“Being a Doctor Will Never Be the Same After A.I.”

Posted on by
Reply

Rachael Bedard. NY Times 9/25/26: Being a Doctor Will Never Be the Same After A.I.

An excerpt:

“I have a confession: A.I. is making me a better doctor. And I worry that it’s making doctors-in-training worse…

I already use the technology in my practice all the time…This summer, I used an A.I. tool — a platform called OpenEvidence, accessible only to health care providers — to help me choose antibiotics for one patient and to interpret unusual bloodwork for another. A.I. reminded me to consider migraines when a woman presented with dizziness. ..

Almost every month, I’m confronted with a complaint or syndrome that I don’t recognize. I’m confident in my mastery over what doctors do — history-taking, reasoning, communicating. I’m less confident about my continued mastery of an ever-evolving universe of facts. Now, the chatbot in my pocket reassures me that I will always know enough, or have access to the cloud-based intelligence that generally does.

All of my students and residents also use OpenEvidence, however, and I worry about the consequences of introducing such a powerful decision aid so early in their careers. Not only have they memorized less than I’d like, but they can seem almost passive in their relationship to their machines…

OpenEvidence is trained exclusively on peer-reviewed evidence and guidelines, and includes citations for all its claims…To use the app well, you must stay skeptical as you scroll…

I’m surprised by how much I learn from, and enjoy, these interactions. More important, my patient care has improved as conversations with the agent push my thinking beyond its usual limits…

Adam Rodman, a physician and A.I. researcher at Harvard Medical School,… said he shared my concern that trainees aren’t benefiting from “productive struggles” as much as their predecessors. “In experienced hands, decision support might cause a little de-skilling, but a little de-skilling probably doesn’t matter much to you,” Dr. Rodman told me. “But if you do that to somebody who has much less skill, the cognitive offloading can cause never-skilling”…

Current doctors-to-be may be the most adversely affected generation when it comes to A.I. They’re training before we know enough about how to teach them well in this new paradigm.

My take: In all aspects of learning, not just medicine, using AI shortcuts may make learners increasingly dependent on their devices, undermine their judgment and hinder developing their own voice. How to best train individuals in this new era remains unclear.

Related blog posts:

Svörtuloft Lighthouse is located at the westernmost tip of the Snæfellsnes Peninsula in West Iceland. It is perched atop a 2.5-mile stretch of pitch-black volcanic lava cliffs.

Outcomes of Biliary Atresia in Large Cohort

Posted on by
1

G Boroni et al. J Pediatr Gastroenterol Nutr. 2026;83:491–499. The Italian biliary atresia registry: Insights and lessons from the retrospective analysis of a 10-year period cohort

This retrospective study (2012-2012) examined the outcomes of 309 children with biliary atresia (BA) from 13 centers. Clearance of jaundice (CoJ) was defined as total bilirubin <1.2 mg/dL within 6 months.

Key findings:

  • The calculated incidence of BA in Italy during the study period was 1/15,142 live births
  • Kasai portoenterostomy (KPE) was performed in 272 infants (88%) at a median age of 68.5 days.
  • CoJ was achieved in 39% of cases.
  • CoJ was significantly associated with younger age and lower total bilirubin at referral (p = 0.0446 and p = 0.0144, respectively), younger age at KPE (p = 0.0345), and postoperative corticosteroid use (p = 0.0036). 
  • Liver transplantation was performed in 212/309 patients, and overall 5-year actuarial patient survival was 97.4%.
  • Overall patient survival was excellent: 97% at 5 years and 95% at 10 years.
Steroids were used in 71% of KPE cases. Different centers had different steroid protocols
Steroids were associated with improved clearance of jaundice after Kasai.
In those with a failed Kasai, steroid use did not improve outcomes.

Discussion points:

  • “This analysis contributes further to the controversy surrounding the effect of steroids.”
  • “The success of KPE decreases progressively with age at operation, with each additional day reducing the odds of CoJ by approximately 1.3%.”
  • “Despite decades of calls for earlier diagnosis and earlier KPE, little progress has been made in achieving earlier access to surgery…The evidence suggests that fibrosis is already advanced when KPE is performed at around 60 days of life and is likely to persist for life even when CoJ is achieved. Cirrhosis and portal hypertension remain common in long‐term survivors, who may face severe comorbidities.”
  • “Standards should therefore aim for KPE closer to, or before, 30 days of age, rather than accepting the current usual timing of 50–70 days achieved worldwide.”

My take: In this cohort, ~70% needed a liver transplant. Even with optimal timing and management, more than 50% are likely to need a liver transplant for long-term survival.

Related blog posts:

Disclaimer: This blog, gutsandgrowth, assumes no responsibility for any use or operation of any method, product, instruction, concept or idea contained in the material herein or for any injury or damage to persons or property (whether products liability, negligence or otherwise) resulting from such use or operation. These blog posts are for educational purposes only. Specific dosing of medications (along with potential adverse effects) should be confirmed by prescribing physician. Because of rapid advances in the medical sciences, the gutsandgrowth blog cautions that independent verification should be made of diagnosis and drug dosages. The reader is solely responsible for the conduct of any suggested test or procedure. This content is not a substitute for medical advice, diagnosis or treatment provided by a qualified healthcare provider. Always seek the advice of your physician or other qualified health provider with any questions you may have regarding a condition.

AI for Capsule Endoscopy:

Posted on by
Reply

D Fan et al. Clin Gastroenterol Hepatol 2026; 24: 2571-2583. Open Access! INTELCAPE: A Deep Learning-Powered System for Automated, High-Accuracy Crohn’s Disease Diagnosis via Capsule Endoscopy

Methods: In this retrospective, multi-center study with data from 2 Chinese hospitals, the authors developed artificial intelligence, INTELCAPE, for a multi-task deep learning system, to perform small-intestine segmentation, lesion detection, and CD diagnosis from full (capsule endoscopy) CE videos.

Key findings:

  • “INTELCAPE achieved state-of-the-art performance across all tasks.”
  • “For lesion detection, it achieved area under the curve values of 0.993 (Cohort 1) and 0.980 (Cohort 2), with 99.33% classification accuracy, which was comparable to that of specialists (97.83%) but superior to that of residents (91.05%; P < .001).”
  • “For CD diagnosis, INTELCAPE demonstrated robust generalizability, achieving area under the curve values of 0.982 (Cohort 1) and 0.984 (Cohort 2) with 90% diagnostic accuracy, comparable to that of specialists (93.33%) but 10-fold faster (P < .001).”
  • “INTELCAPE improved doctors’ diagnostic accuracy (76.7%–94.8%; P < .001), while reducing their interpretation time (67.9–22.5 minutes; P < .001).”

Discussion Points:

  • “CE generates thousands of images per examination, imposing a substantial analytical burden on clinicians. Manual analysis is labor-intensive and prone to human error, increasing the risk of missed lesions, particularly those with subtle appearances.”
  • “Real-world clinical workflows will require prospective validation on “all-comers” populations, robust handling of poor-quality videos, and device-specific fine-tuning.”

My take: Capsule endoscopy appears to be an ideal target for AI assistance. It has the potential to improve accuracy, reduce time, and augment the performance of less experienced clinicians.

Related blog posts:

Long-Term Effectiveness of Dupilumab for Eosinophilic Esophagitis

Posted on by
Reply

S Oliva et al. Clinical Gastroenterology and Hepatology; 2026 (Epub, 9/7/26). Open Access! Long-Term Effectiveness of Dupilumab in Eosinophilic Esophagitis: Results From the DUPEOETALY Study

Methods: This retrospective observational study included 167 patients, median age, 21.5 years, with EoE from 50 Italian centers, unresponsive or intolerant to conventional therapies. Given the real-world design of the study, no standardized protocol mandated patient re-evaluation at fixed follow-up timepoints. Histologic remission was considered having <15 eos/hpf. All patients, however, underwent at least 3 endoscopic assessments: at baseline, after the induction phase (performed between weeks 12 and 24), and at 1-year follow-up. At baseline, 76% had a personal history of atopy, 86.2% had used corticosteroids, and 94% had used proton pump inhibitors.

Key findings:

  • DSQ score decreased from 22.14 ± 26.63 to 0.21 ± 2.30, EREFS from 4.95 ± 3.43 to 0.07 ± 0.09, and Eos/HPF from 36.80 ± 31.75 to 0.06 ± 0.46.
  • Improvements increased with treatment duration. By week 72, 98.3% of patients achieved remission criteria (DSQ ≤5, Eos/HPF ≤15, and EREFS ≤2). 
  • No serious or systemic adverse events were reported, and no patients discontinued treatment due to intolerance. 
Remission criteria were defined as DSQ ≤5, EREFS ≤2, and <15 eos/HPF,
with complete remission achieved when all 3 were met simultaneously.24

Discussion:

  • “Only a small proportion of patients in our cohort had a history of esophageal dilation (8.4%), which may suggest a relatively lower burden of advanced fibrostenotic disease…could partially influence remission rates and should be considered when interpreting the generalizability of our findings to populations with more severe structural disease.”

My take: This study supports the long-term effectiveness of dupilumab in pediatric and adult patients with EoE. It is not clear why there was such a high remission rate in this cohort compared to previous reports.

Related blog posts:

Some good brief YouTube EoE educational videos for families from GIKids.org (with pharmaceutical funding), links:

Flawed Dual Therapy Study of Vedolizumab and Upadacitinib

Posted on by
Reply

J Yao et al. Clinical Gastroenterology and Hepatology, 2026. Combined Upadacitinib and Vedolizumab as 8-Week Induction Therapy for Moderate-to-Severe Ulcerative Colitis: A Multicenter, Randomized Controlled Trial

Many patients do not respond to current advanced therapies which have prompted evaluation of dual therapy regimens. In this randomized open-label trial, the authors compared upadacitinib-vedolizumab dual therapy against vedolizumab monotherapy (40 combination, 73 monotherapy) for moderate-to-severe ulcerative colitis. Upadacitinib was dosed at 45 mg per day.

Key findings:

  • Endoscopic remission at week 8 was achieved by 37.5% in the dual therapy group compared to 15.1% with vedolizumab monotherapy (adjusted odds ratio, 3.34, 1.34–8.58; P = .010)
  • Clinical remission (65.0% vs 35.6%; P = .002) was significantly higher with combination therapy.
  • Adverse event rates were comparable (7.5% vs 6.8%), with no serious adverse events.

It is great to see more dual therapy data . While I am a little reluctant to criticize this study, as I think this type or research is both important and difficult, this trial has a couple problems. First of all, vedolizumab monotherapy may take twice as long to become effective; as such, the results at week 8 in isolation provoke more questions than answers. In addition, at this time point, it is not clear if combination therapy would be more effective than upadacitinib monotherapy.

In their discussion, the authors state that “the 65.0% clinical remission rate at week 8 substantially exceeds rates reported in pivotal induction trials for either upadacitinib (up to 34%11,25) or vedolizumab (approximately 17%24) as monotherapy….. The absence of a upadacitinib monotherapy arm precludes formal assessment of synergy; however, the observed combination endoscopic remission rate (37.5%) exceeds published upadacitinib monotherapy rates for Mayo score = 0 (approximately 14%–18%),11 suggesting a benefit beyond that of upadacitinib monotherapy alone.” However, in a study (RS Dalal et al. Clin Gastroenterol Hepatol 2024; 22: 666-668) comparing monotherapy with upadacitinib versus ustekinumab, upadacitinib had a steroid-free clinical remission rate of 62.1 %, and an endoscopic remission 37.5%. These results are nearly identical to the results of the combination therapy group.

My take: This study shows that upadacitinib works quicker than vedolizumab for moderate-to severe UC. It does not prove that upadacitinib in combination with vedolizumab is more effective than upadacitinib monotherapy.

The anticipated followup data at 1 year will be helpful to determine whether the combination with vedolizumab impacts long-term effectiveness of upadacitinib monotherapy. It is unfortunate that an upadacitinib monotherapy arm was not included in this study.

Another useful study would be whether patients who respond to upadacitinib as an induction combination therapy with vedolizumab could transition to vedolizumab monotherapy. This would leverage upadacitinib’s rapid onset and if effective, allow long-term treatment with vedolizumab which is considered to have the most favorable long-term safety data.

Related blog posts:

The Median Arcuate Ligament Syndrome (MALS) Study For Skeptics Like Me

Posted on by
Reply

MA Nassif et al. J Pediatr Gastroenterol Nutr. 2026;83:397–403. Outcomes of surgical versus conservative treatment inpediatric median arcuate ligament syndrome

Methods: This was a retrospective pediatric study (n=34) evaluating surgical versus conservative management in pediatric MALS. Conservative therapy included the following: 100% pharmacologic, 80% behavioral, 30% botulinum toxin, 20% neurostimulation.

Key findings:

  • Conservative therapy outcomes (n=10): resolution (20%), improvement (40%), unchanged (40%), and none worsened.
  • Surgical therapy outcomes (n=24) resolution (21%), improvement (33%), unchanged (17%), worsened (29%); thus, these outcomes are not significantly different from the conservative group (p = 0.21). Median hospital stays: 4 days. Postoperative complications occurred in 21%. The one major complication was an intraoperative splenic artery injury in a patient with Ehlers-Danlos Syndrome.
  • Overall, 60% of children with MALS improved with conservative DGBI‐directed therapy and 54% improved with decompression surgery at long‐term follow‐up (at median 9.8 months), despite a robust short‐term postoperative response (87%). At 20 days postop: 52% reported resolution, 35% improved.
Recent follow‐up data show comparable rates of resolution and improvement between the two groups, with no statistically significant difference (p = 0.21).

Discussion points:

  • Other studies have reported higher response rates for MALS surgery: “The newest and largest‐scale review suggests a 70% symptom relief rate in three of six pediatric studies, with follow‐ups of 6–62 months after laparoscopic MALS release.[28]”
  • “A more recent study conducted in 2017 determined that only post‐exertional abdominal pain was a predictor of a good surgical outcome.[31]”
  • “The lack of universally accepted diagnostic criteria for MALS remains a challenge.”

My take: In this study, surgery for MALS did not seem to improve long-term outcome more than DGBI therapy. If one finds celiac artery compression which may be identified in many healthy individuals (10-24% of population), it is unclear to me if an MALS operation is indicated and how to determine when it is indicated.

Related blog posts:

Experts Doubt Benefits of Popular Supplements. Yet, In New Survey – Nearly 80% of Americans Taking Supplements

Posted on by
Reply

Alice Callahan, NY Times, 9/11/26: Americans Love Supplements, but Experts Doubt Their Benefits “A new survey found that 8 in 10 Americans were taking vitamins, protein powders or other supplements. But experts said there is little evidence for many of these products.”

This article was based on a Pew Research Study with 3,554 U.S. Adults: Emma Kikuchi, Brian Kennedy, Pew Research Center, 9/10/26. About 8 in 10 Americans take supplements, and many see them as important to their health “Supplements are a booming industry, with an estimated global value of $209.5 billion in 2025.”

While the PEW Research study indicated that the majority of individuals taking these supplements thought they were very important for their health, the NY Times article stated the following:

“I would guess that well over 80, 90 percent of supplement consumption doesn’t offer any proven benefit to the person who’s taking it,” said Dr. Pieter Cohen, an associate professor of medicine at Harvard Medical School…

There are good reasons to take dietary supplements, for example to treat a nutrient deficiency or to prevent birth defects, said Dr. Eric Topol, a cardiologist and the founder of the Scripps Research Translational Institute. “But that’s the minority,” he added.

People often take omega-3 supplements because they believe they will improve their heart or brain health, for instance, but most clinical trials have failed to find those benefits.

And most people probably don’t need protein supplements, Dr. Topol said…in reality, most people already consume enough protein from the foods they eat, Dr. Topol said…

Supplement use…has increased in recent decades, said Elizabeth Kantor, an epidemiologist at Memorial Sloan Kettering Cancer Center. In June, she and her colleagues published a study that included more than 63,000 U.S. adults, surveyed between 1999 and 2023. Over that time, the researchers found, supplement use climbed to 60 percent from 51 percent of adults.

The rise in supplement use may be driven in part by claims of their benefits on social media, many of which are unsubstantiated, Dr. Topol said.

My take: Most people do not need or benefit from supplements. In addition, some supplements result in adverse outcomes. Supplements are often needed in individuals who are pregnant and those with previous intestinal resections and restricted diets.

Related blog posts:

How Effective Is Treatment of Eosinophilic Esophagitis In Patients with Rumination Syndrome?

Posted on by
1

D Yang et al. J Pediatr Gastroenterol Nutr. 2026;83:374–380. Rumination syndrome and eosinophilic esophagitis in children: Defining the relationship

Methods: This was a retrospective cohort study of children with RS and EoE evaluated at our institution from 2016 to 2023.

Key findings:

  • In this cohort with rumination syndrome, 22 of 230 had EoE. This is a significantly greater prevalence of EoE (10%) among children with RS than in the general population (0.1%).
  • Among those diagnosed with EoE first (70%), RS diagnosis occurred after a median of 15.4 months.
  • EoE treatment led to mucosal remission in 73% and improved dysphagia in 41%, but 86% continued to experience regurgitation.
  • RS treatment, including behavioral therapy and baclofen, improved or resolved regurgitation in 64%.
Improvement in Regurgitation to EoE vs RS ‐based treatments among patients with RS and EoE.
EoE, eosinophilic esophagitis;RS, rumination syndrome

Limitations: retrospective design and potential referral/selection bias in a tertiary care population (specialized center for rumination).

My take: In patients with both EoE and RS, regurgitation continued in 86% of patients who achieved EoE remission. Especially in those without dysphagia, most will need treatment of RS in additon to EoE. In addition, earlier treatment of RS may improve outcomes.

Related blog posts:

Balanced Fluid (like Lactated Ringer’s) vs Saline in Pediatric Sepsis

Posted on by
Reply
  • Balamuth F, Weiss SL, Long E, et al. N Engl J Med 2026;395:870-881. Balanced fluid or 0.9% saline in children treated for septic shock. 

Key finding: No significant difference was seen in the incidence of death, new renal-replacement therapy, or persistent kidney dysfunction when fluid resuscitation was administered with balanced fluid as compared with 0.9% saline.

  • MF O’Connor, J Bubeck-Wardenburg. N Engl J Med 2026;395:921-922. Commentary: Fluid Resuscitation in Patients with Sepsis — For Whom the Balance Tolls

From the commentary:

“Balamuth and colleagues report the findings of the Pragmatic Pediatric Trial of Balanced versus Normal Saline Fluid in Sepsis (PRoMPT BOLUS), a large, international, pediatric trial evaluating whether treatment with balanced crystalloid fluid (lactated Ringer’s solution, Plasma-Lyte, or Hartmann’s solution according to clinician discretion) is associated with better kidney-function outcomes than therapy with normal saline in patients with sepsis..

Evaluating more than 8000 children who were well matched with respect to the severity of sepsis at initial presentation, the current trial showed that the nature of fluid administered did not significantly affect patient outcomes…This finding contrasts with those of SMART and the SALT-ED trial as well as those of two other trials…6,7 

As appropriately recognized by Balamuth et al., less-severe illness in the participants in the present trial may have limited the ability of the trial to detect an influence of fluid composition on clinical outcome. Taken together, both adult and pediatric studies suggest that the clinical benefit of balanced-fluid administration correlates directly with the degree of cellular homeostatic disruption in patients with sepsis…

It is important to consider that harm has not been associated with the administration of balanced fluids in any clinical study. With the notable exception of patients with intracranial hypertension, the prudent approach may be to use balanced fluids as standard care in patients with sepsis.”

My take: For most children with sepsis, the outcomes are likely to be similar between those receiving balanced fluids and saline. However, sicker patients, which may be difficult to discern initially, may benefit from balanced fluids.

Related blog posts:

Congratulations to NASPGHAN’S NEWLY ELECTED LEADERS:

Disclaimer: This blog, gutsandgrowth, assumes no responsibility for any use or operation of any method, product, instruction, concept or idea contained in the material herein or for any injury or damage to persons or property (whether products liability, negligence or otherwise) resulting from such use or operation. These blog posts are for educational purposes only. Specific dosing of medications (along with potential adverse effects) should be confirmed by prescribing physician. Because of rapid advances in the medical sciences, the gutsandgrowth blog cautions that independent verification should be made of diagnosis and drug dosages. The reader is solely responsible for the conduct of any suggested test or procedure. This content is not a substitute for medical advice, diagnosis or treatment provided by a qualified healthcare provider. Always seek the advice of your physician or other qualified health provider with any questions you may have regarding a condition.