher query and analysis.
27. Federated Security
(in collaboration with Georgia Tech)
Allow federated management of accounts across
institutional boundaries
Policy-driven, dynamic authorization based on
attributes.
Selection of applicable policies and conflict
resolution algorithm occurs in a dynamic fashion.
Standards based and leverage existing tools:
XACML, SAML, Shibboleth based standards
A paper at BIBM 2011 conference
28. Testing of ACTSI Federated Environment
(in collaboration with Georgia Tech)
Studies involve multiple databases and (complex) data
gathering and management processes
How to assess the integrity of the federated environment
when Data sources are added, updated, deleted
A framework to
Define rules that describe constraints, dependencies,
relationships, and business protocols
Compose and execute offline and online tests based on
rules and federated databases
A paper and a poster in AMIA Joint Summit. Another paper
submitted to a software engineering conference
29. Next Generation Exome Sequencing
(in collaboration with MSM)
Motivated by Minority Health GRID project
Exome sequencing of specimens from 2400 patients
Analysis and integration of genomic data with EHR and
observational data
Development of infrastructure for storage and
management
High performance computing support through use of
compute clusters
30. Interactions with other Institutions
The Southeast CTSA Consortium of eight CTSA projects in the
southeastern United States including ACTSI.
ACTSI BIP leads the informatics group.
a clinical data sharing initiative to study and develop regulatory
policies, governance and informatics infrastructure surrounding inter-
CTSA clinical and translational research
Collaboration with the Ohio State University (OSU) CTSA in the
development of a common middleware toolkit to support
data integration and resource federation
part of OSU-led CTSA Service Oriented Architecture affinity group
efforts
BIP is pursuing collaborative work with NCBO to integrate
their tools for semantic data modeling into the clinical registry
capability.
31. Interactions with other Institutions
Institution Collaborative Activities
Development of standards-based data sharing framework (initially driven by
University of North Carolina cardiovascular disease research) as part of the Southeast CTSA consortium and use of
BIP’s Analytical Information Warehouse and semantic ETL tools for EHR-linked
bioinformatics and bio-repository infrastructure.
Deployment of Emory eCOI system at University of Florida CTSA. Collaboration on
University of Florida interfacing of eBIRT and VIVO systems.
Collaborations through CTSA Imaging Informatics Working Group and caBIG® Imaging
Mayo Clinic Workspace on informatics tools for secure image data sharing in translational research
and in defining the image data sharing infrastructure in the RSAN image sharing project.
Collaboration through CTSA Imaging Informatics Working Group (IWG) to create common
Duke University Medical Center infrastructure and data models for management and sharing of biomedical image data
and quantitative imaging biomarkers.
Joint design and development of LIMS Study Design Module that has been deployed in
Children's Hospital of Philadelphia both institutions. Shared implementation strategies.
32. Interactions with other Institutions
Institution Collaborative Activities
Collaboration in the CTSA Service Oriented Architecture Affinity Group for development of
University of Michigan interoperable translational research informatics systems. Joint development of integrative
cardiovascular and cancer related research projects. Dr. Saltz serves as Chair of Michigan CTSA
Biomedical Informatics Core external advisory committee.
Collaborations in the Service Oriented Architecture Affinity Group for CTSA, the caGrid
Ohio State University infrastructure development, and the caGrid Knowledge Center -- Emory and Ohio State co-lead
the caGrid Knowledge Center effort. Development of interoperable translational research
informatics infrastructure.
Development of standards-based, federated informatics infrastructure and clinical data
Johns Hopkins University management systems for the CardioVascular Research Grid (CVRG) and application of these
systems in the driving biomedical projects of the CVRG consortium.
Deployment at Emory of REDCap and ResearchMatch systems. Active participation in
Vanderbilt consortium, shared deployment strategies, and extension of REDCap code.