Microsoft: A Waking Giant In Healthcare Analytics and Big DataHealth Catalyst
In 2005, Northwestern Memorial Healthcare embarked upon a strategic Enterprise Data Warehousing (EDW) initiative with the Microsoft technology platform as the foundation. Dale Sanders was CIO at Northwestern and led the development of Northwestern’s Microsoft-based EDW. At that time, Microsoft as an EDW platform was not en vogue and there were many who doubted the success of the Northwestern project. While other organizations were spending millions of dollars and years developing EDW’s and analytics on other platforms, Northwestern achieved great and rapid value at a fraction of the cost of the more typical technology platforms. Now, there are more healthcare data warehouses built around Microsoft products than any other vendor. The risky bet on Microsoft in 2005 paid off.
Ten years ago, critics didn’t believe that Microsoft could scale in the second generation of relational data warehouses, but they did. More recently, many of these same pundits have criticized Microsoft for missing the technology wave du jour in cloud offerings, mobile technology, and big data. But, once again, Microsoft has been quietly reengineering its culture and products, and as a result, they now offer the best value and most visionary platform for cloud services, big data, and analytics in healthcare.
In this context, Dale will talk about:
His up and down journey with Microsoft as an Air Force and healthcare CIO, and why he is now more bullish on Microsoft like never before
A quick review of the Healthcare Analytics Adoption Model and Closed Loop Analytics in healthcare, and how Microsoft products relate to both
The rise of highly specialized, cloud-based analytic services and their value to healthcare organizations’ analytics strategies
Microsoft’s transformation from a closed-system, desktop PC company to an open-system consumer and business infrastructure company
The current transition period of enterprise data warehouses between the decline of relational databases and the rise of non-relational databases, and the new Microsoft products, notably Azure and the Analytic Platform System (APS), that bridge the transition of skills and technology while still integrating with core products like Office, Active Directory, and System Center
Microsoft’s strategy with its PowerX product line, and geospatial analysis and machine learning visualization tools
Improving Healthcare Operations Using Process Data Mining
It’s estimated that 80% of healthcare data is unstructured, which makes it challenging to do any sort of analytics to drive improvements in population health, patient care and operational efficiency. Machine learning techniques can be utilized to predict future events from similar past events, anticipate resource capacity issues and proactively identify bottlenecks and patient outcome risks. This session will provide an overview of how process data mining can be applied to healthcare and provide real-world examples of process data mining in action.
Maximize Your Understanding of Operational Realities in Manufacturing with Pr...Bigfinite
Maximize Your Understanding of Operational Realities in Manufacturing with Predictive Insights using Big Data, Artificial Intelligence, and Pharma 4.0
by Toni Manzano, PhD, Co-founder and CSO, Bigfinite
PDA Annual Meeting 2020
Healthcare and Life Sciences organizations are leveraging Big Data technology to capture data in order to get a better insight into patient centric and research centric information. Combining these two requires extreme computing power. We will discuss use cases where Big Data technology was instrumental ; Merging Genomic and Clinical Data in order to advance personalized Medicine
Big Data and its Impact on Industry (Example of the Pharmaceutical Industry)Hellmuth Broda
While we bemoan the ever increasing data tsunami new technologies allow to harvest the gold nuggets in the hay stack.
Using the example of the Pharmaceutical Industry some of the possible business uses for Big Data Analitics are outlined.
Improving Healthcare Operations Using Process Data Mining Splunk
It’s estimated that 80% of healthcare data is unstructured, which makes it challenging to do any sort of analytics to drive improvements in population health, patient care and operational efficiency. Machine learning techniques can be utilized to predict future events from similar past events, anticipate resource capacity issues and proactively identify bottlenecks and patient outcome risks. This session will provide an overview of how process data mining can be applied to healthcare and provide real-world examples of process data mining in action.
Microsoft: A Waking Giant In Healthcare Analytics and Big DataHealth Catalyst
In 2005, Northwestern Memorial Healthcare embarked upon a strategic Enterprise Data Warehousing (EDW) initiative with the Microsoft technology platform as the foundation. Dale Sanders was CIO at Northwestern and led the development of Northwestern’s Microsoft-based EDW. At that time, Microsoft as an EDW platform was not en vogue and there were many who doubted the success of the Northwestern project. While other organizations were spending millions of dollars and years developing EDW’s and analytics on other platforms, Northwestern achieved great and rapid value at a fraction of the cost of the more typical technology platforms. Now, there are more healthcare data warehouses built around Microsoft products than any other vendor. The risky bet on Microsoft in 2005 paid off.
Ten years ago, critics didn’t believe that Microsoft could scale in the second generation of relational data warehouses, but they did. More recently, many of these same pundits have criticized Microsoft for missing the technology wave du jour in cloud offerings, mobile technology, and big data. But, once again, Microsoft has been quietly reengineering its culture and products, and as a result, they now offer the best value and most visionary platform for cloud services, big data, and analytics in healthcare.
In this context, Dale will talk about:
His up and down journey with Microsoft as an Air Force and healthcare CIO, and why he is now more bullish on Microsoft like never before
A quick review of the Healthcare Analytics Adoption Model and Closed Loop Analytics in healthcare, and how Microsoft products relate to both
The rise of highly specialized, cloud-based analytic services and their value to healthcare organizations’ analytics strategies
Microsoft’s transformation from a closed-system, desktop PC company to an open-system consumer and business infrastructure company
The current transition period of enterprise data warehouses between the decline of relational databases and the rise of non-relational databases, and the new Microsoft products, notably Azure and the Analytic Platform System (APS), that bridge the transition of skills and technology while still integrating with core products like Office, Active Directory, and System Center
Microsoft’s strategy with its PowerX product line, and geospatial analysis and machine learning visualization tools
Improving Healthcare Operations Using Process Data Mining
It’s estimated that 80% of healthcare data is unstructured, which makes it challenging to do any sort of analytics to drive improvements in population health, patient care and operational efficiency. Machine learning techniques can be utilized to predict future events from similar past events, anticipate resource capacity issues and proactively identify bottlenecks and patient outcome risks. This session will provide an overview of how process data mining can be applied to healthcare and provide real-world examples of process data mining in action.
Maximize Your Understanding of Operational Realities in Manufacturing with Pr...Bigfinite
Maximize Your Understanding of Operational Realities in Manufacturing with Predictive Insights using Big Data, Artificial Intelligence, and Pharma 4.0
by Toni Manzano, PhD, Co-founder and CSO, Bigfinite
PDA Annual Meeting 2020
Healthcare and Life Sciences organizations are leveraging Big Data technology to capture data in order to get a better insight into patient centric and research centric information. Combining these two requires extreme computing power. We will discuss use cases where Big Data technology was instrumental ; Merging Genomic and Clinical Data in order to advance personalized Medicine
Big Data and its Impact on Industry (Example of the Pharmaceutical Industry)Hellmuth Broda
While we bemoan the ever increasing data tsunami new technologies allow to harvest the gold nuggets in the hay stack.
Using the example of the Pharmaceutical Industry some of the possible business uses for Big Data Analitics are outlined.
Improving Healthcare Operations Using Process Data Mining Splunk
It’s estimated that 80% of healthcare data is unstructured, which makes it challenging to do any sort of analytics to drive improvements in population health, patient care and operational efficiency. Machine learning techniques can be utilized to predict future events from similar past events, anticipate resource capacity issues and proactively identify bottlenecks and patient outcome risks. This session will provide an overview of how process data mining can be applied to healthcare and provide real-world examples of process data mining in action.
Building a Data Warehouse at Clover (PDF)Otis Anderson
A brief tour of why we focused on building out a data warehouse early on at Clover, and why we think the Data Science function has room to grow in health insurance.
Improving Healthcare Operations Using Process Data MiningSplunk
It’s estimated that 80% of healthcare data is unstructured, which makes it challenging to do any sort of analytics to drive improvements in population health, patient care and operational efficiency. Machine learning techniques can be utilized to predict future events from similar past events, anticipate resource capacity issues and proactively identify bottlenecks and patient outcome risks. This session will provide an overview of how process data mining can be applied to healthcare and provide real-world examples of process data mining in action.
Artificial Intelligence, Neural Networks, Rate Prediction, Large Datasets, Data Cleanups...
The Health Insurance Marketplace Public Use Files (PUF) which contain data on health and dental plans offered to individuals and small businesses through the US Health Insurance Marketplace.
As the author of “Big Data in Healthcare Hype and Hope,” Dr. Feldman has interviewed over 180 emerging tech and healthcare companies, always asking, “How can your new approach help patients?” Her research shows that data, as an enabling tool, has the power to give us critical new insights into not only what causes disease, but what comprises normal. Despite this promise, few patients have reaped the benefits of personalized medicine. A panel of leading big data innovators will discuss the evolving health data ecosystem and how big data is being leveraged for research, discovery, clinical trials, genomics, and cancer care. Case studies and real-life examples of what’s working, what’s not working, and how we can help speed up progress to get patients the right care at the right time will be explored and debated.
• Bonnie Feldman, DDS, MBA - Chief Growth Officer, @DrBonnie360
• Colin Hill - CEO, GNS Healthcare
• Jonathan Hirsch - Founder & President, Syapse
• Andrew Kasarskis, PhD - Co-Director, Icahn Institute for Genomics & Multiscale Biology; Associate Professor, Genetics & Genomic Studies, Icaahn School of Medicine at Mt. Sinai
• William King - CEO, Zephyr Health
New York eHealth Collaborative Digital Health Conference
November 18, 2014
By leveraging Big Data, the healthcare industry has an incredible potential to improve lives. This session will give examples of how data volume, velocity and variety is transforming the “art” of a doctor to the science of care. It will describe how the use of machine learning and massive amount of data will drive the new Consumer Drive healthcare movement.
An overview of the i2b2 clinical research platform, and the implications of connecting Indivo to i2b2 as a source of patient-reported outcomes. Presented at the 2012 Indivo X Users' Conference.
By Shawn Murphy MD, Ph.D., Partners Healthcare.
Strata Rx 2013 - Data Driven Drugs: Predictive Models to Improve Product Qual...EMC
Like most of healthcare and life science, pharmaceutical companies are undergoing a data-driven transformation. The industry-wide need to reduce the cost of developing, manufacturing and distributing drugs while bringing to market new products is not a novel concept or challenge. However, the ability to process and analyze large amounts of data using cutting-edge massively parallel processing (MPP) technologies means innovation can be found not only in the traditional hypothesis-driven approaches we have come to expect. New technologies and approaches make it possible to incorporate all available data, structured and unstructured. At Pivotal, it is the goal of our data science practice to demonstrate the capabilities of the technologies we offer. We focus on building predictive models by combining the vast and variable data that is available to elicit action or generate insights. In our talk we will focus on a use case in pharmaceutical manufacturing, wherein we created a predictive model to produce more consistent, high-quality products and drive decisions to abandon lots with expected poor outcomes. In addition, we demonstrate how we used machine learning to cleanse data and to improve efficiencies in data collection by identifying low information-content measurements and incorporate under-utilized data sources in manufacturing. Beyond this use case, we will discuss our vision of using machine learning in all areas of the industry, from research through distribution, to drive change.
Whitepaper: Healthcare Data Migration - Top 10 Questions Carestream
Healthcare data migration is a challenging and critical undertaking. What do IT managers need to know before getting started? Read our white paper on the top 10 questions – and answers – you need to know before starting a healthcare data migration.
How To Avoid The 3 Most Common Healthcare Analytics Pitfalls And Related Inef...Health Catalyst
Analytics are supposed to provide data-driven solutions, not additional healthcare analytics pitfalls and other related inefficiencies. Yet such issues are quite common. Becoming familiar with potential problems will help health systems avoid them in the future. The three common analytics pitfalls are point solutions, EHRs, and independent data marts located in many different databases. An EDW will counter all three of these problems. The two inefficiencies include report factories and flavor of the month projects. The solution that best overcomes these inefficiencies is a robust deployment system.
The Why And How Of Machine Learning And AI: An Implementation Guide For Healt...Health Catalyst
Join Kenneth Kleinberg, Health IT Strategist, and Eric Just, Senior Vice President, Health Catalyst, as they discuss the What, Why, and How of Machine Learning and AI for healthcare leaders.
Attendees will learn:
Practical steps, timeframes and skills as well as real-time data and moving targets associated with the Implementation of ML and AI
How to deal with challenges inherent in ML and AI implementation
What the future holds for ML and AI
How BrackenData Leverages Data on Over 250,000 Clinical TrialsBracken
Learn about our why we've created our clinical trial intelligence solutions, how they provide big value to teams in the life sciences industry, and how you can start leveraging data immediately.
Dynamic Rule Base Construction and Maintenance Scheme for Disease Predictionijsrd.com
Business and healthcare application are tuned to automatically detect and react events generated from local are remote sources. Event detection refers to an action taken to an activity. The association rule mining techniques are used to detect activities from data sets. Events are divided into 2 types' external event and internal event. External events are generated under the remote machines and deliver data across distributed systems. Internal events are delivered and derived by the system itself. The gap between the actual event and event notification should be minimized. Event derivation should also scale for a large number of complex rules. Attacks and its severity are identified from event derivation systems. Transactional databases and external data sources are used in the event detection process. The new event discovery process is designed to support uncertain data environment. Uncertain derivation of events is performed on uncertain data values. Relevance estimation is a more challenging task under uncertain event analysis. Selectability and sampling mechanism are used to improve the derivation accuracy. Selectability filters events that are irrelevant to derivation by some rules. Selectability algorithm is applied to extract new event derivation. A Bayesian network representation is used to derive new events given the arrival of an uncertain event and to compute its probability. A sampling algorithm is used for efficient approximation of new event derivation. Medical decision support system is designed with event detection model. The system adopts the new rule mapping mechanism for the disease analysis. The rule base construction and maintenance operations are handled by the system. Rule probability estimation is carried out using the Apriori algorithm. The rule derivation process is optimized for domain specific model.
Building a Data Warehouse at Clover (PDF)Otis Anderson
A brief tour of why we focused on building out a data warehouse early on at Clover, and why we think the Data Science function has room to grow in health insurance.
Improving Healthcare Operations Using Process Data MiningSplunk
It’s estimated that 80% of healthcare data is unstructured, which makes it challenging to do any sort of analytics to drive improvements in population health, patient care and operational efficiency. Machine learning techniques can be utilized to predict future events from similar past events, anticipate resource capacity issues and proactively identify bottlenecks and patient outcome risks. This session will provide an overview of how process data mining can be applied to healthcare and provide real-world examples of process data mining in action.
Artificial Intelligence, Neural Networks, Rate Prediction, Large Datasets, Data Cleanups...
The Health Insurance Marketplace Public Use Files (PUF) which contain data on health and dental plans offered to individuals and small businesses through the US Health Insurance Marketplace.
As the author of “Big Data in Healthcare Hype and Hope,” Dr. Feldman has interviewed over 180 emerging tech and healthcare companies, always asking, “How can your new approach help patients?” Her research shows that data, as an enabling tool, has the power to give us critical new insights into not only what causes disease, but what comprises normal. Despite this promise, few patients have reaped the benefits of personalized medicine. A panel of leading big data innovators will discuss the evolving health data ecosystem and how big data is being leveraged for research, discovery, clinical trials, genomics, and cancer care. Case studies and real-life examples of what’s working, what’s not working, and how we can help speed up progress to get patients the right care at the right time will be explored and debated.
• Bonnie Feldman, DDS, MBA - Chief Growth Officer, @DrBonnie360
• Colin Hill - CEO, GNS Healthcare
• Jonathan Hirsch - Founder & President, Syapse
• Andrew Kasarskis, PhD - Co-Director, Icahn Institute for Genomics & Multiscale Biology; Associate Professor, Genetics & Genomic Studies, Icaahn School of Medicine at Mt. Sinai
• William King - CEO, Zephyr Health
New York eHealth Collaborative Digital Health Conference
November 18, 2014
By leveraging Big Data, the healthcare industry has an incredible potential to improve lives. This session will give examples of how data volume, velocity and variety is transforming the “art” of a doctor to the science of care. It will describe how the use of machine learning and massive amount of data will drive the new Consumer Drive healthcare movement.
An overview of the i2b2 clinical research platform, and the implications of connecting Indivo to i2b2 as a source of patient-reported outcomes. Presented at the 2012 Indivo X Users' Conference.
By Shawn Murphy MD, Ph.D., Partners Healthcare.
Strata Rx 2013 - Data Driven Drugs: Predictive Models to Improve Product Qual...EMC
Like most of healthcare and life science, pharmaceutical companies are undergoing a data-driven transformation. The industry-wide need to reduce the cost of developing, manufacturing and distributing drugs while bringing to market new products is not a novel concept or challenge. However, the ability to process and analyze large amounts of data using cutting-edge massively parallel processing (MPP) technologies means innovation can be found not only in the traditional hypothesis-driven approaches we have come to expect. New technologies and approaches make it possible to incorporate all available data, structured and unstructured. At Pivotal, it is the goal of our data science practice to demonstrate the capabilities of the technologies we offer. We focus on building predictive models by combining the vast and variable data that is available to elicit action or generate insights. In our talk we will focus on a use case in pharmaceutical manufacturing, wherein we created a predictive model to produce more consistent, high-quality products and drive decisions to abandon lots with expected poor outcomes. In addition, we demonstrate how we used machine learning to cleanse data and to improve efficiencies in data collection by identifying low information-content measurements and incorporate under-utilized data sources in manufacturing. Beyond this use case, we will discuss our vision of using machine learning in all areas of the industry, from research through distribution, to drive change.
Whitepaper: Healthcare Data Migration - Top 10 Questions Carestream
Healthcare data migration is a challenging and critical undertaking. What do IT managers need to know before getting started? Read our white paper on the top 10 questions – and answers – you need to know before starting a healthcare data migration.
How To Avoid The 3 Most Common Healthcare Analytics Pitfalls And Related Inef...Health Catalyst
Analytics are supposed to provide data-driven solutions, not additional healthcare analytics pitfalls and other related inefficiencies. Yet such issues are quite common. Becoming familiar with potential problems will help health systems avoid them in the future. The three common analytics pitfalls are point solutions, EHRs, and independent data marts located in many different databases. An EDW will counter all three of these problems. The two inefficiencies include report factories and flavor of the month projects. The solution that best overcomes these inefficiencies is a robust deployment system.
The Why And How Of Machine Learning And AI: An Implementation Guide For Healt...Health Catalyst
Join Kenneth Kleinberg, Health IT Strategist, and Eric Just, Senior Vice President, Health Catalyst, as they discuss the What, Why, and How of Machine Learning and AI for healthcare leaders.
Attendees will learn:
Practical steps, timeframes and skills as well as real-time data and moving targets associated with the Implementation of ML and AI
How to deal with challenges inherent in ML and AI implementation
What the future holds for ML and AI
How BrackenData Leverages Data on Over 250,000 Clinical TrialsBracken
Learn about our why we've created our clinical trial intelligence solutions, how they provide big value to teams in the life sciences industry, and how you can start leveraging data immediately.
Dynamic Rule Base Construction and Maintenance Scheme for Disease Predictionijsrd.com
Business and healthcare application are tuned to automatically detect and react events generated from local are remote sources. Event detection refers to an action taken to an activity. The association rule mining techniques are used to detect activities from data sets. Events are divided into 2 types' external event and internal event. External events are generated under the remote machines and deliver data across distributed systems. Internal events are delivered and derived by the system itself. The gap between the actual event and event notification should be minimized. Event derivation should also scale for a large number of complex rules. Attacks and its severity are identified from event derivation systems. Transactional databases and external data sources are used in the event detection process. The new event discovery process is designed to support uncertain data environment. Uncertain derivation of events is performed on uncertain data values. Relevance estimation is a more challenging task under uncertain event analysis. Selectability and sampling mechanism are used to improve the derivation accuracy. Selectability filters events that are irrelevant to derivation by some rules. Selectability algorithm is applied to extract new event derivation. A Bayesian network representation is used to derive new events given the arrival of an uncertain event and to compute its probability. A sampling algorithm is used for efficient approximation of new event derivation. Medical decision support system is designed with event detection model. The system adopts the new rule mapping mechanism for the disease analysis. The rule base construction and maintenance operations are handled by the system. Rule probability estimation is carried out using the Apriori algorithm. The rule derivation process is optimized for domain specific model.
1. Patient Safety is a health care professionals’ duty. A sur.docxSONU61709
1. Patient Safety is a health care professionals’ duty. A surgical team’s duty is the “…functioning of the unit and provide safety and well-being to the person who will submit to a surgical procedure” (Ventin Amorim Oliveira, Nunes Oliveira, Guedes Fontoura, et al, 2017). Surgical and treatment errors occur due to underlying causes. For instance, the failure to properly sterilize medical instruments following surgeries. Porter Adventist Hospital in Denver have notified some patients whom have been exposed to HIV, hepatitis B or hepatitis C in breaches that occurred during the time frame of July 21, 2016 and February 20th (CNN Wire, 2018).
2. Due to this error, stakeholders that were affected were the possible affected patients. The article from CNN Wire stated that the surgeries were “…found to be inadequate, which may have compromised the sterilization of the instruments” (CNN Wire, 2018). Highest risk is in hospital surgical rooms at which, “In patients who went through surgical interventions, 14-17% all hospital-acquired infections are comprised of “Surgical Area Infections”” (Ay & Gencturk, 2018). Due to the complex environments of hospitals and operating rooms, preventative factors must be to follow protocols and assure patients that they are in a safe environment to undergo the surgical procedures.
3. What information is needed to perform a root cause analysis?
Quality improvement involves numerous perspectives to detect root causes and develop optimum solutions for triumph. “A root cause analysis is used to find out what happened, why it happened, and determine what changes need to be made to improve performance” (U.S. Department of Veterans Affairs, 2018). Several pieces of information are required to perform a root cause analysis. Some of the information that might be helpful consists of “incident reports, risk management referrals, patient or family complaints, and health department citations” (Centers for Medicare & Medicaid Services, 2011). Collecting data helps prove there is a problem and helps determine how long the problem has existed, as well as how it has impacted the organization.
4. Which tool would you use to create a root cause analysis? Why?
“Root cause analysis is increasingly being used in health and social services to improve safety and quality and minimize adverse events” (Pearson, 2005). The tool that would best work to create a root cause analysis would be a cause and effect chart such as a fishbone analysis. “This process elicits root causes rather than just symptoms and results in a detailed visual diagram of all the possible causes of a particular problem” (Phillips & Simmonds, 2013). The reason a fishbone analysis would be used to create a root cause analysis is because it helps explore the issue in detail, which often will demonstrate possible solutions that might have been previously excluded. “Fishbone analysis provides a template to separate and categorize possible causes of a probl ...
Technology Considerations to Enable the Risk-Based Monitoring Methodologywww.datatrak.com
TransCelerate BioPharma Inc developed a methodology based on the notion that shifting monitoring processes from an excessive concentration on source data verification to comprehensive risk-driven monitoring will increase efficiencies and enhance patient
safety and data integrity while maintaining adherence to good clinical practice regulations. This philosophical shift in monitoring processes employs the addition of centralized and off-site mechanisms to monitor important trial parameters holistically, and it uses adaptive on-site monitoring to further support site processes, subject safety, and data quality. The main tenet is to use available data to monitor, assess, and mitigate the overall risk associated with clinical trials. Having the right technology is critical to collect and aggregate data, provide analytical capabilities, and track issues to demonstrate that a thorough quality management framework is in place. This paper lays out the high-level considerations when designing and building an integrated technology solution that will aid in scaling the methodology across an organization’s portfolio.
Keeping up with tech trends can be difficult, especially when it comes to healthcare — an industry that’s fast-evolving, notoriously complex, and shouldering an ever higher demand — but it is crucial.
Here’s an overview of the tech trends that are having the greatest impact on small to mid-sized practices, along with input from Staples Business Advantage Director of Healthcare Technology, James Clarke, on the importance of keeping pace.
From remote patient monitoring to antimicrobial devices, discover the technology that’s helping practices meet a wider range of patient needs, boost efficiency and improve the overall quality of care for patients.
Big Data Analytics for Healthcare Decision Support- Operational and ClinicalAdrish Sannyasi
Splunk’s data analytics platform could be utilized to solve many high impact business problems in healthcare delivery systems to reduce cost, improve patient outcome and safety, and enhance care coordination experience. Analyze observed behavior from healthcare event data and metadata to discover patterns, monitor compliance, and optimize the workflow. Furthermore 80% of healthcare data is unstructured (clinical free text and documentation), or semi-structured and many new data sources are such as tele health, mobile health, sensors, and devices are getting integrated in many healthcare systems specifically in the area of chronic disease management. So, one need analytics software that can harvest, interpret, enrich, normalize, and model diverse structured and unstructured data and analytics approaches that embrace the “data turmoil” by relying less on standardized data items and more on the capability to process data in any format.
Fidelis Cybersecurity commissioned 360Velocity to conduct an enterprise study on the State of the SOC, including current trends and practices of threat detection and response. Join this webinar to listen to security experts Dr. Chenxi Wang of 360Velocity and Tim Roddy, VP of Cybersecurity Product Strategy at Fidelis examine how to standardize processes for threat detection and response & the case for and how to integrate network sensors and endpoint enforcement
Big data, RWE and AI in Clinical Trials made simpleHadas Jacoby
Technology is slowly but surely penetrating the healthcare industry in general and the clinical trials sector in particular. New and advanced solutions offer a variety of possibilities aimed to both improving existing processes and creating new and more efficient ones. And on top of all stands the desire to make clinical trials more patient centric.
In all of this, even though some of the technologies have yet to mature enough to meet the high quality standards necessary, it is important to know them and begin imagining the promise they hold for clinical trials.
Whitepaper next generation_patient_safety_bertine_mc_kenna.01Ronan Martin
This is not your grandfather’s white paper. Dr. Bertine McKenna talks about healthcare cybersecurity from an executive perspective. Learn where to put your attention when it comes to tailoring a cybersecurity program.
Executives are missing an opportunity to ensure that we are ahead of this curve like every other curve we have had to be ahead of. Cybersecurity is not an IT issue – it is an operational issue focused on patient safety. It is a safety hazard requiring full attention and innovative solutions.
What is the best Healthcare Data Warehouse Model for Your Organization?Health Catalyst
Join Steve Barlow as he addresses the strengths and weaknesses of each of the following three primary Data Model approaches for data warehousing in healthcare:
1. Enterprise Data Model
2. Independent Data Marts
3. Late-binding Solutions
How to Use Open Source Technologies in Safety-critical Digital Health Applica...Shahid Shah
Presented at 3rd Annual Open Source EHR Summit - Key Takeaways:
* Outcomes driven care (vs. fees for service or volume driven care) is in our future
* Because outcomes now matter more than ever, open source digital health solutions are even more important
* There are new realities of patient populations driving open source even faster
* How to use open source reliably and and securely in a safety-critical environment like medical devices
This presentation summarizes our research on 40 companies from around the world that are leveraging Artificial Intelligence to improve the Healthcare Industry. They are all well-funded, have highly qualified CEOs & Boards, and are poised to achieve their product development milestones.
The I-Square Ventures proprietary rating algorithm indicates that almost all of these companies will receive more funding, and/or be acquired by larger companies.
CHC Briefing: OSEHRA is a great business opportunity for healthcare IT ISVs a...Shahid Shah
An opinionated look at why current health IT systems integrate poorly and how it’s a big opportunity for the OSEHRA Community
Topics Covered:
* An overview of VA, VHA, VistA, and OSEHRA
* The macro healthcare environment and why OSEHRA is am important participant
* What’s needed by the industry that OSEHRA can provide
Key takeaways:
* OSEHRA is major business opportunity for ISVs and systems integrators
* There’s nothing special about health IT data that justifies complex, expensive, or special technology
CHC Briefing: OSEHRA is a great business opportunity for healthcare IT ISVs a...
IBM impact-final-reviewed1
1. Agenda
1
• The business problem
• Current solution
• Proposed solution
• User interface and technologies
• Ilog and integration with the user interface
• Real time rule detection
• Q&A
3. Who are we?
3
• A healthcare alliance with 2500 hospitals and 80000
healthcare sites, improving the health of our communities
• Premier collects data from participating hospitals. We
house the nation's largest detailed clinical and financial
database, holding information on more than 130 million
patient discharges.
• Web-based tools allow hospitals to compare their
performance in specific areas to peers and best
performers, find opportunities for improvement, and track
the results of their efforts. Also provide surveillance
capabilities with the clinical warehouse.
4. Business Problem
4
• Meet regulatory needs to decrease healthcare associated infection
occurrences and their associated costs.
• Improve infection prevention efforts and reduce costs associated with
HAIs by supporting automated infection control, surveillance and
medication management.
• Increase pharmacists' efficiency, optimize antimicrobial utilization,
enhance outcomes and reduce pharmacy expenditures.
• Handle complex event detection rules, to ensure accuracy in identifying
patients at risk of HAIs.
• Prevent too many false positive events which would generate too much
“noise” for clinicians leading to a lack of trust in the tool.
• Monitor and prevent outbreaks
5. Healthcare Associated Infections (HAIs)
Every year HAIs account for:
~ 2 million infections
90,000 deaths
$4.5 billion in excess healthcare costs
SafetyAdvisorTM
Improves infections prevention efforts
Reduces costs associated with HAIs
Positively impacts patient care
6. Customer Stories
6
"SafetySurveillor has been a boost to productivity. Before we went through stacks of cultures every day and tried to pick out the
ones that were significant. With SafetySurveillor, we just set our alerts. We don’t have to go through that sorting process. It makes
data mining easy. It has really made us more efficient so we can dedicate our time to engaging with staff to make a difference in
patient care. Without SafetySurveillor, we’d be struggling with all the new CMS requirements. It would be scary. I don’t know how
we’d do it. I don’t know how facilities without automated surveillance do it. I really don’t."
Rebecca Bartles, MPH, CIC
Corporate Manager, Infection Prevention Mountain States Health Alliance
Johnson City, TN
"We get alerts 48 to 72 hours before we would
have gotten them before SafetySurveillorTM. In three months we
identified 13 cases where we were able to intervene before
anybody else... 12 were accepted immediately... I’m not saying
they wouldn’t have been caught in the old system, but they
wouldn’t have been caught by the pharmacy, and there would
have been delay. There is plenty of information in the literature
that supports the idea that delay of appropriate antibiotics or
antimicrobials in septic patients leads to increased mortality. All
the interventions were accepted within one to six hours...There
was a high success rate..."
Erik Schindler, Clinical Pharmacist
St. Luke's Hospital
An experienced user of SafetySurveillor®, Rochester General
chose to concentrate on sepsis and catheter associated urinary
tract infections – not necessarily to reduce costs, but to improve
patient outcomes and decrease mortality.
"SafetySurveillor is the mechanism that allowed us to be able to
initiate this project. When you’re looking at a large number of
infections in a house-wide project, especially when you’re
drilling down to each of the units, it’s impossible to do that
without electronic surveillance. . . . We did a very, very modest
estimate of our savings but for credibility with administration, I
always use a lowball figure. . . . SafetySurveillor is definitely on
the cutting edge. We’ve been pleased. We’ve been very, very
satisfied."
Linda Greene, RN, MPS, CIC, Director of Infection Prevention
8. Challenges
8
• Near real-time event detection (job runs every ten
minutes detecting events)
• Scalability (with the pod structure and the 250+
databases)
• Providing a broad range of events that can be detected,
in addition to tailoring event detection to specific patient
populations to reduce alert “noise”
• Event Detection/Rule Detection using set of stored
procedures limits the ability to modify events and extend
to support complex events.
• Data standardization using industry standards allowing
for a better match in rules and enhancing the data’s
usefulness.
10. Definitions
10
Event Definition Template – A template defining a type of Event Definition. For
example, a Pharmacy Event type has the following as a list of parameters to choose
from (patient location, service, patient class, hours of hospitalization, lab test
timeframe, lab test result, % change of lab result, drug, drug route, age, gender,
drug schedule code). An event definition template is one that provides the above as
parameters to choose from.
Event Types – Categories of Event Definition. Some event types are Pharmacy,
Lab Only, Lab & Drug.
Event Definition – Applying values to an event definition template creates a set of
rules/rulesets. For example, using a pharmacy event definition template, I can
create n number of event definitions, such as if patient location = pediatric ward and
service = cardiovascular and (drug=xxx or drug=yyy) do blah.
Event – When applying the event definition to a set of data elements like patient or
lab, the decision that is derived creates an event.
Alert – The occurrence of the event for a subscribed individual is an alert.
11. High-Level UI Architecture
11
WebSphere Portal 7
WAR
JSR-286 Portlet
Dojo Widget
Dojo Widget
Dojo Widget
Spring 3 Controller
[REST Services]
<<JSON>>
REST Web Services
Running on WebSphere
App Server
<<XML>>
12. Event Definition– An Example
Group 1 - ((Hydralazine [drug])
AND
Group 2
Set 1 - (Isosorbide Dinitrate [drug] OR Isosorbide Mononitrate [drug] ))
OR
Set 2 - (Angiotensin Converting Enzyme Inhibitors [drug group) OR (Angiotensin II Inhibitors [drug group])
AND
Group 3 - (Non-steroid anti-inflammatory agents [drug group])
12
Use Case
Patients at Premier Memorial Hospital with orders for drugs with significant interactions
35. The challenge
• Creation of multiple rules automatically in RTS without
any human interaction
• External Access to ILog vocabulary
• Guided Editor for Rule Creation
35
36. The Solution
• The Event Definition framework is primarily based on the
following key principles:
– Creation of a service to handle all the API level interaction with
ILog
– Business Rules Templates
36
37. Templates
• Templates are used to create Business Rules, based on
data entered in Safety Advisor UI.
• These Templates are created for each Parameter:
– Examples of Parameters include
• DRUG, TAG,FACILITY, PATIENT CLASS
• For a parameter, number of templates are created based
on the attributes and possible patterns
– Examples of attributes
• Route of Drug, Schedule Code of Drug, Dosage of Drug
38. Templates Design
• Templates are defined such that they are dynamic and support all
possible patterns of data. Following are the features in Templates:
– Has “definitions” so that the rules are run only on specific set
– Has “identifiers” that can be replaced with actual values when creating the
Rules
• Templates are designed to support any AND/OR conditions
between groups. It’s always OR condition within a Group.
• A Rule will be created for each Parameter within a Group. Each of
the rule is are evaluated for TRUE and the whole group is set to
True if any of the rule is TRUE within the group.
• In the final evaluation, each group is evaluated for TRUE and the
whole event is triggered based on how the groups are combined
(AND/OR). For example, if they have only OR between the groups,
evaluation of at least one group to TRUE will trigger the event.
41. Event Definition - Rule Creation
41
SafetyAdvisor
UI
Rule
Execu7on
Server
Rule
Template
Selec7on
Rule Creation
Request
BRMS Service
Web service call
1
HTDS - Get the Business Rule Template
Rule
Team
Server
Symphony
Rule
Project
Create Rules using ILOG API
2
Symphony
3
Deploy Ruleapp
47. Projected Volumes – Clarified – add current
events + projected number of events
47
Projected 5% growth
factor from current
Projected 1 to 1 Ratio of
Lab Orders to Lab
Results (based on
Hans’ previous
experiences)
Assumes we
transmit all
messages, either
HL7 or XML or
both
The projected number of HL7 or XML messages that would be received at the
Premier application level if we were processing all four data types for all 250+
facilities in December 2011
Doubled if we
receive both HL7
and use Meddius
or an IBM edge
solution to
generate XML