Archive for September 11, 2012

Hackathon Aims to Clear the Air

In late April, more than 200 data scientists from more than 10 cities around the world spent 24 hours in London designing solutions to help improve the U.S. Environmental Protection Agency’s (EPA) Air Quality Index.

People who suffer from asthma and other respiratory diseases use the index to avoid dangerous levels of attack-triggering outdoor air pollutants, and the hackathon’s goal was to help build local early warning systems to accurately predict dangerous levels of pollutants on an hourly basis.

“We wanted to use open data, but more than that, we wanted data that was meaningful in terms of social change or influence,” said Carlos Somohano, a data scientist for Data Science London (DSL), about the choice to use an environmental data set from Cook County, Ill.

The Data Science Hackathon was created and hosted by DSL and Data Science Global in collaboration with Kaggle, a platform for predictive modeling and analytics competitions. The activities were part of Big Data Week, a series of community led events and hackathons involving big data.

David Chudzicki, data scientist for Kaggle, said Chicago’s thriving data science and machine learning community was involved in the event from early on. “Cook County is making a big drive toward open gov data,” he said, “so the collaboration with them providing the data set occurred quite naturally as we were searching for a good problem for the hackathon.”

If the hackathon can contribute to positive health-care outcomes, then the event will prove more than worthwhile, said Chris Roche, regional director for Greenplum, a division of EMC, which sponsored the event. “What I like about the hackathon and the data science community is the accelerated innovation that they create.”

On the whole, the competition led to some great insights into the problem and started people looking at this type of data, Chudzicki said. Cash prizes totaling 3,000 pounds (approximately $4,700) were awarded between a global winner and a London-based winner.

The winning solutions were submitted and ranked through Kaggle’s competition platform that provided real-time leader boards, allowing participants to continuously keep track of their scores.

Though the top winner, Ben Hamner, was ineligible for any prize money as a Kaggle-employed data scientist, his solution is notable in that he claims to have barely glanced at the domain before training the model — meaning he could devise a winning solution without knowing anything about the actual issues going on in Cook County. To him, he was working with truly random data.

“I was surprised that domain insight wasn’t necessary to win the hackathon,” Hamner said. “Key insights have been crucial in many of our longer-running competitions.”

While it’s too early to know what his solution could mean for Cook County, the EPA and citizens who follow the Air Quality Index, the solution is now undergoing a period of thorough exploration and development.

Melbourne’s James Petterson won the global first prize and, like Hamner, spent little time looking at the data itself. He said he was surprised to achieve such a high-quality result without having spent time trying to understand the data set.

“If you’re a data scientist, let the data talk,” said DSL’s Somohamo. “You don’t have to be a domain expert. The competition proves that a good data scientist doesn’t have to know the domain context to achieve results.”

The code for both winning models discussed above, as well as that of the local London winner, has been made publicly available by Kaggle and Data Science London, meaning it’s accessible to anyone who wants to explore it and continue working on it. Development may well continue outside the expected channels.

Currently, predictive models drafted at the hackathon are being reviewed to determine their relevance at the local, state, U.S. EPA and National Weather Service levels. “We’re looking at who is most appropriate to use this,” said Cook County CIO Greg Wass. “Once these solutions are refined, they may go up the chain. We’ll see how far we get with this thing.”

“One of our missions is to promote awareness of data science and the dissemination of data science knowledge,” Somohano said. “It’s a new thing here in the UK, but in the U.S., it’s already getting quite trendy.”

The best way to raise awareness and involve local and international data science communities was through a hackathon, determined Somohano and his DSL partner Stewart Townsend.

“The concept of a ‘hackathon’ has deep roots in Silicon Valley as an event that combines innovation and competition in a very short, intense period of time,” Chudzicki said. “While the term ‘hacker’ has negative connotations from being used to describe computer security crackers, the meaning in the community is someone who delights in solving problems and building new things.”

The EPA data set was chosen because air pollution affects people regardless of their location, even if the specific data used in the competition was sourced from one U.S. city.

“We worked in partnership with Big Data Chicago to make this happen and to share our environmental data sets,” said Cook County Deputy Director of New Media Sebastian James. “We were asked if we could get the specific data about air quality to the event organizers. They needed a big data set to work with, something that served a public need and was very topical.”

As Data Science Global organizes and promotes future events, DSL’s Somohano said that other subject matter and data of high relevance to government — such as health care — will be the objective.

Health-care provision is one of the major concerns of governments worldwide, said Greenplum’s Roche. “Serious respiratory disease affects over 700 million people globally and chronic disease accounts for over 80 percent of all primary care consultations.”

You may use or reference this story with attribution and a link to

View the original article here

4 Approaches to Health Information Exchanges

Rhonda Hoeffner, a nurse in the cancer center’s intensive care unit at Johns Hopkins, uses a computer to chart information. Photo by the Baltimore Sun/Lloyd Fox

In June, the board of the nonprofit Health Information Partnership for Tennessee (HIP TN) announced plans to wind down its operations. The group was created three years ago to help Tennessee create a statewide clinical health information exchange. Officials at HIP TN said the state decided to pursue a simpler strategy that relies on secure email transmission of health information among providers.

And Tennessee may not be the only state changing direction. With limited grant funding and tight time frames, others also are re-evaluating ambitious goals of creating an infrastructure that would allow searching for patient records across hospitals and doctors’ offices statewide. Instead, states are downshifting to more incremental plans that start with enabling email connections between providers or that focus on supporting state Medicaid organizations. (HIEs — health information exchanges — are not to be confused with health insurance exchanges, which are being set up to allow consumers to comparison-shop for health plans.)

Tennessee intended to offer enterprise services, including links to an immunization registry, electronic lab results for reporting to the Department of Health, and compiled patient medication histories. “Our plan was to create a network-of-networks model that would connect existing RHIOs [regional health information organizations], not be a replacement for them,” said HIP TN CEO Keith Cox, who was hired in January 2011 to run the statewide operation and develop enterprise and value-added services for the network.

“Tennessee has been a leader in many HIE efforts, and we have a lot of experience in developing models of collaboration,” Cox said. “And as a state and a region, we are following and even anticipating the trends and visions that have been set forth for almost a decade.” Although the state received $11.6 million in federal grant funding to create the HIE, Tennessee officials say the new aim is to ensure that Tennessee providers meet the expected information exchange goals of Stage 2 meaningful use criteria of the incentive payment program funded by the American Recovery and Reinvestment Act of 2009. The new initiative, known as Direct, will be the basis, in the near term, to accomplish this.

“The board supported the change in direction and remains committed to the national vision for an interoperable health-care information infrastructure,” Cox explained. “It was very disappointing to think we would wind down after hundreds of stakeholders volunteered their time to work on an HIE framework,” he added. “However, all remain passionately committed to making this work for the state.”

Tennessee’s abrupt change in direction is unusual, but the frustration expressed there about the difficulty of the HIE process is common. For instance, in May, California replaced Cal eConnect, the nonprofit organization created to develop the state’s HIE. That effort is now led by the Institute for Population Health Improvement at the University of California, Davis. Cal eConnect had struggled with several changes in leadership. A joint statement from the California Health and Human Services Agency and Cal eConnect noted that the Cal eConnect board determined that as a startup with a large board, it was “not able to move fast enough to implement approved programs.”

One challenge that public-sector HIEs face is competition from private HIEs being set up by health systems to support patient-centered medical homes and accountable care organizations. In Connecticut, the three main hospital systems are expanding rapidly by buying hospitals and physician practices, and building out their own private HIE architectures that are tied to specific electronic health record vendors. “That is changing the thought process about the role the state HIE will play,” said David Gilbertson, CEO of the Health Information Technology Exchange of Connecticut. “What is the incentive for providers to connect to us? One is to fill the gaps and offer access to the providers that are not part of these organizations,” he said. “Another is to provide access to public health and Medicaid data. Those are the value propositions.”

A snapshot of the development of statewide HIEs reveals a patchwork quilt with widely varied levels of activity and success. Some states have been working on transmitting health data for almost a decade, although even these exchanges struggle with financial sustainability. Other states are still doing planning and governance work. Because the federal funding was part of the stimulus bill, it must be spent in the next year and a half. That aggressive timeline puts the states in a difficult situation. “If the question is, can they complete a robust exchange in that time frame, the answer is probably no,” said Julia Adler-Milstein, an assistant professor at the School of Information at the University of Michigan. “But will information exchange increase considerably? For the majority of states, the answer will be yes.” However, if any progress at all on exchange is considered success, that is setting the bar rather low, added Adler-Milstein, whose research focuses on policy and management issues related to the use of IT in health-care delivery.

States are being forced to reassess their role in HIE, said Rick Ratliff, global connected health managing director for consulting firm Accenture. “Pennsylvania did an initial procurement over a year ago for planning a fully functionalHIE for the whole state,” he said. That procurement has been pulled, and a new procurement is likely to be much more modest, he said, taking advantage of exchange efforts already going on and with the state playing a much smaller part.

The states that are going to stand up a sophisticated central technology platform are few and far between, Ratliff said. “But it still makes sense for them to provide some shared services such as registry services for chronic disease management,” he said. States may focus on a smaller set of core government initiatives including public health reporting. “If the HIE can offer visibility into Medicaid members and increasing efficiency on their behalf,” he added, “that can be a key driver.” For instance, the Alabama Medicaid Agency has been the lead agency for the development and implementation of that state’s HIE plans. And the Arizona Medicaid program is offering incentives over the next three years to offset costs for providers to join the Health Information Network of Arizona.

Adler-Milstein contributed to a 2012 Robert Wood Johnson Foundation report on the state of U.S. health information technology. It used a model created by Deloitte that groups the state approaches to fostering HIE into four types:

Elevator: States with an elevator model focus on rapid facilitation of exchange capabilities to help clinicians meet stage 1 of the federal “meaningful use” requirements to earn electronic health record implementation incentive funding. These states typically start with very limited health IT adoption and exchange activity locally or at the state level. Thus, they need to rely on a technical approach that can be built quickly and does not require mature infrastructure. Examples of elevators include Illinois and Wisconsin (and perhaps now Tennessee), Adler-Milstein said.

Capacity-Builder: These states focus on providing financial and technical support to bolster existing local exchanges that have comprehensive geographic coverage. Indiana, which already has several mature HIEs, including the Indiana Health Information Exchange, is a good example. “It would be crazy for the state of Indiana to try to stand up something totally new,” Adler-Milstein said. “Instead, they are using grants to try to get more provider groups connected to these existing exchanges.”

At a National eHealth Collaborative meeting earlier this year, John Kansky, vice president of product management for the Indiana HIE (IHIE), said the key to Indiana’s success is keeping the focus on providing value to customers. “We approach it and sustain it as a business,” he said. Affiliated with the Regenstrief Institute, the IHIE connects 90 Indiana hospitals, and 19,000 physicians use it. Its DOCS4DOCS subscription service provides physicians lab and radiology results in a Web-based inbox. The IHIE also offers a service that enables hospitals and physicians to electronically share clinical images.

Orchestrator: States with an orchestrator model focus on building the basic services required to connect existing substate exchanges. A good example is New York, which has nine RHIOs up and running, and its Statewide Health Information Network for New York will create a set of core services that participants will use to exchange information across organizational boundaries. Another state that is orchestrating exchange but not standing up a strong state-level organization is Minnesota. The state decided to certify and regulate exchange as it develops in the private sector, said Marty LaVenture, director of Minnesota’s Office of Health Information Technology.

“Given the limited funds available, it was determined to support a market-based approach,” he said. “As much as others may have wanted us to do this in a big bang, we determined to reduce our risk and do it incrementally.” The government role is oversight — ensuring there’s a fair playing field and that privacy and security guidelines are established and followed. “But we have a fairly thin layer of governance,” LaVenture stressed. So far, the state has certified five health information service providers, including Surescripts and Ability Network.

Public utility: States with a public utility model build a single hub for exchange focused on providing a wide spectrum of HIE services directly to end users and to substate exchanges where they exist. The exchange is either based inside state government or in a nonprofit state-designated entity. Such a model is particularly well suited for small states like Vermont and Delaware that can obtain sufficient stakeholder buy-in, as well as states with sufficient authority and resources to build statewide infrastructure. “Smaller states are more likely to play a broader and deeper role in the exchange,” Accenture’s Ratliff said. “There tends to be more willingness for health systems to come together and to allow a state health department, for instance, to play a significant role in driving governance and standards.”

Maine’s HealthInfoNet, which started in 2004, is a good example of a public utility, even though the organization is nonprofit and sits outside of state government. It’s expected that all Maine hospitals will be under contract to HealthInfoNet by year’s end and will be connected by the end of 2013. The exchange also expects that at least 80 percent of the state’s ambulatory providers will be connected by 2014.

HealthInfoNet’s executives see one early decision as critical: the creation of a commingled central database. (Competing health systems have trouble agreeing to do that because they see their data as a competitive advantage. Most states are using a federated model in which the data is stored in separate places and queried from other locations.) “One key problem with the federated model is that the data is not standardized,” said Dev Culver, CEO of HealthInfoNet. “They can’t create a view of the patient. We put a lot of time into mapping all that data to standards. In a federated model, that is impossible to do.”

In another example of value-added services it can offer, HealthInfoNet is launching the nation’s first statewide medical image archive. The goal is to reduce the cost of storage and transport of electronic medical images and make sharing these images possible through the HIE.

But even HIEs that are successful in linking providers are still struggling to create a model of sustainability. The Delaware Health Information Network (DHIN) connects all hospitals in the state and 93 percent of providers. Yet Dr. Jan Lee, DHIN’s executive director, is charged with finding ways to make the network financially sustainable once federal and state funding run out. Previously, the state and private-sector providers have split what federal grants have not covered, but DHIN will have to identify value-added services that providers will be willing to pay for, such as unified medication history reports and data analytics on population health. This year DHIN had to go back to the state for an additional $3 million, but Lee said legislators were reluctant to provide that funding and basically said, “Don’t come back next year.”

Delaware has been working on HIE for 10 years — “before it was trendy,” Lee said, and it still has issues to work through. She believes that states trying to catch up now face daunting challenges. “Look at Pennsylvania just to our north,” she said. “They have not been able to get off the dime. Issues of competition and mistrust have sent them back to the starting block several times. Now they are getting started and only have 15 months left in the ONC [Office of the National Coordinator for Health IT] funding grants. They cannot get connected in that time,” Lee added. “Dealing with data structure, consent issues, security, consumer advisory groups, broadband coverage — all this takes a long time.”

State HIE governance organizations are spending the most time on business cases and models for sustainability. It seems that the most successful HIEs, such as IHIE in Indiana, have focused on building only those services that stakeholders will pay for. It may be that there isn’t a strong market demand for statewide services, especially in large states where several regional exchanges have already been established. “They should do a needs assessment about how much demand there is for statewide exchange across big regions,” Adler-Milstein said.

Maine’s Culver believes his central data repository is valuable and can make HealthInfoNet sustainable if the HIE can offer analytics tools around it. “To organizations setting up accountable care organizations, there is a lot of value in that data set,” he said. “And if we can demonstrate a significant impact on cost and quality, then we can distinguish ourselves.”

View the original article here

PracTutor launches the pre-registration to help students learn Math and English in an adaptive innovative way

Louisville, KY. September 08, 2012 – PracTutor ( is an adaptive learning platform to help students excel in Math and English. PracTutor was established with just one focus – THE STUDENT. PracTutor is trying to solve the challenge of how can we make any student love, learn and enjoy Math and English.

There are 39 million students in US in K-8 in public and private schools. Only 69% students make it to a high school and less than 70% to a college. Most of them falter at one of the numerous high school or college admission tests.  In college, majority of the students need to take remedial courses in Math and English. About 40% of the students take some form of Math and English training program to prepare for high school and more than 75% to prepare for college admission tests. The students get frustrated with the narrow focus of such trainings or possible interventions not available when needed. PracTutor experience is personalized and it understands the student’s strengths to challenge them more on their strengths and it understands their weaknesses to eliminate them.

PracTutor is virtually effortless and very intuitive for the student to use. It applies intelligent algorithms to understand the student’s abilities in Math and English and provide practice and training to strengthen their skills. This training is mapped to each and every standard of the common core curriculum. PracTutor involves the parents and the school teacher in the student’s progress and provides all the elements required for the success of the student. A private tutor can help the student whenever they need any help.

“I created PracTutor because I was frustrated after using quite a few after-school Math and English programs for my two sons in Grades 3 and 5, I felt there had to be a better way, a better product and not seeing one, decided to create one.”, said Vatsal Ghiya, co-founder, PracTutor.

“I have seen a lot of my cousins and sons and daughters on my friends struggle with Math and English with numerous programs they work on. All of the training programs seem to be missing one or several elements. We wanted to provide the entire ecosystem – a complete solution. That is what PracTutor is.”, said Hardik Parikh, co-founder and CEO, PracTutor.

PracTutor’s team comprises experts on Math and English from common core team, web designers, software developers, child psychologists, parents and school administrators.

PracTutor is in development right now and we would like to invite users for beta testing as soon as we have it out.

Watch what we do at

Take a tour of the product at –

Pre-register using this link –

About PracTutor

Started in April -2012, PracTutor ( is an adaptive learning platform to help students excel in Math and English. PracTutor is part of emPower Training Solutions ( that has been providing online compliance solutions to 100+ healthcare practices and hospitals since the last 4 years.

To learn more about PracTutor follow us at:

12806 Townepark Way
Louisville, KY 40243-2311

Hardik Parikh, Co-founder and CEO
12806 Townepark Way,
Louisville, KY 40243-2311
Direct (502) 400-9374
Twitter: @hardikvparikh

All press related inquiries to

Tags: , , , , , , ,

View the original article here

Medical Transcription and Coding demand will increase with ICD-10

Medical Coder and TranscriptionistThe world of medical transcription and medical coding is extensive and always changing. The change that has the medical field buzzing right now is the change from ICD-9 to ICD-10 (International Classification of Diseases – Version 10). Currently, health care facilities use ICD-9 for documentation and coding, but by October of 2014 every facility must abide by the new system. These new changes will increase the need for skilled medical transcription and medical coding. It will also bring these two jobs expertise closer and merge at some time in the future.

Why will demand for transcription and coding increase?

For healthcare employees already working as a medical transcriptionist or medical coder, they don’t need to worry about these changes affecting their chances of employment. The truth is that the need for these highly skilled workers will actually increase with the implementation of ICD-10.

One of the main reasons for the increase of work is that the new book of codes is a lot more specific than ICD-9. For instance, in ICD-9, the code for a burn on the left arm is the same code as a burn on the right arm. While this may not matter to the insurance company, it does matter to the treating physician, the patient and the transcription. There are not numerous new diseases in the new manual, but it will have over 70,000 codes listed. These are also going to be seven digits, instead of the five seen in the past. The increase in codes and length of codes will help the medical coder be more specific.

There is no substitute for an intelligent human mind, so the fear that medical transcription will be obsolete after the new implementation is unfounded. Both transcriptionist and coders will actually have to work harder and attend more training to become compliant. The new system may be confusing and overwhelming to those who have worked on ICD-9 for years. As these older employees leave the workforce, fresh new recruits will be needed.

Importance of Implementing Electronic Health Records (EHRs) from ICD-10 prospective

In order to be compliant with the new rules, healthcare facilities will find that having an efficient EHR (electronic health record) system in place first will be a huge benefit. There are still thousands of private practices that have not made the switch to electronic medical records, but this will hurt them when they must face compliance with the new coding regulations.

By implementing an easy to use and efficient EHR, the transition to ICD-10 will be a lot smoother. If a facility does not yet use computers for their records, they should consider doing this as soon as possible to be ready for the upcoming coding and documentation changes.

The reason an EHR is so important is because it helps streamline the coding process. It is much easier to use a search function on a computer than trying to pore through hundreds of pages in a patient’s chart to find information. To determine whether an injury was on the left or right side of the body, for example, the coder can simply search for this terminology within the patient’s electronic record. To find this information in a paper chart wastes hours of valuable time.

How will the New System Help Medical Transcription?

It may be true that the new system will mean less hours of transcribing work but it doesn’t appear transcription will be absolute. In fact, those that choose to stay in the field and learn ICD-10 coding will be rewarded with more hours than ever of transcribing work.

Because ICD-10 demands greater detail, physicians will have to begin giving greater detail in their records. This translates into more words for the transcription, which equals greater pay. Also, the increased need for transcription with coding expertise will mean better rewarding opportunities.

Tags: EHR, Electronic Health Record, ICD-10, ICD-10 Coding, ICD-9, medical billing, medical coding, Medical Documentation, Medical Transcription Service

View the original article here