Tuesday, December 28, 2010

HTML5, WebGL and Google Body Browser

Google has recently demoed an interesting WebGL application called Body Browser, which lets you explore the human body just like you can explore the world in Google Earth. Now you can try Google Body Browser before it's added to Google Labs, assuming that you have a WebGL-enabled browser:

* WebGL is available, but not enabled by default in Chrome 8 (the latest stable version).

* WebGL is enabled by default in Chrome 9 Beta, Chrome 9 Dev Channel, Chrome Canary Build and Firefox 4 beta.

Google Body is a detailed 3D model of the human body. You can peel back anatomical layers, zoom in, and click to identify anatomy, or search for muscles, organs, bones and more. You can also share the exact scene you are viewing by copying and pasting the URL.

The application doesn't require a plugin. Unlike many other web-based medical applications, no Flash, Java, or other plugins are needed. This application will run on any WebGL-supported browser.

WebGL is based on OpenGL ES 2.0 and provides a programmatic interface for 3D graphics. It uses the HTML5 canvas element and is accessed using Document Object Model interfaces. Automatic memory management is provided as part of the JavaScript language. HTML5 was discussed in some of my earlier posts.

Click here for Getting a WebGL Implementation

here for An Introduction to HTML5

Comment: Years ago, matrices (and tensors) were taught only to graduate students. After some time, these subject(s) were taught to undergraduates too. Today, even a few elite secondary schools teach these subject(s). Similarly, anatomy references were once available only to medical students at institutions like the Harvard and Johns Hopkins Medical Schools. Today, anyone with a high-speed internet connection can access such an application.

For a 1-minute video on Google Body Browser, click here.

For a 7-minute video on Google Body Browser, click here.

Friday, November 12, 2010

Strategies for Closed-loop Radiology Workflow with Speech-Driven Documentation and Communication

Commercially-available Clinical Radiology Support

Nationally, it is estimated that 20 to 30 percent of currently performed High Tech Diagnostic Imaging (HTDI) exams are medically unnecessary or inappropriate.

This is due, in part, because many HTDI exams are currently scheduled without the benefit of a standardized, evidence-based, decision support tool.

After a yearlong pilot program, in which more than 2,300 physicians from five Minnesota medical groups, five health plans, and the Minnesota Department of Human Services used e-Ordering (defined later) to order high-tech diagnostic imaging exams, it was found that the exams ordered with evidence-based decision-support technology had an increase in medical appropriateness versus orders initiated without it. The pilot also showed that using decision-support appropriateness criteria (defined later) in the physician’s office reduced patient exposure to unnecessary radiation, and contributed to a 0 percent increase in HTDI scans ordered in 2007 (following an 8 percent increase in Minnesota in 2006). N.B. During the time of the pilot, an estimated $28 million in healthcare cost savings was reported.

Going forward, Nuance’s RadPort, an electronic, evidence-based, decision-support (e-Ordering) solution is going to be used to support a statewide initiative to help ensure Minnesotans only receive medically appropriate high-tech (MRI, CT, PET and nuclear cardiology) diagnostic imaging (HTDI) tests.

Derived from the American College of Radiology (ACR) Appropriateness Criteria, and designed in conjunction with Massachusetts General Hospital, RadPort’s scoring methodology is continuously reviewed and updated by a panel of clinical and radiology experts.

RadPort combines the clinical information provided by the referring physician at the time of ordering with patient demographics to produce a “utility score” for the examination requested.

Click here for a discussion of appropriateness criteria and utility scores.

A high score indicates that the information provided strongly supports the use of the requested imaging test. A low score indicates that the request may not be appropriate. As a result, RadPort displays alternate procedure choices with corresponding utility scores of other relevant and appropriate exams.

In the event of a low score, RadPort provides clinical reference material designed to educate the referring physician so as to ensure appropriate ordering in the future.

Nuance Healthcare manages radiology as a single, end-to-end or closed-loop process. This approach gives radiologists and administrators a continuous view of the order from diagnosis through results process, which allows for analysis that can drive improvements at each stage.

The benefits of closed-loop radiology are evident: saving time, money, and resources, improving patient safety and care, and better clinical documentation.

Click here for an overview.

Click here for info on RadCube, a comprehensive, yet flexible, data warehouse for multi-dimensional business analysis and visualization tool. RadCube is another key application in the Nuance portfolio of imaging documentation and communication software.

RadCube merges OLAP and web architecture. This radiology-centric solution allows its users to perform highly complex clinical and detailed business analysis on your data in mere seconds using a simple drop-and-drag interface. By integrating advanced On-Line Analytical Processing (OLAP) techniques and Natural Language Processing (NLP) with one's unique institutional data, RadCube provides ways to visualize, analyze and optimize healthcare delivery to each patient. With RadCube, you can explore information from various business, clinical and research perspectives or identify trends, opportunities and potential issues quickly with familiar visualization techniques. You can analyze all operational aspects of your business including: Business Productivity, Quality Assurance, Utilization Management, Throughput Analysis, Communication Management, Evidence-Based Radiology, Advanced Data Mining Techniques, Trending and Forecasting, and Benchmarking.

{ click on image to see larger view }

Click here for info on applying “Six Sigma” principles to the radiology process.

Click here for an early article of mine on “Six Sigma”

A link to this article is also available near the top of "My [partial] bibliography" at the bottom of this blog.

Finally, click here for a brief introduction to i2b2, an open-source calable informatics framework that enables clinical researchers to use existing clinical data for discovery research and, when combined with IRB-approved genomic data, facilitate the design of targeted therapies for individual patients with diseases having genetic origins.

Tuesday, October 26, 2010

HTML5 and Adobe Redux

With the rise of HTML5, Adobe's Flash has been positioned as the antagonist of the open standard. Increasingly, HTML5 is used to serve online videos though the matter is far from resolved.

Adobe has just released an embeddable video player that plays HTML5 native video in browsers that support it, and falls back to Flash in browsers that don't. It's cross-browser and cross-platform, so it works on iPhones, iPads and other devices that don't support Flash. Using Adobe's new player, these devices can show videos in web pages without the Flash plug-in. The shift takes place regardless of the screen -- from phone to monitor to TV.

This means that Adobe wasn't kidding when they said they were riding the HTML5 bandwagon as hard as anybody right now.

The HTML5 Video Player widget, now available through the Adobe Widget Browser, works with or without Dreamweaver CS5. Code generated from the widget plays video in the best possible player for the requested platform using a range of video codecs. Based on the Kaltura open source library, the HTML5 Video Player widget is fully cross-browser compatible with support for Internet Explorer, Firefox, Safari, Chrome, and Opera. Moreover, the player is completely customizable with industry standard CSS techniques.

You can run the Adobe Widget Browser directly from within Dreamweaver and, once you’ve set it up, insert the generated code and files for the HTML5 Video Player widget with point-and-click simplicity. But if you’re not a Dreamweaver user, you can also download the Widget Browser independently. (You’ll need to install Adobe AIR first.)

Click here for links to several new tutorials on HTML5.

Click here for my post on the Dreamweaver CS5 HTML5 Pack

Monday, October 11, 2010

HTML5 And Risks To Privacy On The Front Page Of The Non-Techinal Press

I have a couple of posts on HTML5 below. Nonetheless, I was a little surprised to see this topic (in the context of "risks to privacy") discussed on the front page of this morning's edition of the New York Times (and elsewhere):

From this morning’s front page:

Most Web users are familiar with so-called cookies, which make it possible, for example, to log on to Web sites without having to retype user names and passwords, or to keep track of items placed in virtual shopping carts before they are bought.

The new Web language (HTML5) and its additional features present more tracking opportunities because the technology uses a process in which large amounts of data can be collected and stored on the user’s hard drive while online. Because of that process, advertisers and others could, experts say, see weeks or even months of personal data. That could include a user’s location, time zone, photographs, text from blogs, shopping cart contents, e-mails and a history of the Web pages visited.

Click here for more.

Thursday, October 7, 2010

Cost/Benefit and ROI aspects of Health Information Technology (HIT)

Whether or not EHR and other HIT systems benefits exceed costs is a question being discussed in many quarters today. A 2006 report { click here } based on research conducted by the Southern California Evidence-based Practice Center provides what I consider a good framework for a priori and a posteriori examination of the cost/benefit and ROI aspects of this question.

Despite the heterogeneity in the analytic methods used, all cost-benefit analyses predicted substantial savings from EHR (and health care information exchange and interoperability) implementation: The quantifiable benefits are projected to outweigh the investment costs. However, the predicted time needed to break even varied from three to as many as 13 years.

Many of the studies concerned HIT systems developed and evaluated by academic and institutional leaders in HIT.

  • Regenstrief Institute in Indianapolis, IN
  • Partners/Brigham and Women’s Hospital in Boston, MA
  • Intermountain Health in Salt Lake City, UT
  • Kaiser Permanente health care system
  • Vanderbilt University in Nashville, TN
  • U.S. Department of Veterans Affairs (VA) health care
As asserted above, you need to ask when a particular system will reach the break even point. You also need to examine any potential for a mismatch between who pays for and who accrues cost savings from HIT use. Private organizations deciding whether to invest in HIT must weigh the costs and benefits of doing so. Although the primary goal of nonprofit healthcare organizations may be to provide high-quality care, these organizations still need to watch the bottom line to survive, which includes understanding the costs of measures designed to improve quality. Such private return-on-investment (ROI) calculations can provide results that are quite different from those of societal cost-benefit analysis, which are often reported in clinical journals. For example, one study showed that a hospital that installed a computerized reminder system to alert providers when patients were not up-to-date on their immunizations increased pneumococcal vaccine orders by 8 percent. Another study showed that, among the elderly, each $12 vaccination averts $20.27 in hospital costs and increases life expectancy an average of 1.2 days. From society’s point of view, the reminder system saves money and improves health, so it is a win-win program. However, from a financial perspective, the hospital has spent money on a system that had no effect on the costs or revenues of current stays because the pneumococcal vaccine is not delivered in the hospital. To benefit from this intervention, the hospital must make a reputation for higher quality and convert it into profits. This is one example of the potential for a mismatch between who pays for and who accrues cost savings from HIT use. A more extreme example would be a hospital’s implementation of a HIT intervention that averts future hospitalization. In this case, HIT implementation both costs the hospital money and decreases hospital revenues, even if the HIT implementation has a net cost-savings from a societal (or Medicare) perspective.

For more, click here, here and here.

Thursday, August 12, 2010

HTML5 - its support in Dreamweaver CS5, Internet Explorer 9 and elsewhere - Part II

There's been a lot of discussion lately about whether or not the HTML5 video tag is going to replace Flash Player for video distribution on the Web.

Consensus: While the video tag is a big step forward for open standards, the Adobe Flash Platform will continue to play a critical role in video distribution.

Click here for a discussion of this topic in the YouTube context (a pretty significant one).

HTML5 (and CSS3) are works in progress. While some parts of these specs are finished or stable, other parts are still under development or have no current browser support.

Nonetheless, leading development tools, e.g., Adobe's Dreamweaver, have begun to support these technologies. To wit, specs that are stable or that have some level of browser implementation are now seen in the new Dreamweaver CS5 HTML5 Pack. Select the Product Details tab.

While the official specifications are still not yet complete, they are now supported to varying degrees by a number of different desktop browsers – and more importantly by all smartphones using Webkit-based browsers (e.g. iPhone, Android, Nokia WRT, Blackberry OS). Given the recent surge of interest around HTML5, Dreamweaver CS5’s compatibility with HTML5 and CSS3 was updated so you can begin exploring their potential today.

Tuesday, July 13, 2010

Epocrates Mobile Electronic Health Record

Health care delivery is now moving away from a specific location and into a virtual care space, where patient medical records and real-time clinical data will reside.

There has also been a revolution in access to clinical reference material, and physicians and other care providers are moving core scientific knowledge from books to apps. Today’s doctors are no longer what they can memorize.

Throughout this blog, I've been discussing many of the components of Electronic Health Record (EHR) systems that will likely be used in the larger systems installed throughout entire hospitals and regions. However, 50 percent of physicians in the US work in small or solo practices.

The Epocrates EHR is specifically targeting the solo practitioner and the small physician groups, which have different needs from the larger enterprise care facilities that so many EHR providers are pursuing. To that end, Epocrates says that it has "teamed up with a very well known” but still undisclosed practice manager partner, whose software will be integrated into the Epocrates EHR for calendaring, scheduling, appointments, billing and more.

The as-yet-not-released Epocrates EHR app will include the company's drug and safety content and will, they say, meet “meaningful use” and HIPAA compliance requirements.

There are offerings from other vendors such as Microsoft and Symantec too, but I've decided to look at Epocrates Mobile EHR because Epocrates was the first company to introduce a medical app for the iPhone. Furthermore, as seen in the image below, their app is now available for many of the popular hand-held smart devices.

Their fully functioning mobile EHR app will work both when connected and disconnected. It’s not enough to just have a mobile EHR, of course, and it is also a fully featured, web-enabled desktop application, too.

The mobile and desktop versions may have the same functionalities, but the different form factors will likely lead to certain applications being favored on each.

There is a functional parity between their mobile and web interface. The information will be delivered differently and the iPhone version will be used for some use cases more often than the desktop version and vice versa. These two platforms are complementary, so Epocrates is not necessarily "leading" with mobile.

Unlike some mobile “portals” to EHR systems, Epocrates offering is a native app with patient data stored in it.

One differentiator between the Epocrates mobile EHR app and some others is that theirs will be a native app and it will store patient data on the device. Users will interact with the EHR differently from a mobile device vs. a desktop client. The iPhone interface is not ideal for text entry, so they are looking for other ways to get information into the device. The iPhone interface will be used more for things like dictation, while the desktop interface won’t be used for that as much. From a task perspective, though, they are not looking to hobble the handheld interface in any way.

Click here to see new apps from Epocrates

Click here to see the Dragon speech-to-text application on a hand-held device

Epocrates is launching an EHR offering now because of the increase in EHR adoption because of the ARRA deadlines for stimulus fund incentives payments. These external deadlines are encouraging physicians to adopt EHR, making it an ideal time to enter the market.

There are also drivers from the technology perspective as well. It’s a good time to enter the market with a mobile EHR because more clinics have a high penetration of smartphone users. Also, 3G wireless networks now have higher bandwidth – enough to support these kinds of applications. Physicians rarely take note of [mobile] Internet connectivity issues anymore. Note: I've also talked a little about the less-ubiquitous 4G (WiMax) networks in earlier posts.

Epocrates plans to integrate the features of the iPhone, such as the camera, as well as dictation directly into the app, an interesting feature especially in light of the recent announcement by Nuance that they will be shipping a medical transcription application for the iPhone.

Epocrates will also utilize the iPhone’s Push Notification Service to alert doctors of important or timely information (and hopefully not overuse it). Given Epocrates’ depth of knowledge of pharmaceutical formularies, e-prescribing will be built in.

Although the mobile application will synchronize with the web application, it will continue working even when there is no internet connection. Data will be stored on the handheld device in a secure, encrypted manner and synchronize when a connection is available, a real issue for hospitals where there are many “dead” zones. And, there will be condition-based templates for easy entry of clinical information.

There will also be integration with a revenue-cycle platform so physicians can charge and submit codes, through a partnership with a “known” company. Epocrates anticipates they will achieve Certification Commission for Health Information Technology (CCHIT) certification by the time of release. The EHR will be delivered as a software-as-a-service (SAAS) model, meaning the physician will effectively lease, not purchase it.

This could be an attractive low-cost product for solo or small group physicians who do not have complex office staff EHR integration needs. In particular, for the physician who already uses their smart phone for many work activities, the potentially painless transition to using it as the primary interface into their office EHR may be very appealing.

Stay tuned.

Click here to see Epocrates executives at HIMSS 2010

Click here to see Andy Wiesenethal, Kaiser Permanente at HIMSS 2010

As an aside, I'd like to note that when Epocrates Online can be accessed with a browser on which Google's (or other) translation app has been installed, as shown in the image below.

Friday, June 25, 2010

Contemporary Speech Analysis and Systems - A Palimpsest

Computers are making strides in recognizing speech, as reported in earlier posts to this blog. Beyond that, a host of companies — AT&T, Microsoft, Google and startups — are investing in services that hint at the concept of machines that can act on spoken commands. They go well beyond voice-enabled Internet search.

Click here for a comprehensive review article on all this. My links Spoken Language Systems and Audio, Speech, and Language at the top of the right-hand column are very good sources for up-to-date information on these subjects.

Finally, to see a contemporary system at work, click here for Medical Bayesian Kiosk, a voice-based system designed to ask patients about their symptoms and to respond with empathy. (Microsoft Research)

Tuesday, June 22, 2010

The Promise of Information Technology in Electronic Health Records

This blog is written by and largely viewed by IT professionals, 5,217 visits from 106 countries according to Google Analytics at last count. While the [technical] subject matter herein applies to many fields, its application to electronic heath records (EHR) has been a large part of my focus.

So, to add balance to this blog, I've provided below several links to material written by medical professionals within the healthcare industry who are concerned with these same subjects.

The Promise of Information Technology in Electronic Health Records (EHR)

Information Technology Tools to Support Best Practices in Health Care

Microsoft HealthVault Platform

Electronic Medical Records (EMR) and The Prospect of Real-Time Evidence Development

Executive Summary

Evidence-Based Medicine and the Changing Nature of Healthcare

Tuesday, May 25, 2010

HTML5 - its support in Dreamweaver CS5, Internet Explorer 9 and elsewhere

With HTML5, an open Web standard, the browser becomes a first class RIA citizen.

HTML5 is being developed as the next major revision of HTML (HyperText Markup Language), the core markup language of the World Wide Web. HTML5 is the proposed next standard for HTML 4.01, XHTML 1.0 and DOM Level 2 HTML. It aims to reduce the need for proprietary plug-in-based rich internet application (RIA) technologies such as Adobe Flash and Microsoft Silverlight.

The HTML5 video tag is a markup language tag, introduced in the HTML5 draft specification, that adds support for embedding video in an HTML page.

The Adobe Flash Player has been and continues to be widely used to embed video on web sites such as YouTube, since the majority of web browsers have Adobe's Flash Player installed (with controversial exceptions such as the browser on the Apple iPhone and iPad). Now, however, HTML5 video is intended by its creators to become the new standard way to show video online, but has been hampered by lack of agreement as to which video formats should be supported in the video tag.

Rather than relying on the browser plug-in Flash, Apple has adopted HTML5, CSS and JavaScript – all open standards. Apple’s mobile devices now ship with high performance, low power implementations of these open standards.

Not to be left out, Adobe has recently added HTML5 support to Dreamweaver CS5. This move should not be viewed only in light of the company's war of words with Apple regarding Flash, but in the other reality that HTML5 is reaching critical mass as evidenced by long-time holdout Microsoft adding HTML5 support to Internet Explorer 9 and a slew of HTML5 books being published by leading houses this summer. I've pictured the covers of a few of them at the end of this post.

These developments come despite the fact that HTML5 is still a work in progress. Even so, HTML5 in Dreamweaver CS5 makes for a mighty application development tool, as shown in the video http://www.youtube.com/watch?v=OEXrd8CR5AY

The HTML5 compatibility pack for Dreamweaver CS5 lets you author CSS3 and HTML5 compatible Web pages for modern browsers. And, of course, it supports the audio and video tags.

Note: The HTML5 extension will work only with Dreamweaver CS5 and not with any of the previous versions.

For more on this new Dreamweaver HTML5 support, check out labs.adobe.com and the following videos:

HTML5 Fundamentals with Dreamweaver CS5 - Semantic Structural Tags - Part 1

HTML5 Fundamentals with Dreamweaver CS5 - Semantic Structural Tags - Part 2

Readers of this blog who are interested in the Semantic Web may find the Part 2 video of particular interest.

HTML5 Fundamentals with Dreamweaver CS5 - Using the Video Tag

Finally, Microsoft will support HTML5 and CSS3 in Internet Explorer 9.0. A developer preview of their next browser can be downloaded from


and click here for a discussion of I.E. 9's
support for video content.

Note: There has been a lot of interest and debate about HTML5 and its support for video tags. This release of Internet Explorer provides such support, with tags available for H.264/MPEG4 and MP3/AAC codecs, leaving out support for the open source Ogg Vorbis and Ogg Theora video codecs.

A final note: HTML5 is not likely to displace Adobe Flash videos any time soon. As evidence of this, consider the latest news from Dell: Dell Inc. yesterday unveiled plans for a computer tablet based on Google Inc.’s Android operating system.

Called Streak, the tablet will have a 5-inch screen, Wi-Fi, Bluetooth, and work on a 3G network. Users can download music; interact with social-networking sites; send e-mail, text and instant messages; and make phone calls. It has turn-by-turn navigation with Google Maps, a 5-megapixel camera with flash, and a removable battery.

Streak will have 2 gigabytes of internal storage. Memory can be expanded up to 32 gigabytes allowing it to store as many as 42 movies or 16,000 songs.

Later in the year, the tablet will support Adobe Flash 10.1 — something Apple Inc.’s iPhone, iPad, and iPod Touch devices do not. Flash is widely used for online video.

The Streak is designed to be larger than a smartphone but more portable than a laptop. It is 6 inches wide, nearly 3 inches high, and half an inch thick.

Thursday, May 20, 2010

Tim O'Reilly on State of the Internet Operating System

Click on the image below to watch a talk given by Tim O'Reilly at Web 2.0 Expo San Francisco 2010.

"The fox knows many things, but the hedgehog knows one big thing." -Archilochus

Note: Tim graduated from Harvard College in 1975 with a B.A. in Classics. His honors thesis explored the tension between mysticism and logic in Plato's dialogues.

Saturday, May 15, 2010

Adobe's Extensible Metadata Platform (XMP) as used with DICOM images - Photoshop, MathWorks and Oracle Multimedia

Healthcare-related images (e.g., those that conform to the DICOM standard) can be moved from place-to-place within a local organization over a network and, with help from HL7, moved from place-to-place globally (and interoperably).

DICOM and HL7 are about program to program communication between computers, not a standard file format, and not information retrieval for use by humans.

The DICOM Upper Layer protocol (DUL) is the language used to make connections, compose, send, receive and decode messages.

• DICOM Services are the operations DICOM programs can do, e.g., send, store, look up information.

• DICOM Objects are the data that programs can send and receive, e.g., patient data, CT, MR and other images, radiation beams, anatomic structure contours.

This post will be concerned with the last of these: i.e., DICOM Objects.

These images can be imported into Adobe Photoshop for a great deal of manipulation and, from there, accessed by Mathlab, which has powerful image analysis capabilities, and finally stored and managed (with search and much else) in Oracle Multimedia. Throughout, Adobe's Extensible Metadata Platform (XMP) - a labeling technology that allows you to embed data about a file, known as metadata, into the file itself - plays an important role.

Click here for more information on XMP.

Click here for an example of medical image processing with Photoshop

Click here for an introduction to medical image processing with MathWorks

Click here for an overview of Oracle Multimedia

and here for the first of several in-depth pages on Mutimedia DICOM

The figure below illustrates the architecture of typical DICOM Web application. Shown only as "Third-Party Media Processors" are Adobe Photoshop and MathLab Medical Imaging.

Click here for an example of a Photoshop and Mathlab collaboration before the advent of XMP

and here for how Mathlab can read XMP metadata today.

Click here for info on work with metadata (Dicom, XMP, etc.) in Photoshop

Finally, click here for another introduction to using Photoshop for processing DICOM files.

Friday, May 7, 2010

Speech transcription with Adobe Soundbooth CS5 and Dragon Naturally Speaking 10

Nuance Communications’ voice recognition software – Dragon Naturally Speaking 10 – is the industry-leading speech recognition software. In the healthcare space, the software eliminates physicians’ need to rely on typing, clicking and scrolling, something that a high percent of doctors surveyed cited as a usability concern. Using Dragon Medical 10 gives physicians more time to allocate toward patient care instead of reporting. And, because most doctors speak three times faster than they type, Dragon Medical speech recognition software can improve productivity by up to 25%. For more on this product, see my May 30, 2009 and May 1, 2009 posts below.

Meanwhile, Adobe Soundbooth CS5 is normally used in entirely different environments. For example, you can jump directly into Soundbooth from within other Adobe Creative Suite components to create, clean up, or enhance your audio. The nondestructive ASND file format shares audio files easily with Flash Professional, Adobe Premiere Pro, or After Effects, and the ability to export cue markers as FLV or XML files makes coordinating sound to your project easier than ever. Click here for more on the Soundbooth CS5 application.

Nonetheless, Naturally Speaking and Soundbooth have this in common: both can perform speech-to-text translation and then synchronize the playing audio file and its transcript during deferred playback, thus enabling a third party to correct errors easily. To demonstrate this, I had them both perform a speech-to-text transformation on a single, randomly-selected mp3 file named Checkers.mp3. This audio file and its transcriptions by Naturally Speaking and Soundbooth are downloadable:

Click here for Checkers.mp3

Click here for CheckersDragon.txt

Click here for CheckersSoundbooth.txt

What follows is not a scientific (i.e., statistically rigorous) analysis. It's simply a quick look at how the two products performed at end-to-end transcription during an elementary test. As a matter of fact, I examined only part of a single sentence. Here are the results:

An excerpt from the actual speech (see Dragon.mp3): "- charges are made against you is to -"

An excerpt from the Dragon Medical 10's transcription (see CheckersDragon.txt): "- charges were made against is to -"

An excerpt from the Soundbooth CS5's transcription (see CheckersSoundbooth.txt): "- charges are made against him is to -"

As you can see, Dragon dropped the word "you" entirely and Soundbooth got the word "you" wrong. But, Soundbooth got the verb "are" correct while Dragon did not.

Keeping score is not the point here. The point is that they both (like all speech-to-text engines) make mistakes that have to be corrected. So, they both provide for error correction. I made no effort to optimize either tool. The results outlined above were produced after doing nothing more than installing the two products side-by-side on the same 32-bit PC and loading the same mp3 source into each product. Note: Both products have 64-bit versions but only Soundbooth runs on a Mac.

The figure below shows Sooundbooth CS5 simultaneously playing the audio and highlighting the text -- word-by-word -- as the speech progresses. The play/stop button allows you to stop the progression at any point and to edit the text before continuing. Dragon has similar functionality.

{click on image above for a larger view}

Again, these are not competing products. They each serve different populations. However, there are organizations in which Soundbooth is available and Dragon is not, where a Mac is available and a PC is not, etc. In these cases, one should consider the sometimes much less expensive Soundbooth for the automatic transcribing of audio into text.

Click here for a video that demonstrates turning spoken dialogue into searchable metadata with Soundbooth CS5.

The searching of metadata for a specific word is also shown in the following figure.

{click on image above for a larger view}

I want to conclude by noting that Dragon Medical 10 is the industry-leading speech recognition software in the healthcare space because, for among other reasons, it includes medical vocabularies covering nearly 80 medical specialties and subspecialties, as well as the tools to further customize vocabularies for a specific medical practice, which Soundbooth does not. But, Soundbooth has unique integration with the Adobe suite of applications, which Dragon Naturally Speaking does not. So, in a way, I've been comparing apples with oranges.

Saturday, May 1, 2010

The Lens Correction Filter in Adobe Photoshop CS5

If you take a photograph with a digital camera and load your picture into Photoshop CS5, its lens correction filter can automatically detect the manufacturer, model and lens settings that you had used, using the image file’s EXIF data.

When it doesn't have the additional information needed to correct any changes your camera and settings might introduce, Photoshop CS5 presents a button that lets you search the Web for this information in a trouble-free way. In either case, it automatically corrects lens distortions and fixes chromatic aberration and vignetting.

However, there are other scenarios: In another blog, The North Country Chronicles, I posted the photograph (jpg file) that is shown in the figure below.

This image was created by scanning a century-old picture that had very obvious distortions. Just take a look at the flagpole and the corners of the main building.

So, I spent about 10 seconds to manually straighten the flag pole and corners of the main building by dragging the Vertical Perspective slider in the Lens Correction Filter of Photoshop CS5 a little to the left as shown in the figure below.

{click on image above for a larger view}

and was immediately presented with the compensated – to a visually acceptable level - image shown in the next figure.

This manual intervention was required because no digital photography was available in 1917, when this particular photograph was taken with the Kodak Junior, Model A camera shown below, nor was digital photography used in any of the steps taken in my correcting of this photograph.

Note: The North Country Chronicles post where the original photograph appears is about the early 20th century. So, I chose to leave the original – that is, uncorrected - scanned image there.

The final figure below presents an overview of the flagpole (and other objects) correction process for the case where a digital camera is involved.

While I’m stopping here, I encourage you to watch the following easy-to-understand videos that demonstrate a good deal of additional functionality provided in this extremely handy Photoshop CS5 tool.

Click here for Video 1
Click here for Video 2
Click here for Video 3

Thursday, April 15, 2010

Apple’s SDK brouhaha explained for non-developers

So what’s up with Apple this week? In short, they are now the dominant platform in a space, and they intend to maintain that dominant position for as long as possible by preventing the ability to write an application once and run it anywhere. Apple’s tactics for maintaining their dominance are: bullying and complexity. They’re the same tactics use by every computer platform dominator (e.g., IBM, AT&T, and Microsoft)
before them. All of this has happened before, and it will happen again. Click here for Brent Noorda's take on Apple’s SDK brouhaha.

An update (5/4/2010):

The Federal Trade Commission and the Department of Justice are exploring whether to open an antitrust inquiry into Apple over its recent actions restricting developers writing apps for its iPhone operating system.

The basis for a potential antitrust probe stems from Apple’s recent changes to its iPhone software developer kit. The changes, which were quietly rolled out during the announcement of the company’s new iPhone 4.0 operating system, made it clear that Apple would no longer allow apps into the iTunes iPhone and iPad store that are built using third-party programs.

The sudden changes to Apple’s rules came just days before Adobe was set to showcase its newest software update to its Flash authoring tools. The feature, called Packager for iPhone, would make it easy for developers to produce iPhone applications using Adobe’s software.

Tuesday, April 13, 2010

Decision Makers Are Not Always "Insiders"

Over the past year or so, this blog has bandied about terms like interoperability, open-source, disambiguation, security and databases. All of this has been from the points of view shared by most "insiders" concerned with the introduction of electronic health records (EHR) systems into their local, regional or even national computer networks. I'm talking about individuals (including me) who typically follow other blogs like http://i2b2-zak.blogspot.com and http://geekdoctor.blogspot.com.

However, there are many more individuals who follow (and whose thinking is influenced by) publications like The Wall Street Journal and The New York Times. What they read is reports like "In a paper published last year, Alessandro Acquisti and Ralph Gross (two researchers from Carnegie Mellon University) reported that they could accurately predict the full, nine-digit Social Security numbers for 8.5 percent of the people born in the United States between 1989 and 2003 — nearly five million individuals." that I believe are sometimes more likely to influence their thinking than are the reports that you and I read in the blogs (and other publications) written by "insiders." So, with this last thought in mind, I place the following links to a few recent articles read by many of the decision makers out there.







This is not meant to be a representative sample. Just a reminder that you and I may or may not be speaking the same language as the general public, which counts among its numbers many high-ranking decision makers. So, what else is new?

Sunday, April 4, 2010

How Green Is My iPad? & Who Were The Luddites?

How Green Is My iPad?

Click here for a discussion which ends with the assertion "All in all, the most ecologically virtuous way to read a book starts by walking to your local library."

Who Were The Luddites?

Machine smashers of the 19th century or members of a fascinating social movement with visionary insights into the unfolding drama of industrialization?

The impact of today's technologies on social relations and the planet itself is becoming an intriguing field of inquiry. However so far the discussion of nuclear power, biotechnology, deforestation, automobiles or computers is pretty much dominated by industry and government who want us to take all this for granted.

In this context it is inspiring to remember the Luddites who questioned industrial civilization at its very beginning in England during the introduction of mechanized textile mills. They knew that the power-looms that they selectively destroyed were not just a technology but would create a whole new set of relations: Factory work, child labor, and the demise of artisan and skilled labor. They anticipated that the new machines, that they themselves had helped build, were not the promised tool to help them in their work but would eventually become part of a machine culture with power over human life and even human consciousness.

Click on the links below for a two part talk given by Iain Boal, an independent scholar and historian of technology. He taught a course on the Luddites at Stanford University.

Note: During the introduction, you'll hear the term Time of Useful Consciousness. This is an aeronautical term. It's the time between the onset of oxygen deficiency and the loss of consciousness, the brief moments in which a pilot may save the plane.

Part 1: http://WaldenITech.com/Luddites1.mp3

Part 2: http://WaldenITech.com/Luddites2.mp3

Note: The download of these audio files could take several minutes, depending on the speed of your connection and other resources.

Tuesday, March 23, 2010

Does the Semantic Web need Ontologies?

The answer to the question "Does the Semantic Web need Ontologies?" is "yes" according to most but "no" according to some. For a discussion of this question, click here for the view of one individual who is convinced that ontologies are a luxury, not a necessity, plus the comments of others.

Wednesday, February 24, 2010

Business Process Management and Service Oriented Architecture

Business Process Management (BPM) is used to model, simulate, automate, manage, and monitor processes, in order to coordinate operations with dynamic business priorities.

With BPM, workflows (both human and automated) are determined in real-time by events and/or outcomes within the process, and effective knowledge transfer is made possible as processes become well-documented business artifacts on which staff members can be trained.

To enjoy the full benefits of BPM, processes must integrate with existing applications and systems (e.g., hospital EHR and EMR, to name a couple of areas currently being funded by the Obama administration in the U.S.). This is where Service Oriented Architecture (SOA) - the subject of earlier posts - comes in. BPM and SOA are a natural match. There are links to a few of my early articles on SOA, in the bibliography at the bottom of this blog.

In preparation for my next post to this blog, I'd like to cite the following book:

This book shows the reader how to fill the semantic gap between the process model and the applications:

Modeling business processes for SOA and developing end-to-end IT support has become one of the top IT priorities. The SOA approach is based on services and on processes. Processes are focused on composition of services and in that sense services become process activities.

Experience has shown that the implementation and optimization of processes are the most important factors in the success of SOA projects. SOA is so valuable to businesses because it enables process optimization. In order to optimize processes, we need to know which processes are relevant and we have to understand them – something that cannot be done without business process modeling. There is a major problem with this approach – a semantic gap between the process model and the applications.

This book will show you how to fill this gap. It describes a pragmatic approach to business process modeling using the Business Process Modeling Notation (BPMN) and the automatic mapping of BPMN to the Business Process Execution Language (BPEL), which is the de-facto standard for executing business processes in SOA. The book will also cover related technologies like Business Rules Management and Business Activity Monitoring which play a pivotal role in achieving closed loop Business Process Management.

From http://www.packtpub.com/business-process-driven-SOA-using-BPMN-and-BPEL/book

Wednesday, February 10, 2010

Interoperability Between Oracle and Microsoft Technologies, Using RESTful Web Services - BPEL

A guide to developing REST Web services using the Jersey framework and Oracle JDeveloper 11g follows.

RESTful Web services are the latest revolution in the development of Web applications and distributed programming for integrating a great number of enterprise applications running on different platforms. Representational state transfer (REST) is the architectural principle for defining and addressing Web resources without using the heavy SOAP stack of protocols (WS-* stack). From the REST perspective, every Web application is a service; thus it's very easy to develop Web services with basic Web technologies such as HTTP, the URI naming standard, and XML and JSON parsers.

For a detailed account of how to create RESTful Web services by using Oracle technologies such as Oracle JDeveloper 11g, the Jersey framework (the reference implementation of the JAX-RS [JSR 311] specification), and Oracle WebLogic Server as well as how to consume the Web service by using Microsoft technologies such as Visual Studio .NET 2008 and the .NET 3.5 framework, click here.

Building a Web Services Network with BPEL - Caveat Emptor

Buoyed by maturing Web service standards, more and more organizations are using Web services in a collaborative environment. BPEL is fast becoming the platform for orchestrating these Web services for inter-enterprise collaboration. As discussed in earlier posts in this blog, BPEL offers the compelling benefits of a standards-based approach and loosely-coupled process integration to companies building an online marketplace or collaborative network.

Yet the exciting new capabilities offered by Web services carry some risk. In many cases, partner relationships break down or integration costs skyrocket if certain technical and administrative challenges are not addressed at design time:

* Partners must agree well in advance to conduct business according to specific criteria. Transport protocol, purpose of the interaction, message format, and business constraints have to be communicated clearly.

* Joining the network has to be an easy process; collaborative networks become successful mainly through growth.

* Users must easily find business services at runtime, or the promise of services-oriented architecture (SOA) is largely lost. (Service repositories are useful for this purpose.) If developers cannot readily find and reuse services, the services essentially don't exist.

* Partners should have the ability to monitor Web services in real-time. End users should be able to track the progress of a specific order, and trading partners diagnose a specific bottleneck within a business process.

These challenges are exacerbated when a collaborative network operates in a hosted environment. In that model, partners expose the functionality provided by their legacy applications into a Web service. This Web service is published into a centralized repository. The host is responsible for orchestrating the complex business processes, which in turn, leverage partner Web services.

Monday, February 1, 2010

Front-end Web Application for use in the Human Workflow used to Disambiguate IDs in an Electronic Healthcare Record (or other) Automated System

From December 14, 2009 post

Disambiguation is a process through which multiple potential identification matches are further parsed until the patient can be matched with his or her data with sufficient certainty to allow for the delivery of a health service with reasonable confidence. The complexity of disambiguation varies according to factors such as the number of potential matches and the type of information available for further analyses. When sufficient digital data are not available to further differentiate potential matches, automated disambiguation may not be possible and may require human involvement.

Disambiguation entails implementing significant new workflows and may require substantial time and resources. When human involvement is required, many of the potential benefits of automation are lost. For example, at the point of care, disambiguation is often done by asking the patient further questions regarding personal characteristics and/or health care history. In some situation, disambiguation may not be possible, as when the patient is not present and information needed to further facilitate matching may not be accessible.

From December 7, 2009 post:

Disambiguation of IDs is the process of resolving multiple potential matches into a match with the correct person. In general, statistical matching algorithms are likely to require substantially more-frequent disambiguation compared to that required by a system that uses theoretically perfect universal IDs; often, disambiguation is done by human intervention. Such disambiguation imposes significant costs and operational inefficiencies, particularly if, for example, a physician must resolve the ambiguities.

Note 1: Many of the efficiency and safety benefits theoretically possible with health information technology (HIT) systems depend on eliminating such human involvement and its concomitant slowness, expense, and propensity for error.

Note 2: What follows applies to IDs in general, even though I’ve chosen the healthcare industry for much of this discussion.

When the business process can’t be completed by automation alone, the business process incorporates human workflow. Manual disambiguation of an uncertain ID is one such human task. The form shown in the figure below illustrates a Web app created with Visual Studio 2010 [Beta 2] that a user employs to carry out part of a human workflow.

Please note: This post is presented in early draft form.

Communication between the client (user interface shown in the figure above) and the application services is performed by using proxy classes that run in the client and that represent the application service. In practice, a Web reference is a generated proxy class that locally represents the exposed functionality of an XML Web service. The proxy class defines methods that represent the actual methods exposed by an XML Web service. When your application creates an instance of the proxy class, your application can call the XML Web service methods as if the XML Web service were a locally available component.

At design time, the proxy class enables you to use statement completion for the XML Web service methods. At run time, a call to a method of the proxy object is processed and encoded as a SOAP request message. If the XML Web service does not support SOAP, the proxy class uses HTTP GET and POST. The message is then sent to the target Web Service for processing. If the service description defines a response message, the proxy object processes this message and returns a response to your application.

Note: To make XML Web services outside a firewall available to the Web browser, when creating the Web reference in Visual Studio, you must explicitly specify the address and port of your network's proxy server.

{ click the figures for a larger view }

Click here for more on Microsoft Visual Studio 2010

Click here for more on Oracle BPEL and Human Workflow

Note: If patients cannot be unambiguously identified via a computer-based process, machine-level interoperability will be hampered significantly.