How artificial intelligence will make my work easier

A recent article in the Pittsburgh Post-Gazette outlined the various ways that artificial intelligence (AI) is improving health care in Pennsylvania. For example, AI software can serve as a "virtual scribe," listening to the doctor-patient conversation during an office visit and drafting a note, freeing the doctor to focus on the patient for 100% of the time. AI can "draft letters to health insurers on behalf of patients who need specialty medications, medical equipment or other care that's not standard in their insurance benefits," saving time for doctors and office staff. In the future, AI could respond to patient portal messages, triage phone calls, or even suggest diagnoses.

That all sounds great, but a lot of people thought that electronic health records would make clinicians' work easier when they were implemented, too, and we know how that worked out (or didn't). So what's the evidence that AI will actually deliver on its promise in health care?

A case study published in NEJM Catalyst described Kaiser Permanente (KP) Medical Group's implementation of AI scribes using smartphone microphones to document more than 300,000 patient encounters across all medical specialties:

The response from physicians who have used the ambient AI scribe service has been favorable; they cite the technology’s capability to facilitate more personal, meaningful, and effective patient interactions and to reduce the burden of after-hours clerical work. In addition, early assessments of patient feedback have been positive, with some describing improved interaction with their physicians. Early evaluation metrics, based on an existing tool that evaluates the quality of human-generated scribe notes, find that ambient AI use produces high-quality clinical documentation for physicians’ editing. Further statistical analyses after AI scribe implementation also find that usage is linked with reduced time spent in documentation and in the EHR.

How about the electronic inbox and the increasing burden of responding to patient portal messages? One approach to streamlining this workload is making sure that requests are routed to the right person in the practice, often front office staff or nurses rather than physicians. A research letter in JAMA Network Open illustrated the content of nearly 5 million electronic messages from patients received by KP Northern California between April and August 2023 and classified using real-time natural language processing. In a pilot quality improvement study in primary care and gastroenterology practices at Stanford Health Care, responses to messages were drafted by a large language model (LLM), and clinicians (physicians, advanced practice providers, nurses, and clinical pharmacists) were surveyed pre- and post-program implementation. Although the LLM drafted responses to 75% of messages, the average clinician used the draft only 20% of the time, with primary care clinical pharmacists using them the most (44%). There was no change in the amount of time clinicians spent managing their inboxes. However, task load and work exhaustion scores declined in the post-survey, and many clinicians appreciated that editing a draft required less effort than writing a response from scratch.

As a medical editor and author of hundreds of published papers, that last point makes sense - leading me finally to the use of AI outside of the clinic to draft scientific review articles. Currently, most journals either prohibit AI use or require authors to describe exactly how AI was used to develop a manuscript. A recent study compared papers on 3 topics related to bone health (Alzheimer's disease, fracture healing regulation, and effects if COVID-19) that were written by 1) a human only; 2) ChatGPT only; and 3) a human and ChatGPT working together ("AI-assisted"). Unsurprisingly, the most accurate papers that required the least amount of time to write were AI-assisted (human-supervised?) where the AI was given not only a prompt but an outline and references. I'm still waiting to see the first American Family Physician submission where the authors were assisted by AI. It's only a matter of time - unless, of course, it's already happened and I just didn't realize it.

Reducing harms associated with PSA screening

In the U.K. Cluster Randomized Trial for PSA Testing for Prostate Cancer (CAP), more than 400,000 men in primary care practices between 2001 and 2009 were either invited to receive a single PSA screening test or usual care. After a median follow-up of 10 years, there were more prostate cancer diagnoses in the screening group, but no effect on prostate cancer mortality. (Men diagnosed with localized prostate cancer were invited to participate in a separate trial comparing active monitoring, surgery, and radiotherapy, which Dr. Middleton discussed previously on the AFP Community Blog.) In a secondary analysis of the CAP trial after 5 more years of follow-up, researchers found a small difference in prostate cancer mortality favoring the screening group (absolute reduction = 0.09%, number needed to screen = 1,111 to prevent one prostate cancer death). However, the screening group was at greater risk of detection of low-grade (Gleason score <=6) cancers that are likely to be clinically unimportant and represent overdiagnosis.

Magnetic resonance imaging (MRI) is increasingly being used as a triage strategy for men with suspected prostate cancer to avoid unnecessary biopsies while still detecting clinically significant cancers at curable stages. A 2024 systematic review and meta-analysis of 72 studies (n=36,366) examined associations between MRI Prostate Imaging Reporting & Data System (PI-RADS) findings, clinical data, and clinically significant prostate cancer. Compared to performing prostate biopsies on all patients, avoiding biopsies in patients with PI-RADS category 3 or lower lesions and PSA density of 0.10 or less reduced unnecessary biopsies by 30% and missed 1 in 17 significant tumors. Increasing the PSA density threshold to 0.15 reduced unnecessary biopsies by 48% and missed 1 in 15 significant tumors.

Several randomized trials are evaluating the effectiveness of a screening strategy combining MRI and a PSA-based biomarker risk score (e.g., 4-Kallikrein Panel) to determine which patients with abnormal PSA levels should be biopsied. The ProScreen trial, involving more than 60,000 Finnish men aged 50 through 63 years, recently reported preliminary results from its baseline screening round. Researchers found that compared to the usual care group, men invited for screening were more likely to have high-grade prostate cancer detected (1 per 196 men) at the cost of also being more likely to have low-grade prostate cancer detected (1 per 909 men). Whether these small differences will lead to meaningful improvements in prostate cancer mortality will not be known for at least several years.

A systematic review published on April 7 in JAMA reiterated the importance of continuing to use cancer-specific mortality as the primary outcome in randomized trials of cancer screening. The authors evaluated the strength of correlations between reductions in stages 3 and 4 cancer (a proposed surrogate outcome for trials of multicancer screening tests) and reductions in cancer-specific mortality in 41 published randomized trials of screening for breast, colorectal, lung, ovarian, prostate, and other cancers. They found high correlations for ovarian and lung cancers, but only a moderate correlation for breast cancer, and weak correlations for colorectal and prostate cancers.

**

This post first appeared on the AFP Community Blog.

Should race be incorporated into weight management decisions?

I have a personal stake in the answer to this question. For most of my adult life, my body mass index (BMI) has ranged between 22 and 25 kg/m2, which is considered to be in the normal range (the threshold for overweight is a BMI of 25, and obesity a BMI of 30). But it turns out that I've been overweight for most of that time if one applies a race-specific definition of overweight (BMI greater than 23) for individuals of Asian descent. Where did this race-based cutpoint come from, and is it still relevant in an era when we generally frown on using race as a surrogate for social determinants of health in making clinical decisions?

The story starts more than two decades years ago, when an expert committee convened by the World Health Organization (WHO) examined associations between BMI, body fat percentage, and risk factors for type 2 diabetes and cardiovascular disease in studies of Asian populations. They found that at similar BMI levels, Asian adults have higher body fat percentages and more metabolic risk factors than White adults. Although the WHO declined to formally establish different BMI thresholds for overweight and obesity in Asian populations, it suggested "additional trigger points for public health action": BMI greater than 23 represents "increased risk" and BMI greater than 27.5 represents "high risk."

In 2015, the American Diabetes Association (ADA) examined evidence from 4 cohort studies in Asian American populations and concluded that Asian American adults should be considered for diabetes screening if they have a BMI greater than 23, based on the prevalence of type 2 diabetes in this population being roughly equivalent to that in White Americans with a BMI greater than 25. (The U.S. Preventive Services Task Force recommends screening for prediabetes and diabetes in nonpregnant adults aged 35 to 70 with a BMI of 25 or greater, but it alludes to the ADA's lower threshold for Asian Americans in its practice considerations.) Notably, the studies cited by the ADA included virtually no persons of Chinese descent, despite Chinese being the largest Asian American subgroup. So this guideline does not necessarily apply to me.

However, a 2009 study of a large cohort (n=36,386) of Taiwanese civil servants and schoolteachers over age 40 found that all-cause mortality increased significantly at BMIs greater than 25, analogous to the increase in mortality seen in White populations with obesity (BMI > 30). Taiwanese adults with BMIs from 23 to 24.9 had no difference in all-cause mortality compared to persons with lower BMIs but showed a nonsignificant trend toward increased cardiovascular mortality that was not modified by smoking status. That this study suggested a nearly identical risk threshold as studies in other Asian American populations would argue that I am not exempt.

A more recent comparative study of minority populations living in England found that South Asians with lower BMIs had the highest risk of developing diabetes, followed by Arab, Chinese, Black, and finally White populations. Presumably, race and ethnicity were self-identified. Similarly, a 2023 scientific statement from the American Heart Association found that the risk of coronary artery disease appears to be highest among South Asian and Filipino Americans and lowest among Chinese, Japanese, and Korean Americans, but cautioned that limited disaggregated data precluded making clinical recommendations based on race or ethnicity. As a JAMA news article recently noted, the common practice of national surveys lumping diverse ethnic groups into a single "Asian" obscures disparities within those groups and frustrates efforts to achieve health equity.

My admittedly selective review of the data leads me to believe there is probably some value to considering more intensive lifestyle counseling and metabolic screening in Asian patients with BMIs between 23 and 25, like me. But what do we do about the rising numbers of American adults of mixed race? Perhaps "precision medicine" will eventually find a way to integrate genetic and environmental risks and let clinicians dispense entirely with numeric thresholds and race categories, but I would be surprised if this occurs before the end of my career in medicine.

HPV vaccination is highly effective but remains underused in the U.S.

Since human papillomavirus (HPV) vaccines were first added to the routine U.S. childhood immunization schedule nearly two decades ago, the evidence of their effectiveness has become stronger every year.

In 2019, a Medicine by the Numbers in American Family Physician summarized a Cochrane review of 26 randomized, controlled trials comparing HPV vaccines to placebo. The authors found that vaccination reduced the risk of precancerous cervical lesions (cervical intraepithelial neoplasia [CIN] grades 2 or 3 and adenocarcinoma in situ) with numbers needed to treat (NNT) ranging from 55 to 73, depending on participants’ baseline HPV status. A 2021 observational study of girls and young women in England found that vaccination at ages 16-18, 14-16, and 12-13 years was associated with reductions in cervical cancer of 34%, 62%, and 87%, respectively. Remarkably, a study published this year found that 30,000 Scottish women who received at least one dose of HPV vaccine at age 12 or 13 had developed zero cases of invasive cervical cancer 11 to 20 years later!

Nonetheless, HPV vaccination coverage among U.S. adolescents remains lower than that for other childhood vaccines. Although coverage has gradually increased over time, an analysis of 2022 National Immunization Survey (NIS) data found that only 69% of 13 year-olds and 77% of 17 year-olds had received at least one dose, and 50% and 68% of these respective age groups were up-to-date (had received 2 doses if starting the series before age 15, or 3 doses if starting later). In comparison, 90% of 17 year-olds had received a least one dose of tetanus, diphtheria, and acellular pertussis (Tdap) and at least 2 doses of measles, mumps, and rubella (MMR) vaccines.

Historically, children living in socioeconomically disadvantaged households have been less likely to be up-to-date on immunizations. The Centers for Disease Control and Prevention’s Vaccines for Children program, which celebrates its 30th anniversary this year, aims to eliminate disparities in access by providing vaccines at no cost to children who are uninsured, Medicaid-eligible, American Indian or Alaska Natives.

A recent study of the 2017-2021 NIS examined factors associated with the intent to vaccinate by socioeconomic status and education level among parents of adolescents who had not received HPV vaccine. Participating parents were considered “advantaged” if their income was greater than 200% of the federal poverty level and they had at least a high school education; parents with lower incomes who had not completed high school were considered “deprived.” Surprisingly, 65% of advantaged parents of unvaccinated adolescents reported no intent to vaccinate in the future, compared to 41% of parents in the deprived group. Reasons for not vaccinating also differed between the groups: the advantaged group most often cited “safety concerns,” while the deprived group reported “lack of knowledge,” “not recommended,” and “not needed.” These data suggest that HPV vaccine hesitant parents may respond to different approaches.

In a 2015 AFP editorial, Drs. Herbert Muncie and Alan Lebato advised presenting the vaccine’s benefit as cancer prevention rather than focusing on HPV as a sexually transmitted infection, and taking a non-judgmental approach when explaining the recommendation to vaccinate:

To improve acceptance of immunizations, physicians must be knowledgeable about vaccine safety and effectiveness, and non-judgmental about parents' beliefs. … Hesitant parents may respond to the CASE method: the physician corroborates the parents' concerns, talks about his or her own experience with the vaccine, summarizes the science about vaccine effectiveness and safety, and explains advice in terms of the child's health.

Regarding safety, the World Health Organization’s Global Advisory Committee on Vaccine Safety has repeatedly found no evidence of a causal association between HPV vaccination and a variety of serious adverse effects.

**

This post first appeared on the AFP Community Blog.

Deadly drivers and the limits of preventive counseling

I believe that I'm a pretty safe driver. I don't use my phone in the car except for calls on my Bluetooth hands-free system, I come to a complete stop at stop signs even when no one else is around, and I never get in the driver's seat after I've been drinking. During the fall of 2020 and spring of 2021, though, I paid more attention than usual to driving safely. Our auto insurance company offered a discount for installing a device in my car that monitored my driving behavior, and my then 15 year-old son (in Utah, the minimum age for a learner's permit is 15) began learning to drive.

There has been a lot of media attention in recent months to the increase in distracted driving and its deadly consequences since the start of the pandemic. After falling for decades thanks to legislation mandating safety features such as airbags to a low of 32,479 in 2011, annual traffic-related deaths (including pedestrians) gradually rose, then spiked during the pandemic from 38,824 in 2020 to 42,795 in 2022. This statistic is similar to the 48,000 firearm homicides and suicides that occur in the U.S. every year.

Why have traffic-related deaths been going in the wrong direction? A New York Times Magazine story highlighted deferred road maintenance, larger and more powerful vehicles, aggressive driving and road rage, and the perennial culprit, intoxicated drivers. A recent analysis of data from the National Highway Traffic Safety Administration found that 1 in 5 deaths of child passengers in motor vehicle crashes involved an alcohol-impaired driver (blood alcohol concentration > 0.08 g/dL), and the more impaired the driver was, the less likely the child was to be wearing a seat belt.

 A Vox story pointed the finger at smartphones, noting that a company that sells a more sophisticated version of the device I installed in my car a few years ago - an app that measures phone motion and screen interaction while driving - found that in 2022, drivers interacted with their phones on nearly 58% of trips (an average of 2 minutes, 11 seconds per hour), more than one-third while driving over 50 miles per hour. This is when they knew the app was monitoring their behavior; one wonders if they would have been on their phones even more without it.

The difference between a medical and a public health problem is often merely a matter of perspective. For example, the solution to the medical problem of hypertension is to screen patients for high blood pressure and put the ones whom we diagnose on medications and/or encourage them to be more physically active and eat differently. But treating high blood pressure as a medical problem has been an abysmal failure. According to the National Health and Nutrition Examination Survey, of the one-third of Americans who had hypertension from 2017-2020, more than half had uncontrolled blood pressure (>140/90 mm Hg) and even among patients taking blood pressure medication, nearly one-third had uncontrolled blood pressure. Zoom out from the office setting to communities, counties, and states, and it's easy to see that hypertension is really a public health problem: too much sodium in food, too little access to safe places to exercise without a gym membership, difficulty getting a primary care appointment due to insufficient supply and uneven distribution, and so on.

Is impaired driving a medical or a public health problem? I got a lot of flak from readers when I wrote in a Medscape commentary that I would report to law enforcement a patient who declined to stop driving while high on cannabis. Clinical guidelines recommend counseling parents and guardians about keeping their children in rear-facing car seats until age two, using age and size-appropriate car and booster seats, and having children age 13 and younger ride exclusively in the back seat. With any adolescent approaching the minimum age for a learner's permit (16 years in Pennsylvania), I spend time during the well-child visit discussing the dangers of driving and texting, substance use before or while driving, and getting into a car with an impaired or distracted driver. Perhaps my counseling has saved a few lives over the past 20 years, but it's never been proven that this type of counseling improves health outcomes.

However, the evidence is clear that public health interventions and laws reduce motor vehicle crash injuries and deaths. The Community Preventive Services Task Force has evaluated a long list of interventions that save lives by reducing alcohol-impaired driving and increasing use of child safety seats, seat belts, and motorcycle helmets. The Vox story cited data that associated the passage of "hands free" phone laws with reductions in phone motion and driver distractions, but a lack of enforcement may cause these bad habits to reassert themselves over time.

Birthday blessings

The following is a guest post from my sister-in-law, Dr. Therese Duane, a trauma surgeon who is blogging about her medical mission in Uganda. You can read more about the essential work she and her colleagues have been doing at Mercy Trips Healthcare Outreach.

**

As a little girl growing up in a big family, there were few things that I could actually call my own. Not only did I share a room, but for a long time my sisters and I even shared a twin bed. Going clothes shopping meant venturing into another sister’s closet for hand-me-downs, and toys belonged to whomever could run away fast enough without tripping and getting tackled by the rest of us. But there was one thing we could call our own, and that was our birthday—although I did share mine with an uncle and George Washington.

Still yet, in our home, my mother made an effort for each of her seven children to have a special birthday. I have fond recollections of sleepovers filled with giggles, scary movies, and not enough sleep that always culminated in Mickey Mouse pancakes my mother would prepare especially for me. I knew I was loved.

If someone had told me 40 years ago that I would have spent my birthdays in Uganda doing medical mission work, I am not sure I would have believed them. And yet, here I am turning 54 years old and instead of giggles with my girlfriends, I am getting chuckles from children who—despite being far from home undergoing painful procedures—still manage to share their smiles with strangers.

Caring for all these families, many of which are large, reminds me how the gift of family is universal. I see many women struggling with fertility with few options. One 42-year-old with only one child came to have her fibroids removed so she could carry another pregnancy to term, as she had previous miscarriages. Sadly, her evaluation demonstrated enormous tumors that were compressing her pelvic organs and causing significant pain. After explaining that her only option was removal of her uterus and more biological children weren’t possible regardless of surgery, I could see the devastation. She left clinic having been informed of the risks of delaying surgery and never returned, choosing instead to be in pain than accept the inevitable. Other women come in with many children, and want more, but need surgery for another complaint. Hence, fertility awareness education is incredibly important for this impoverished country so that couples can make healthy decisions for themselves as they cherish their gift of family.

So, as this birthday comes to a close, I have already been privileged to bring a baby boy into this world through a c-section for one patient and remove a diseased ovary of a different woman, preserving her other, healthy ovary in the hopes that this will help her future fertility. In Uganda, general surgery is certainly general as we provide a wide array of service to the best of our ability. We strive to ensure that the gift of family is embraced, preserved, and expanded based on God’s will and that every person knows they are loved.

Before I rest for the evening in preparation for another long day in the OR tomorrow, I will call my mother to thank her for the gift of my life and family. And as we reminisce about Micky Mouse pancakes, I will remind her that it was her example and that of my father’s that began this call for me. I see the same generosity of spirit in all my siblings and pray to set the right example for my four children just as my parents did for me.