Artificial intelligence for ultrasound scanning in regional anaesthesia: a scoping review of the evidence from multiple disciplines.

BACKGROUND: Artificial intelligence (AI) for ultrasound scanning in regional anaesthesia is a rapidly developing interdisciplinary field. There is a risk that work could be undertaken in parallel by different elements of the community but with a lack of knowledge transfer between disciplines, leading to repetition and diverging methodologies. This scoping review aimed to identify and map the available literature on the accuracy and utility of AI systems for ultrasound scanning in regional anaesthesia. METHODS: A literature search was conducted using Medline, Embase, CINAHL, IEEE Xplore, and ACM Digital Library. Clinical trial registries, a registry of doctoral theses, regulatory authority databases, and websites of learned societies in the field were searched. Online commercial sources were also reviewed. RESULTS: In total, 13,014 sources were identified; 116 were included for full-text review. A marked change in AI techniques was noted in 2016-17, from which point on the predominant technique used was deep learning. Methods of evaluating accuracy are variable, meaning it is impossible to compare the performance of one model with another. Evaluations of utility are more comparable, but predominantly gained from the simulation setting with limited clinical data on efficacy or safety. Study methodology and reporting lack standardisation. CONCLUSIONS: There is a lack of structure to the evaluation of accuracy and utility of AI for ultrasound scanning in regional anaesthesia, which hinders rigorous appraisal and clinical uptake. A framework for consistent evaluation is needed to inform model evaluation, allow comparison between approaches/models, and facilitate appropriate clinical adoption.

Adopting human factors in early phase and experimental medicine research: A nested pilot study observing controlled human infection with SARS-CoV-2.

AIMS: The influence of human factors on safety in healthcare settings is well established, with targeted interventions reducing risk and enhancing team performance. In experimental and early phase clinical research participant safety is paramount and safeguarded by guidelines, protocolized care and staff training; however, the real-world interaction and implementation of these risk-mitigating measures has never been subjected to formal system-based assessment. METHODS: Independent structured observations, systematic review of study documents, and interviews and focus groups were used to collate data on three key tasks undertaken in a clinical research facility (CRF) during a SARS CoV-2 controlled human infection model (CHIM) study. The Systems Engineering Initiative for Patient Safety (SEIPS) was employed to analyse and categorize findings, and develop recommendations for safety interventions. RESULTS: High levels of team functioning and a clear focus on participant safety were evident throughout the study. Despite this, latent risks in both study-specific and CRF work systems were identified in all four SEIPS domains (people, environment, tasks and tools). Fourteen actionable recommendations were generated collaboratively. These included inter-organization and inter-study standardization, optimized checklists for safety critical tasks, and use of simulation for team training and exploration of work systems. CONCLUSIONS: This pioneering application of human factors techniques to analyse work systems during the conduct of research in a CRF revealed risks unidentified by routine review and appraisal, and despite international guideline adherence. SEIPS may aid categorization of system problems and the formulation of recommendations that reduce risk and mitigate potential harm applicable across a trials portfolio.

Evaluation of the impact of assistive artificial intelligence on ultrasound scanning for regional anaesthesia.

BACKGROUND: Ultrasound-guided regional anaesthesia relies on the visualisation of key landmark, target, and safety structures on ultrasound. However, this can be challenging, particularly for inexperienced practitioners. Artificial intelligence (AI) is increasingly being applied to medical image interpretation, including ultrasound. In this exploratory study, we evaluated ultrasound scanning performance by non-experts in ultrasound-guided regional anaesthesia, with and without the use of an assistive AI device. METHODS: Twenty-one anaesthetists, all non-experts in ultrasound-guided regional anaesthesia, underwent a standardised teaching session in ultrasound scanning for six peripheral nerve blocks. All then performed a scan for each block; half of the scans were performed with AI assistance and half without. Experts assessed acquisition of the correct block view and correct identification of sono-anatomical structures on each view. Participants reported scan confidence, experts provided a global rating score of scan performance, and scans were timed. RESULTS: Experts assessed 126 ultrasound scans. Participants acquired the correct block view in 56/62 (90.3%) scans with the device compared with 47/62 (75.1%) without (P=0.031, two data points lost). Correct identification of sono-anatomical structures on the view was 188/212 (88.8%) with the device compared with 161/208 (77.4%) without (P=0.002). There was no significant overall difference in participant confidence, expert global performance score, or scan time. CONCLUSIONS: Use of an assistive AI device was associated with improved ultrasound image acquisition and interpretation. Such technology holds potential to augment performance of ultrasound scanning for regional anaesthesia by non-experts, potentially expanding patient access to these techniques. CLINICAL TRIAL REGISTRATION: NCT05156099.

Assistive artificial intelligence for ultrasound image interpretation in regional anaesthesia: an external validation study.

BACKGROUND: Ultrasonound is used to identify anatomical structures during regional anaesthesia and to guide needle insertion and injection of local anaesthetic. ScanNav Anatomy Peripheral Nerve Block (Intelligent Ultrasound, Cardiff, UK) is an artificial intelligence-based device that produces a colour overlay on real-time B-mode ultrasound to highlight anatomical structures of interest. We evaluated the accuracy of the artificial-intelligence colour overlay and its perceived influence on risk of adverse events or block failure. METHODS: Ultrasound-guided regional anaesthesia experts acquired 720 videos from 40 volunteers (across nine anatomical regions) without using the device. The artificial-intelligence colour overlay was subsequently applied. Three more experts independently reviewed each video (with the original unmodified video) to assess accuracy of the colour overlay in relation to key anatomical structures (true positive/negative and false positive/negative) and the potential for highlighting to modify perceived risk of adverse events (needle trauma to nerves, arteries, pleura, and peritoneum) or block failure. RESULTS: The artificial-intelligence models identified the structure of interest in 93.5% of cases (1519/1624), with a false-negative rate of 3.0% (48/1624) and a false-positive rate of 3.5% (57/1624). Highlighting was judged to reduce the risk of unwanted needle trauma to nerves, arteries, pleura, and peritoneum in 62.9-86.4% of cases (302/480 to 345/400), and to increase the risk in 0.0-1.7% (0/160 to 8/480). Risk of block failure was reported to be reduced in 81.3% of scans (585/720) and to be increased in 1.8% (13/720). CONCLUSIONS: Artificial intelligence-based devices can potentially aid image acquisition and interpretation in ultrasound-guided regional anaesthesia. Further studies are necessary to demonstrate their effectiveness in supporting training and clinical practice. CLINICAL TRIAL REGISTRATION: NCT04906018.

A study of validity and usability evidence for non-technical skills assessment tools in simulated adult resuscitation scenarios.

BACKGROUND: Non-technical skills (NTS) assessment tools are widely used to provide formative and summative assessment for healthcare professionals and there are now many of them. This study has examined three different tools designed for similar settings and gathered evidence to test their validity and usability. METHODS: Three NTS assessment tools designed for use in the UK were used by three experienced faculty to review standardized videos of simulated cardiac arrest scenarios: ANTS (Anesthetists' Non-Technical Skills), Oxford NOTECHS (Oxford NOn-TECHnical Skills) and OSCAR (Observational Skill based Clinical Assessment tool for Resuscitation). Internal consistency, interrater reliability and quantitative and qualitative analysis of usability were analyzed for each tool. RESULTS: Internal consistency and interrater reliability (IRR) varied considerably for the three tools across NTS categories and elements. Intraclass correlation scores of three expert raters ranged from poor (task management in ANTS [0.26] and situation awareness (SA) in Oxford NOTECHS [0.34]) to very good (problem solving in Oxford NOTECHS [0.81] and cooperation [0.84] and SA [0.87] in OSCAR). Furthermore, different statistical tests of IRR produced different results for each tool. Quantitative and qualitative examination of usability also revealed challenges in using each tool. CONCLUSIONS: The lack of standardization of NTS assessment tools and training in their use is unhelpful for healthcare educators and students. Educators require ongoing support in the use of NTS assessment tools for the evaluation of individual healthcare professionals or healthcare teams. Summative or high-stakes examinations using NTS assessment tools should be undertaken with at least two assessors to provide consensus scoring. In light of the renewed focus on simulation as an educational tool to support and enhance training recovery in the aftermath of COVID-19, it is even more important that assessment of these vital skills is standardized, simplified and supported with adequate training.

Artificial Intelligence: Innovation to Assist in the Identification of Sono-anatomy for Ultrasound-Guided Regional Anaesthesia.

Ultrasound-guided regional anaesthesia (UGRA) involves the targeted deposition of local anaesthesia to inhibit the function of peripheral nerves. Ultrasound allows the visualisation of nerves and the surrounding structures, to guide needle insertion to a perineural or fascial plane end point for injection. However, it is challenging to develop the necessary skills to acquire and interpret optimal ultrasound images. Sound anatomical knowledge is required and human image analysis is fallible, limited by heuristic behaviours and fatigue, while its subjectivity leads to varied interpretation even amongst experts. Therefore, to maximise the potential benefit of ultrasound guidance, innovation in sono-anatomical identification is required.Artificial intelligence (AI) is rapidly infiltrating many aspects of everyday life. Advances related to medicine have been slower, in part because of the regulatory approval process needing to thoroughly evaluate the risk-benefit ratio of new devices. One area of AI to show significant promise is computer vision (a branch of AI dealing with how computers interpret the visual world), which is particularly relevant to medical image interpretation. AI includes the subfields of machine learning and deep learning, techniques used to interpret or label images. Deep learning systems may hold potential to support ultrasound image interpretation in UGRA but must be trained and validated on data prior to clinical use.Review of the current UGRA literature compares the success and generalisability of deep learning and non-deep learning approaches to image segmentation and explains how computers are able to track structures such as nerves through image frames. We conclude this review with a case study from industry (ScanNav Anatomy Peripheral Nerve Block; Intelligent Ultrasound Limited). This includes a more detailed discussion of the AI approach involved in this system and reviews current evidence of the system performance.The authors discuss how this technology may be best used to assist anaesthetists and what effects this may have on the future of learning and practice of UGRA. Finally, we discuss possible avenues for AI within UGRA and the associated implications.

Validation of the Partners at Care Transitions Measure (PACT-M): assessing the quality and safety of care transitions for older people in the UK.

BACKGROUND: The Partners at Care Transitions Measure (PACT-M) is a patient-reported questionnaire for evaluation of the quality and safety of care transitions from hospital to home, as experienced by older adults. PACT-M has two components; PACT-M 1 to capture the immediate post discharge period and PACT-M 2 to assess the experience of managing care at home. In this study, we aim to examine the psychometric properties, factor structure, validity and reliability of the PACT-M. METHODS: We administered the PACT-M over the phone and by mail, within one week post discharge with 138 participants and one month after discharge with 110 participants. We performed principal components analysis and factors were assessed for internal consistency, reliability and construct validity. RESULTS: Reliability was assessed by calculating Cronbach's alpha for the 9-item PACT-M 1 and 8-item PACT-M 2 and exploratory factor analysis was performed to evaluate dimensionality of the scales. Principal components analysis was chosen using pair-wise deletion. Both PACT-M 1 and PACT-M 2 showed high internal consistency and good internal reliability values and conveyed unidimensional scale characteristics with high reliability scores; above 0.8. CONCLUSIONS: The PACT-M has shown evidence to suggest that it is a reliable measure to capture patients' perception of the quality of discharge arrangements and also on patients' ability to manage their care at home one month post discharge. PACT-M 1 is a marker of patient experience of transition and PACT-M 2 of coping at home.

Developing a measure to assess the quality of care transitions for older people.

BACKGROUND: The transition of older patients (over 65 years of age) from hospital to their own home is a time when patients are at high risk. No measure currently exists to assess the experience, quality and safety of care transitions relevant to UK population. We aim to describe the development and initial testing of the Partners at Care Transitions Measure (PACT-M) as a patient-reported questionnaire for evaluation of the quality and safety of care transitions from hospital to home in older patients. METHODS: We used an established measure development procedure which includes conceptualising the components of care transitions, item development, conducting a modified Delphi process and pilot-testing of the PACT-M with patients over 65 years old using telephone administration. RESULTS: Pilot testing of the PACT-M suggests that the components identified cover the issues of most importance to patients. Face validity testing showed that the measure in its current form is acceptable to older patients. CONCLUSIONS: The measure developed in this study shows promise for use by those involved in planning, implementing and evaluating discharge care, and could be used to inform interventions to improve the transition from hospital to home for older patients.