Search

A recent study by Suissa and colleagues explored the clinical relevance of a medical image segmentation metric (Dice metric) commonly used in the field of artificial intelligence (AI). They showed that pixel-wise agreement for physician identification of structures on ultrasound images is variable, and a relatively low Dice metric (0.34) correlated to a substantial agreement on subjective clinical assessment. We highlight the need to bring structure and clinical perspective to the evaluation of medical AI, which clinicians are best placed to direct. [ABSTRACT FROM AUTHOR]

ABSTRACT Background and Aims Methods Results Conclusions Metabolic dysfunction‐associated steatotic liver disease (MASLD) is a growing public health problem. The secondary stage in MASLD is steatohepatitis (MASH), the co‐existence of steatosis and inflammation, a leading cause of progression to fibrosis and mortality. MASH resolution alone improves survival. Currently, MASH diagnosis is via liver biopsy. This study sought to evaluate the accuracy of imaging‐based tests for MASH diagnosis, which offer a non‐invasive method of diagnosis.Eight academic literature databases were searched and references of previous systematic reviews and included papers were checked for additional papers. Liver biopsy was used for reference standard.We report on 69 imaging‐based studies. There were 31 studies on MRI, 27 on ultrasound, five on CT, 13 on transient elastography, eight on controlled attenuation parameter (CAP) and two on scintigraphy. The pathological definition of MASH was inconsistent, making it difficult to compare studies. 55/69 studies (79.71%) were deemed high‐risk of bias as they had no preset thresholds and no validation. The two largest groups of imaging papers were on MRI and ultrasound. AUROCs were up to 0.93 for MRE, 0.90 for MRI, 1.0 for magnetic resonance spectroscopy (MRS) and 0.94 for ultrasound‐based studies.Our study found that the most promising imaging tools are MRI techniques or ultrasound‐based scores and confirmed there is potential to utilise these for MASH diagnosis. However, many publications are single studies without independent prospective validation. Without this, there is no clear imaging tool or score currently available that is reliably tested to diagnose MASH. [ABSTRACT FROM AUTHOR]

Background: Inconsistent nomenclature and anatomical descriptions of regional anesthetic techniques hinder scientific communication and engender confusion; this in turn has implications for research, education and clinical implementation of regional anesthesia. Having produced standardized nomenclature for abdominal wall, paraspinal and chest wall regional anesthetic techniques, we aimed to similarly do so for upper and lower limb peripheral nerve blocks., Methods: We performed a three-round Delphi international consensus study to generate standardized names and anatomical descriptions of upper and lower limb regional anesthetic techniques. A long list of names and anatomical description of blocks of upper and lower extremities was produced by the members of the steering committee. Subsequently, two rounds of anonymized voting and commenting were followed by a third virtual round table to secure consensus for items that remained outstanding after the first and second rounds. As with previous methodology, strong consensus was defined as ≥75% agreement and weak consensus as 50%-74% agreement., Results: A total of 94, 91 and 65 collaborators participated in the first, second and third rounds, respectively. We achieved strong consensus for 38 names and 33 anatomical descriptions, and weak consensus for five anatomical descriptions. We agreed on a template for naming peripheral nerve blocks based on the name of the nerve and the anatomical location of the blockade and identified several areas for future research., Conclusions: We achieved consensus on nomenclature and anatomical descriptions of regional anesthetic techniques for upper and lower limb nerve blocks, and recommend using this framework in clinical and academic practice. This should improve research, teaching and learning of regional anesthesia to eventually improve patient care., Competing Interests: Competing interests: EA: grants from Swiss Academy for Anesthesia Research, Bbraun, Swiss National Science Foundation. Honoraria from Bbraun and Sintetica. JG: consulting fees from Pacira Biosciences and Pajunk Medical. AP: honoraria from FuijiFilm Sonosite. MW: advisory Board for Sintetica, Honoraria from Wisonic and Medovate. SA: Advisory Panel for DATAR innovations. JA: moderator of the Working Group Regional Anaesthesia Switzerland, Honoraria from Medtronic and Sintetica. AMRA: honoraria form AllerganSébastien Bloc—Consulting fees from BBraun—GE Medical Systems—Pajunk—Pfizer SAS. JB: Consulting fees from Intelligent Ultrasound. BC: jonoraria from Bbraun and Rivanna, Consulting from Stryker and Flat Medical, Research funding from Pacira, Share Options from Flat Medical. AC: speaking honoraria from GE Healthcare, royalties from textbook Oxford University Press. SC: consulting fees from MSD, Bbraun Medical, Wisonic, research grants from BARA (Belgian association of Regional anesthesia), ESRA and BeSARP (Belgian anesthesia society) HE-Consulting/Advisory Board Neuronoff, SPR, GateScience, NeuronoffBenjamin Fox—Speaking fees from Medovate and Sintetica. SG: consulting and speaking fees from MSD Switzerland. PH: royalties from Bestek Products. NH: Honoraria from Butterfly Network. RMGH- Honoraria from GE Healthcare. MH: consulting fees from Pacira Biosciences, Honoraria from Parcira Biosciences and Pajunk Medical. BMI: research funding to institution from SPR Therapeutics, Infutronix, Epimed International. AM: Consultant fees from Intelligent Ultrasound. CM: consultant fees from Masimo Corporation. SGM: Owner SGM Consulting, Partner Parvizi Surgical Innovations, Patent for Multicatheter infusion system. AN: Research support from SPR Therapeutics. SLO: Royalties from book Wolters-Kluwer. APawa: Honoraria from GE Healthcare, Consulting fees from Pacira Biosciences. PP: equipment support from Sonosiite Fujifilm Canada. MPS: Medovate speaking but no honoraria paid. SKS- Cofounder of Gate Science (developing a catheter for performing nerve blocks) JS: consulting fees from Sintetica. RT: Consulting fees from Clarius Mobile Health. VU: Associate Editor of the Canadian Journal of Anesthesia and Regional Anesthesia & Pain Medicine journals. TV: honoraria from CSL Behring, Pajunk., (© American Society of Regional Anesthesia & Pain Medicine 2024. No commercial re-use. See rights and permissions. Published by BMJ.)

Objectives: Ultrasound-guided regional anesthesia (UGRA) relies on acquiring and interpreting an appropriate view of sonoanatomy. Artificial intelligence (AI) has the potential to aid this by applying a color overlay to key sonoanatomical structures.The primary aim was to determine whether an AI-generated color overlay was associated with a difference in participants' ability to identify an appropriate block view over a 2-month period after a standardized teaching session (as judged by a blinded assessor). Secondary outcomes included the ability to identify an appropriate block view (unblinded assessor), global rating score and participant confidence scores., Design: Randomized, partially blinded, prospective cross-over study., Setting: Simulation scans on healthy volunteers. Initial assessments on 29 November 2022 and 30 November 2022, with follow-up on 25 January 2023 - 27 January 2023., Participants: 57 junior anesthetists undertook initial assessments and 51 (89.47%) returned at 2 months., Intervention: Participants performed ultrasound scans for six peripheral nerve blocks, with AI assistance randomized to half of the blocks. Cross-over assignment was employed for 2 months., Main Outcome Measures: Blinded experts assessed whether the block view acquired was acceptable (yes/no). Unblinded experts also assessed this parameter and provided a global performance rating (0-100). Participants reported scan confidence (0-100)., Results: AI assistance was associated with a higher rate of appropriate block view acquisition in both blinded and unblinded assessments (p=0.02 and <0.01, respectively). Participant confidence and expert rating scores were superior throughout (all p<0.01)., Conclusions: Assistive AI was associated with superior ultrasound scanning performance 2 months after formal teaching. It may aid application of sonoanatomical knowledge and skills gained in teaching, to support delivery of UGRA beyond the immediate post-teaching period., Trial Registration Number: www.clinicaltrials.govNCT05583032., Competing Interests: JSB is a Senior Clinical Advisor for GE Healthcare (and previously Intelligent Ultrasound, receiving research funding and honoraria). MM was employed by Intelligent Ultrasound as a medical writer during this study. DBSL is a clinical advisor for Intelligent Ultrasound, receiving honoraria. NH is the President of Regional Anaesthesia UK. AJRM is the immediate Past-President of Regional Anaesthesia UK and has received honoraria from Intelligent Ultrasound and GE Healthcare. AP is a Past-President of Regional Anaesthesia UK, has received honoraria from GE Healthcare and has consulted for Pacira Biosciences. TA, MPS, AT and JW are board members of Regional Anaesthesia UK. JAN is a senior scientific advisor for Intelligent Ultrasound., (Copyright © Author(s) (or their employer(s)) 2024. Re-use permitted under CC BY-NC. No commercial re-use. See rights and permissions. Published by BMJ.)

Competing Interests: Competing interests: DM and AN are members of the EMJ editorial board. JSB is a senior clinical advisor and has received research funding and honoraria from Intelligent Ultrasound, which develops assistive artificial intelligence systems for medical ultrasound including ultrasound-guided regional anaesthesia.