Utility of Artificial Intelligence for Real-Time Anatomical Landmark Identification in Ultrasound-Guided Thoracic Paravertebral Block.

Thoracic paravertebral block (TPVB) is a common method of inducing perioperative analgesia in thoracic and abdominal surgery. Identifying anatomical structures in ultrasound images is very important especially for inexperienced anesthesiologists who are unfamiliar with the anatomy. Therefore, our aim was to develop an artificial neural network (ANN) to automatically identify (in real-time) anatomical structures in ultrasound images of TPVB. This study is a retrospective study using ultrasound scans (both video and standard still images) that we acquired. We marked the contours of the paravertebral space (PVS), lung, and bone in the TPVB ultrasound image. Based on the labeled ultrasound images, we used the U-net framework to train and create an ANN that enabled real-time identification of important anatomical structures in ultrasound images. A total of 742 ultrasound images were acquired and labeled in this study. In this ANN, the Intersection over Union (IoU) and Dice similarity coefficient (DSC or Dice coefficient) of the paravertebral space (PVS) were 0.75 and 0.86, respectively, the IoU and DSC of the lung were 0.85 and 0.92, respectively, and the IoU and DSC of the bone were 0.69 and 0.83, respectively. The accuracies of the PVS, lung, and bone were 91.7%, 95.4%, and 74.3%, respectively. For tenfold cross validation, the median interquartile range for PVS IoU and DSC was 0.773 and 0.87, respectively. There was no significant difference in the scores for the PVS, lung, and bone between the two anesthesiologists. We developed an ANN for the real-time automatic identification of thoracic paravertebral anatomy. The performance of the ANN was highly satisfactory. We conclude that AI has good prospects for use in TPVB. Clinical registration number: ChiCTR2200058470 (URL: http://www.chictr.org.cn/showproj.aspx?proj=152839 ; registration date: 2022-04-09).

Examining the impact perceptual learning artificial-intelligence-based on the incidence of paresthesia when performing the ultrasound-guided popliteal sciatic block: simulation-based randomized study.

OBJECTIVE: To explore the impact of artificial-intelligence perceptual learning when performing the ultrasound-guided popliteal sciatic block. METHODS: This simulation-based randomized study enrolled residents who underwent ultrasound-guided sciatic nerve block training at the Department of Anesthesiology of Beijing Jishuitan Hospital between January 2022 and February 2022. Residents were randomly divided into a traditional teaching group and an AI teaching group. All residents attended the same nerve block theory courses, while those in the AI teaching group participated in training course using an AI-assisted nerve identification system based on a convolutional neural network instead of traditional training. RESULTS: A total of 40 residents were included. The complication rates of paresthesia during puncture in the first month of clinical sciatic nerve block practice after training were significantly lower in the AI teaching group than in the traditional teaching group [11 (4.12%) vs. 36 (14.06%), P = 0.000093]. The rates of paresthesia/pain during injection were significantly lower in the AI teaching group than in the traditional teaching group [6 (2.25%) vs. 17 (6.64%), P = 0.025]. The Assessment Checklist for Ultrasound-Guided Regional Anesthesia (32 ± 3.8 vs. 29.4 ± 3.9, P = 0.001) and nerve block self-rating scores (7.53 ± 1.62 vs. 6.49 ± 1.85, P < 0.001) were significantly higher in the AI teaching group than in the traditional teaching group. There were no significant differences in the remaining indicators. CONCLUSION: The inclusion of an AI-assisted nerve identification system based on convolutional neural network as part of the training program for ultrasound-guided sciatic nerve block via the popliteal approach may reduce the incidence of nerve paresthesia and this might be related to improved perceptual learning. CLINICAL TRIAL: CHiCTR2200055115 , registered on 1/ January /2022.

General anesthesia combined with bilateral 2-level erector spinae plane block may accelerate postoperative gastrointestinal function recovery and rehabilitation process in patients undergoing posterior lumbar surgery: A randomized controlled trial.

BACKGROUND: This randomized controlled trial explored whether bilateral 2-level erector spinae plane block could accelerate postoperative gastrointestinal function and rehabilitation in patients undergoing posterior lumbar surgery. METHODS: A total of 80 adult patients undergoing posterior lumbar surgery between March 2021 and August 2021 were randomized to either ultrasound-guided bilateral 2-level erector spinae plane block (group E) or not (group C). General anesthesia was routinely performed. The primary outcome was the time of the first flatus after surgery. We also recorded the first food and liquid intake, first off-bed activity, days of hospital stay, and postoperative complications. Postoperative visual analog scale score and opioid consumption were also recorded. A venous blood sample was taken to measure the serum concentration of lipopolysaccharides, c-reactive protein, tumor necrosis factor-alpha, interleukin-6, and blood glucose before induction of anesthesia, immediately after, and 24 and 48 hours after surgery. RESULTS: Seventy-seven patients, 39 in group C and 38 in group E, finished the trial. Patients in group E had a significantly shorter time to first flatus (16.2 ± 3.2 vs 19.7 ± 3.0 hours, P < .05), earlier liquid intake (1.7 ± 0.2 vs 1.9 ± 0.3 hours, P < .05), earlier food intake (1.9 ± 0.2 vs 2.1 ± 0.3 hours, P < .05), and first off-bed activity (27.9 ± 3.2 vs 31.4 ± 3.3 h, P < .05). Patients in group E had shorter postoperative hospital stay (4.6 [4.2-5.5] d vs 5.4 [4.5-6.3], P < .05). We found that patients in group E had less pain and total sufentanil consumption (129 [120-133] vs 138 [132-147] µg, P < .05) within 24 hours after surgery. At 24 hours after surgery, the serum concentrations of lipopolysaccharides, tumor necrosis factor-alpha, interleukin-6, and C-reactive protein in group E were significantly decreased compared to group C (P < .05). CONCLUSION: Bilateral 2-level erector spinae plane block can accelerate gastrointestinal function recovery and shorten the length of hospital stay in patients undergoing open posterior lumbar surgery. The potential mechanism may attribute to the opioids-sparing effects and anti-stress-related anti-inflammatory effects of bilateral 2-level erector spinae plane block.

Effects of erector spinae plane block and retrolaminar block on analgesia for multiple rib fractures: a randomized, double-blinded clinical trial.

OBJECTIVE: To investigate the effects of Erector Spinae Plane Block (ESPB) and Retrolaminar Block (RLB) on intra- and postoperative analgesia in patients with Multiple Rib Fractures (MRFs). METHODS: A total of 80 MRFs patients were randomly divided into the ESPB (Group E) and RLB (Group R) groups. After general anesthesia, ESPB and RLB were performed under ultrasound guidance, respectively, together with 20 mL of 0.5% ropivacaine and Patient-Controlled Intravenous Analgesia (PCIA). RESULTS: Thirty-four cases in Group E and 33,cases in Group R showed unclear paravertebral spaces. The intraoperative dosage of remifentanil (mean ± SD) (392.8 ± 118.7 vs. 501.7 ± 190.0 µg) and postoperative morphine PCIA dosage, (7.35 ± 1.55 vs. 14.73 ± 2.18 mg) in Group R were significantly less than those in Group E; the Visual Analog Scale (VAS) scores in Group R at 2 (2.7 ± 1.2 vs. 3.4 ± 1.4), 4 (2.2 ± 1.1 vs. 2.8 ± 0.9), 12 (2.5 ± 0.9 vs. 3.0 ± 0.8), and 24 hours (2.6 ± 1.0 vs. 3.1 ± 0.9) after surgery were significantly lower than those in Group E. Finally, the normal respiratory diaphragm activity (2.17 ± 0.22 vs. 2.05 ± 0.19), pH (median [IQR] (7.38 [7.31-7.45] vs. 7.36 [7.30-7.42]), and partial pressure of carbon dioxide (PaCO2) (44 [35-49] vs. 42.5 [30-46]) after the operation in Group R were significantly better than those in Group E (p < 0.05). CONCLUSIONS: RLB was a more effective analgesic method than ESPB in the treatment of MRF.

Comparison of the feasibility and validity of a one-level and a two-level erector spinae plane block combined with general anesthesia for patients undergoing lumbar surgery.

Background: Spinal surgery causes severe postoperative pain. An erector spinae plane (ESP) block can relieve postoperative pain, but the optimal blocking method has not been defined. The aim of this study is to compare the feasibility of a one-level and a two-level lumbar ESP block and their effect on intraoperative and postoperative analgesia in lumbar spinal surgery. Methods: A total of 83 adult patients who were scheduled for posterior lumbar interbody fusion were randomly divided into two groups. Patients in Group I (n = 42) received an ultrasound-guided bilateral one-level ESP block with 0.3% ropivacaine, while patients in Group II (n = 41) received a bilateral two-level ESP block. Blocking effectiveness was evaluated, including whether a sensory block covered the surgical incision, sensory decrease in anterior thigh, and quadriceps strength decrease. Intraoperative anesthetic dosage, postoperative visual analogue scale scores of pain, opioid consumption, rescue analgesia, and opioid-related side effects were analyzed. Results: Of the total number, 80 patients completed the clinical trial and were included in the analysis, with 40 in each group. The time to complete the ESP block was significantly longer in Group II than in Group I (16.0 [14.3, 17.0] min vs. 9.0 [8.3, 9.0] min, P = 0.000). The rate of the sensory block covering the surgical incision at 30 min was significantly higher in Group II than in Group I (100% [40/40] vs. 85.0% [34/40], P = 0.026). The rate of the sensory block in the anterior thigh was higher in Group II (43.8% [35/80] vs. 27.5% [22/80], P = 0.032), but the rate of quadriceps strength decrease did not differ significantly between the groups. The mean effect-site remifentanil concentration during intervertebral decompression was lower in Group II than in Group I (2.9 ± 0.3 ng/ml vs. 3.3 ± 0.5 ng/ml, P = 0.007).There were no significant differences between the groups in terms of intraoperative analgesic consumption, postoperative analgesic consumption, and postoperative VAS pain scores at rest and with movement within 24 h. There were no block failures, block-related complications, and postoperative infection. Conclusions: Among patients undergoing posterior lumbar interbody fusion, the two-level ESP block provided a higher rate of coverage of the surgical incision by the sensory block when compared with the one-level method, without increasing the incidence of procedure-related complications. Clinical Trial Registration: www.chictr.org.cn, identifier: ChiCTR2100043596.

Neuroprotective effect of ginsenoside Rg1 prevents cognitive impairment induced by isoflurane anesthesia in aged rats via antioxidant, anti-inflammatory and anti-apoptotic effects mediated by the PI3K/AKT/GSK-3ß pathway.

Ginsenoside Rg1 is the primary active substance in ginseng, and it has multiple pharmacological actions. Investigations on the pharmacologic action of ginsenoside Rg1 have developed, with a particular focus on the regulation of metabolism. The present study hypothesized that the neuroprotective effects of ginsenoside Rg1 prevent cognitive impairment induced by isoflurane anesthesia via antioxidant, anti­inflammatory and anti­apoptotic effects, mediated by the phosphoinositide 3­kinase (PI3K)/AKT/glycogen synthase kinase­3ß (GSK­3ß) pathway in aged rats. Sprague­Dawley rats were divided into isoflurane and ginsenoside Rg1 groups and were treated with 20 mg/kg ginsenoside Rg1 for 7 days. Morris water maze was performed to analyze the cognitive function of the rats. Enzyme­linked immunosorbent assays were used to analyze the levels of malondialdehyde, glutathione, interleukin (IL)­1ß, IL­6 and caspase 3. The protein expression levels of AKT, GSK 3ß, p21WAF1/CIP1 and p53 were measured using western blot analysis. Ginsenoside Rg1 significantly improved cognitive function, and exhibited antioxidant and anti­inflammatory effects, demonstrating the neuroprotective effects of ginsenoside Rg1 against the effect of isoflurane anesthesia in the rats. In addition, ginsenoside Rg1 significantly reduced caspase­3 activity, upregulated the expression of PI3K/AKT/GSK­3ß and downregulated the mRNA expression levels of p21WAF1/CIP1 and p53 in the aged rats exposed to isoflurane anesthesia. The data obtained in the present study provided evidence that the neuroprotective effects of ginsenoside Rg1 prevented the cognitive impairment induced by isoflurane anesthesia via antioxidant, anti­inflammatory and anti­apoptotic effects, mediated by the PI3K/AKT/GSK­3ß pathway.