Current evidence on artificial intelligence in regional anesthesia

The recent advancement in regional anesthesia (RA) has been largely attributed to ultrasound technology. However, the safety and efficiency of ultrasound-guided nerve blocks depend upon the skill and experience of the performer. Even with adequate training, experience, and knowledge, human-related limitations such as fatigue, failure to recognize the correct anatomical structure, and unintentional needle or probe movement can hinder the overall effectiveness of RA. The amalgamation of artificial intelligence (AI) to RA practice has promised to override these human limitations. Machine learning, an integral part of AI can improve its performance through continuous learning and experience, like the human brain. It enables computers to recognize images and patterns specifically useful in anatomic structure identification during the performance of RA. AI can provide real-time guidance to clinicians by highlighting important anatomical structures on ultrasound images, and it can also assist in needle tracking and accurate deposition of local anesthetics. The future of RA with AI integration appears promising, yet obstacles such as device malfunction, data privacy, regulatory barriers, and cost concerns can deter its clinical implementation. The current mini review deliberates the current application, future direction, and barrier to the application of AI in RA practice.

Artificial intelligence-assisted ultrasound-guided regional anaesthesia: An explorative scoping review

Purpose

The present study reviews the available scientific literature on artificial intelligence (AI)-assisted ultrasound-guided regional anaesthesia (UGRA) and evaluates the reported intraprocedural parameters and postprocedural outcomes.

Methods

A literature search was performed on 19 September 2023, using the Medline, EMBASE, CINAHL, Cochrane Library and Google Scholar databases by experts in electronic searching. All study designs were considered with no restrictions regarding patient characteristics or cohort size. Outcomes assessed included the accuracy of AI-model tracking, success at the first attempt, differences in outcomes between AI-assisted and unassisted UGRA, operator feedback and case-report data.

Results

A joint adaptive median binary pattern (JAMBP) has been applied to improve the tracking procedure, while a particle filter (PF) is involved in feature extraction. JAMBP combined with PF was most accurate on all images for landmark identification, with accuracy scores of 0.83, 0.93 and 0.93 on original, preprocessed and filtered images, respectively. Evaluation of first-attempt success of spinal needle insertion revealed first-attempt success in most patients. When comparing AI application versus UGRA alone, a significant statistical difference (p < 0.05) was found for correct block view, correct structure identification and decrease in mean injection time, needle track adjustments and bone encounters in favour of having AI assistance. Assessment of operator feedback revealed that expert and nonexpert operator feedback was overall positive.

Conclusion

AI appears promising to enhance UGRA as well as to positively influence operator training. AI application of UGRA may improve the identification of anatomical structures and provide guidance for needle placement, reducing the risk of complications and improving patient outcomes.

Level of Evidence

Level IV.

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.

Regional anesthesia for pain control in children with solid tumors-a review of case reports

Introduction

Around seventy percent of all childhood cancer patients suffer from severe pain. This pain can arise from various sources, including tumors themselves, pain caused by metastasizing tumor cells or as the outcome of therapy meant to deal with tumors. If managed inadequately, such pain can lead to many hazardous sequelae. However, there are extreme cases when pain does not respond to standard treatment. For such cases, regional anesthesia or nerve blocks are utilized as the utmost pain control measure. Blocks are used to treat pain in patients who no longer respond to conventional opioid-based treatment or whose worsened condition makes it impossible to receive any other therapy. The data regarding the use of regional anesthesia for such cases in the children population is limited.

Methods

For this review we searched for case reports in Scopus and PubMed from inception to 2023. The descriptive search items included terms related to childhood cancer and the description of each block. The inclusion criteria for review include children (0-18 years old) receiving oncology-related surgical procedures or palliative care. The data collection was limited to solid tumor-related cases only. We analyzed a total of 38 studies that included case reports and one retrospective study.

Results and discussion

It was concluded that nerve blocks, although rarely performed, are a safe and efficient way of pain control in children with solid tumors. The major settings for block performance are postoperative pain control and palliative care. We observed that block indication and its outcomes depend on unique health circumstances in which they should be performed. Patients with similar diagnoses had differing outcomes while receiving the same block treatment.

The Advances and Utility of Artificial Intelligence and Robotics in Regional Anesthesia: An Overview of Recent Developments

The integration of artificial intelligence (AI) and robotics in regional anesthesia has brought about transformative changes in acute pain management for surgical procedures. This review explores the evolving landscape of AI and robotics applications in regional anesthesia, outlining their potential benefits, challenges, and ethical considerations. AI-driven pain assessment, real-time guidance for needle placement during nerve blocks, and predictive modeling solutions for nerve blocks have the potential to enhance procedural precision and improve patient outcomes. Robotic technology aids in accurate needle insertion, reducing complications and improving pain relief. This review also highlights the ethical and safety considerations surrounding AI implementation, emphasizing data security and professional training. While challenges such as costs and regulatory hurdles exist, ongoing research and clinical trials demonstrate the practical utility of these technologies. In conclusion, AI and robotics have the potential to reshape regional anesthesia practice, ultimately improving patient care and procedural accuracy in pain management.

"Knowing It Before Blocking It," the ABCD of the Peripheral Nerves: Part C (Prevention of Nerve Injuries)

"A clever person solves the problem. A wise person avoids it" (Albert Einstein). There is no convincing evidence that any modality 100% effectively prevents nerve injury. The risk of nerve injury remains the same even with the ultrasound due to limitations in the resolution of images and inter-operator and inter-patient differences. In a nutshell, caution is required when dealing with precious nerves in the perioperative period, either during peripheral nerve blocks (PNBs), patient positioning, or surgery. Identifying pre-existing nerve injury, either due to trauma or an existing neuropathy, and preventing further nerve injury should be an important goal in providing safe regional anesthesia (RA). Multimodal monitoring is key to avoiding multifactorial nerve injuries. The use of triple guidance (ultrasound + peripheral nerve stimulator + injection pressure monitor) during PNBs further improves the safety of RA. The ultrasound helps in real-time visualization of the nerve, needle, and drug spread; the peripheral nerve stimulator helps confirm the target nerves; and the injection pressure monitor helps avoid nerve injury. Such multimodalities can also give the confidence to administer PNB without risk of nerve injury. This article is part of the comprehensive overview of the essential understanding of peripheral nerves before blocking them. It describes various preventive measures to avoid peripheral nerve injuries while administering PNBs. It will help readers understand the importance of prevention in each step to avoid perioperative PNIs.

Pupillary Pain Index Predicts Postoperative Pain but Not the Effect of Peripheral Regional Anaesthesia in Patients Undergoing Total Hip or Total Knee Arthroplasty: An Observational Study

Background and Objectives: The pupillary pain index (PPI) allows the evaluation of intraoperative nociception by measuring pupillary reaction after a localized electrical stimulus. It was the objective of this observational cohort study to investigate the pupillary pain index (PPI) as a method to evaluate the fascia iliaca block (FIB) or adductor canal block (ACB) sensory areas during general anaesthesia in orthopaedic patients with lower-extremity joint replacement surgery. Materials and Methods: Orthopaedic patients undergoing hip or knee arthroplasty were included. After anaesthesia induction, patients received an ultrasound-guided single-shot FIB or ACB with 30 mL and 20 mL of 0.375% ropivacaine, respectively. Anaesthesia was maintained with isoflurane or propofol/remifentanil. The first PPI measurements were performed after anaesthesia induction and before block insertion, the second at the end of surgery. Pupillometry scores were evaluated in the area of the femoral or saphenous nerve (target) and C3 dermatome (control). Primary outcomes were differences between PPIs before and after peripheral block insertion as well as the relationship between PPIs and postoperative pain scores; secondary outcomes were the relationship between PPIs and opioid requirements after surgery. Results: PPI decreased significantly from the first to the second measurement (4.17 ± 2.7 vs. 1.6 ± 1.2, p < 0.001 for target; 4.46 ± 2.7 vs. 2.17 ± 2.1, p < 0.001 for control). Control and target measurements did not show significant differences. A linear regression analysis showed that early postoperative pain scores could be predicted with intraoperative piritramide with improved prediction after adding PPI scores, PCA opioids and surgery type. Forty-eight-hour pain scores at rest and in movement were correlated with intraoperative piritramide and control PPI after the PNB in movement and with second-postoperative-day opioids and target PPI scores before block insertion, respectively. Conclusions: While the effect of an FIB and ACB could not be shown with PPI postoperative pain scores due to a large effect of opioids, perioperative PPI was shown to be associated with postoperative pain. These results suggest that preoperative PPI may be used to predict postoperative pain.

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.

A Systematic Review and Meta-analysis of General versus Regional Anesthesia for Lower Extremity Amputation

OBJECTIVE

Postoperative morbidity in patients undergoing lower extremity amputation (LEA) has remained high. Studies investigating the influence of the anesthetic modality on the postoperative outcomes have yielded conflicting results. The aim of our study was to assess the effects of regional anesthesia vs general anesthesia on postoperative complications for patients undergoing LEA.

METHODS

We systematically searched PubMed, Embase, MEDLINE, Web of Science, and Google Scholar from 1990 to 2022 for studies investigating the effect of the anesthetic modality on the postoperative outcomes after LEA. Regional anesthesia (RA) included neuraxial anesthesia and peripheral nerve blocks. The outcomes included 30-day mortality, respiratory failure (unplanned postoperative intubation, failure to wean, mechanical ventilation >24 hours), surgical site infection, cardiac complications, urinary tract infection, renal failure, sepsis, venous thrombosis, pneumonia, and myocardial infarction.

RESULTS

Of the 25 studies identified, we included 10 retrospective observational studies with 81,736 patients, of whom 69,754 (85.3%) had received general anesthesia (GA) and 11,980 (14.7%) had received RA. In the GA group, 50,468 patients were men (63.8%), and in the RA group, 7813 patients were men (62.3%). The results of the meta-analyses revealed that GA was associated with a higher rate of respiratory failure (odds ratio, 1.38; 95% confidence interval, 1.06-1.80; P = .02) and sepsis (odds ratio, 1.21; 95% confidence interval, 1.11-1.33; P < .0001) compared with RA. No differences were found in postoperative 30-day mortality, surgical site infection, cardiac complications, urinary tract infection, renal failure, venous thrombosis, pneumonia, and myocardial infarction between the GA and RA groups.

CONCLUSIONS

The results of our meta-analysis have shown that GA could be associated with a higher rate of respiratory failure and sepsis compared with RA for LEA.

Recommendations for anatomical structures to identify on ultrasound for the performance of intermediate and advanced blocks in ultrasound-guided regional anesthesia

Recent recommendations describe a set of core anatomical structures to identify on ultrasound for the performance of basic blocks in ultrasound-guided regional anesthesia (UGRA). This project aimed to generate consensus recommendations for core structures to identify during the performance of intermediate and advanced blocks. An initial longlist of structures was refined by an international panel of key opinion leaders in UGRA over a three-round Delphi process. All rounds were conducted virtually and anonymously. Blocks were considered twice in each round: for “orientation scanning” (the dynamic process of acquiring the final view) and for “block view” (which visualizes the block site and is maintained for needle insertion/injection). A “strong recommendation” was made if ≥75% of participants rated any structure as “definitely include” in any round. A “weak recommendation” was made if >50% of participants rated it as “definitely include” or “probably include” for all rounds, but the criterion for strong recommendation was never met. Structures which did not meet either criterion were excluded. Forty-one participants were invited and 40 accepted; 38 completed all three rounds. Participants considered the ultrasound scanning for 19 peripheral nerve blocks across all three rounds. Two hundred and seventy-four structures were reviewed for both orientation scanning and block view; a “strong recommendation” was made for 60 structures on orientation scanning and 44 on the block view. A “weak recommendation” was made for 107 and 62 structures, respectively. These recommendations are intended to help standardize teaching and research in UGRA and support widespread and consistent practice.

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.

International consensus on anatomical structures to identify on ultrasound for the performance of basic blocks in ultrasound-guided regional anesthesia

There is no universally agreed set of anatomical structures that must be identified on ultrasound for the performance of ultrasound-guided regional anesthesia (UGRA) techniques. This study aimed to produce standardized recommendations for core (minimum) structures to identify during seven basic blocks. An international consensus was sought through a modified Delphi process. A long-list of anatomical structures was refined through serial review by key opinion leaders in UGRA. All rounds were conducted remotely and anonymously to facilitate equal contribution of each participant. Blocks were considered twice in each round: for "orientation scanning" (the dynamic process of acquiring the final view) and for the "block view" (which visualizes the block site and is maintained for needle insertion/injection). Strong recommendations for inclusion were made if ≥75% of participants rated a structure as "definitely include" in any round. Weak recommendations were made if >50% of participants rated a structure as "definitely include" or "probably include" for all rounds (but the criterion for "strong recommendation" was never met). Thirty-six participants (94.7%) completed all rounds. 128 structures were reviewed; a "strong recommendation" is made for 35 structures on orientation scanning and 28 for the block view. A "weak recommendation" is made for 36 and 20 structures, respectively. This study provides recommendations on the core (minimum) set of anatomical structures to identify during ultrasound scanning for seven basic blocks in UGRA. They are intended to support consistent practice, empower non-experts using basic UGRA techniques, and standardize teaching and research.

Identifying anatomical structures on ultrasound: assistive artificial intelligence in ultrasound-guided regional anesthesia

Ultrasound-guided regional anesthesia involves visualizing sono-anatomy to guide needle insertion and the perineural injection of local anesthetic. Anatomical knowledge and recognition of anatomical structures on ultrasound are known to be imperfect amongst anesthesiologists. This investigation evaluates the performance of an assistive artificial intelligence (AI) system in aiding the identification of anatomical structures on ultrasound. Three independent experts in regional anesthesia reviewed 40 ultrasound scans of seven body regions. Unmodified ultrasound videos were presented side-by-side with AI-highlighted ultrasound videos. Experts rated the overall system performance, ascertained whether highlighting helped identify specific anatomical structures, and provided opinion on whether it would help confirm the correct ultrasound view to a less experienced practitioner. Two hundred and seventy-five assessments were performed (five videos contained inadequate views); mean highlighting scores ranged from 7.87 to 8.69 (out of 10). The Kruskal-Wallis H-test showed a statistically significant difference in the overall performance rating (χ² [6] = 36.719, asymptotic p < 0.001); regions containing a prominent vascular landmark ranked most highly. AI-highlighting was helpful in identifying specific anatomical structures in 1330/1334 cases (99.7%) and for confirming the correct ultrasound view in 273/275 scans (99.3%). These data demonstrate the clinical utility of an assistive AI system in aiding the identification of anatomical structures on ultrasound during ultrasound-guided regional anesthesia. Whilst further evaluation must follow, such technology may present an opportunity to enhance clinical practice and energize the important field of clinical anatomy amongst clinicians.

Continuous erector spinae plane block at lumbar level for relief of severe pain due to hip fracture: case series

Introduction: Hip fracture pain is frequently acute and disabling and increases perioperative complications in the patient; hence it requires a multimodal analgesia approach. This case series describes the continuous erector spinae plane block at the lumbar level for hip fracture analgesia. Methods: A search was conducted of patients with hip fracture referred to the pain service of Hospital Universitario San Vicente Fundación (HUSVF) from August 2019 to March 2020, who had undergone continuous erector spinae plane block as part of their analgesic regimen. Results: A total of 6 patients, 4 females and 2 males with an average age of 75 years were identified. A reduction in pain intensity from acute to mild or absent was observed in every case, up to 24 hours after the initial injection. 66 % experienced a relapse of severe pain after 24 hours and 2 patients the catheter functionality failed after 24 hours. One patient underwent dermatome pinprick assessment. Conclusions: The continuous erector spinae plane block with a single injection provided analgesic efficacy similar to other single injection peripheral blocks, although continuous analgesia for more than 24 hours was not achieved. Some variations in the block technique described may improve the analgesic effectiveness in patients with hip fracture pain.

Increased body mass index does not impact the imaging quality of focused assessment with sonography in trauma

BACKGROUND

Many clinicians believe that a patient's body mass index (BMI) affects the likelihood of obtaining high quality ultrasound images.

OBJECTIVES

To assess the hypothesis that increased BMI is associated with worsening focused assessment with sonography in trauma (FAST) image quality.

METHODS

We conducted a retrospective single-center study of FAST examinations performed in a large academic emergency department (ED) with fellowship-trained emergency ultrasonography faculty performing quality assurance review.

RESULTS

Mean (SD) BMI was 28.0 (6.6) among the 302 included studies. The overall quality rating tended to decrease as BMI increased but did not achieve statistical significance in a univariable setting (P = .06) or after adjustment for age and sex (P = .06). Operators perception of image adequacy was largely unaffected by BMI, with the exception of the pericardial view.

CONCLUSION

This study did not identify a statistically significant difference in FAST quality with increased BMI. This result may help assuage clinician concerns about ultrasonography for patients in the ED.