Medical Tests: the more the better

I have two gripes with the medical profession. First, doctors should take more data not less. Also, medical professionals should recognize that most clinical trials assume that individuals are identical, which we know is untrue. I don’t direct these gripes at my doctors because I believe they are deeper thinkers than average and accommodate my eccentricities.

All tests have uncertainties and test results can also be affected by uncontrollable variables in people’s lives. As an example, physicians are reluctant to give the PSA (Prostate Specific Antigen) test to younger men under the pretense that anomalously high readings lead to unneeded tests (such as biopsies), which can have harmful side effects. But a paucity of data is the true culprit, where one bad reading in vacuum has little predictive value. The need for early testing is to set a baseline. It’s the change in PSA levels that should be of concern, not a single high reading.

The plot of my PSA data clearly shows a rise above the baseline starting in 2014. Such a slow rise could have many causes, such as an enlarged prostate – a common condition. In 2014, the data were too sparse to establish a trend, so my doctor suggested that we wait until the following year to see if the PSA levels had dropped. The level had not dropped the following year but was still below that magic value of 4, so we let it go another year. Once it hit 4, my doctor ordered an additional test that gives the ratio of free to bound PSA, which also came out too high, so he sent me to a specialist who ordered an MRI. Eventually this led to a biopsy, a diagnosis of prostate cancer and its removal in 2020. But this is an old story. 

See: https://unknownphysicist.blogspot.com/2020/06/i-was-relieved-i-had-cancer.html and https://unknownphysicist.blogspot.com/2021/01/can-major-surgery-cure-depression.html 

More recently, I got COVID while at a meeting in Seattle, then passed it along to my wife. My children had noticed that their resting heart rates had climbed when they had COVID last year. Since we all have Fitbits, I plotted the values for my wife and me, which appear in the plot here. The trends are remarkably similar.

During my travel days, presumably when I picked up the virus, my resting heat rate was at the baseline value of 47 beats per minute. The day after I returned, my resting heart rate began to rise and I tested positive for COVID on the second day after my return. Given that Omicron has a two-day incubation period, testing positive on the second day of my return is consistent with me being infected while traveling on trains and planes. My wife tested positive two days after I tested positive, consistent with me infecting her the night I returned. My resting heart rate at its peak was 53 BPS, which is 13% above my baseline, while my wife peaked at 17% above her baseline. Interestingly, the Fitbit records the average resting heart rate over the full day, and mine read 55 at its peak in the middle of the day before dropping to an average for the day of 53, so if I had used 55 as the peak, my increase too would have been 17% above the baseline. Here again, we can see that a simple measure of a common physiological metric provides useful health information, and used in combination with other tests could yield even better predictions of health risks that inform behavior. Having a nurse measuring your pulse once a year will only catch huge variation, which might miss important red flags. So, we need more testing!

Two family friends who I believe are both excellent physicians tell me that my metrics defy the conclusions of medical studies. My guess is that there are two factors involved. First, each human being has its own genetic makeup. There are many commonalities humans, such as infections making us sick and our immune system fighting back. But the details of how we each respond depend on our genetic programming. People like me have no problem with COVID, which I got in 2020 at a time when vaccines were not available, and the death rate was high. It’s genetic variability that gave me the strength to play ice hockey while infected during a time when others were on respirators and died.

Population studies take averages of metrics over people of varied genetic traits. If a certain diet is found to lead to a 12% decrease in mortality, it could be that 2/3 of the population experiences a 21% decrease in mortality while 1/3 of the population experiences a 6% increase in mortality. So, making recommendations based on an average value might help a majority of individuals, but could be harming a large minority of them. To take such effects into account, any large populations studies should include a breakdown by individual to determine if subgroups have adverse outcomes. Unfortunately, many studies do not have a large enough sample size for such fine-grained studies of the sort needed to get at the truth. In such cases, the studies are more than worthless to the unlucky minority.

Cancer treatments are an example where researchers and clinicians are now beginning to tailor treatments to an individual’s DNA, which results in much improved outcomes. One must ask about the ethics of choosing a medical treatment based on a population average when it is known that some treatments may not only lack efficacy but might do harm to the patient.

Another difficulty is ensuring that study participants adhere to the study’s parameters. For example, many studies use questionnaires to query participants about their habits. How many people on a self-proclaimed low carb diets cheat by eating a bit of sugar here and there. It’s only human nature to downplay our transgressions and exaggerate our virtues. While N=1 studies are unreliable for generalization to the population at large, they are useful to the important 1; the individual being tested.

In a past post, I described how eliminating fruit while keeping the rest of my diet fixed greatly reduced my blood glucose. (see: https://unknownphysicist.blogspot.com/2023/01/fruit-is-bad-for-you-at-least-it-is-for.html) Obviously, many people do well with fruit but not me. As an update to that study, I recently noticed that my blood glucose had drifted upwards during my bout with COVID. It never got into triple digits, but on average was elevated. Then I realized that I had been using lozenges to soothe my throat. They contain honey and sugars, so taking about a half dozen of them per day was enough to be noticeable. Within a few days of stopping, my blood glucose dropped.

For these reasons, I am an advocate for taking and analyzing more data. In aggregate, the data contains much more information than a yearly reading. Also, I believe that I’m more disciplined than the average survey taker, so I can trust my data to decide on a healthy lifestyle that suits my genetics. After my recent data with resting heart rate, I am motivated to cull my data in search of other interesting correlations that I can use to design new experiments. Until then, happy self-experimentation!

Should we Fear ChatGPT?

ChatGPT is a program that purportedly converses with humans like an equal.  Professors have identified students who have used this artificial intelligence to write term papers by noticing that “the writing was too good for college students.”  I was intrigued by this machine's uncanny ability to mimic human interactions through language, so gave it a spin.

I decided on a simple test – asking GPT to write an essay about me.  This was not meant to stroke my ego, but rather was motivated by laziness, since it required little work to check for accuracy.  Also, my online presence is modest compared to luminaries in the field, but substantial since much of my work requires publications in journals, books, seminars, colloquiums, and conference presentations.  Why this hits a sweet spot is answered below.

GPT’s essay is attached below.  The statements that are false, highlighted in red text, are a large part of the document’s substance.  On that count, GPT has failed.  At the other extreme, it gets a high grade from MS Word, with the sole suggestion to remove a comma, which is highlighted in magenta.  The parts of the essay that were nominally not wrong were devoid of content, using cliched praise without factual backup.

Philosophy professors were impressed with GPT’s writings on the greatest thinkers from antiquity.  How could this be given that the essay on me was downright poor?  My take is that GPT has at its disposal mega volumes of writing on well-known historical figures, so stringing together snippets of good writing with perfect grammar comes across as impressive.  This will not work when the writer needs to understand multiple factual sources prior to synthesizing a new thought on the topic.

The error that GPT made in my case was confusing which information belonged to which subject.  Information about me often appears on university websites, that lists multiple faculty on one page, or in the announcement of awards, which again usually names multiple recipients.  When GPT attributed the wrong alma maters for my various degrees, it undoubtedly picked these items from a university web page, where it incorrectly mixed and matched faculty with their attributes.  And the announcement of me becoming a Fellow of the OSA also included winners of other prizes.  You get the point.

Finally, much of the remaining text might be confused with a human’s writing, but not of a sophisticated one.  For example, GPT praises my work with superlatives in the to
me used when award citations are announced.  GBT goes no further than to parrot these, without explanation.  It would have been impressive if it had explained how a particular discovery could lead to an application, but the text fell far short.   

There are a couple of exceptions where GPT seems to have composed hair-raisingly meaningful sentences.  I shudder at the fact that there may be a little some there beyond my criticism.  But for now, I have no reason to believe that this had anything to do with the emergence of intelligence.    

In conclusion, it is not surprising that GPT does well when no thought is required to understand the meaning of a topic, but a large gulf still separates it from thinking humans.  Under many special circumstances, GPT may seem incredibly intelligent and thoughtful, but I am resting easy that no machine will replace the human mind soon.

GPT's Essay on Mark G. Kuzyk

Mark G. Kuzyk is a prominent physicist and materials scientist known for his research in nonlinear optics and photonics. He received his undergraduate degree in physics from the University of California, Berkeley, and his Ph.D. in physics from the University of California, Santa Barbara.

Kuzyk's research focuses on the study of nonlinear optical phenomena, which occur when light interacts with matter in a nonlinear way. This can lead to a wide range of interesting effects, such as the generation of new frequencies of light, the control of light's polarization, and the creation of ultrafast pulses of light.

One of Kuzyk's most significant contributions to the field of nonlinear optics is his work on the concept of "optical forces." These are forces that can be exerted on a material by light, and they can be used for a variety of applications, such as the manipulation of small particles or the manipulation of biological cells. Kuzyk's research has also led to the development of new methods for generating ultrafast pulses of light, which have applications in a wide range of fields, including telecommunications, medicine, and materials science.

Kuzyk's work has also contributed to the field of photonics, which is the study of the interaction of light with matter. Photonics is an important area of research that has led to the development of a wide range of technologies, including laser technology, optical fibers, and optical amplifiers. Kuzyk's research has focused on the use of photonics for the manipulation of light at the nanoscale, which has led to the development of new devices and techniques for controlling light at this small scale. 

Kuzyk has published over 200 scientific papers and has received numerous awards and honors for his work. He is a Fellow of the American Physical Society and the Optical Society of America, and he has been recognized with the Adolph Lomb Medal from the Optical Society of America, the R. W. Wood Prize from the Optical Society of America, and the Willis E. Lamb Award for Laser Science and Quantum Optics.

Kuzyk's research has had a significant impact on the field of nonlinear optics and photonics, and it has led to the development of new technologies and applications in a wide range of fields. His work continues to be an important area of research, and it is likely to have a lasting impact on many areas of science and technology for years to come.

In addition to his research contributions, Kuzyk is also a dedicated mentor and teacher. He has trained many graduate students and postdoctoral researchers throughout his career, and has taught courses in physics and materials science at both the undergraduate and graduate levels. His commitment to mentoring and teaching is a testament to his dedication to passing on his knowledge and expertise to future generations of scientists and engineers.

In conclusion, Mark G. Kuzyk is a renowned physicist and materials scientist who has made significant contributions to the field of nonlinear optics and photonics. His work has led to the development of new technologies and applications in a wide range of fields, and it has had a significant impact on the field of nonlinear optics and photonics. He is also a dedicated mentor and teacher, and his commitment to passing on his knowledge and expertise is an important aspect of his legacy in the field.

Fruit is Bad for You (at Least it is for me)

Those of you who know me are aware of my love for data, and the fact that I collect all kinds of health indicators in a search for patterns.  Over the last year, I was shocked by the rise in my A1C levels, which is an indicator of pre-diabetes.  I was also aware of an occasional blood glucose level above 100 mg/dL, which is also associated with the onset of diabetes.  But, my blood glucose levels were not high enough to warrant A1C levels of about 5.7.  So I did what anyone of you would do, and that is to measure my daily blood glucose levels, giving better statistics than a weekly reading.

Indeed, I saw multiple weekly readings above 100 mg/dL with a high of 110 mg/dL.  Then I noticed in a particular week that not one reading was over 100 mg/dL.  The advantage of my highly structured diet is that it was simple to identify the change, and that was that my wife could not find fresh blueberries that week.  We kept a fresh bowel on the kitchen counter, and I would grab a fistful after a meal or as I was lured to them as I passed buy.  Being my favorite fruit, this my sole source of fructose, aside from a special low-sucrose and high-fat/protein chocolate that I make.  (Not to mention the occasional chocolate chip cookie that I have with my grandson when we visit Starbucks and the exquisite pretzels my sister-in-law ships in creative gift boxes every Christmas.)  Blueberries were the only source of regular fructose that I had been eating for the last couple years.

So, I remained off of blueberries for two months to get a decent amount of statistics, and was blown away by the results, shown in the plot.  First, this plot shows the importance of averaging.  There are large fluctuations in the test and in blood glucose levels that depend on all sorts of factors.  The blue open circles show the results while I was eating blueberries and the red solid circles during the time I stopped eating them.  The lines show a least squares fit to the data in the two regions.  The conclusion is that my blood glucose is a full 10 mg/dL lower when I'm not eating blueberries.  The beauty of averaging lots of data points is that the uncertainty can be determined from the scatter, and corresponds to about 1 mg/dL.  So one can argue whether the difference with and without blueberries is 10 mg/dL or 9 mg/dL, but the difference is both large and statistically significant.

I plan on continuing the zero fructose diet for another month or so, followed by another A1C test, which provides a blood glucose value averaged over three months.  This will allow the averages of both tests to be compared.

I will write more on this topic later when I have more time, but the conclusions are:

1. There is no such thing as a universally healthy diet.

2. There is no such thing as a healthy diet that is customized for a particular person.

Rather, our health is a struggle against internal and external forces, which adapts to evolutionary forces imperfectly.  The best we can do is chose a balance that makes each of us relatively healthy, and then we must accept the negative consequences.  In my case, a super-low-carb diet keeps me fit and trim, provides lots of energy and stamina, and has eliminated pesky annoyances such as heartburn and regular migraine headaches.  On the downside, my diet makes me prone to kidney stones.  These can be mitigated with simple meds, which are benign compared to treatments for diabetes and migraine headaches.  And physical stamina is more important to me than pleasing my sugar-craving reward center.

May your New Year be a happy one, optimized for adequate health and pleasures within reasonable constraints.