Can Google Predict if You Have Cancer?

If Google can predict cancer, should they?

I was listening to a podcast the other day and was introduced to the idea that google search trends are a very powerful tool in predicting many different things.  Some of these have real life implications in medicine.  I looked it up and sure enough research has been done to see if specific search terms can predict if a user is developing certain medical conditions.  I thought it would be interesting to explore this topic.

In the Journal of Oncology Practicean article was published looking at the ability of google searches to predict pancreatic cancer.  The researchers looked for people who queried the internet for precursor symptoms to pancreatic cancer such as jaundice or itchy skin, light stool, dark urine, sudden weight loss, and abdominal swelling or pressure among other symptoms. They then cross referenced this with users who were eventually diagnosed with pancreatic cancer. Their final results showed “that we can identify 5% to 15% of cases, while preserving extremely low false-positive rates (0.00001 to 0.0001).” In the case of pancreatic cancer this is important because early detection can translate to longer survival rates.

Another study done in the JAMA Dermatology journal sought to determine if internet searches correlate with incidence and mortality rates of common cancers.  They came to the conclusion that “population-level internet search behavior may be a valuable real-time tool to estimate cancer incidence and mortality rates” in colon cancer, lung cancer, lymphoma, melanoma and thyroid cancer. This positive correlation is groundbreaking and can have real-world utility.  While this study was population based, if we were able to identify these patients through searches and inform them to seek care and screening tests, cancers could be found early and there would be decreased illness burden and death.



Lest we think that data mining can yield only positive results, let’s look at one more article where the findings were not as compelling.  In Nature in 2013, an article was published showing google’s flu trend drastically overestimated peak flu levels when compared with the CDC’s real world data.  It is a sobering reminder that as “flu-tracking techniques based on mining of web data and on social media proliferate… they will complement, but not substitute for, traditional epidemiological surveillance networks.”  While this is an example of where data mining failed, this was in a more public health related capacity and not on the individual level to predict cancer.  

So based on the studies above, it does appear that Google has the data and ability to predict if at least some individuals were at an increased risk for cancer.  What may be the downside of this though?  First, arguments against the practice of data mining should be put aside considering this is already done.  We’ll forgo that discussion.  There is the worry of false positives and alarming those who may not have cancer, even though this may be rare.  In my opinion this would be worth it to save a few lives (and the symptoms those without cancer are googling should probably be seen by a doctor anyway).  

What if something was missed? Obviously if people are relying on being told if they cancer or not, there may be repercussions if they are not told.  Then there is the worry that people may rely more on google than their doctors.  As the Nature  study above states, googling should compliment but not substitute the evaluation of a doctor.  I think all of these are legitimate concerns.

In conclusion, I think the possibility of having Google predict cancer is an exciting frontier to explore.  There are some downsides that need to be considered though. Google and other big name tech companies are already mining our data and using it to make our web experiences more tailored to us an individuals.  Should this data be used to improve our health?  Do these companies have an ethical duty to warn a person if their search histories are in line with a possible cancer? Are there other downsides? I’d like to know your thoughts.  Comment below and add to the conversation.



Sacrificing Customer Service for Quality Metrics?

A greater emphasis is being placed on meeting quality metrics than customer service for physicians. Is this a good thing?

A few weeks ago I received an email from the Independent Physicians Association (IPA) I am a part of.  It was announcing there would be a change in their payment model with a bigger emphasis on “quality.”  Quality refers to meeting certain evidence-based measurable categories (also called metrics) to assure doctors are practicing medicine well.  Examples include getting a majority of blood pressures under 140/90, getting diabetes under control with an a1c under 8 and getting patients over 50 screened for colon cancer.  Essentially, through chart reviews, the IPA is able to see how well I do in these and other categories and adjust my payment based on results.

Within this email was further information on how this payment was going to be disbursed.  Money that used to be given based on patient satisfaction was being moved into the quality category.  Essentially a greater emphasis was being placed on quality metrics than patient satisfaction. This initially irked me because I do very well in the patient satisfaction department.  I take time and care for my patients with a genuine attention and this is reflected on my patient satisfaction scores.

I also do my best with the quality department but sometimes find it difficult to get all patients within the metrics set. Part of this is because some of these quality metrics are outside of my control.  For example, I can refer a person for a colonoscopy but I cannot make them get it done.  I can adjust medications for diabetes and blood pressure but if the medication is not taken or the person is not adhering to a proper diet and exercising, their numbers may not improve.  I feel like patient satisfaction is under my control whereas metrics may not be.

So, why the shift?

It is extremely important to provide a quality product that improves and lengthens lives.  This is what the world looks at when judging how well doctors are doing.  Customer service is secondary.  Both are important and ideally, a doctor provides both, but when it comes down to it, our job is in health and the best way to judge this is through these quality metrics.



My Take

In the long run, this will be a good thing. If we meet the mark set for each of these metrics, patients will benefit with less death and disability from disease processes. I hope that doctors will not throw their customer service skills by the wayside and solely focus on achieving the quality metrics.  My biggest concern with this shift is that doctors may start sacrificing customer service for quality metrics.

Personally, I will continue to provide excellent customer service.  This shift has motivated me to make a more concerted effort to make sure I meet the measures.  I will likely be a little more assertive in convincing my patients to get tests done and make medication changes to improve control of their disease.  I need to be aware of doing this in a gentle and non-coercive manner to maintain patient satisfaction. So for me, this will be a good thing and there will be an improvement.

So don’t be surprised if your doctor starts to work harder to control your blood pressure, get your A1c down for your diabetes or get certain tests done.  Hopefully, this is still done in a respectful manner that shows superb customer service as well. This will translate to a more healthy life for you. With all this, I’m curious what you think. Comment below and let me know.



The Value of Physician Extenders

PAs and Nurse Practitioners are a great addition to the medical team. See why.

We were sitting around the table at our monthly office meeting. Our new Physician Assistant (PA) brought up an encounter she had with a patient. The patient was unsatisfied with seeing her because he felt he was getting poor care. He wanted to see the doctor for his care. This led me to think about the value of PAs and nurse practitioners. The new term “physician extenders” has been put into place to try to convey the value of these practitioners. A physician extender includes any healthcare provider who is not a physician but is able to perform the typical activities of a physician. This includes PAs and nurse practitioners (NPs) who work in collaboration with an overseeing physician.

These practitioners used to be referred to as “mid levels,” however this conveys an inferiority which is not the case. PAs and nurse practitioners are a valuable part of the medical team. Many offices (ours included) are moving towards having a combination of physicians and physician extenders to provide care given the value and quality of care they provide.  Physician extenders can do just about anything a doctor can.  They can take medical histories, perform physical examinations, order diagnostic tests and studies, diagnose medical conditions, and implement a treatment plan in consultation with a supervising physician.  They can prescribe medications in all states and counsel patients on health promotion.

I must admit that I didn’t use to have such fond feelings of physician extenders. Mostly this was jealousy because they were able to perform the same activities as me as a physician with less training. This changed after I worked more closely with them. My experience showed me that they were very capable primary care providers. They were experienced and competent and were able to function independently in a primary care roll to provide excellent care.



PAs are the first type of physician extender.  PAs were only recently recognized as primary care providers with the Affordable Care Act. They can work as generalists such as in Family Medicine or they can specialize.  Their training is similar to that of a doctor including in classroom didactics and hands on clinicals.  It typically takes 2 years to complete and is broad covering all areas of medicine making them ideal primary care providers. They have a rigorous certification system consisting of completing a PA program and passing a national certification exam.  They must also complete continuing education courses throughout their career to maintain their certification. They work closely with physicians as a collaborative team.  

Nurse Practitioners are the second type of physician extender and they are very similar.  NPs are initially trained as registered nurses and then complete a advanced master’s or doctoral degree program. These programs can take 1 to 3 years to complete.  They undergo similar didactic and clinical courses to medical school for a physician. Their education is extensive and prepares them well to participate in primary care and specialty care. They have to complete their program and undergo national certification.  They too need to complete continuing medical education courses throughout their career and work closely with physicians as a team.

As you can see, Physician Extenders are capable medical care practitioners and are a valuable member of any medical team. Medical care that used to be confined to only a physician has now extended to include these providers. There will always be those who want to see a physician. In today’s medical world, this will not always be possible.  You will likely find yourself being seen by a physician extender at your doctor’s office or in the hospital at some point. Do not see this as a decrease in your care. To the contrary, this is allowing doctors to extend their reach in caring for more patients.  PA’s and nurse practitioners are a wonderful addition to the medical team and are able to function in a collaborative and independent role to provide excellent care.  If you currently see a physician extender make sure you thank them for their great care.



The Mindlessness of E-Prescribing

Is the ease of e-prescribing causing problems?

E-prescribing is an amazing innovation that saves me time with almost every patient.  Instead of having to write out a prescription and hand to the patient to take to the pharmacy, I am able to click a few buttons and have it electronically sent in.  This of course comes with its rare pitfalls such as defaults and errors not caught but overall has made my life much easier.  This ease was extended even further when I was introduced to e-prescribing of controlled substances.  

If you are not familiar with it, e-prescribing of controlled substances refers to the ability to send in a controlled substance over the internet directly to a pharmacy.  First a brief primer on controlled substances and writing for them.  Controlled medications include medications with the potential for abuse such as narcotics like Norco (hydrocodone) and benzodiazepines such as Xanax (alprazolam). Since controlled medications can be abused and are sought on the streets, it takes a specialized prescription pad to write for them called a triplicate prescription. This piece of paper contains a watermark and microprint for security reasons.  It used to be an actually three page “triplicate” with one copy filed in the chart, one sent with the patient and the last sent to the state controlling agency.  With the advent of two factor authentication on phones with a password, this was changed.  Controlled prescriptions became digital.  

Here is the process now: I order a controlled prescription on my computer and send it to the pharmacy.  A popup then appears asking for an authorization number.  I break out my phone where I use my fingerprint to open the device and open a secure app that has a 6 digit number that refreshes every 30 seconds. This number is tied to my online identity. After entering the number in the EMR (electronic medical record), I then enter my EMR password one more time and the prescription is sent. While this sounds very cumbersome, it is not and typically takes 10 seconds at most.

In my opinion the above process is much more secure as well. It is more difficult to go through the 2 layers of passwords (EMR login by using one of our computers and fingerprint on phone which is on my person all the time) than to get access to one of my prescription pads and forge my signature (even though I have a pretty sweet signature). Because of this, I was feeling very good about this process… until recently.

Last week we had a problem with our internet.  When you use a cloud based EMR like we do, this is a major issue and makes any computerized charting impossible. We couldn’t even get to the log on screen. With this we resigned to using paper to keep our charts for the day. Fortunately the internet issue was short lived and back up the next day, but in the time it was out I had a revelation: E-prescribing is not always a good thing.



While the computers were down I had to write a controlled prescription the old way.  I fished out an old triplicate prescription and hand wrote the medication.  I had to write the patient’s name, date of birth and the date.  I had to write the name of the medication, the dose, the directions and the dispense amount.  I had to check a box confirming the dispense amount.  I had to write an expiration date for the prescription. I had to confirm the number of medications prescribed. And lastly, I had to recheck everything to make sure there were no errors and sign my name. This process triggered something inside me.

I had become numb to the process of e-prescribing.  Hand writing the controlled prescription made me feel something down deep in my gut.  It made me do a double check to make sure the medication was appropriate and in the patient’s best interest.  E-prescribing didn’t do this.  Clicking a button was not the same as signing my signature in ink. It made me question: Does e-prescribing make us write more prescriptions?  Is it contributing to the narcotic problem instead of helping it?

I did some research to find if any studies had been done on this and came up dry.  Let me make a bold statement though.  I believe that e-prescribing can lead to overprescribing due to its ease.  Here’s why. I have read multiple studies that show people spend more when they use a credit card vs using cash.  Psychologists have concluded that this is because handing over cash creates a “pain of paying” due to the direct action of surrendering your hard earned money.  This is in contrast to using a credit card which is only plastic remotely connected to money.  

Let’s apply this to prescribing. When I e-prescribe I go through a couple clicks to send in a prescription.  When I hand write a prescription I have to go through a more lengthy process that requires my physical signature.  I feel a (to coin a new phrase) “pain of prescribing” that makes me make sure the medication is appropriate.  While this has implications on prescribing in general, it has more serious implications with e-prescribing of controlled substances.  

Despite all this, with the use of EMRs and abundance of e-prescribing, we will not be going back to hand writing prescriptions.  Technology is making it obsolete.  So I and other physicians need to create a process that brings the “pain of prescribing” back. I’m not sure there is a universal way this can be done.  I’m not sure it can even be done.  So, I will need to take care to make sure medications I prescribe are safe, necessary and correctly written.  Every time I hover over the “sign” button with the mouse I will ask myself “Is this the best option for this patient?”



EMR Use and the Future

Computerized records and its advantages and disadvantages.

A patient came into my office the other day complaining of chest pain.  This is a serious symptom that needs to be evaluated fully so as not to miss a serious causes.  While he was in the office, I was quickly able to access his last cardiology note including recent stress test and echocardiogram along with his most recent labs and xrays through my EMR (Electronic Medical Record or computerized records system).  I was able to rule out many serious causes with the access I had to his health record at the tip of my fingers.  I did an EKG in the office and was able to access his last one and compare it.  It turned out to be nothing serious but if needed I could have even ordered lab tests which I would have had access to as soon as they were available through a push notification on my phone from my EMR’s mobile app.  This is merely one instance but it highlights just a few of the advantages with incorporation of EMR technology into mainstream medical practice.

I have always been a fan of technology and the power we are able to leverage when we incorporate it into our lives.  Just look at that cell phone in your hands and all that you are able to accomplish with it.  In the time it takes me to walk from my car into my office I can check my email, scroll through some facebook posts, see if my team won the game last night and know the weather for the day.  When this technology is used in medicine its benefits can be amazing.  Things I simply cannot know, such as obscure interactions between medications, are readily available.  

Despite the benefits of an EMR, there are still doctors that choose to hold out and refuse to move into the 21st century. In an online webinar I attended last month on how to work cooperatively with my EMR, I was shocked when one of my physician colleagues was proud of not converting to an EMR and therefore avoiding some of the “hassles” with it. Some doctors are perfectly satisfied writing out their notes and keeping physical charts that take up the space of a small closet.

Reasons cited for holding out include: time consuming note entry, interference with face to face care, lack of computer skills to maneuver through an electronic chart and expense, among other complaints.  Some older doctors have even retired when faced with the possibility of converting to an EMR.  I am not going to lie, the above concerns are valid.  Computers can and often do take away from a patient interaction.  It is harder to type than write (for some people).  EMRs are very expensive.



Here’s the thing though: Medicine has progressed into a digital age and it’s not going back.  The future of medicine will move closer and closer to an all computerized paperless system.  The doctors that refuse to hop on this train are going to become irrelevant and disconnected from patients in an increasingly online and computer based society.   According to dashboard.healthit.gov, since 2008, office-based physician adoption of an EHR has nearly doubled, from 42% to 87%.  

First, some background. The dramatic increase in EMR adoption was mostly because of a program called Meaningful Use as part of the American Reinvestment & Recovery Act (ARRA) in 2009. While this program promised cash incentives to help offset the cost of EHR adoption, the metrics to meet were often confusing and difficult to access with some EMRs.  Many doctors and practices adopted EMRs without receiving the incentive.

As of earlier this year there were about 1100 vendors that offer an EHR.  Many of these are start up companies trying to get a piece of the EMR pie that promises big returns as the medical community becomes more digital.  Many of these EMR vendors are unfortunately not in a place keep up with the mounting regulations that are being placed on EMRs and in the future will be bought out or go out of business.   According to Medical Economics magazine, 26% of doctors doubt their EMR vendor will be in business in 5 years.



So where does this leave us? The Meaningful Use program is no longer active, but it has left us with a more widespread adoption of EMRs (which in my opinion is a good thing).  It has crossed the point of no return.  The future will see consolidation of a lot of these EMRs and there will likely come a time when having an EMR will be federally regulated and mandated to participate in certain insurance programs and Medicare.

How do we solve the concerns voiced by the holdouts?  First, the doctors that are holding out and still using paper are still good doctors.  We just need to provide a way for them to incorporate into the electronic record keeping system as easily and pain free as possible.  Incentives should be given to offset the cost (with easy to attain goals for using an EMR).  Data entry needs to be made easy and not time consuming through the use of a scribe or transcription. Classes need to be offered on how to properly navigate an EMR and use it cooperatively while minimizing any negative effects on patient interaction.  All of these things have been mastered and are done daily by other EMR users.  We need to rely on their expertise and expand it to all.

Lastly, how does this affect patients?  With increasing adoption and interaction between EMRs, the patient will definitely benefit.  Having access to more information on a patient is always a good thing.  We can avoid the serious consequences of medication interactions and know medical histories to enlighten our medical decision making.  We can avoid repeating vaccines or tests when they have already been done and decrease costs.  We can have immediate access to other physician and hospital notes to know about their decision making and why certain medications are being used.  The benefits are numerous.  Yes, there are some minor drawbacks, but hopefully these have been or are being worked on. So if you are a patient reading this, choose a physician that uses an EMR.  If your current doctor doesn’t use an EMR, encourage him or her to start.  If he or she does, then be thankful for all of the benefits (seen and unseen) that it is providing in your medical care.