Wednesday, July 23, 2014

Adding Some Structure to Last Week’s #HITsm Tweetchat

Last week’s #HITsm tweetchat topic – Unstructured Data – was of particular interest to me. Kudos to Bernadette Keefe (@nxstop1) for wrangling some good information, ideas and opinions out of the participants. The tweets were flying through my tweet stream fast and furious.  In an attempt to pull a little more value from that stream, I went ahead and added a little order and structure. Here’s what I came up with.

Note: Thanks to all who contributed. I’ve not noted who tweeted each item in this post as I didn’t want to misquote or omit anyone – which I surely would have done. You can learn who said what and to whom via the transcript of last week’s #HITsm tweetchat here.

Topic 1: How will the analysis of Unstructured Data aid in healthcare delivery: for MDs/Providers/Patients/Payers?

Are we talking systemic use or manual? If data can be systemically used, a flood gate of use cases open up.

Think the promise is truly in analysis of the unstructured data~eventually.

Gain valuable info about patient experience with drugs and interactions

Well good portion is 'the patient's story' how their health makes them feel. may never be structured

Yes, lets talk re value in unstructured data. It contains all patient narratives, the stories told to countless MDs ~inval…

Agree but worth asking the question, problem is too structured means less innovative thinking

IMO, biggest #unstructured data miss is in the 4th "P" a patient's peers. Blog:

No because there is high value in "the narrative" for telling and communicating the patient story

Need all: structured, unstructured, human intelligence together

For Providers – reduce over-utilization, eliminate redundant diagnostic tests see JACR

Value in unstructured data--patient narratives, the stories told to countless MDs ~invaluable

Interpreting clinical text ultimately requires more than just sound, structure & meaning. It involves goal, plan & task recognition

#1 question I always ask when someone brings up BI and BIG DATA is what problem are we trying to solve

It's possible NOW to analyze unstructured data - query it & add value to existing structured datasets

What percentage is unstructured today? Seems like a big hole in the "complete record". Possible risks for systemic analysis.

Yes, the benchpoint number given is 80% ~ Massive!

Should we make HCP use structured data only, or develop tools to analyse unstructured data?

Unstructured data is ALL TEXT ~ so all MD/ other HCP provider notes, all radiolog reports, surgical reports, etc

Indexing a semantic searching is a good start and facilitate finding relevant data, but still may require manual analysis.

SOAP notes and plans the gold mine of unstructured, free-text data. RT @nxtstop1 T1 Unstructured data is ALL TEXT

My MAC just puked some 0s and 1s out the side seeing "SOAP"

Please educate me - what about data from wearables? Is that unstructured? I believe @Brian_Eastwood touched on this recently.

One benefit of "unstructured data" is that using can can add value w/o changing physician workflow.

If no impact, no worth RT @JMCelio RT @georgemargeli yes -- how is data driving clinical decision-making, improving quality of life?

But have to keep in mind safety issues, ambiguity can be dangerous

Can analyze common terminology used...first within institutions & expanding outward-->standard terminology-->structured data

I suppose we only know a little if funnel is limited to ‘structured data’ & way beyond nuance?

Explicit or implied delimiters, tags and/or “context” can add structure to unstructured data.

Any analysis & exchange between these constituents (structured, semi-structured or unstructured) can only help.

Topic 2: How can you, your firms, #HealthIT in general, help in the retrieval & analysis of Unstructured Data?

Really like this from @CLOUDHealth "Structure is not defined by databases but by relationships with people."

Yes -- how is data driving clinical decision-making, improving quality of life? #NoDataForDatasSake

No #data is #unstructureddata Structure is not defined by databases but by relationships with people.

We get so excited over having more data > don't spend enough time *thinking* about what it's really for

Adding time layer to storytelling aspect of Patient's history. It's very complex and multi dimensional story to tell.

Realized I'd misspoken. Data is structured, identifying quantifiable things, but unreadable to clinical systems.

T%, or ‘business as usual no longer an option…question is ‘what is new biz model’? Is there ‘one’?

That's the common problem, right? There's structured data here, but won't make sense there

Asking questions of unstructured narrative isn't an exact science but it's a better than spending valuable clinical sight time

Unstructured just a tech term b/c its unstructured TO TECH.New thought:text data is Gr8>& tech will step up 

I believe the solution we're looking for is I-N-T-E-R-O-P-E-R-A-B-I-L-I-T-Y.

I wrote bit of a rant on #wearabletech and an inability to get tangible insight from it: Does that count?

Some standardisation around terminology would make it easier, just because its free text doesn't mean we need to be too free :)

SNOMED gives us some reference clinical terminology

Room for Web crawlers in EHRs? :) Think unstructured data us fine if smartly presented in collective to MD viewing files.

Start turning unstructured data to semi-structured data. Turn semi-structured data to structured data.

Consider adding delimiters, tags & considering “context” for everything you touch and/or have control over.

Don’t just run on sentences. Add white space. Use CR/LF’s… Spell correctly. Make the text “processable”

Actually, IMO it's really just grunt work and getting people to agree on "code translations"

Whoa! Not one single ‘de-limiting’ reference to HIPAA today. A miracle? Or simply context/competence appropriate?

Topic 3: If you have worked on a project with Unstructured Data-please describe pros/cons of the experience. 

One benefit of "unstructured data" is that using can can add value w/o changing physician workflow.

Unstructured healthcare data is not just free text, it includes a variety of multimedia content: video, audio, etc.

One challenge of unstructured data is that using it allows physicians to avoid change

Other hard part is asking the right Qs @HealthFusionKMc: Agree! And if do the data prep right, analysis even easier

Attributing data to member and provider (provider in all its variations: individual, practice, network, etc) is hard.

Biggest prsnl complaint: get unstructured data of my Rx. So tired of getting the wrong thing at the Pharm

A concern kinda BUT~ MDs will always (and should always) use free text to render appropriate nuance to pts stories

Con=Unstructured text includes ambiguity. Need to balance specificity with sensitivity. May result in FP/FN. Set user expectations.

I collect a lot of data which has never been used...yet. I'm confident it will be one day.

Will be even huger with HIEs RT @ShimCode: identifying and properly handling CHANGES to data previously processed is huge.

I'd almost rather see investment in smarter systems to interpret unstructured data then more standards

Wide variation of how “standards” are used & re-purposing of fields without consistent use are 2.

You know hand writing is a type of encryption, especially coming from docs :)

This may generate some controversy but analyzing data is easy. It’s getting the data ready to analyze that’s hard.

Yep. Cleaning data is supposedly 80% of the workload.

Agree! And if do the data prep right, analysis even easier @ShimCode analyzing data easy

Exactly @nickdawson: when I've done big financial models, most of the work is in prepping and normalizing the data

I used to do NLP, which got me into standards like #CDA, here are some of my observations:

Workflow highly important 2 speech recognition & text disambiguation. Used 2 more accurately estimate tokens & meaning probabi…

Topic 4: Given the base data is text,can you think of creative presentations of the analyzed data which might especially engage MDs/Providers/Patients/Payers? 

Can you think of creative presentations of the analyzed data/text that may engage caregivers/Patients/Payers?

IMAGINE all of us having our INDIVIDUALIZED , PERSONALIZED WORD CLOUD AT THE BEGINNING OF #EHR -and it could chg (improve hope)

"Creative" is key. As a patient, I don't get pumped about taking charge of my health by looking at pie charts, bar graphs

Yes, lets get around to the creative presentation. Particularly fond of this as we see w/ Pinterest Interest, FB pix, VISUALS ROCK

Longitudinal progression of a health concern over time, from out of shape to overweight to diabetic...

Good txt summarizer can [make] pages of unstructured text afew sentences

MDs, MAs, Nurses.. Always looking for data on patient. Spending more time being a detective than doing actual work.

It's all about the use case - not the tech, not the data - but the value in unstructured clinical narrattive to improve healthcare

Tie in the social #data for prevention will be good

Word clouds hit the popular pairs but the real relationships are often hidden

Nice, but might b better to see (creatively) predictions of how my lifestyle choices will affect me 5, 10, 15 years on.

NLP is cool tech but it should be about solving problems - not tech for tech sake

Crawl it, index it, search it, rank it, and present it.

Here is a great tool to help convey your analyzed data "Visualizing Health"

Teaching clinical analytics key to future HIT pros -

"Communicating Data for Impact"

Absolutely!!! Crawl it, index it, and apply context.

There are some real HIPAA issues with web crawlers in EHR.

Topic 5: Any other thoughts on the current use of EHR data? 

Creating registries for reseach and quality. Have worked on this for CKD successfully

Need to teach HCP value of EHR data and focus on clinical outcome, not just data for data sake

Developing tools to analyze both structured and unstructured data will be incredibly valuable

Really need tools to make data collection passive. I'm not slowed down @ bedside,you get your data

Painful doing manual abstractions for research in #EHR feels like little progress from paper#decretefields

Your point well taken & key 2emphasize. he goal is actionable data which will better Rx/prevent disease

I think about data libraries and a place to house all the structured data once it's clean. But may violate HIPAA 

"The Business Case for Using Unstructured Text Analytics for Critical Decision Making"

Comments on Statistics about Unstructured Data

Good question. Do you know how much health data is unstructured today?

We're talking about how much HIT data is currently unstructured & how to address that.

Said to be 80% , but that's a quess RT @jonmertz @Greg_Meyer93 Good question. Do you know how much health data is unstructured today?

I’ve seen estimates that up to 90& of healthcare ‘data points’ are unstructured. Is that true?

I'd also say 90% of collected data is never used again

Of 1.2 billion clinical docs produced-US each year, approx 60% valuable data unstructured documents

And what would any #healthit discussion be without some chatter about 'Standards?'

A ‘what if? Might single payer enable a ‘standards’ agenda? Or pluralism worshipped at any cost?

The industry really need standards defined. without that we will have this discussion forever

We have standards.... just may need to be more firm than fuzzy.

That there are no standards is a common complaint. It usually indicates lack of knowledge OR lack of implementation

Agree! No shortage of standards. Some are even worthwhile.. Some result from confusing activity w/results.

Standards are one thing: but anything can be structured with any standard. Get to structure first, then apply standards.

Which we won't have until we start thinking message sets as opposed to documents (so 1950s like carbon paper). (Forgot)

Even without standards master data management can help

Could addressing unstructured data be elementary for Watson?

Any #watson projects happening in this area? Sorry if someone already mentioned it.

Couldn't that be a #watson job? dealing with legacy code?

The installed base of legacy code prolly won't go away under Single Payer. Still need to process data? 

Closing Tweet

Can't forget ultimate end user... The patient. "How will this data help them be healthy in future?"

Sunday, July 20, 2014

Inspiration, Insight, Facts, Opinion & Tips from Recent #ClinicalCoding14 Meeting

On June 6th, 2014, AHIMA sponsored a Clinical Coding Meeting. Coding tips, education & training, working with payers, impact of coding on financial performance and clinical documentation improvement programs were shared on Twitter using the #ClinicalCoding14 hashtag. Here are some select tweets from that conference that I think will provide some inspiration, insight, facts, opinion and tips relevant to clinical coding under ICD-10.

"The will to succeed is important, but what’s more important is the will to prepare." ‐ Bobby Knight

“Before everything else, getting ready is the secret of success.”-Henry Ford

Coding Wisdom

1. Coding should always completely & accurately represent the diagnoses & procedures for a patient-Susan Belley

2. Physician documentation is the cornerstone of accurate coding- Jon Elion

3. Data Should be Relevant, Timely, Accurate, Accessible, Comprehensive, Consistent, Current, Defined, Granular & Precise.

4. Essential Components of Coding Compliance Detection, Correction, Prevention, Verification & Comparison

5. Dual coding benefits can be very substantial but it can be expensive & resource-intensive, thus having a plan is key.

6. Root operations division and release may cause the biggest challenges in ICD-10-PCS.

7. ICD-10 PCS will improve accuracy & efficiency of procedure coding & replace ICD-9 CM w/a more logical system- Laura Leg…

8. ICD-10-CM’s use of 6th & 7th characters allows for more granular data capture within the fracture codes-Marty Beckman

9. Home Health coders must know how to code in #icd10 by August 3, 2015 because of HH billing requirements.

10. Analyze your data and GEM MAPS to discover the hidden impact of less specified codes.

Impact to Financial Performance & Working with Payers

1. If you pursue the High Quality Medical Record, the proper reimbursement will follow. -Jon Elion

2. The premise is why would payers pay for procedures when the reason for it can't be specified? Joanne Schade-Boyce.

3. Measures will increase though claims-based data. - Cheryl Bowling

4. Improving the accuracy of clinical documentation is the greatest opportunity for financial improvement

5. 50% of healthcare organizations are experiencing positive ROI results in data analytics & reporting technologies

6. Pay for performance outcome measures will continue to expand. -Cheryl Bowling

7. Important success factor in the move to #ICD10 relates to enabling the exchange of clinical information w/payers

8. Dr. Elion: "If the high quality medical record is pursued, reimbursement will follow."

9. 5-Phases to Engaging Payers Contract Management, Payer Communication, Implementation, Payer Testing, Post-Implementation

Process, Training and Project Management

1. It’s time for physicians to show what they know w/the robust #ICD10 coding system & begin to report 21st Century medicine

2. Coding clinics are the key to success in clinical documentation improvement

3. Work hard to get on your payer's testing schedule and coordinate with clearing houses.

4. MTs are a Key Resource. They already know clinical content & healthcare documentation-Claudia Tessier

5. Five Steps To Pass The CCS Exam Change your perspective, have a plan, prioritize your life, practice, prepare

6. Simplify the educational process with the ICD-10-CM transition by first identifying stakeholder needs. - Deborah Neville

7. Get creative. Establish an internal post graduate program that involves training and mentoring new graduates. Kayce Dover

8. Data Mining & Machine Learning are closely tied and often used interchangeably.

9. Growing your own coders can help you marry CDI and coding.

10. Plan for the worst. Utilize tools to analyze the new standards. Kayce Dover

General Tips

1. More specific documentation is needed when reporting sepsis. -Laura Legg

2. Develop documentation tip sheets for providers to utilize to help in documenting services in the emergency department.

3. Prior to implementation of #ICD10, have 2 or more coders code same case & review any discrepancies in codes or DRGs

4. Dual coding benefits can be very substantial but it can be expensive & resource-intensive, thus having a plan is key.

5. Develop documentation tip sheets for providers to utilize to help in documenting services in the emergency department.

6. Mapping from NOS to NOS is not good enough. Elevate that Not Otherwise 'Satisfied' documentation - Andrea Clark

7. Don't NOS (Not Otherwise Specified) your data! Consider the CHDA

8. Top worry of Home Health agencies regarding #icd10 is ADRs and denials caused by face to face documentation.

9. Ensure coding professionals have access to all reference material such as device formulary says Susan Belley.

10. The most challenging aspect of CDI is physician buy in- Laura Legg

11. Data Mining & Machine Learning are closely tied and often used interchangeably.

12. Concurrent CDI and coding = the route toward data improvement and integrity


As Claudia Tessier, ‏co-founder of Coding for Healthcare Professionals, posited to the crowd:

"What do #CD-10 & death have in common? Everybody tries to delay them, but they are inevitable."

Note: Thanks to all the Twitter accounts who shared info from this meeting including a few who stood out - as noted by Symplur@ahimaresources @louwiedemann @julezd @lhima1 @acomfort03 

Wednesday, July 16, 2014

266 Tweeps Sharing #healthit & #HITsm Content, Insight & Commentary

Here are 266 people or companies that I believe offer up good content, insight and/or commentary on healthcare information, technology and related topics on Twitter. Every one of these people or companies received at least one vote in this years #HIT100 Contest.



Note: I'm not wholeheartedly recommending every one of these people and companies. In fact, I disagree with most of what a few of these Twitter accounts regularly emit. But I do follow all of them directly or via various lists I maintain.

Saturday, July 12, 2014

20 New Twitter Sources for #healthit and #HITsm Topics

During the first 10 days of July, the tweet streams I use for monitoring the #healthit and #HITsm hashtags on Twitter were flooded with a lot of tweets related to the 2014 #HIT100 event. At times, the nominations for people I already knew about (and all the spam that seems to accompany events like the #HIT100) were a bit too much to sift through. But as is the case when panning for gold, I had to be willing to sift through LOTS of soil to find a few precious flakes.

Good People to Follow on Twitter

Here are some of the "precious flakes" I believe will provide value to those interested in healthcare information technology and social media

Note: You can follow all of these folks using this HIT100 Twitter list I created or pick and choose those that may interest you. Or skip all of them.

David E. Albert, MD @DrDave01
- Physician, Scientist, Inventor, Entrepreneur

Howard Brooks @HowardbrooksEY
- Americas Life Sciences Leader @ EY; @JDRF advocate

Austin Chiang MD @AustinChiangMD
- Youngish doctor with many aspirations.

Naomi Fried @NaomiFried
- Chief Innovation Officer @Boston Children's. #Telehealth and #HIT Evangelist

Craig Fukushima @ctffox
- Health care Consultant with over 30 years of operational experience.

R. Grossmann, MD @ZGJR
- TEDx Futurist / Surgeon

Bill Hersh @williamhersh
- Professor and Chair, Department of Medical Informatics & Clinical Epidemiology, OHSU

Martin Kelly @martykelly
- Founder @health_XL previously Partner IBM Venture Capital 

Paul Lane @PBLsciupdate
- Medical Publications Professional

Michael Martineau @eHealthMusings
- eHealth consultant and commentator

Greg Matthews @chimoose
- Healthcare. Social media. Enterprise change management.

Sally McGee Barlow @lonestarsally
- RN, Associate Director Business Analytics

Sean McGuire @SeanNMcGuire
- Health Policy Wonk. America's Healthcare Challenge Host.

Jan Oldenburg @janoldenburg
- Chief editor of Engage! Transforming Healthcare Through Digital Patient Engagement.

Ruby Raley @ruby_raley
- Itinerant Technologist focused on Health Care and Supply Chain

Keith Salzman @klsalzman

Dale Sanders @drsanders
- Healthcare #DataWarehousing & #analytics guy.

Mark Underwood @knowlengr
- Big Data, Cyber security, informaticist

Alice Westerfield @AGWesterfield
- Data Integration and Data Management

Mary Pat Whaley @Mary_Pat_Whaley
- Physician Advocate. Resources for Physicians & Managers at Manage My Practice

Saturday, July 5, 2014

11 Qualities of a Good #HIT100 Nominee

A primary purpose of the #HIT100 event is to recognize individuals (and companies, although I disagree that companies should be included) that are leaders in curating and creating useful information on healthcare information technology.

Here’s what I look for in people I follow for information, news, ideas and tips on healthcare and healthcare information technology - on Twitter and elsewhere.

Qualities of a Good Health IT Resource

1. Is involved with some aspect of healthcare information technology, healthcare informatics and/or closely related products and services AND shares this involvement via social media.

There are many extremely knowledgeable, experienced and “high-level” health care information technology resources that rarely, if ever, share their knowledge via social media. I may follow these people but what good are they to me if they don’t share their knowledge unless I’m paying for it via a webinar, book or conference? 

2. Curates content on a topic or topics I care about.

"Content curation is not about collecting links or being an information pack rat, it is more about putting them into a context with organization, annotation, and presentation. Content curators provide a customized, vetted selection of the best and most relevant resources on a very specific topic or theme."

3. Remains somewhat focused on the topic of healthcare technology and related matters.

4. Creates original content and shares it - at least occasionally.

5. Comments on others tweets, blog posts and content - at least occasionally.

6. Retweets good content from others on a TIMELY basis.

One of social medias primary values is timeliness – particularly with Twitter. I really don’t want to read your tweet several days or weeks after I’ve learned about that particular topic from dozens of other sources.

7. Doesn’t clutter up my stream with lots of superfluous and useless chatter. An occasional tweet about something off-topic is fine and helps me understand and appreciate you and your personality.

8. Does not use Twitter as a chat room.

9. Avoids publicly thanking every single person who mentions them.

10. Avoids responding with “You’re welcome” to every person who thanks them.

11. Maintains their true personality and interacts with others on a down to earth basis.

Doesn’t hide their real personality just to be “politically correct” and avoid offending sensitive people.

I don't think a good #HIT100 nominee needs to have all of these qualities but should have at least 4 or 5 of them.

Wednesday, July 2, 2014

How to Win the #HIT100 and Become an #HITSM Superstar in Your Own Mind

Feeling down? Need an ego boost? Want to win the admiration and adulation of complete strangers? Then follow these tips to rise in the ranks of the #HIT100. If you follow each of these tips, I guarantee* you will make one of the top 99 positions in the #HIT100 list.

Note: If you really want to just participate in the #HIT100 event on a down-to-earth basis, here are 10 Simple Suggestions to Keep the #HIT100 Event Real

Tricks of the #HIT100 Trade

1. Vote early and vote often. If you vote enough times one or two of those duplicate votes may sneak past @TheEHRGuy when he counts them. I grew up in Chicago. It works there and it’ll work here.

2. If you have multiple Twitter accounts, vote with each one of them.

3. Nominate every person in last year’s list. Some will feel obligated to return the favor.

4. Create a Twitter account for your long deceased great, great grandmother and every other deceased relative you can think of. They would have voted for you anyway if they were alive, right?

Update: Tip #4 won't work due to new rule that accounts must exist for at least 6 months.

5. Vote for yourself. It’s totally “legal” and demonstrates a healthy level of pride.

6. Pressure your workmates, family and friends to vote for you. Free food and booze works for those recalcitrant cronies and reluctant relatives.

7. Dig up some dirt on people and threaten to expose them if they don’t vote for you. Send your friends @Guido and @Annunzio over to encourage them to nominate you if they balk.

8. Ask @katyperry, @justinbieber, @barackobama, @taylorswift, @ladygaga and @britneyspears to tell their followers to vote for you. You never know… Here’s the top 100 Twitter accounts with the most followers.

9. Retweet every tweet that mentions you.

10. Publicly thank every person who votes for you in the most ostentatious fashion possible and then retweet that tweet. The more often you get your name out there, the greater the chance that tweet will be double counted by @TheEHRGuy.

11. Hijack the #HIT100 Hashtag. Add it to every tweet you make. Include it in your email signature. Tattoo it on your forehead along with the name of your Twitter account.

12. Get extra exposure by adding #WorldCup to your plea for votes. This works well when bundled with Tip #13 and/or Tip #14.

13. Create an automated means to make it easy for others to tweet their nomination of you. 

14. Trick people into voting for you. Tweet the following: "Click here for cute cat pictures" and include a link to a tweet nominating yourself. 

15. Employ a gang of low-paid ‘click farm’ workers in Bangladesh to vote for you. limited to a full refund of the price paid for this how-to guide.

16. Pretend you have a terminal illness and tell everyone your last wish is to make the #HIT100 list.

Now Go Become a Top-Ranked Health IT Star

So there you have it.  Now get out there and start campaigning. You're an #HITSM superstar and you know it. Now you just have to convince enough others.

*Guarantee limited to a full refund of the price paid for this how-to guide. 

10 Simple Suggestions to Keep the #HIT100 Event Real

After last year’s #HIT100 event I made three blog posts about The Good, The Bad, & The Ugly aspects of the #HIT100 event (an event some label as a popularity contest or vote-stuffing exercise.) I’m extracting and summarizing 10 suggestions from those posts that I believe, if followed, would make the #HIT100 event more valuable to those working in and/or interested in health care information technology. Here they are and if you’re upset that some of these apply to you – then that’s on you and you may want to think harder about why it upsets you.

Consider These Simple Guidelines

1. Add a short note as to why the person you’re nominating deserves to be nominated.

2. Honor the one person, one vote ideal of American democracy.

3. Don’t use multiple Twitter accounts to vote.

4. Don’t create a Twitter account just to vote for yourself or someone else.

5. If you’re going to cheat, don’t be so obvious - be creative. Last year one dad voted for his son using – at least - 3 separate accounts; submitting all votes within a few minutes of each other.

6. Avoid extreme self-promotion. Humility is a virtue.

7. Don’t RT every single tweet that mentions you.

8. Resist the temptation to cajole co-workers, family and friends who rarely, if ever, participate on Twitter or other platforms to vote for you.

9. Nominate people who actually participate in the healthcare IT space in some meaningful way on a regular basis –whether on Twitter, Google+, blogs or elsewhere.

10. Don’t hijack the #HIT100 or any other Hashtag to promote yourself.

Who are You Going to Be?

If you really want to dominate the #HIT100, why not just get it over with and employ a gang of low-paid ‘click farm’ workers in Bangladesh to generate votes?

What other suggestions do you have? If you disagree with any of my suggestions, I'd like to hear why.