Two studies demonstrate the benefits and limitations of artificial intelligence in colonoscopy

Embargoed for release until 5:00 p.m. ET on Monday 28 August 2023
Annals of Internal Medicine Tip Sheet
@Annalsofim
Below please find summaries of new articles that will be published in the next issue of Annals of Internal Medicine. The summaries are not intended to substitute for the full articles as a source of information. This information is under strict embargo and by taking it into possession, media representatives are committing to the terms of the embargo not only on their own behalf, but also on behalf of the organization they represent.
----------------------------
1. Two studies demonstrate the benefits and limitations of artificial intelligence in colonoscopy

Editorial: https://www.acpjournals.org/doi/10.7326/M23-2022 

New research published in Annals of Internal Medicine explores the possible benefits and limitations of using computer assistance, or artificial intelligence, in detecting lesions and cancer during colonoscopy. An editorial accompanying these articles highlights that the current gap between randomized controlled trial performance and real-world performance likely reflects both differences in clinician behavior outside of trials and the complexity of real-world clinical environments.

AI not associated with improved detection of advanced colorectal neoplasias during colonoscopy

Abstract: https://www.acpjournals.org/doi/10.7326/M22-2619 
URL goes live when the embargo lifts
A randomized controlled trial found that colonoscopy assisted by computer-aided detection (CAD) was not associated with improved detection of advanced colorectal neoplasias.

Screening for colorectal cancer has greatly improved mortality rates due to greater detection of malignant and premalignant lesions. Systems relying on artificial intelligence using deep-learning technology have been linked to improved adenoma detection rates and reduce miss rate, but there are concerns that adenoma detection rates will continue to improve due to better detection of small polyps and nonadvanced adenomas, rather than detection of advanced and clinically significant lesions.

More than 3,000 persons with a positive fecal immunochemical test (FIT) were randomly assigned to colonoscopy with or without CAD to evaluate the contribution of CAD to colonoscopic detection of advanced colorectal neoplasias, adenomas, serrated polyps, and non-polypoid and right-sided lesions. FIT-positive patients were chosen because this group has the highest prevalence of advanced colorectal neoplasias, and therefore offers the best context for investigating the ability of computer aided detection to support the diagnosis of advanced colorectal neoplasias. The researchers found no significant difference in advanced colorectal neoplasia detection rate or the mean number of advanced colorectal neoplasias detected per colonoscopy between the two groups. Small effect was observed in increasing number of nonpolypoid lesions, proximal adenomas and small lesions of 5 mm or less, either colonic polyps in general, and adenomas and serrated polyps in particular, detected per colonoscopy. These findings suggest the need for additional research and more defined detection parameters in CAD before it can be integrated into routine clinical care.

Media contacts: For an embargoed PDF, please contact Angela Collom at acollom@acponline.org. To speak with the corresponding author Rodrigo Jover, MD, PhD, please email Carolina Mangas Residente at cmangassanjuan@gmail.com.

----------------------------

Computer-assisted colonoscopy may increase polyp detection and removal but not cancer detection

Abstract: https://www.acpjournals.org/doi/10.7326/M22-3678
 URL goes live when the embargo lifts
 A review of 21 randomized trials found that the use of CAD for polyp detection during colonoscopy resulted in increased detection of polyps and polyp removal, but not detection of advanced adenomas, the types of polyps at higher risk of cancer progression. 

Artificial intelligence computer-aided detection (CADe) of colorectal neoplasia during colonoscopy may

increase adenoma detection rates (ADRs) and reduce adenoma miss rates, but it may increase overdiagnosis and overtreatment of nonneoplastic polyps.

Researchers from Humanitas University conducted a systematic review and meta-analysis of 21 randomized controlled trials comprising 18,232 participants. The authors found the use of CADe was associated with a 55 percent relative risk reduction in miss rate of adenoma detection, but it was also associated with an increase in the removal of nonneoplastic polyps. The authors also report that CADe was also associated with a marginal increase in mean inspection time. The authors note that the studies mostly involved experienced gastroenterologists, and CADe programs may be more helpful to less experienced endoscopists.

Media contacts: For an embargoed PDF, please contact Angela Collom at acollom@acponline.org. To speak with the corresponding author Marco Spadaccini, MD, please email marco.spadaccini@humanitas.it.

----------------------------

2. After age 70, higher BMI and the presence of diabetes or cancer associated with lower testosterone in men

Abstract: https://www.acpjournals.org/doi/10.7326/M23-0342 
URL goes live when the embargo lifts
 An analysis of more than 25,000 men found that sociodemographic, lifestyle, and medical factors including age >70 years, hypertension, higher body mass index (BMI), diabetes, and cancer, were associated with lower testosterone concentrations. The analysis is published in Annals of Internal Medicine.

Lower testosterone concentrations are associated with a range of poor health outcomes in aging men,

including higher risks for diabetes, dementia, and death. It remains unclear whether reduced testosterone production is intrinsic to male aging or reflects accumulation of age-related comorbid conditions.

Researchers from the University of Western Australia in collaboration with colleagues from Australia, Europe and North America conducted a systematic review and meta-analysis of 11 studies comprising individual participant data from 21,074 men and aggregate data from 4,075 men. The authors analyzed concentrations of testosterone, dihydrotestosterone (DHT), and estradiol which were measured accurately using mass spectrometry. They found that testosterone concentrations did not differ with age until 70 years, after which testosterone concentrations decreased and luteinizing hormone (LH) concentrations increased, suggesting impaired testicular production of testosterone. Testosterone concentrations were slightly lower in men who were married, less physically active, were former smokers, or had hypertension, cardiovascular disease (CVD), or were on lipid-lowering medications. Testosterone concentrations were notably lower in men with higher BMI, or with a history of cancer or diabetes. The authors recommend that interpretation of testosterone measurements in individual men should account particularly for age older than 70 years, higher BMI, and the presence of diabetes or cancer. They conclude that additional research is needed to determine the health implications of reduced testosterone production in men above the age of 70 years.

Media contacts: For an embargoed PDF, please contact Angela Collom at acollom@acponline.org. To speak with the corresponding author Bu B. Yeap, MBBS, PhD, please email bu.yeap@uwa.edu.au.

--------------------------------

3. Recurrent firearm injury common among firearm injury survivors, especially among young, Black males

Abstract: https://www.acpjournals.org/doi/10.7326/M23-0069 
URL goes live when the embargo lifts
 A study of more than 10,000 persons with firearm injury found that recurrent injury is common among firearm injury survivors. Survivors experiencing recurrent injury were most often young, male, Black, and uninsured. These findings highlight the need for interventions to prevent recurrent injury. The study is published in Annals of Internal Medicine.

Firearm injury is a known and ongoing public health crisis in the United States. It is the leading cause of death for Americans ages one to 19 years of age, and disproportionately affects Black children and young adults. Previous evaluations have estimated that nonfatal firearm injuries occur at twice the rate of fatal firearm injuries, but this may be an underestimate.

Researchers from Washington University School of Medicine participated in the development

of the St. Louis Region-Wide Hospital-Based Violence Intervention Program (HVIP) Data Repository (STL-HVIP-DR). The repository houses data on all patients who present to 1 of the 4 St. Louis adult or pediatric level I trauma hospitals with a violent injury, including firearm injury. The authors identified 9,553 persons who survived initial firearm injury and observed that 1,155 persons experienced recurrent firearm injury over an average follow-up period of 3.5 years. The authors found that persons experiencing recurrent firearm injury were often young. They report that 93 percent of persons were male, 96 percent were Black, and half were uninsured. Most resided in areas of high social vulnerability.. They also found that the estimated risk for firearm reinjury increased each year, beginning at 7 percent risk after one year and increasing to 17 percent risk at eight years. According to the authors, their findings highlight the need for interventions including community-based care, counseling, and substance use disorder screening to prevent recurrent firearm injury and death.

Media contacts: For an embargoed PDF, please contact Angela Collom at acollom@acponline.org. To speak with the corresponding author Kristen L. Mueller, MD, please email Diane Williams at williamsdia@wustl.edu.

--------------------------------

Also new in this issue:

The Case for Flourishing in the Time of Wellness

Cynthia Kay, MD, MS; Ashley Pavlic, MD, MA; and Leslie Ruffalo, PhD, MS

Ideas and Opinions

Abstract: https://www.acpjournals.org/doi/10.7326/M23-0907