Hyung-Chul Lee

Seoul National University Hospital | SNU · Department of Anesthesiology and Pain Medicine

Delirium can result in undesirable outcomes including increased length of stays and mortality in patients admitted to the intensive care unit (ICU). Dexmedetomidine has emerged for delirium prevention in these patients; however, optimal dosing is challenging. A reinforcement learning-based Artificial Intelligence model for Delirium prevention (AID)...

The American Society of Anesthesiologist’s Physical Status (ASA-PS) classification system assesses comorbidities before sedation and analgesia, but inconsistencies among raters have hindered its objective use. This study aimed to develop natural language processing (NLP) models to classify ASA-PS using pre-anesthesia evaluation summaries, comparing...

Background: Erector spinae plane block (ESPB) can has been used for analgesia after lumbar spine surgery. However, its effect on postoperative quality of recovery (QoR) remains underexplored in patients undergoing transforaminal lumbar interbody fusion (TLIF) or oblique lumbar interbody fusion (OLIF). This study hypothesized that ESPB would improv...

Titrating tacrolimus concentration in liver transplantation recipients remains a challenge in the early post-transplant period. This multicenter retrospective cohort study aimed to develop and validate a machine-learning algorithm to predict tacrolimus concentration. Data from 443 patients undergoing liver transplantation between 2017 and 2020 at a...

Background Perioperative stroke is a severe complication following surgery. To identify patients at risk for perioperative stroke, several prediction models based on the preoperative factors were suggested. Prediction models often focus on preoperative patient characteristics to assess stroke risk. However, most existing models primarily base their...

We present the INSPIRE dataset, a publicly available research dataset in perioperative medicine, which includes approximately 130,000 surgical operations at an academic institution in South Korea over a ten-year period between 2011 and 2020. This comprehensive dataset includes patient characteristics such as age, sex, American Society of Anesthesio...

Background Cerebral vasospasm after aneurysmal subarachnoid hemorrhage (ASAH) is a serious complication and has a strong relationship with systemic inflammatory responses. Given previously reported relationships between leukocytosis and anemia with ASAH-related cerebral vasospasm, this study examined the association between the preoperative white b...

Background A real-time model for predicting short-term mortality in critically ill patients is needed to identify patients at imminent risk. However, the performance of the model needs to be validated in various clinical settings and ethnicities before its clinical application. In this study, we aim to develop an ensemble machine learning model usi...

BACKGROUND Machine learning (ML) has the potential to enhance performance by capturing nonlinear interactions. However, ML-based models have some limitations in terms of interpretability. OBJECTIVE To address this, we developed and validated a more comprehensible and efficient ML-based scoring system using SHapley Additive exPlanations (SHAP) valu...

This study evaluated the effect of hyperbilirubinemia on the accuracy of continuous non-invasive hemoglobin (SpHb) measurements in liver transplantation recipients. Overall, 1465 SpHb and laboratory hemoglobin (Hb) measurement pairs (n = 296 patients) were analyzed. Patients were grouped into normal (< 1.2 mg/dL), mild-to-moderate (1.2–3.0 mg/dL),...

Background Postoperative acute kidney injury (AKI) is associated with poor clinical outcomes. Identification of risk factors for postoperative AKI is clinically important. Serum lactate can increase in situations of inadequate oxygen delivery and is widely used to assess a patient’s clinical course. We investigated the association between intraoper...

Predicting in-hospital cardiac arrest in patients admitted to an intensive care unit (ICU) allows prompt interventions to improve patient outcomes. We developed and validated a machine learning-based real-time model for in-hospital cardiac arrest predictions using electrocardiogram (ECG)-based heart rate variability (HRV) measures. The HRV measures...

Objectives Automatic detection of atrial fibrillation and flutter (AF/AFL) is a significant concern in preventing stroke and mitigating hemodynamic instability. Herein, we developed a Transformer-based deep learning model for AF/AFL segmentation in single-lead electrocardiograms (ECGs) by self-supervised learning with masked signal modeling (MSM)....

Background Based on the controversy surrounding pulmonary artery catheterization (PAC) in surgical patients, we investigated the interchangeability of cardiac index (CI) and systemic vascular resistance (SVR) measurements between ClearSight™ and PAC during living-donor liver transplantation (LDLT). Methods This prospective study included consecuti...

Background: Use of endotracheal tubes (ETTs) with appropriate size and depth can help minimize intubation-related complications in pediatric patients. Existing age-based formulae for selecting the optimal ETT size present several inaccuracies. We developed a machine learning model that predicts the optimal size and depth of ETTs in pediatric patie...

Several technical aspects of the Fick method limit its use intraoperatively. A data-driven modification of the Fick method may enable its use in intraoperative settings. This two-center retrospective observational study included 57 (28 and 29 in each center) patients who underwent off-pump coronary artery bypass graft (OPCAB) surgery. Intraoperativ...

Study objective: To determine whether changes in the pleth variability index (PVi) during preoxygenation with forced ventilation for 1 min could predict anesthesia-induced hypotension. Design: Prospective, observational study. Setting: A tertiary teaching hospital. Patients: Ninety-six patients who underwent general anesthesia using total in...

Neurological pupil index (NPi) calculated by automated pupillometry predicts clinical outcomes in critically ill patients. However, there are few data on intraoperative NPi and postoperative outcome after cardiac surgery. We evaluated the relationships between intraoperative NPi and clinical outcomes, such as delirium, in cardiac surgery patients....

With the growing interest of researchers in machine learning and artificial intelligence (AI) based on large data, their roles in medical research have become increasingly prominent. Despite the proliferation of predictive models in perioperative medicine, external validation is lacking. Open datasets, defined as publicly available datasets for res...

Blocking the abrupt increase in systolic blood pressure associated with autonomic response during bladder hydrodistention in patients with interstitial cystitis/bladder pain syndrome (IC/BPS) is essential for patient safety. We conducted this study to compare autonomic responses during bladder hydrodistention in patients with IC/BPS under general a...

Continuous, comfortable, convenient (C3), and accurate blood pressure (BP) measurement and monitoring are needed for early diagnosis of various cardiovascular diseases. To supplement the limited C3 BP measurement of existing cuff-based BP technologies, though they may achieve reliable accuracy, cuffless BP measurement technologies, such as pulse tr...

Background The endotracheal cuff pressure depends on the airway pressure during positive-pressure ventilation. A high endotracheal cuff pressure may be related to intraoperative coughing, which can be detrimental during neurosurgery. We investigated the incidence of intraoperative coughing and its association with peak inspiratory pressure (PIP) du...

Background: The Hypotension Prediction Index (HPI) was recently introduced and clinically validated in different surgical conditions. This prospective observational study evaluated HPI's performance in living donor liver transplant recipients under the hypothesis that HPI would be inferior to the previously reported predictability in major surgery...

Background Reducing the duration of intraoperative hypoxemia in pediatric patients by means of rapid detection and early intervention is considered crucial by clinicians. We aimed to develop and validate a machine learning model that can predict intraoperative hypoxemia events 1 min ahead in children undergoing general anesthesia. Methods This ret...

Importance Massive transfusion is essential to prevent complications during uncontrolled intraoperative hemorrhage. As massive transfusion requires time for blood product preparation and additional medical personnel for a team-based approach, early prediction of massive transfusion is crucial for appropriate management. Objective To evaluate a rea...

The effect of intraoperative tidal volume (VT) on clinical outcomes after off-pump coronary artery bypass grafting (OPCAB) has not been studied. The aim of this study was to assess the relationship between intraoperative tidal volume (VT) and acute kidney injury (AKI ) after OPCAB. A total of 1049 patients who underwent OPCAB between January 2009 a...

R-peak detection is an essential step in analyzing electrocardiograms (ECGs). Previous deep learning models reported their performance primarily in a single database, and some models did not perform at the highest levels when applied to a database different from the testing database. To achieve high performances in cross-database validations, we de...

Introduction: Perioperative stroke is one of the most devastating events after surgery. To prevent perioperative stroke and stratify the patients at risk, several prediction models or scores based on the preoperative factors were suggested. However, there had been never reported a prediction model using intraoperative physiologic parameters. Aim: W...

Acute kidney injury (AKI) is one of the most common complications after cardiac surgery, associated with increased mortality and morbidity. Near-infrared spectroscopy (NIRS) continuously measures regional oxygen saturation(rSO2) in real-time. This exploratory retrospective study aimed to investigate the association between intraoperative plantar rS...

Background To evaluate the impact of intraoperative hypotension and hemodynamic instability on survival outcomes in patients with high-grade serous ovarian carcinoma (HGSOC). Methods We retrospectively identified patients with HGSOC, who underwent primary or interval debulking surgery between August 2013 and December 2019. We collected anesthesia-...

Attention mechanisms are widely used to dramatically improve deep learning model performance in various fields. However, their general ability to improve the performance of physiological signal deep learning model is immature. In this study, we experimentally analyze four attention mechanisms (e.g., squeeze-and-excitation, non-local, convolutional...

Impaired cerebral autoregulation (CA) can cause negative outcomes in neurological conditions. Real-time CA monitoring can predict and thereby help prevent postoperative complications for neurosurgery patients, especially those suffering from moyamoya disease (MMD). We applied the concept of moving average to the correlation between mean arterial bl...

To develop deep learning models for predicting Interoperative hypotension (IOH) using waveforms from arterial blood pressure (ABP), electrocardiogram (ECG), and electroencephalogram (EEG), and to determine whether combination ABP with EEG or CG improves model performance. Data were retrieved from VitalDB, a public data repository of vital signs tak...

Attention mechanisms are widely used to dramatically improve deep learning model performance in various fields. However, their general ability to improve the performance of physiological signal deep learning model is immature. In this study, we experimentally analyze four attention mechanisms (e.g., squeeze-and-excitation, non-local, convolutional...

Accurate prediction of postoperative mortality is important for not only successful postoperative patient care but also for information-based shared decision-making with patients and efficient allocation of medical resources. This study aimed to create a machine-learning prediction model for 30-day mortality after a non-cardiac surgery that adapts...

In modern anesthesia, multiple medical devices are used simultaneously to comprehensively monitor real-time vital signs to optimize patient care and improve surgical outcomes. However, interpreting the dynamic changes of time-series biosignals and their correlations is a difficult task even for experienced anesthesiologists. Recent advanced machine...

Background: Appropriate monitoring of intradialytic biosignals is essential to minimize adverse outcomes because intradialytic hypotension and arrhythmia are associated with cardiovascular risk in hemodialysis patients. However, a continuous monitoring system for intradialytic biosignals has not yet been developed. Methods: This study investigat...

Background: Post-reperfusion syndrome (PRS) results in sudden hemodynamic instability following graft reperfusion. Although PRS is known to influence outcomes following liver transplantation, little is known regarding the effects of anesthetics on PRS. This study investigated the association between the type of anesthetic agent and PRS in liver tr...

The dynamic response (DR) of the arterial pressure monitoring system (APMS) may depend on the intraarterial catheter (IAC) diameter. We hypothesized that adequate DR would be more common when using a smaller IAC. We compared the DR of the AMPS (Auto Transducer™) between three IACs (BD Angiocath Plus™) with different diameters. 353 neurosurgical pat...

Unexpected cardiorespiratory compromise has been reported during ophthalmic arterial chemotherapy in pediatric patients with retinoblastoma. Although the underlying mechanisms remain unclear, autonomic responses are presumed to contribute to these events. We hypothesized that periprocedural heart rate variability would differ between patients with...

Recent advancements in artificial intelligence (AI) techniques have enabled the development of accurate prediction models using clinical big data. In the field of perioperative medicine, AI models for perioperative risk stratification, intraoperative event prediction, biosignal analysis, and intensive care medicine have been developed. Some of thes...

Background Despite an improved understanding of pheochromocytoma and extra-adrenal sympathetic parganglioma (PPGL), including diagnosis and management, some PPGLs are postoperatively diagnosed. Clinical characteristics and intraoperative haemodynamic instability (HI) in postoperatively diagnosed PPGL patients have been poorly defined. Thus, we inve...

Background: Limited data exist regarding optimal intraoperative ventilation strategies for the paediatric population. This study aimed to determine the optimal combination of PEEP and tidal volume (VT) based on intratidal compliance profiles in healthy young children undergoing general anaesthesia. Methods: During anaesthesia, infants (1 month-1...

For pheochromocytoma and sympathetic paraganglioma (PPGL), surgery can be used as a curative treatment; however, the life-threatening risk of perioperative hemodynamic instability (HI) presents challenges. This study aimed to analyze the incidence and predictive factors of perioperative HI. The electronic medical records of 114 consecutive patients...

Background Arterial pressure-based cardiac output (APCO) is a less invasive method for estimating cardiac output without concerns about complications from the pulmonary artery catheter (PAC). However, inaccuracies of currently available APCO devices have been reported. Improvements to the algorithm by researchers are impossible, as only a subset of...

Background: This study aimed to investigate the association between sugammadex use and the occurrence of delayed passage of first flatus and oral intake tolerance following open pancreaticoduodenectomy (PD). Methods: We reviewed consecutive patients who underwent open PD between 2015 and 2019; subsequently, they were divided into the sugammadex...

Performance measurement variables can be applied in clinical practice to evaluate hemodynamic instability. This study aimed to evaluate the relationship between the performance measurement of mean arterial pressure during cardiac surgery using cardiopulmonary bypass and postoperative mortality. A retrospective cohort study of patients who underwent...

Sore throat after tracheal intubation impairs postoperative recovery. We randomly allocated 172 ASA physical status 1–2 participants, scheduled for laparoscopic lower abdominal surgery, to tracheal intubation with larger tubes (n = 88) or smaller tubes (n = 84), with internal diameters 7.5‐mm vs. 6.5‐mm for men and 7.0‐mm vs. 6.0‐mm for women. Prim...

Purpose Diabetes insipidus (DI) develops commonly after endoscopic transsphenoidal surgery (ETS). We retrospectively investigated the incidence, onset, duration and predictors of DI after ETS in patients with non-functioning pituitary adenoma (NFPA). Methods A total of 168 patients who underwent ETS to remove NFPAs were included. Various periopera...

Background Although perioperative hypothermia was found associated with gastrointestinal anastomotic leakage in preclinical studies, its association with postoperative pancreatic fistula (POPF) following pancreaticoduodenectomy was never evaluated. We investigated the association between intraoperative hypothermia and clinically relevant (CR)-POPF...

Background Although the association between an increase in anastomotic leakage (AL) and non-steroidal anti-inflammatory drugs (NSAIDs) has been reported in gastrointestinal surgeries, this issue has rarely been addressed for pancreaticoduodenectomy (PD). We aimed to investigate the association between postoperative NSAIDs administration and clinica...

Background Intraoperative hypotension is associated with a risk of postoperative organ dysfunction. In this study, we aimed to present deep learning algorithms for real-time predictions 5, 10, and 15 min before a hypotensive event. Methods In this retrospective observational study, deep learning algorithms were developed and validated using biosig...

Objective Platelets play a critical role in the inflammatory response, accompanied by microvascular endothelial dysfunction, underlying postoperative symptomatic cerebral hyperperfusion syndrome (PSCHS) after superficial temporal artery–middle cerebral artery (STA-MCA) anastomosis in moyamoya patients. We examined whether the preoperative platelet...

Anesthesia with desflurane and remifentanil can be maintained with either fixed or titrated desflurane concentration. We hypothesized that the fixed-gas concentration (FG) method would reduce the number of anesthetic titrations without hypnotic and hemodynamic instability compared to the bispectral index (BIS)-guided (BG) method. Forty-eight patien...

BACKGROUND Arterial pressure-based cardiac output (APCO) is a less invasive method for estimating cardiac output without concerns about complications from the pulmonary artery catheter (PAC). However, inaccuracies of currently available APCO devices have been reported. Improvements to the algorithm by researchers are impossible, as only a subset of...

Background: Emergence delirium (ED) in children after general anaesthesia causes significant distress in patients, their family members, and clinicians; however, electroencephalogram (EEG) markers predicting ED have not been fully investigated. Methods: This prospective, single-centre observational study enrolled children aged 2-10 yr old under...

Background: The cross-sectional area of the subclavian vein (csSCV) is a crucial factor in the successful catheterization of the subclavian vein. This randomized controlled study investigated the effects of the csSCV on landmark-based subclavian vein catheterization. Methods: This study was performed using a two-stage protocol. During stage I, t...

Background: The relationship between intraoperative low bispectral index (BIS) values and poor clinical outcomes has been controversial. Intraoperative hypotension is associated with postoperative complication. The purpose of this study was to investigate the influence of intraoperative low BIS values and hypotension on postoperative mortality in...

Background: Moyamoya disease is a progressive, steno-occlusive arteriopathy involving the internal carotid artery and its branches and causing recurrent stroke episodes in children. Patients with moyamoya disease may be more susceptible to influences that cause endothelial dysfunction. We evaluated whether flow-mediated dilatation (FMD) of the bra...

Background: McGrath MAC videolaryngoscopy is a useful technique for successful intubation in cervical spine-injured patients with manual in-line stabilization of the neck during intubation. We aimed to identify radiographic predictors of difficult McGrath MAC videolaryngoscopy in patient undergoing cervical spine surgery. Methods: Patients under...

Background Optimal intraoperative lung protective ventilation (LPV) strategies in young children are largely under-explored. Individualised PEEP levels are likely to contribute to optimal lung protection. We determined optimal PEEP levels in young children during general anaesthesia by evaluating changes in intratidal compliance with varying PEEP....

We present a real-time electroencephalogram (EEG) based depth of anesthesia (DoA) monitoring system in conjunction with a deep learning framework, AnesNET. An EEG analog front-end (AFE) that can compensate ±380-mV electrode DC offset using a coarse digital DC servo loop is implemented in the proposed system. The EEG-based MAC, EEGMAC, is introduced...

Background Anesthetic techniques can affect perioperative neuroendocrine function. The objective of this study was to compare 3‐month postoperative neuroendocrine functional outcomes between sevoflurane and propofol anesthesia in patients undergoing endoscopic transsphenoidal surgery (ETS) for removal of non‐functional pituitary adenomas (NFPAs) re...

Background The influence of intraoperative low bispectral index (BIS) values and hypotension on poor clinical outcomes has been controversial. The purpose of this study was to investigate the influence of intraoperative low BIS values and hypotension on postoperative mortality in patients undergoing major abdominal surgery. Methods This retrospecti...

Background The relationship between intraoperative low bispectral index (BIS) values and poor clinical outcomes has been controversial. Intraoperative hypotension is associated with postoperative complication. The purpose of this study was to investigate the influence of intraoperative low BIS values and hypotension on postoperative mortality in pa...