Improving case duration accuracy of orthopedic surgery using bidirectional encoder representations from Transformers (BERT) on Radiology Reports.

PURPOSE: A major source of inefficiency in the operating room is the mismatch between scheduled versus actual surgical time. The purpose of this study was to demonstrate a proof-of-concept study for predicting case duration by applying natural language processing (NLP) and machine learning that interpret radiology reports for patients undergoing radius fracture repair. METHODS: Logistic regression, random forest, and feedforward neural networks were tested without NLP and with bag-of-words. Another NLP method tested used feedforward neural networks and Bidirectional Encoder Representations from Transformers specifically pre-trained on clinical notes (ClinicalBERT). A total of 201 cases were included. The data were split into 70% training and 30% test sets. The average root mean squared error (RMSE) were calculated (and 95% confidence interval [CI]) from 10-fold cross-validation on the training set. The models were then tested on the test set to determine proportion of times surgical cases would have scheduled accurately if ClinicalBERT was implemented versus historic averages. RESULTS: The average RMSE was lowest using feedforward neural networks using outputs from ClinicalBERT (25.6 min, 95% CI: 21.5-29.7), which was significantly (P < 0.001) lower than the baseline model (39.3 min, 95% CI: 30.9-47.7). Using the feedforward neural network and ClinicalBERT on the test set, the percentage of accurately predicted cases, which was defined by the actual surgical duration within 15% of the predicted surgical duration, increased from 26.8 to 58.9% (P < 0.001). CONCLUSION: This proof-of-concept study demonstrated the successful application of NLP and machine leaning to extract features from unstructured clinical data resulting in improved prediction accuracy for surgical case duration.

Intrathecal Morphine Injection for Postoperative Analgesia Following Gender-Affirming Pelvic Surgery: A Retrospective Case-Control Study.

Background Gender-affirming pelvic surgery (GAPS) can be associated with significant postoperative pelvic pain. Given the lack of available peripheral nerve blocks to the perineum, intrathecal morphine (ITM) injection could offer a potent analgesic modality for this patient population. No prior studies to date have been performed examining the analgesic effects of intrathecal morphine for these patients. Methods This retrospective case-control study aims to understand the postoperative analgesic effects of intrathecal morphine for these patients with a historical comparison group of patients who did not receive intrathecal morphine. Results Fourteen patients presented for gender-affirming pelvic surgery over an eight-month period at a single institution and were offered intrathecal morphine for postoperative analgesia. Their analgesic results were compared to a similar historical group of 13 patients who were not offered or declined intrathecal morphine. Conclusions Intrathecal morphine injection is a potent analgesic modality for patients presenting for gender-affirming pelvic surgery.

Serratus anterior plane versus paravertebral nerve blocks for postoperative analgesia after non-mastectomy breast surgery: a randomized controlled non-inferiority trial.

BACKGROUND: Paravertebral and serratus plane blocks are both used to treat pain following breast surgery. However, it remains unknown if the newer serratus block provides comparable analgesia to the decades-old paravertebral technique. METHODS: Subjects undergoing unilateral or bilateral non-mastectomy breast surgery were randomized to a single-injection serratus or paravertebral block in a subject-masked fashion (ropivacaine 0.5%; 20 mL unilateral; 16 mL/side bilateral). We hypothesized that (1) analgesia would be non-inferior in the recovery room with serratus blocks (measurement: Numeric Rating Scale), and (2) opioid consumption would be non-inferior with serratus blocks in the operating and recovery rooms. In order to claim that serratus blocks are non-inferior to paravertebral blocks, both hypotheses must be at least non-inferior. RESULTS: Within the recovery room, pain scores for participants with serratus blocks (n=49) had a median (IQR) of 4.0 (0-5.5) vs 0 (0-3.0) for those with paravertebral blocks (n=51): 0.95% CI -3.00 to -0.00; p=0.001. However, the difference in morphine equivalents did not reach statistical significance for superiority with the serratus group consuming 14 mg (10-19) vs 10 mg (10-16) for the paravertebral group: 95% CI -4.50 to 0.00, p=0.123. Since the 95% CI lower limit of -4.5 was less than our prespecified margin of -2.0, we failed to conclude non-inferiority of the serratus block with regard to opioid consumption. CONCLUSIONS: Serratus blocks provided inferior analgesia compared with paravertebral blocks. Without a dramatic improvement in safety profile for serratus blocks, it appears that paravertebral blocks are superior to serratus blocks for postoperative analgesia after non-mastectomy breast surgery. TRIAL REGISTRATION NUMBER: NCT03860974.

Association of race and ethnicity in the receipt of regional anesthesia following mastectomy.

BACKGROUND: Regional anesthetic techniques have become increasingly used for the purpose of pain management following mastectomy. Although a variety of beneficial techniques have been described, the delivery of regional anesthesia following mastectomy has yet to be examined for racial or ethnic disparities. We aimed to examine the association of race and ethnicity on the delivery of regional anesthesia in patients undergoing surgical mastectomy using a large national database. METHODS: We used the American College of Surgeons-National Surgical Quality Improvement Program database to identify adult patients aged ≥18 years old who underwent mastectomy from 2014 to 2016. We reported unadjusted estimates of regional anesthesia accordingly to race and ethnicity and examined differences in sociodemographic characteristics and health status. Multivariable logistic regression was used to report the association of race and ethnicity with use of regional anesthesia. RESULTS: A total of 81 345 patients who underwent mastectomy were included, 14 887 (18.3%) of whom underwent regional anesthesia. The unadjusted rate of use of regional anesthesia was 18.9% for white patients, 16.8% for black patients, 15.6% for Asian patients, 16.5% for Native Hawaiian/Pacific Islander patients, 17.8% for American Indian or Alaska Native and 17.4% for unknown race (p<0.001). With respect to ethnicity, the unadjusted rate of regional anesthesia use was 18.4% for non-Hispanic patients vs 16.1% for Hispanic patients vs 18.6% for the unknown ethnicity cohort (p<0.001). On multivariable logistic regression analysis, the odds of receipt of regional anesthesia was 12% lower in black patients and 21% lower in Asian patients compared with white patients (p<0.001). The odds of regional anesthesia use were 13% lower in Hispanic compared with non-Hispanic patients (p<0.001). CONCLUSION: Black and Asian patients had lower odds of undergoing regional anesthesia following mastectomy compared with white counterparts. In addition, Hispanic patients had lower odds of undergoing regional anesthesia than non-Hispanic counterparts. These differences underlie the importance of working to deliver equitable healthcare irrespective of race or ethnicity.

Head-up tilt and hyperventilation produce similar changes in cerebral oxygenation and blood volume: an observational comparison study using frequency-domain near-infrared spectroscopy.

PURPOSE: During anesthesia, maneuvers which cause the least disturbance of cerebral oxygenation with the greatest decrease in intracranial pressure would be most beneficial to patients with intracranial hypertension. Both head-up tilt (HUT) and hyperventilation are used to decrease brain bulk, and both may be associated with decreases in cerebral oxygenation. In this observational study, our null hypothesis was that the impact of HUT and hyperventilation on cerebral tissue oxygen saturation (SctO2) and cerebral blood volume (CBV) are comparable. METHODS: Surgical patients without neurological disease were anesthetized with propofol-remifentanil. Before the start of surgery, frequency-domain near-infrared spectroscopy was used to measure SctO2 and CBV at the supine position, at the 30° head-up and head-down positions, as well as during hypoventilation and hyperventilation. RESULTS: Thirty-three patients were studied. Both HUT and hyperventilation induced small decreases in SctO2 [3.5 (2.6)%; P < 0.001 and 3.0 (1.8)%; P < 0.001, respectively] and in CBV [0.05 (0.07) mL x 100 g(-1); P < 0.001 and 0.06 (0.05) mL x 100 g(-1); P < 0.001, respectively]. There were no differences between HUT to 30° and hyperventilation to an end-tidal carbon dioxide (ETCO2) of 25 mmHg (from 45 mmHg) in both SctO2 (P = 0.3) and CBV (P = 0.4). DISCUSSION: The small but statistically significant decreases in both SctO2 and CBV caused by HUT and hyperventilation are comparable. There was no correlation between the decreases in SctO2 and CBV and the decreases in blood pressure and cardiac output during head-up and head-down tilts. However, the decreases in both SctO2 and CBV correlate with the decreases in ETCO2 during ventilation adjustment.

The impact of phenylephrine, ephedrine, and increased preload on third-generation Vigileo-FloTrac and esophageal doppler cardiac output measurements.

BACKGROUND: Cardiac output (CO) monitoring based on pulse contour analysis (Vigileo-FloTrac) has the potential to be used for goal-directed fluid therapy in the perioperative setting. However, factors such as vasopressor usage may impact Vigileo-FloTrac's reliability in tracking CO changes. We tested third-generation Vigileo-FloTrac system's ability to accurately measure the changes in CO induced by vasopressor administration and increased preload in comparison with esophageal Doppler measurements. METHODS: In 33 anesthetized patients, CO was monitored simultaneously by the third-generation Vigileo-FloTrac and esophageal Doppler. Hemodynamic challenges included phenylephrine (to increase vasomotor tone), ephedrine (to increase myocardial contractility and heart rate), and whole-body tilting (to increase preload). Measurements were performed before and after each intervention. RESULTS: Overall, 176 pairs of CO measurements were obtained. The difference between paired pulse contour and Doppler measurements of CO was 0.14 ± 2.13 L/min (mean ± SD), and the percentage error (2 SD of the difference divided by the mean CO of the reference method) was 66%. The trending ability of pulse contour versus Doppler was 23% (concordance, the percentage of the total number of data points that are in 1 of the 2 quadrants of agreement) after phenylephrine treatment, 69% (concordance) after ephedrine treatment, and 96% (concordance) after whole-body tilting. CONCLUSIONS: The pulse contour method of measuring CO, as implemented in the third-generation Vigileo-FloTrac device, accurately tracks changes in CO when preload changes. However, the pulse contour method does not accurately track changes in CO induced with phenylephrine and ephedrine.