Vol. 210 April 1, 2019 Alzheimer’s: There’s an App For That.

April 1, 2019
This image has an empty alt attribute; its file name is hub-thumbnail-2015-e1519515150729.jpeg

Dr. Atul Gawande, CEO of Haven, the new healthcare-innovation company formed by Amazon, Warren Buffet, and J.P. Morgan, has announced that their first “new model of care” is an app for patients with Alzheimer’s. The app’s name is “FIGAWI”, after that ancient Indian tribe that gets lost in the fog almost every Memorial Day weekend on Cape Cod.

The app will provide a number of programs meeting the anticipated needs of Alzeihmer’s patients including:

WMC – Where’s My Car?
When exiting a store and realizing that you forgot where you parked the car, you just have to say WMC? . . . or WTFMC!?, depending on your sense of frustration and degree of patience.
1. The app will immediately access your state’s RMV Dept. database to collect your car’s make, year, and color,
2. then it will scan your credit card charges to find in which near-by store you had just made a purchase. (If you are near a complex of stores or in a mall, you can speak the name of the store into your phone, or if you have been in multiple stores, the program will search your credit card database for the last 10 store charges in order to identify the relevant parking lot.),
3. then it will get a Google satellite picture of the parking lot nearest to you and place a pin on it marking your car’s location.
4. If your phone’s GPS fails to record you moving toward the car within 3 minutes, the app will activate your car’s horn and flashing head lights to aid in its detection.
5 . If you fail to reach your car to turn off the alarm warning system within 12 minutes, the app will call either your emergency contact person in your contact list or 911, depending on your position (vertical or horizontal) as indicated by your phone’s orientation.
6. As an added bonus, if you open and start your car within 15 minutes, the app will show you any current outstanding parking tickets and remind you about the date and amount of your next car loan payment.

WT – Who’s That?
When meeting a person who you know, but can’t remember his or her name, you just have to say WT? or WTFT!?, depending on your sense of urgency. The app will immediately:
1. take a picture of the person approaching you,
2. compare it to pictures of your friends and families stored in your contacts and photo library (If you do not have a picture of that person in your contacts or photo library, the program will access Facebook, Instagram, WhatsApp, the RMV, your local police database, TSA, and the FBI in sequence to seek a match using built-in face recognition software.).
3. The matched name will appear on your phone’s screen along with the date you last saw them, the person’s nickname, spouse’s name (if any), and names of all their children listed by decreasing birth dates.
4. If facial recognition can’t find a match, the phone screen will light up with the following message, “Say hi and take a picture of this person. Ask the person how to spell his or her name so ‘I can get it right for my contact list’, then say, ‘So glad to see you ______________(insert name)’.”

WDISIT – What Day Is it?
The app immediately calls up and displays your calendar, highlights the day and time , and lists the last two places you were in and for how long, as well as where you are expected next.

WIG – Where Am I Going?
Not quite ready for prime time; still under development. Unfortunately our AI program for reading minds currently works only for people who have indwelling brain electrodes or cochlear implant devices masquerading as same.

WAIH – Why Am I Here?
As in “Why did I come into this room?” – (see above WIG) But this function is currently operational based on scans of your house’s floor plan in your town’s Assessor’s Office which is integrated with the time of day, day of the week, and the next two days of appointments on your calendar.

HDIGT – How Do I Get There?
Just say ‘How do I get there?” or “How the f… do I get there?” (almost a shout). The app will discern your different voice volume and tones. If your voice volume threshold exceeds “almost a shout”, the app screen will immediately flash “CALM YOURSELF, and repeat the request please.”
If the volume threshold is exceeded on the repeated request, the screen will show, “OK, TAKE A DEEP BREATH AND COUNT TO 10 — the number of all your fingers, and try again please.”
Please note that this App is separate from Siri, Alexa, and Google so you may choose one of over a dozen app voices which will respond in kind to your sense of urgency and voice volume on a scale of 1 to 10, just like pain.
Once you have respectfully gained the app’s attention, merely say the name of the place you wish to go: as “Super Stop and Shop”, “”Post Office”, “Doctor Smith’s office”, or “The Dump” (also recognized as the “Transfer Station” or “Recycling Center”).
If you can’t remember a specific name, you can say “where I usually buy groceries”, “where I go to Yoga classes”, “nearest liquor store”, or “where I ate Thanksgiving dinner last year”, and the app will bring up the relevant map and directions after scanning your contact list, your most frequent credit card charges, and both yours and national holiday calendars for the past 5 years.
You can also ask the App to give directions with ONLY right hand turns for your safety, if you wish. Of course, “Take me home” will work without any other directions every time and every where.

These seamless cyber connections are all included in the basic FIGAWI App package. Confidential personal notes about your family members and friends can be included at an additional price in the advanced package, as long as you agree to Facebook’s, Amazon’s, Apple’s, Yelp’s and Google’s privacy policies. The app is available in Russian as well as the usual English, Spanish, Hip Hop, and Rap.

Future upgrades of the App will include integration with car ignition breath analyzer devices, if appropriate (the app can scan court data bases and local newspaper “police blotters” for judgements and allegations). The emerging 5G network will also allow this App to connect with other existing helpful apps like: Find my phone, Find my keys, alerts for CD maturing dates, due dates for oil changes and tire rotations, automatic “I’ve fallen and I can’t get up” calls, time to take your pill alerts, “Did I leave the toaster (iron, radio, thermostat ) on?”, etc. Eventually the App will integrate with self-driving cars, so you can find it after it parks itself in the parking lot.

The password for the App is “No Password” or “I Can’t Remember S**t!” whichever the user feels is most appropriate. The App will accept either one depending on the note of frustration and volume of your voice.

One does not actually have to have the diagnosis of Alzeihmer’s (easily confirmed or ruled out by a scan of your primary physician’s EMR) to get this app. The differences between Alzeihmer’s and cognitive impairment of old age is subtle enough to confuse our current AI program, . . . and some physicians.

The FIGAWI App is available to anyone over 65. Despite AARP’s active lobbying we are not offering it to people just over 55.

I was going to list the website where you can order the app, and its price, but I can’t remember either.

HAPPY APRIL FOOLS DAY.

Advertisements

Vol. 204 December 1, 2018 “Why Doctors Hate Computers”

December 2, 2018

 

Digitization promises to make medical care easier and more efficient. But are
screens coming between doctors and patients?
 – Atul Gawande

I wished I had thought of this title.
I wished I had written the article in the New Yorker that went with it. (1) But, it was written by a better writer, and a surgeon no less; a proceduralist, not a cognitive doctor like us pediatricians and internists. Atul Gawande nailed the reasons for the frustrations of most doctors in dealing with electronic medical records, including graphic points of special irritation with one specific computer behemoth, Epic.

Epic is the $100 million computer software system now in place in the Partners Health Care system serving 70,000 employees in 12 teaching hospitals with dozens of different medical/surgical specialities as well as thousands of office-based providers and their staff. In Epic I have learned the 6 different ways of using 13 different tabs or, worse still, those tiny little icons stuffed into the margin of the screen to get the information I need to see the next patient in a pediatric office. As I traverse the various and varied screens I usually am exposed to too much data and not enough information. It is clear to most of my colleagues and our staff that Epic is chiefly designed as an “optimizer of insurance reimbursement”; probably one reason that large hospital systems and their associated physician networks buy it. A recent Epic “upgrade” was so devoid of any upgrade in clinical relevance that it did nothing to dissuade our view of it as a “reimbursement optimization tool”.

One of Dr. Gawande’s insight as to why doctors have some much trouble liking the new way of computer documentation of everything is that computers do not handle “surprises” very well. In seeking a diagnosis and determining treatment, not all doctor’s questions and certainly not all patients’ answers can be accurately recorded with a simple click in a box. The computer thrives on all those clicks in all those boxes. Doctors do not. We often meander around in our conversations with a patient guided by chance comments or even subtle physical clues. If we elicit a “surprise” we can pursue it much more intelligently and enlightening than the computer can document it. In Gawande’s words computer programs are “brittle, bureaucratic, inflexible, designed for large data bases, rule-based, inflexible, and very difficult to adapt”; in short, unable to handle “surprises” easily. 

Defenders of Epic view their efforts as optimization of the medical care process – “reconfiguring various functions according to feedback from users.” An Epic VP labeled that as the “Revenge of the Ancillaries”. The “users” of an MRI or a X-ray request from a doctor are radiology techs or radiology department secretaries.  The questions they want answered may have little clinical importance but have multiplied within the computer screen requisition that now requires more data entry, more reading, and more in-the-box clicking by the doctor. Some computer programs allow the doctor to delegate ordering tasks, some don’t, and some, like Epic, allow delegating some tasks but not for others. Doctors who are now embracing the delegation of tasks by hiring nurse practitioners and physician assistants are confronting computer programs which are restricting delegation.

Studies have documented that doctors spend two hours in front of a computer for every one hour in front of a patient. In response a new “delegated person”, a medical scribe, has been hired by some doctors. A medical scribe is a non-physician that observes the doctor-patient visit and enters information into the computer freeing the doctor up to maximize the face-to-face patient interaction. (In Quality Management, aka Quality Assurance or Performance Improvement, we call this a “work around” – a human adaptation to bypass a problem in a operating system.)

The Clinical Director of the Partners Epic system defends its as being “for the patients, not the doctors.” Patients gain more access to their medical records like their lab test results, their medications, summary of their visits, and increased opportunity for communication with their physicians. Patient access to their medical record is via a “patient portal”; often touted as a successful way to build a practice and be a modern practitioner. Unfortunately the patient portal has not been the slam dunk it was expected to be. It certainly has not been in our pediatric practice. “Why Are Patient Portals Such Duds?” and other recent reviews describe some of both doctor and patient barriers to their adoption.

The Clinical Director of Partners Epic takes the long view that patients will eventually use the EMR as currently hoped and hyped. We shall see, and in the meantime I hope that fewer practicing primary care doctors experience “burn out” and that fewer new medical school graduates shun primary care practice.

References:
1. New Yorker Magazine, November 12, 2018, Atul Gawande


Vol. 195 July 1, 2018 BIG DATA and a whiff of AI in health care

July 1, 2018

Hub thumbnail 2015

“When it comes to health data, Watson hasn’t been much help.”
-STATNEWS, Ross and Swetlitz. Bos Globe 6/18/18

This week all the newspapers (at least in Massachusetts) have been abuzz with the announcement that Atul Gawande, MD has been picked by three moneyed titans of innovation to head their new company to revolutionize health care. Optimism, promise, and hope is in the air! Kind of like when IBM presented Watson, its supercomputer, in 2015 as the tool to provide workable insights into the financial and clinical dilemmas of U.S. hospitals in 2015 via Watson Health.

How is that working out? Watson Health has access to data on tens of millions patients, in part by spending $9 billion to acquire other companies. It’s initial focus was on developing workable products in oncology, designed to help physicians individualize cancer treatments. “With these acquisitions, IBM will be one of the world’s leading health data, analytics, and insights companies, and the only one that can deliver the unique cognitive capabilities of the Watson platform”, said the general manager of Watson Health in 2015.

They (the newly merged companies) struggled with the basic step of learning about the different forms of cancer and the rapidly changing landscape of treatments. Last week Watson Health laid off people partly because, according to some, even Watson had difficulty in digesting all that data. “…They also don’t understand the generation of information, and how it is used, and whether they can do something different with it,” said Robert Burns, professor of health management at U Penn Wharton School. You can almost hear every primary care physician that is struggling to get their new EMR system to give him/her more information and less data cheering loudly in the background, “We couldn’t have said it better!”

The goal of a great deal of innovative technology in health care is “ “zero patient harm”. if Atul can’t do it all with his surgical checklists and Watson can’t do it all with data from tens of millions of patients , what/who can? How about Artificial Intelligence (AI), aka “machine learning”? AI and machine learning is the converting of data into information without the need for human programmers. For instance, if the computer views enough pictures of different dogs, it will learn to correctly identify a cocker spaniel. I think a real test of AI would be to see if it can recognize a Labradoodle,  or any other of the many poodle cross breeds. (Don’t you sometimes worry about the moral standards of poodles that seem to be eager to mate with any kind of passing breed?)

The building of knowledge from patterns in data, both visual and language, is labeled “computer vision”. In some medical studies “computer vision” is used to monitor actual bedside events and identify omissions or non-compliance in procedures. It has apparently improved rapidly beyond just identifying dogs or skin rashes because of “deep learning”: a type of machine learning that uses “multilayered neural networks whose hierarchical computational design is partly inspired by biologic neutron’s structure.” (1)  Got that? Think Google’s self-driving cars. “Computer vision may soon bring us closer to resolving a seemingly intractable mismatch between the growing complexity of intended clinician behavior and human vulnerability to error.” (2)

So, the effort to cut the Gordian knot of patient safety and cost-effective medicine continues. I suspect that the three titans of innovation have turned to Atul Gawande, a health care innovator who successfully uses clinical insight and re-education to effect change, because they recognize the limitations that are becoming more apparent in big data.

  1.  NEJM April 5, 2018 378:14; 1271-2
  2. Ibid.

%d bloggers like this: