HL7 Singapore – Workshop on National IT / International Data Exchange

Dear all,

HL7 Singapore is pleased to announce an upcoming workshop on National IT / International Data Exchange.

When: 15 Apr 2013
Where: MOHH, 1 Maritime Square, Level 11, HarbourFront Centre Singapore 099253 (Lobby C)

2:00pm – Registration
2:30pm – Welcome by Dr. Adam CHEE, Chair, HL7 Singapore
2:35pm – Workshop on National IT / international data exchange by Dr. Henrique MARTINS, Coordinator of the Commission for Health Informatics, Portuguese Government and Coordinator of epSOS project, Portugal
4:00pm – Break
4:30pm – Sharing session by A/Prof LOW Cheng Ooi, Chief Medical Informatics Officer, MOH Singapore

Further Details: http://www.hl7.org.sg/index.php/updates/events/189-workshop-on-national-it-international-data-exchange.html

Dr. Adam CHEE
Chair, HL7 Singapore

Inaugural CDISC Asia-Pacific Interchange

I attended day 1 of the CDISC Asia-Pacific Interchange yesterday (thanks to Bron Kisler for inviting me) and I thought I will share my experience here.

While I am not as deeply involved with CDISC (in comparison to HL7, DICOM or IHE), I did performed a fair amount of research on the standard about three  years ago, during a project pertaining to  preclinical trials.

During that period of time, I tried to find out more on how one can effectively bridge the data between EMR/EHR and CDM solutions (for translational research and analytic purposes). The result wasn’t very encouraging as;

  • I could not locate any information pertaining to the topic on  the Internet
  • The local Clinical Research industry had no idea what goes on in the world of Health Informatics (I ended up delivering mini-lectures on health informatics to those fine folks)
  • The local Healthcare Informatics industry mostly had no idea what CDISC was, nor were they remotely interested in it

So imagine the pleasant surprise I had when I noticed a track in the CDISC Asia-Pacific Interchange, discussing “Clinical Research and Hospital Information Systems / EHRs”.

I would also like to share a particular conversation that took place. An overseas attendee recognised me (remember, this is not a health informatics conference, hence I was a ‘unfamiliar face’ to many people) and queried why I attended this particular conference.

My reply, which I would also like to share with you folks, is that Clinical Research is one area where there are no (or at best – minimum) baggage for implementing standards, if there is one remote field left in the world of healthcare Informatics to do the ‘right thing’ the first time round, then Clinical Research may be the answer.

So if you want to make a difference, then consider working on CDISC.

Rethinking health IT standards

Seems to be that there are others out there sharing the same sentiments.

Consumers have come to expect the conveniences that come with digital transactions. From checking clothing prices at multiple stores to keeping your bank account in your hand, the Internet in tandem with mobile devices has revolutionized the speed and ease of vast swaths of economic activity.

But when it comes to healthcare, patients and providers continue to struggle with new technologies designed to bring these same conveniences to the examining room.

The Healthcare Information and Management Systems Society has defined interoperability as “the ability of different information technology systems and software applications to communicate, exchange data accurately, effectively and consistently, and use the data that has been exchanged.”

Put simply, an interoperable electronic health-record system would allow healthcare providers—whether it is your primary-care physician in your hometown or emergency room doctors in a different state—to easily access your medical records to effectively and efficiently treat you. This means any doctor in the country could know when you had your last flu shot, what medicine allergies you might have, your blood type, and other important information used in treatment.

But we’re not quite there yet.

In 2005, the RAND Corp., a not-for-profit institution that provides research on various public policy topics, published an analysis estimating that EHR adoption has the potential to save $81 billion a year provided the technology is interoperable. And in recent years, government agencies have been working with medical providers to begin implementing health information technologies—even offering incentives for the program through federal stimulus funds.

When RAND recently released a follow-up study, analysts found their original cost-savings estimates have not come to fruition, and many in the IT, provider and political communities have declared IT’s potential a failure. While it may be true that we have not yet seen the cost savings we expected, that does not mean the efforts have been in vain. With minor changes in the course of federal policy, health IT holds vast potential to wring tens of billions in inefficiencies out of our bloated healthcare system.

The U.S. spends almost $3 trillion a year on healthcare—a rate that is steadily increasing by about 3% each year. In 2013, healthcare will consume 24% of the federal budget—the highest percentage of any budgetary item. Even if EHRs had resulted in all the potential savings RAND had first projected, rising costs on other fronts would have simply mitigated the increase in health costs.

Dr. Art Kellermann, the RAND study’s senior author, stated, “The failure of health information technology to quickly deliver on its promise is not caused by its lack of potential, but rather because of the shortcomings in the design of the IT systems that are currently in place.”

For every study finding that health technologies are not reducing costs, there are dozens more accounting for lower costs and better outcomes. I would take Dr. Kellermann’s statement a step further and argue that the design of the IT systems are not the problem; it is the standards in the federal incentive program that have failed to meet RAND’s caveat: We are not close to a truly interoperable IT infrastructure.

So while some are citing the RAND study to adopt a “the sky is falling” mentality to health IT, the dialogue should instead shift to better aligning standards with cost savings.

What we know from the recent RAND analysis is what we knew from the original research: Without an interconnected, interoperable infrastructure, realized savings will not materialize. Put another way, we know that the lack of interoperability is a key factor in limiting the effectiveness of EHRs.

So rather than focus on arguments that computers and information management systems won’t work in healthcare, we should shift our collective attention to rebooting the interoperability framework to begin realizing cost restraint as quickly as possible.

When it comes to adopting and implementing health information technology systems, we have made great progress in recent years. Now that we have laid the adoption groundwork, we must rethink our strategy related to standards.

Bottom line: Fix the standards, realize the savings.

Hidden system makes it easier for elderly people to live at home

Some interesting updates from Germany on Assistive Technology care for elderly. This solution is named ‘Wonderwalls“.

Most senior citizens would prefer to live in their own homes for as long as possible. But memory loss and restricted mobility can lead to problems. Items like glasses or the phonebook disappear into thin air, or seniors can find themselves on the wrong side of a locked door after a trip to the shops. Many seniors end up unwilling to set foot outside the door, wary of their ability to get around or simply worried about the weather.

To alleviate these problems, researchers from Technische Universität Mßnchen (TUM) and partners from the business world have designed a wall panel to assist the elderly in their own homes. A tablet computer is mounted in the wall and this provides a one-stop-shop for all the information they need. The weather forecast, bus timetables, family phone numbers and more can be accessed with a few simple taps on the screen.

Indoor positioning system can locate reading glasses

The prototype was designed for an entrance hall area and looks like a wardrobe. But this is no ordinary wardrobe. Thanks to its smart technology, it can issue a warning if the apartment’s occupant has not taken the front door key from the keyholder when they open the front door. The wall can keep track of other items that are often mislaid, too. It controls an “indoor positioning system” that can locate a pair of glasses, for example.

If the occupant is not feeling well, biosensors can measure key vital signs like blood pressure and blood sugar level. The system can then issue recommendations − from a spot of exercise to a dose of medication. If the smart wall detects a critical health problem, it will contact a physician or a mobile nursing service. These healthcare professionals could also connect to the terminal to regularly check the elderly person’s health status. The terminal could also be linked to shopping or transport service providers.

The wall unit would also handle building automation functions. An integrated air conditioning unit would keep fresh air circulating if the occupant forgets to air the apartment.

Robot brings shopping basket to the kitchen

The researchers’ long-term aim is to design similar wall panels for every room. In the kitchen, the smart wall could monitor the stovetop or make meal preparation easier with height-adjustable cupboards. A small assistant in the form of a mobile robot could move between the hallway and the other rooms. It would be able to carry a shopping basket and bring it to the kitchen on command, for example.

The scientists have been careful to promote independence: “We want people to retain as much of their independence as possible,” affirms Prof. Thomas Bock of the TUM Chair of Building Construction and Robotics. “The assistance should only kick in when people are no longer capable of doing something themselves.” For that reason, the walls will have a modular design, with new functions added as and when required.

The assembly includes more than just high-tech features. The researchers remembered to add the usual hall fittings. Along with standard coat hooks, there is also a practical shoehorn at floor level

IBM Designs Gel To Blow Up Hospital Superbugs

All I can say is ‘wicked’ in a good way!
(And the research is done in collaboration with he Institute of Bioengineering and Nanotechnology in Singapore).

IBM has applied computing technology to the medical field to create a gel that could obliterate hospital superbugs.

Researchers at the firm have taken the semiconductor material that allows the quick transfer of computer messages and used it to explode the bacteria.

The aim is to replace antibiotics, which have been overprescribed, leading to an increasing resistance of hospital-acquired infections to treatment.

Antibiotics cannot penetrate the bacteria in a way that the anti-microbial gel can, and its development has significant implications for the eradication of hospital superbugs.

Although development of the gel is at an early stage, it is envisaged it could be used to coat medical equipment to prevent infection.

It could also be used in drugs or injected directly into wound sites to clear the infection.

The gel can be used to coat medical tools or in drugs to treat patients
Nearly 43,000 people contracted a hospital infection in the UK in a year, figures released last year show, and the NHS has had to pay out ÂŁ20m in compensation to patients in the past three years.

James Hedrick, from IBM Research, said the gel had “immense potential”.

“This new technology is appearing at a crucial time as traditional chemical and biological techniques for dealing with drug-resistant bacteria and infectious diseases are increasingly problematic,” he said.

Nano-technology is an expanding field of research and is becoming increasingly important in the medical field.

IBM started its nano-medicine polymer program in its research labs four years ago.

It worked with the Institute of Bioengineering and Nanotechnology in Singapore on the gel.

According to a recent Health Protection Agency report, some 6% of patients acquire an infection of hospital during their stay.

Can computers save health care? IU research shows lower costs, better outcomes

Recent research from Indiana University indicates that machine learning can drastically improve both the cost and quality of health care in the United States.

New research from Indiana University has found that machine learning — the same computer science discipline that helped create voice recognition systems, self-driving cars and credit card fraud detection systems — can drastically improve both the cost and quality of health care in the United States.

Using an artificial intelligence framework combining Markov Decision Processes and Dynamic Decision Networks, IU School of Informatics and Computing researchers Casey Bennett and Kris Hauser show how simulation modeling that understands and predicts the outcomes of treatment could reduce health care costs by over 50 percent while also improving patient outcomes by nearly 50 percent.

The work by Hauser, an assistant professor of computer science, and Ph.D. student Bennett improves upon their earlier work that showed how machine learning could determine the best treatment at a single point in time for an individual patient.

By using a new framework that employs sequential decision-making, the previous single-decision research can be expanded into models that simulate numerous alternative treatment paths out into the future; maintain beliefs about patient health status over time even when measurements are unavailable or uncertain; and continually plan/re-plan as new information becomes available. In other words, it can “think like a doctor.”

“The Markov Decision Processes and Dynamic Decision Networks enable the system to deliberate about the future, considering all the different possible sequences of actions and effects in advance, even in cases where we are unsure of the effects,” Bennett said.

Moreover, the approach is non-disease-specific — it could work for any diagnosis or disorder, simply by plugging in the relevant information.

The new work addresses three vexing issues related to health care in the U.S.: rising costs expected to reach 30 percent of the gross domestic product by 2050; a quality of care where patients receive correct diagnosis and treatment less than half the time on a first visit; and a lag time of 13 to 17 years between research and practice in clinical care.

“We’re using modern computational approaches to learn from clinical data and develop complex plans through the simulation of numerous, alternative sequential decision paths,” Bennett said. “The framework here easily out-performs the current treatment-as-usual, case-rate/fee-for-service models of health care.”

Bennett is also a data architect and research fellow with Centerstone Research Institute, the research arm of Centerstone, the nation’s largest not-for-profit provider of community-based behavioral health care. The two researchers had access to clinical data, demographics and other information on over 6,700 patients who had major clinical depression diagnoses, of which about 65 to 70 percent had co-occurring chronic physical disorders like diabetes, hypertension and cardiovascular disease.

Using 500 randomly selected patients from that group for simulations, the two compared actual doctor performance and patient outcomes against sequential decision-making models, all using real patient data. They found great disparity in the cost per unit of outcome change when the artificial intelligence model’s cost of $189 was compared to the treatment-as-usual cost of $497.

“This was at the same time that the AI approach obtained a 30 to 35 percent increase in patient outcomes,” Bennett said. “And we determined that tweaking certain model parameters could enhance the outcome advantage to about 50 percent more improvement at about half the cost.”

While most medical decisions are based on case-by-case, experience-based approaches, there is a growing body of evidence that complex treatment decisions might best be handled through modeling rather than intuition alone.

“Modeling lets us see more possibilities out to a further point, which is something that is hard for a doctor to do,” Hauser said. “They just don’t have all of that information available to them.”

Using the growing availability of electronic health records, health information exchanges, large public biomedical databases and machine learning algorithms, the researchers believe the approach could serve as the basis for personalized treatment through integration of diverse, large-scale data passed along to clinicians at the time of decision-making for each patient. Centerstone alone, Bennett noted, has access to health information on over 1 million patients each year.

“Even with the development of new AI techniques that can approximate or even surpass human decision-making performance, we believe that the most effective long-term path could be combining artificial intelligence with human clinicians,” Bennett said. “Let humans do what they do well, and let machines do what they do well. In the end, we may maximize the potential of both.”

“Artificial Intelligence Framework for Simulating Clinical Decision-Making: A Markov Decision Process Approach” was published recently in Artificial Intelligence in Medicine. The research was funded by the Ayers Foundation, the Joe C. Davis Foundation and Indiana University.

Ramblings: I have one of the top 1% most viewed LinkedIn Profiles for 2012

Today is the third  day of the lunar new year and I received a rather  interesting email from ‘Deep Nishar, Senior Vice President, Products & User Experience’ of LinkedIn, informing me that;

Dr. Adam, congratulations!

You have one of the top 1% most viewed LinkedIn profiles for 2012.

LinkedIn now has 200 million members. Thanks for
playing a unique part in our community!

Hmm, 1% of 200 million translates to 2,000,000 profiles so that’s a lot   of profiles out there (1,999,999 others to be exact) that also falls within the top 1%. (the bane of being a Mensan…. I dissected the fluff immediately, should have basked  in the ‘glory’ first.)

Having said that, being informed that I have have one of the top 1% most viewed LinkedIn profiles for 2012 (out of 200 million) is kind of cool.


Update: I added the screenshot of the email as to help better visualise the blog post.


The Optimist’s Timeline (mHealth)

The following article is a rather interesting one, primarily because Bill Gates authored it.

Usually, “optimism” and “realism” are used to describe two different outlooks on life. But I believe that a realistic appraisal of the human condition compels an optimistic worldview. I am particularly optimistic about the potential for technological innovation to improve the lives of the poorest people in the world. That is why I do the work that I do.

Even so, there is one area of technology and global development where reality has tempered my optimism: the idea that cellphones would revolutionize life in developing countries. A decade ago, many people believed that the proliferation of mobile devices in Africa would mean a short leap to digital empowerment. It didn’t. Digital empowerment is a long and ongoing process, and the mere existence of cellular technology does not immediately change how poor people meet their basic needs.

But now, after years of investments, digital empowerment is underway, owing to a confluence of factors, including growing network coverage, more capable devices, and an expanding catalogue of applications. As more people obtain access to better and cheaper digital technology, an inflection point is eventually reached, at which the benefits of providing digitally services like banking and health care clearly outweigh the costs. Companies are then willing to make the investments required to build new systems, and customers are able to accept the transition costs of adopting new behaviors.

Consider the example of M-Pesa, Kenya’s mobile-banking service that allows people to send money via their cellphones. M-Pesa first needed to invest in many brick-and-mortar stores where subscribers could convert the cash they earn into digital money (and back into cash). This real-world infrastructure will be necessary until economies become completely cashless, which will take decades.

Without omnipresent cash points, M-Pesa would be no more convenient than traditional ways of moving money around. At the same time, it was impossible to persuade retail stores to sign on as cash points unless there were enough M-Pesa subscribers to make it profitable for them.

This kind of bootstrapping is exactly what we had to do at Microsoft in the early years of the personal computer. No one wanted a machine unless there was software, and no one would create software unless there were machines. Microsoft convinced both hardware and software companies to bet on future volume by showing how our platform would change the rules.

There have been many successful small-scale pilot programs using cellphones. But examples of large-scale, self-sustaining programs powered by digital technology, like M-Pesa, are harder to find, because the key pieces have not been put into place to enable the required work to advance beyond the limits of controlled experiments.

Digitally-enabled health care, or mHealth, is one area that has been slow to emerge, because it is difficult to build a great platform and then convince everybody in a health system that it is worth using. If some health workers use cellphones to send information to a central database, but others do not see the value, the digital system is incomplete – and thus just as flawed as the current paper system.

The most promising mHealth project that I have seen, called Motech, focuses on maternal and child health in Ghana. Community health workers with phones visit villages and submit digital forms with vital information about newly pregnant women. The system then sends health messages to the expectant mothers, such as weekly reminders about good pre-natal care. The system also sends data to the health ministry, giving policymakers an accurate and detailed picture of health conditions in the country.

Those working on AIDS, tuberculosis, malaria, family planning, nutrition, and other global health issues can use the same platform, so that all parts of a country’s health system are sharing information and responding appropriately in real-time. This is the dream, but it works only if frontline workers are inputting data, health ministries are acting on it, and patients are using the information that they receive on their phones.

I realized that things were taking off when our partners on Motech started talking about burdensome network costs and simplifying the user interface. The application was really being used in the field, and the stickiest challenges were presenting themselves – which meant that the system had proved that it was valuable enough for people to put in the work to solve problems as they arose, instead of just reverting to the old system. This digital approach is now being extended to other regions, including Northern India.

A decade ago, people said that this would happen quickly. It didn’t, because the pieces just were not there. Now they are starting to come into place. It will take a decade to get certain applications into a lot of places, but the momentum will build and we will learn as we go. In the long run, the results will be just as transformative as we hoped, if not more so. Ultimately, when people are truly empowered, they will begin to use digital technology to innovate on their own behalf, building solutions that the established software-development community never considered.

Samsung Medical Center, South Korea

I recently made an extended trip (about 10 days) to South Korea, for a ‘working-holiday’.

The last time I made an extended trip to South Korea, I authored the whitepaper – Medical Tourism in Korea, Enhancing your outlook in life, this time, I will share with you folks, my experience visiting Samsung Medical Center in Seoul, South Korea.

My visit to Samsung Medical Center was not part of work, instead, I was kindly hosted by Dr. Yi, Chair of HL7 Korea.

I must start off by highlighting that Samsung Medical Center is a full fledge multi-speciality hospital with 2000 beds and it exhibits a beautiful, modern design.

In addition to a facility tour, I was also able to obtain some key insights to the hospital’s eHealth adoption as well as some national initiatives and perspectives (which is fantastic).

In all, it was a wonderful visit to Samsung Medical Center and to South Korea in general 🙂