Prediction of intraoperative hypotension using deep learning models based on non-invasive monitoring devices.

PURPOSE: Intraoperative hypotension is associated with adverse outcomes. Predicting and proactively managing hypotension can reduce its incidence. Previously, hypotension prediction algorithms using artificial intelligence were developed for invasive arterial blood pressure monitors. This study tested whether routine non-invasive monitors could also predict intraoperative hypotension using deep learning algorithms. METHODS: An open-source database of non-cardiac surgery patients ( https://vitadb.net/dataset ) was used to develop the deep learning algorithm. The algorithm was validated using external data obtained from a tertiary Korean hospital. Intraoperative hypotension was defined as a systolic blood pressure less than 90 mmHg. The input data included five monitors: non-invasive blood pressure, electrocardiography, photoplethysmography, capnography, and bispectral index. The primary outcome was the performance of the deep learning model as assessed by the area under the receiver operating characteristic curve (AUROC). RESULTS: Data from 4754 and 421 patients were used for algorithm development and external validation, respectively. The fully connected model of Multi-head Attention architecture and the Globally Attentive Locally Recurrent model with Focal Loss function were able to predict intraoperative hypotension 5 min before its occurrence. The AUROC of the algorithm was 0.917 (95% confidence interval [CI], 0.915-0.918) for the original data and 0.833 (95% CI, 0.830-0.836) for the external validation data. Attention map, which quantified the contributions of each monitor, showed that our algorithm utilized data from each monitor with weights ranging from 8 to 22% for determining hypotension. CONCLUSIONS: A deep learning model utilizing multi-channel non-invasive monitors could predict intraoperative hypotension with high accuracy. Future prospective studies are needed to determine whether this model can assist clinicians in preventing hypotension in patients undergoing surgery with non-invasive monitoring.

Recurrence-free survival after curative resection of non-small cell lung cancer between inhalational gas anesthesia and propofol-based total intravenous anesthesia: a multicenter, randomized, clinical trial (GAS TIVA trial): protocol description.

BACKGROUND: Surgery is the primary treatment for non-small cell lung cancer (NSCLC), but microscopic residual disease may be unavoidable. Preclinical studies have shown that volatile anesthetics might suppress host immunity and promote a pro-malignant environment that supports cancer cell proliferation, migration, and angiogenesis, whereas propofol may preserve cell-mediated immunity and inhibit tumor angiogenesis. However, clinical evidence that propofol-based total intravenous anesthesia (TIVA) can reduce tumor recurrence after curative resection remains inconsistent due to the retrospective observational nature of previous studies. Therefore, we will test the hypothesis that the recurrence-free survival (RFS) after curative resection of NSCLC is higher in patients who received TIVA than volatile anesthetics (GAS) in this multicenter randomized trial. METHODS: This double-blind, randomized trial will enroll patients at 22 international sites, subject to study registration, institutional review board approval, and patient written informed consent. Eligible patients are adult patients undergoing lung resection surgery with curative intent for NSCLC. Exclusion criteria will be contraindications to study drugs, American Society of Anesthesiologists physical status IV or higher, or preexisting distant metastasis or malignant tumor in other organs. At each study site, enrolled subjects will be randomly allocated into the TIVA and GAS groups with a 1:1 ratio. This pragmatic trial does not standardize any aspect of patient care. However, potential confounders will be balanced between the study arms. The primary outcome will be RFS. Secondary outcomes will be overall survival and complications within postoperative 7 days. Enrollment of 5384 patients will provide 80% power to detect a 3% treatment effect (hazard ratio of 0.83) at alpha 0.05 for RFS at 3 years. DISCUSSION: Confirmation of the study hypothesis would demonstrate that a relatively minor and low-cost alteration in anesthetic management has the potential to reduce cancer recurrence risk in NSCLC, an ultimately fatal complication. Rejection of the hypothesis would end the ongoing debate about the relationship between cancer recurrence and anesthetic management. TRIAL REGISTRATION: The study protocol was prospectively registered at the Clinical trials ( https://clinicaltrials.gov , NCT06330038, principal investigator: Hyun Joo Ahn; date of first public release: March 25, 2024) before the recruitment of the first participant.

Effect of remimazolam versus propofol anesthesia on postoperative delirium in neurovascular surgery: study protocol for a randomized controlled, non-inferiority trial.

BACKGROUND: Remimazolam is a short-acting benzodiazepine newly approved for the induction and maintenance of general anesthesia. Remimazolam emerges as an ideal drug for the neurosurgical population due to its rapid emergence, enabling early neurological assessment, and its ability to maintain perfusion pressure, which is crucial for preventing cerebral ischemia. However, the use of benzodiazepine has been associated with an increased risk of postoperative delirium (POD). There is currently limited evidence about the relationship between remimazolam-based total intravenous anesthesia (TIVA) and POD. METHODS: In this double-blind, randomized, non-inferiority trial, we plan to include 696 adult patients with American Society of Anesthesiologists physical status class I to III, undergoing elective neurovascular surgery under general anesthesia. After informed consent, the patients will be randomized to receive either remimazolam or propofol-based TIVA with a 1:1 ratio. The primary outcome is the incidence of POD within 5 days after surgery. Secondary outcomes include subtypes, number of positive assessments and severity of POD, emergence agitation, intraoperative awareness and undesirable patient movement, intraoperative hypotension, and postoperative cognitive function. The data will be analyzed in modified intention to treat. DISCUSSION: This trial will evaluate the effect of remimazolam on the development of POD compared to propofol anesthesia. The results of this trial will provide evidence regarding the choice of optimal anesthetics to minimize the risk of POD in neurosurgical patients. TRIAL REGISTRATION: The study protocol was prospectively registered at the Clinical trials ( https://clinicaltrials.gov , NCT06115031, principal investigator: Jiseon Jeong; date of first registration: November 2, 2023, before the recruitment of the first participant.

Comparison of high-flow nasal cannula and conventional nasal cannula during deep sedation for endoscopic submucosal dissection: a randomized controlled trial.

PURPOSE: Adequate oxygenation and airway management during deep sedation can be challenging. We investigated the effect of high-flow nasal cannula (group HF) and conventional nasal cannula (group CO) during sedation for endoscopic submucosal dissection (ESD). METHODS: Patients undergoing ESD with deep sedation were enrolled. The primary outcome was difference in lowest oxygen saturation (SpO2) between the groups. Incidence of hypoxia (SpO2 < 90%), patients with SpO2 < 95%, hypercapnia, and airway interventions; operator satisfaction; and adverse events were recorded. RESULTS: Thirty-two patients in each group completed the study. The mean of minimum SpO2 values was significantly higher in group HF than in group CO (96.8% ± 4.2% vs. 93.3% ± 5.3%, p = 0.005). The incidence of hypoxia was comparable between the groups (4 [12.5%] vs. 6 [18.8%], p = 0.491); however, patients with SpO2 < 95% were significantly less in group HF (5 [15.6%] vs. 18 [56.3%], p = 0.003). Incidence of hypercapnia was higher in group HF than in group CO (14 [46.7%] vs. 5 [16.7%], p = 0.013). Airway rescue interventions were significantly less common in group HF. Satisfaction of operators and post-procedural complications were comparable between the two groups. In multivariable analysis, group CO and higher body mass index were risk factors for airway managements (odds ratio [95% confidence interval]: 6.204 [1.784-21.575], p = 0.004; 1.337 [1.043-1.715], p = 0.022, respectively). CONCLUSIONS: Compared to conventional nasal cannula, high-flow nasal cannula maintained higher minimum SpO2 value during deep sedation with propofol-remifentanil for ESD. TRIAL REGISTRATION: Clinical Trial Registry of the Republic of Korea (KCT0006618, https://cris.nih.go.kr ; registered September 29, 2021; principal investigator: Ji Won Choi).

Anesthesia and cancer recurrence: a narrative review.

Cancer is a leading cause of death worldwide. With the increasingly aging population, the number of emerging cancer cases is expected to increase markedly in the foreseeable future. Surgical resection with adjuvant therapy is the best available option for the potential cure of many solid tumors; thus, approximately 80% of patients with cancer undergo at least one surgical procedure during their disease. Agents used in general anesthesia can modulate cytokine release, transcription factors, and/or oncogenes. This can affect host immunity and the capability of cancer cells to survive and migrate, not only during surgery but for up to several weeks after surgery. However, it remains unknown whether exposure to anesthetic agents affects cancer recurrence or metastasis. This review explores the current literature to explain whether and how the choice of anesthetic and perioperative medication affect cancer surgery outcomes.

Comparison of tracheal versus esophageal temperatures during laparoscopic surgery.

PURPOSE: Recently, endotracheal tubes with an embedded temperature sensor in the inner surface of the tube cuff (temperature tracheal tubes) have been developed. We sought to assess whether temperature tracheal tubes show a good agreement with esophageal temperature probes during surgery. METHODS: We enrolled 40 patients who underwent laparoscopic surgery in an observational study. The tracheas of all patients were intubated with a temperature tracheal tube, and an esophageal temperature probe was inserted into the esophagus. Tracheal and esophageal temperatures were recorded at 15-min intervals until the end of surgery. Temperatures from both devices were analyzed using Bland-Altman analysis, four-quadrant plots, and polar plots. RESULTS: We analyzed 261 data points from 36 patients. Temperatures ranges were 34.2 °C to 36.6 °C for the tracheal temperature tube and 34.7 °C to 37.2 °C for the esophageal temperature probe. Bland-Altman analysis showed an acceptable agreement between the two devices, with an overall mean bias (95% limit of agreement) of -0.3 °C (-0.8 °C to 0.1 °C) and a percentage error of 3%; the trending ability (temperature changes over time) between the two devices showed a concordance rate of 94% in four-quadrant plot (cut-off ≥ 92%), but this was higher than the acceptable mean angular bias of 177° (cut-off < ± 5°) and radial limits of agreement of 52° (cut-off < ± 30°) in the polar plot. Bronchoscopy during extubation and patient interviews at six hours postoperatively revealed no serious injuries related to the use of the temperature tracheal tube. CONCLUSION: The temperature tracheal tube showed an acceptable overall mean bias of -0.3 °C and a percentage error of 3%, but incompatible trending ability with the esophageal temperature probe. STUDY REGISTRATION: cris.nih.go.kr (KCT0007265); 22 April 2022.

RéSUMé: OBJECTIF: Récemment, des sondes endotrachéales munies d'un capteur de température intégré dans la surface interne du ballonnet de la sonde (sondes thermiques trachéales) ont été mises au point. Nous avons cherché à évaluer si les sondes trachéales de température montraient une bonne concordance avec les sondes thermiques œsophagiennes pendant la chirurgie. MéTHODE: Nous avons recruté 40 patient·es ayant bénéficié d'une chirurgie par laparoscopie dans le cadre d'une étude observationnelle. Les trachées de tou·tes les patient·es ont été intubées à l'aide d'une sonde trachéale de température et une sonde thermique œsophagienne a été insérée dans l'œsophage. Les températures trachéale et œsophagienne ont été enregistrées à des intervalles de 15 minutes jusqu'à la fin de la chirurgie. Les températures des deux appareils ont été analysées à l'aide d'une analyse de Bland-Altman, de diagrammes à quatre quadrants et de diagrammes polaires. RéSULTATS: Nous avons analysé 261 points de données provenant de 36 patient·es. Les plages de température allaient de 34,2 °C à 36,6 °C pour la sonde trachéale de température et de 34,7 °C à 37,2 °C pour la sonde thermique œsophagienne. L'analyse de Bland-Altman a montré une concordance acceptable entre les deux dispositifs, avec un biais moyen global (limite de 95 % de la concordance) de −0,3 °C (−0,8 °C à 0,1 °C) et un pourcentage d'erreur de 3 %; la capacité de tendance (changements de température au fil du temps) entre les deux dispositifs a montré un taux de concordance de 94 % dans un diagramme à quatre quadrants (limite ≥ 92 %), mais cette capacité était plus élevée que le biais angulaire moyen acceptable de 177° (limite < ± 5°) et que les limites radiales de l'accord de 52° (limite < ± 30°) dans le diagramme polaire. La bronchoscopie réalisée lors de l'extubation et les entretiens avec les patient·es six heures après l'opération n'ont révélé aucune blessure grave liée à l'utilisation de la sonde trachéale de température. CONCLUSION: La sonde trachéale de température a montré un biais moyen global acceptable de −0,3 °C et un pourcentage d'erreur de 3 %, mais une capacité de tendance incompatible avec la sonde thermique œsophagienne. ENREGISTREMENT DE L'éTUDE: cris.nih.go.kr (KCT0007265); 22 avril 2022.

Effect of Sevoflurane Anesthesia on Diastolic Function: A Prospective Observational Study.

BACKGROUND: The effect of sevoflurane on left ventricular diastolic function is not well understood. We hypothesized that parameters of diastolic function may improve under sevoflurane anesthesia in patients with preexisting diastolic dysfunction compared to patients with normal diastolic function. METHODS: This observational study included 60 patients undergoing breast surgery or laparoscopic cholecystectomy. Patients were assigned to diastolic dysfunction (n = 34) or normal (n = 26) groups of septal e' < 8 or ≥ 8.0 cm/s on the first thoracic echocardiography (TTE) performed before anesthesia. During anesthesia, sevoflurane was maintained at 1 to 2 minimum alveolar concentration (MAC) to maintain the bispectral index at 40 to 50. At the end of surgery, the second TTE was performed under 0.8 to 1 MAC of sevoflurane with the patient breathing spontaneously without ventilator support. Primary end point was the percentage change (Δ) of e' on 2 TTEs (Δe'). Secondary end points were ΔE/e', Δleft atrial volume index (ΔLAVI), and Δtricuspid regurgitation maximum velocity (ΔTR Vmax). These percentage changes (Δ) were compared between diastolic dysfunction and normal groups. RESULTS: e' (Δe': 30 [6, 64] vs 0 [-18, 11]%; P < .001), mitral inflow E wave velocity (E), mitral inflow E/A ratio (E/A), and mitral E velocity deceleration time (DT) improved significantly in diastolic dysfunction group compared to normal group. LAVI decreased in diastolic dysfunction group but did not reach statistical significance between the 2 groups (ΔLAVI:-15 [-31, -3] vs -4 [-20, 10]%, P = .091). ΔE/e' was not different between the 2 groups (11 [-16, 26] vs 12 [-9, 22]%, P = .853) (all: median [interquartile range, IQR]). TR was minimal in both groups. CONCLUSIONS: In this study, echocardiographic parameters of diastolic function, including septal e', E, E/A, and DT, improved with sevoflurane anesthesia in patients with preexisting diastolic dysfunction, but remained unchanged in patients with normal diastolic function.

Association of Mechanical Energy and Power with Postoperative Pulmonary Complications in Lung Resection Surgery: A Post Hoc Analysis of Randomized Clinical Trial Data.

BACKGROUND: Mechanical power (MP), the rate of mechanical energy (ME) delivery, is a recently introduced unifying ventilator parameter consisting of tidal volume, airway pressures, and respiratory rates, which predicts pulmonary complications in several clinical contexts. However, ME has not been previously studied in the perioperative context, and neither parameter has been studied in the context of thoracic surgery utilizing one-lung ventilation. METHODS: The relationships between ME variables and postoperative pulmonary complications were evaluated in this post hoc analysis of data from a multicenter randomized clinical trial of lung resection surgery conducted between 2020 and 2021 (n = 1,170). Time-weighted average MP and ME (the area under the MP time curve) were obtained for individual patients. The primary analysis was the association of time-weighted average MP and ME with pulmonary complications within 7 postoperative days. Multivariable logistic regression was performed to examine the relationships between energy variables and the primary outcome. RESULTS: In 1,055 patients analyzed, pulmonary complications occurred in 41% (431 of 1,055). The median (interquartile ranges) ME and time-weighted average MP in patients who developed postoperative pulmonary complications versus those who did not were 1,146 (811 to 1,530) J versus 924 (730 to 1,240) J (P < 0.001), and 6.9 (5.5 to 8.7) J/min versus 6.7 (5.2 to 8.5) J/min (P = 0.091), respectively. ME was independently associated with postoperative pulmonary complications (ORadjusted, 1.44 [95% CI, 1.16 to 1.80]; P = 0.001). However, the association between time-weighted average MP and postoperative pulmonary complications was time-dependent, and time-weighted average MP was significantly associated with postoperative pulmonary complications in cases utilizing longer periods of mechanical ventilation (210 min or greater; ORadjusted, 1.46 [95% CI, 1.11 to 1.93]; P = 0.007). Normalization of ME and time-weighted average MP either to predicted body weight or to respiratory system compliance did not alter these associations. CONCLUSIONS: ME and, in cases requiring longer periods of mechanical ventilation, MP were independently associated with postoperative pulmonary complications in thoracic surgery.