"This October 2,000 of the best and brightest will gather to discuss, witness, and share the leading cutting-edge innovations transforming today’s global health care system. Health 2.0’s flagship event connects thought leaders, providers, innovators, investors, and start-ups for four days packed full of curated discussions, demos, exhibits and networking…"
Conference block rate for the onsite Hyatt Regency hotel expires Sept 7th. Mercifully, the NFL 49ers play Arizona at Arizona on October 1st, so there won't be that huge traffic mess around Levi Stadium.
I booked my hotel rez starting on Saturday September 30th so I can hit the ground running Sunday morning. Joe Flower will keynote the Provider Symposium Sunday morning.
BTW, Sept 30th is the final day of federal FY 2017. President Trump is threatening a government shutdown to try to coerce congressional funding of his Mexico Wall (yeah, right). More seriously, the "Freedom Caucus" right wing Tea Party faction of the GOP wants another federal shutdown to try to get their way on the federal debt ceiling. My note on this now-hardy perennial a couple of years ago on another of my blogs:
Let's be very clear here: While "defunding" and transiently shutting down the government by failing to pass budget legislation is a political act within the bounds of tripartite government (notwithstanding its inanity), intentionally defaulting on the public debt is a separate and explicit Constitutional violation of legislative branch members' Oaths of office -- notwithstanding the GOP extremists' conflating attempt to glom it all together. to wit,During the 2013 Health 2.0 Conference we had a number of federal officials in attendance (e.g., ONC, CMS) to speak. Because of the 2013 federal shutdown they had to leave early and return to DC.
Section 4 of the 14th Amendment declares that "the validity of the public debt shall not be questioned." Section 5 subsequently states that the Congress has the sole responsibility over this question.
More broadly, as set forth in Article I, Sections 7 and 8, only Congress has the authority to appropriate funds and levy taxes. They can appropriate funds by raising taxes and/or borrowing from the private credit markets in the name of the nation. If they choose the latter, they are required to see to it that payment is always honored, even should that mean raising taxes or cutting other program expenditures. Neither the President not the Supreme Court has any Constitutional authority here. Should honoring the public debt require a presidential veto override, so be it. Muster the requisite votes. Should it require taking out "poison pill" provisions in order to pass debt service legislation, so be it. Those are among the legitimate mechanics of governance, in this case devolving to the Congress and no other entity...
We'll see.
HIMSS
Interestingly, this will be the first Health 2.0 Conference under HIMSS ownership (should we call it "The 1st Annual HIMSS 2.0 Conference?")
I find it a bit curious that there is no prominent, static mention/link (as of today) regarding the 2017 Health 2.0 Conference on the HIMSS homepage. What's up with that? (Mention of the Conference does appear transiently amid a rotating group of small horizontal banner ads at the top of the page. Hit "Ctrl-R" repeatedly to see if you can get it to pull up.)
I went to the HIMSS Facebook page.
OK. Nyet. Nada. Zilch.
They do cite this on the HIMSS homepage at the right side "top of the fold":
Interesting timing overlap. I just searched through the agenda. Maybe I've missed something, but I see no mention of "Health IT Week." (Neither do repeated spelling-variant searches on the health2con.com site turn up any mention.) Wonder if they'll have an exhibit hall booth presence?
Now that HIMSS owns the Health 2.0 Conferences, I hope I don't get any photography grief, like I encountered at the HIMSS16 closing Keynote.
BTW, loves my New Yorker...
NLP on the agenda?
Searching the conference agenda also fails to turn up any mention of the acronym "NLP" or its referent phrase "Natural Language Processing," on which I've previously ruminated here and here.
I continue to study and follow the topic. Ran across this the other day (which I've excerpted below):
FDA, UCSF-Stanford CERSI, and San Francisco State University Collaborative WorkshopJune 15, 2017
Goals and Objectives:
The objective of this workshop was to identify current and emerging natural language processing (NLP) efforts being applied to unstructured text such as clinical notes or narratives in electronic health records (EHRs). The workshop provided insights into utility and challenges in designing and implementing NLP systems to capture relevant or missing information from clinical notes or text for conducting postmarketing safety surveillance and informing the design and execution of clinical trials for medical products, which include drugs, biologics, and devices. The workshop included panel discussion sessions to provide stakeholders with a forum to discuss natural language processing with experts in the field.
The workshop focused on whether NLP can be applied to unstructured text in clinical notes to:
Use of Natural Language Processing to Extract Information from Clinical Text: Summary of the FDA Workshop
- Identify indication or reason for medical product use, adverse outcomes or events associated with use of these products, and confounders or personal behaviors that may modify risks associated with use of these products
- Support protocol design, feasibility, recruitment efforts and execution of clinical trials
A public workshop organized by the U.S. Food and Drug Administration (FDA), the UCSF-Stanford Center of Excellence in Regulatory Science and Innovation (UCSF-Stanford CERSI), and San Francisco State University was held at the FDA White Oak Campus on June 15, 2017. The objective of the workshop was to identify current and emerging natural language processing (NLP) efforts being applied to unstructured text such as clinical notes or narratives in electronic health records (EHRs)…
While this workshop focused on NLP, it was noted by several speakers that it is only one part of the solution pipeline (sequence of software tools) – it is most often preceded by complex data acquisition and pre-processing, and followed up with some combination of machine learning or rule-based systems to produce desired decisions or interpretations. In many cases, NLP is in fact performed as a set of rules, or has been replaced with text mining and statistical methods with good success in specific areas especially when a large number of records are available.
Classical NLP technology, designed for regular text, encounters significant challenges in processing information from clinical text in medical records such as EHRs. The challenges come from two key areas: a) NLP was not originally designed to process data in this format and with the “noise” inherent in EHRs, and b) most NLP algorithms require large gold standard databases for training ground truth data, which are hard to come by. It was also noted that for NLP to be successful in these areas, it will need to adequately handle negative statements (negations) and medical context.
In spite of the above challenges, a literature review presented by one of the speakers showed that NLP and related methods were successful for some specific applications (e.g., radiology diagnosis, filling in certain EHRs, extraction of specific medical terms, etc.). Since each of these applications were developed separately, the issue of generalization remains.
To move forward, several possible approaches and directions were identified by one or more speakers/panelists:
DATA
- Given that NLP is only part of the analysis pipeline that may include (deep) machine learning, it is important to optimize the whole pipeline, from data capture to final data/decision representation.
- Leveraging new analytics methods that reduce dependence on large training databases (e.g., deep learning, CNN, text mining etc.) would be beneficial.
- Developing general solutions using a single generalizable NLP/analytics method is difficult, so it may be worthwhile to work on solving specific problems first, then analyzing commonalities among successful solutions, leading to possible generalizations…
Electronic Health Records (EHRs) and other structured clinical documents were originally designed for very different purposes (patient care, billing, reporting). The clinical notes or text contained in these documents may contain additional information and context about the medical encounter but the clinical information it contains is non-standardized, has errors, typos, omissions and often miss key information necessary for envisioned FDA applications (e.g., confounders, prescriber and patient intent or behavior). This poses significant challenges for classical NLP tools designed to work on regular text. Further complicating the situation, the applications of NLP addressed at the workshop are many, and often require information and context not originally coded or missing in EHRs and related documents (e.g., confounders, temporal components, state of instrumentations)…
Leveraging a variety of complementary data sources (including other patient records, observations during the exam etc.) in addition to EHRs would help to provide missing information, redundancy, as well as context, all of which are important for making the correct decisions…Recall from my earlier posts, there are two materially differing subtopics: [1] NLG, Natural Language Generation (expressing "structured" numerical data and informatics codes in narrative form -- relatively old news), and [2] NLU, Natural Language Understanding, the far more difficult area (and the focus of my abiding dubiety).
TOOLS AND RESOURCES
The following ideas were suggested by one or more speakers/panelists as possibilities to help develop tools…
Availability of accessible, easy to share gold standard databases remains critical. The positive experience of other areas on machine learning where such databases have helped to make significant advances needs to be leveraged. This remains, however, a technical/cost issue as well as a policy and legal issue due to data privacy considerations…
- Using and leveraging best practices of open source software.
- Developing software environments in the form of interactive workbench where one can easily create and test analytic pipelines (aggregate of software tools used) by integrating available tools, as has been done for other areas.
- Provide and disseminate open source NLP and machine learning tools with adequate distribution, licensing and documentation.
Hope I find some good NLP stuff at the Conference (amid my myriad other topics of KHIT interest).
UPDATE: NLP NEWS ITEM
Apple's Siri latest target in string of natural language patent lawsuitsInteresting. A "patent troll?" At first blush, looks like one to me. Bears watching.
One-man company Word to Info on Friday expanded a string of patent lawsuits over natural language processing technology — active cases involve Amazon, Google, Microsoft and Nuance — to include Apple, taking specific aim at the tech titan's Siri virtual assistant.
ON THE VENTURE CAPITAL COMMUNITY
A staple of Health 2.0 events involves panels of Silicon Valley VCs. Below, an interesting read (particularly in the wake of the persistent troubles at Uber, and the misfortunes of bro'grammer #GoogleManifesto Man):
In December 2010, Sheryl Sandberg gave a talk about women’s leadership in which she mentioned “sitting at the table.” Women, she said, have to pull up a chair and sit at the conference-room table rather than clinging to the edges of the room, “because no one gets to the corner office by sitting on the side.”Yikes. Read all of it. (a fairly long read). I ran into it here. Just an excerpt from her forthcoming book Reset.
Less than a year later, I would take those words to heart. I had been working for six years at the Silicon Valley firm Kleiner Perkins Caufield & Byers as a junior partner and chief of staff for managing partner John Doerr. Kleiner was then one of the three most powerful venture-capital firms in the world. One day, I was part of a small group flying from San Francisco to New York on the private jet of another managing partner, Ted Schlein. I was the first to arrive at Hayward Airport. The main cabin of the plane was set up with four chairs in pairs facing each other. Usually the most powerful seat faces forward, looking at the TV screen, with the second most powerful next to it. Then came the seats facing backward. I was sure the white men booked on the flight (Ted, senior partner Matt Murphy, a tech CEO, and a tech investor) would be taking those four seats and I would end up on the couch in back. But Sheryl’s words echoed in my mind, and I moved to one of the power seats — the fourth, backward-facing seat, but at the table nonetheless. The rest of the folks filed in one by one. Ted sat across from me, the CEO next to him, and the tech investor next to me on my right. Matt ended up with what would have been my original seat on the couch.
Once we were airborne, the CEO, who’d brought along a few bottles of wine, started bragging about meeting Jenna Jameson, talking about her career as the world’s greatest porn star and how he had taken a photo with her at the Playboy Mansion. He asked if I knew who she was and then proceeded to describe her pay-per-view series (Jenna’s American Sex Star), on which women competed for porn-movie contracts by performing sex acts before a live audience.
“Nope,” I said. “Not a show I’m familiar with.”
Then the CEO switched topics. To sex workers. He asked Ted what kind of “girls” he liked. Ted said that he preferred white girls — Eastern European, to be specific.
Eventually we all moved to the couch for a working session to help the tech CEO; he was trying to recruit a woman to his all-male board. I suggested Marissa Mayer, but the CEO looked at me and dismissively said, “Nah, too controversial.” Then he grinned at Ted and added, “Though I would let her join the board because she’s hot.”
Somehow, I got the distinct vibe that the group couldn’t wait to ditch me. And once we landed at Teterboro, the guys made plans to go to a club, while I headed into Manhattan alone. Taking your seat at the table doesn’t work so well, I thought, when no one wants you there. (When Sandberg’s book Lean In came out, that same Jenna Jameson–obsessed CEO became a vocal spokesperson for it.)
Seven months later, I would sue Kleiner Perkins for sexual harassment and discrimination in a widely publicized case in which I was often cast as the villain — incompetent, greedy, aggressive, and cold. My husband and I were both dragged through the mud, our privacy destroyed. For a long time I didn’t challenge those stories, because I wasn’t ready to talk about my experience in detail. Now I am…
Interesting, accomplished, scary-smart woman. Same age as my younger daughter.
____________
More to come...
No comments:
Post a Comment