We appreciate the opportunity to respond to the three Letters to the Editor [1-3] commenting on our article [4], published in the Journal of Internal Medicine. We have carefully discussed them with the respective authors. We want to express our sincere gratitude for their interest in our work and for the valuable suggestions they have provided. First, we would like to address the concern raised in all three letters regarding the absence of clear exclusion criteria for comorbidities in our study group [4, 5]. We fully acknowledge and agree with the points raised by the authors of the letters. Although we share their concerns, our study was based on a retrospective data analysis. Consequently, we opted to address these effects by applying statistical corrections in a multivariate analysis rather than excluding them from our study altogether. We agree that in future prospective studies on this topic, it is indeed crucial to thoroughly consider and incorporate multiple factors that may influence patient outcomes into the exclusion criteria. Second, we would like to address their comments regarding the significant prehospital characteristics of out-of-hospital cardiac arrest (OHCA) patients highlighted in the study. We concur with the authors that there are numerous factors specific to OHCA patients, as opposed to in-hospital cardiac arrest (IHCA) patients, that can influence outcomes [6]. Indeed, it may be more effective to analyse OHCA patients separately from IHCA patients to reach more definitive conclusions. OHCA patients often face more challenges that can delay extracorporeal membrane oxygenation (ECMO) initiation, and in our data, these factors were associated with a poorer prognosis compared to IHCA patients. In future research, it would be advantageous to analyse OHCA patients separately from IHCA patients using a larger dataset to derive clearer insights on these issues. Third, we would like to comment on the issues raised by the authors regarding the specific details of post-cardiac arrest care. We agree that various post-cardiac arrest interventions—such as blood transfusions, ventilator settings, treatment of infectious complications, and therapeutic temperature management—as well as complications occurring during ECMO, such as insertion site bleeding, limb ischemia, and intracranial hemorrhage, are critical factors that impact the prognosis of cardiac arrest patients [7, 8]. Unfortunately, our study lacked sufficient data in this area to present detailed results. We recognize that detailed descriptions of these post-cardiac arrest treatments and complications may be crucial in understanding the prognosis of ECPR patients, and future studies should include these details and better assess their impact on outcomes. Finally, we would like to respond to the point raised by the authors regarding the insufficient evaluation of long-term outcomes beyond 6 months [6]. To include as many ECPR patients as possible in our study, we analysed data from patients who had recently undergone ECPR, resulting in a relatively short observation period of about 6 months. We agree that this short observation period may have limited our ability to assess long-term outcomes beyond 6 months. In future studies, we believe that it would be highly valuable to analyse patient outcomes over a longer follow-up period of 1 year or more. Despite the many limitations pointed out by the authors, we believe our study is significant in highlighting the importance of timely ECMO intervention in patients with cardiac arrest. We are confident that as more data on ECPR become available, higher quality analyses will help clarify some of the unknowns. Finally, we would like to express our deepest gratitude to the reviewers for their interest in our research and their valuable advice. Sang-Wook Lee: Writing—original draft; conceptualization; writing—review and editing; investigation. Ji-Hoon Sim: Writing—review and editing. The authors declare no conflicts of interest. The data that support the findings of this study are available from the corresponding author upon reasonable request.

Despite recent advances in surgical techniques and perinatal management in obstetrics for reducing intraoperative bleeding, blood transfusion may occur during a cesarean section (CS). This study aims to identify machine learning models with an optimal diagnostic performance for intraoperative transfusion prediction in parturients undergoing a CS. Additionally, to address model performance degradation due to data imbalance, this study further investigated the variation in predictive model performance depending on the ratio of event to non-event data (1:1, 1:2, 1:3, and 1:4 model datasets and raw data).The area under the receiver operating characteristic curve (AUROC) and area under the precision-recall curve (AUPRC) were evaluated to compare the predictive accuracy of different machine learning algorithms, including XGBoost, K-nearest neighbor, decision tree, support vector machine, multilayer perceptron, logistic regression, random forest, and deep neural network. We compared the predictive performance of eight prediction algorithms that were applied to five types of datasets. The intraoperative transfusion in maternal CS was 7.2% (1020/14,254). XGBoost showed the highest AUROC (0.8257) and AUPRC (0.4825) among the models. The most significant predictors for transfusion in maternal CS as per machine learning models were placenta previa totalis, haemoglobin, placenta previa partialis, and platelets. In all eight prediction algorithms, the change in predictive performance based on the AUROC and AUPRC according to the resampling ratio was insignificant. The XGBoost algorithm exhibited optimal performance for predicting intraoperative transfusion. Data balancing techniques employed to alter the event data composition ratio of the training data failed to improve the performance of the prediction model.

BACKGROUND: Cardiopulmonary resuscitation (CPR) is the cornerstone intervention for cardiac arrest, with extracorporeal CPR (ECPR) demonstrating enhanced survival and neurologic outcomes in in-hospital cardiac arrest. This study explores the time interval between CPR initiation and the onset of extracorporeal membrane oxygenation (ECMO) in ECPR recipients, investigating its impact on survival outcomes. METHODS: This retrospective analysis included 1950 adults who received CPR at a single medical center between March 2019 and April 2023. Data from 198 adult patients who had ECMO inserted during CPR were analyzed. The interval from CPR initiation to ECMO initiation was quantified and categorized as ≤20, 20-40, and >40 min. Cox regression analysis assessed associations between CPR-to-ECMO time and short- and long-term mortalities. RESULTS: Among the 198 patients who underwent ECPR, 116 (58.6%) experienced 30-day mortality. Initiation of ECMO within 20 min occurred in 46 (23.2%), whereas 74 (37.4%) had ECMO initiated after 40 min. Cox regression revealed a significant association between time from CPR to ECMO initiation and 30-day mortality (adjusted hazard ratio [HR]: 2.20 in >40 min, HR: 2.63 in 20-40 min, p = 0.006) and 6-month mortality (HR: 1.81, in >40 min, HR: 1.99 in 20-40 min, p = 0.021). CONCLUSIONS: This study revealed that, in ECPR recipients, a shorter duration between CPR initiation and ECMO flow commencement is associated with improved short- and long-term patient prognoses. These findings emphasize the critical role of timely ECMO application in optimizing outcomes for patients undergoing ECPR.

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 to the manageable amount of clinical information as input features and is validated against multi-centered rather than single-centered data. Data were collected from 454,404 patients over 18 years of age who underwent non-cardiac surgeries from four independent institutions. We performed a retrospective analysis of the retrieved data. Only 12-18 clinical variables were used for model training. Logistic regression, random forest classifier, extreme gradient boosting (XGBoost), and deep neural network methods were applied to compare the prediction performances. To reduce overfitting and create a robust model, bootstrapping and grid search with tenfold cross-validation were performed. The XGBoost method in Seoul National University Hospital (SNUH) data delivers the best performance in terms of the area under receiver operating characteristic curve (AUROC) (0.9376) and the area under the precision-recall curve (0.1593). The predictive performance was the best when the SNUH model was validated with Ewha Womans University Medical Center data (AUROC, 0.941). Preoperative albumin, prothrombin time, and age were the most important features in the model for each hospital. It is possible to create a robust artificial intelligence prediction model applicable to multiple institutions through a light predictive model using only minimal preoperative information that can be automatically extracted from each hospital.

We appreciate the opportunity to respond to the three Letters to the Editor [1-3] commenting on our article [4], published in the Journal of Internal Medicine. We have carefully discussed them with the respective authors. We want to express our sincere gratitude for their interest in our work and for the valuable suggestions they have provided. First, we would like to address the concern raised in all three letters regarding the absence of clear exclusion criteria for comorbidities in our study group [4, 5]. We fully acknowledge and agree with the points raised by the authors of the letters. Although we share their concerns, our study was based on a retrospective data analysis. Consequently, we opted to address these effects by applying statistical corrections in a multivariate analysis rather than excluding them from our study altogether. We agree that in future prospective studies on this topic, it is indeed crucial to thoroughly consider and incorporate multiple factors that may influence patient outcomes into the exclusion criteria. Second, we would like to address their comments regarding the significant prehospital characteristics of out-of-hospital cardiac arrest (OHCA) patients highlighted in the study. We concur with the authors that there are numerous factors specific to OHCA patients, as opposed to in-hospital cardiac arrest (IHCA) patients, that can influence outcomes [6]. Indeed, it may be more effective to analyse OHCA patients separately from IHCA patients to reach more definitive conclusions. OHCA patients often face more challenges that can delay extracorporeal membrane oxygenation (ECMO) initiation, and in our data, these factors were associated with a poorer prognosis compared to IHCA patients. In future research, it would be advantageous to analyse OHCA patients separately from IHCA patients using a larger dataset to derive clearer insights on these issues. Third, we would like to comment on the issues raised by the authors regarding the specific details of post-cardiac arrest care. We agree that various post-cardiac arrest interventions—such as blood transfusions, ventilator settings, treatment of infectious complications, and therapeutic temperature management—as well as complications occurring during ECMO, such as insertion site bleeding, limb ischemia, and intracranial hemorrhage, are critical factors that impact the prognosis of cardiac arrest patients [7, 8]. Unfortunately, our study lacked sufficient data in this area to present detailed results. We recognize that detailed descriptions of these post-cardiac arrest treatments and complications may be crucial in understanding the prognosis of ECPR patients, and future studies should include these details and better assess their impact on outcomes. Finally, we would like to respond to the point raised by the authors regarding the insufficient evaluation of long-term outcomes beyond 6 months [6]. To include as many ECPR patients as possible in our study, we analysed data from patients who had recently undergone ECPR, resulting in a relatively short observation period of about 6 months. We agree that this short observation period may have limited our ability to assess long-term outcomes beyond 6 months. In future studies, we believe that it would be highly valuable to analyse patient outcomes over a longer follow-up period of 1 year or more. Despite the many limitations pointed out by the authors, we believe our study is significant in highlighting the importance of timely ECMO intervention in patients with cardiac arrest. We are confident that as more data on ECPR become available, higher quality analyses will help clarify some of the unknowns. Finally, we would like to express our deepest gratitude to the reviewers for their interest in our research and their valuable advice. Sang-Wook Lee: Writing—original draft; conceptualization; writing—review and editing; investigation. Ji-Hoon Sim: Writing—review and editing. The authors declare no conflicts of interest. The data that support the findings of this study are available from the corresponding author upon reasonable request.

Despite recent advances in surgical techniques and perinatal management in obstetrics for reducing intraoperative bleeding, blood transfusion may occur during a cesarean section (CS). This study aims to identify machine learning models with an optimal diagnostic performance for intraoperative transfusion prediction in parturients undergoing a CS. Additionally, to address model performance degradation due to data imbalance, this study further investigated the variation in predictive model performance depending on the ratio of event to non-event data (1:1, 1:2, 1:3, and 1:4 model datasets and raw data).The area under the receiver operating characteristic curve (AUROC) and area under the precision-recall curve (AUPRC) were evaluated to compare the predictive accuracy of different machine learning algorithms, including XGBoost, K-nearest neighbor, decision tree, support vector machine, multilayer perceptron, logistic regression, random forest, and deep neural network. We compared the predictive performance of eight prediction algorithms that were applied to five types of datasets. The intraoperative transfusion in maternal CS was 7.2% (1020/14,254). XGBoost showed the highest AUROC (0.8257) and AUPRC (0.4825) among the models. The most significant predictors for transfusion in maternal CS as per machine learning models were placenta previa totalis, haemoglobin, placenta previa partialis, and platelets. In all eight prediction algorithms, the change in predictive performance based on the AUROC and AUPRC according to the resampling ratio was insignificant. The XGBoost algorithm exhibited optimal performance for predicting intraoperative transfusion. Data balancing techniques employed to alter the event data composition ratio of the training data failed to improve the performance of the prediction model.

BACKGROUND: Cardiopulmonary resuscitation (CPR) is the cornerstone intervention for cardiac arrest, with extracorporeal CPR (ECPR) demonstrating enhanced survival and neurologic outcomes in in-hospital cardiac arrest. This study explores the time interval between CPR initiation and the onset of extracorporeal membrane oxygenation (ECMO) in ECPR recipients, investigating its impact on survival outcomes. METHODS: This retrospective analysis included 1950 adults who received CPR at a single medical center between March 2019 and April 2023. Data from 198 adult patients who had ECMO inserted during CPR were analyzed. The interval from CPR initiation to ECMO initiation was quantified and categorized as ≤20, 20-40, and >40 min. Cox regression analysis assessed associations between CPR-to-ECMO time and short- and long-term mortalities. RESULTS: Among the 198 patients who underwent ECPR, 116 (58.6%) experienced 30-day mortality. Initiation of ECMO within 20 min occurred in 46 (23.2%), whereas 74 (37.4%) had ECMO initiated after 40 min. Cox regression revealed a significant association between time from CPR to ECMO initiation and 30-day mortality (adjusted hazard ratio [HR]: 2.20 in >40 min, HR: 2.63 in 20-40 min, p = 0.006) and 6-month mortality (HR: 1.81, in >40 min, HR: 1.99 in 20-40 min, p = 0.021). CONCLUSIONS: This study revealed that, in ECPR recipients, a shorter duration between CPR initiation and ECMO flow commencement is associated with improved short- and long-term patient prognoses. These findings emphasize the critical role of timely ECMO application in optimizing outcomes for patients undergoing ECPR.

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 to the manageable amount of clinical information as input features and is validated against multi-centered rather than single-centered data. Data were collected from 454,404 patients over 18 years of age who underwent non-cardiac surgeries from four independent institutions. We performed a retrospective analysis of the retrieved data. Only 12-18 clinical variables were used for model training. Logistic regression, random forest classifier, extreme gradient boosting (XGBoost), and deep neural network methods were applied to compare the prediction performances. To reduce overfitting and create a robust model, bootstrapping and grid search with tenfold cross-validation were performed. The XGBoost method in Seoul National University Hospital (SNUH) data delivers the best performance in terms of the area under receiver operating characteristic curve (AUROC) (0.9376) and the area under the precision-recall curve (0.1593). The predictive performance was the best when the SNUH model was validated with Ewha Womans University Medical Center data (AUROC, 0.941). Preoperative albumin, prothrombin time, and age were the most important features in the model for each hospital. It is possible to create a robust artificial intelligence prediction model applicable to multiple institutions through a light predictive model using only minimal preoperative information that can be automatically extracted from each hospital.

Some surgical patients require an arterial or central venous catheterization intraoperatively. This decision relied solely on the experience of individual anesthesiologists; however, these decisions are not easy for clinicians who are in an emergency or inexperienced. Therefore, applying recent artificial intelligence techniques to automatically extractable data from electronic medical record (EMR) could create a very clinically useful model in this situation. This study aimed to develop a model that is easy to apply in real clinical settings by implementing a prediction model for the preoperative decision to insert an arterial and central venous catheter and that can be automatically linked to the EMR. We collected and retrospectively analyzed data from 66,522 patients, > 18 years of age, who underwent non-cardiac surgeries from March 2019 to April 2021 at the single tertiary medical center. Data included demographics, pre-operative laboratory tests, surgical information, and catheterization information. When compared with other machine learning methods, the DNN model showed the best predictive performance in terms of the area under receiver operating characteristic curve and area under the precision-recall curve. Operation code information accounted for the largest portion of the prediction. This can be applied to clinical fields using operation code and minimal preoperative clinical information.

Background/Objectives: Postoperative pain after robot-assisted gynecologic surgery delays recovery and prolongs hospitalization, yet evidence on the role of ultrasound-guided rectus sheath block (RSB) in this setting is limited. We investigated whether preoperative ultrasound-guided RSB was associated with a shorter length of hospital stay (LOS) after robot-assisted gynecologic surgery. Methods: This single-center retrospective cohort study included 266 consecutive female patients who underwent robot-assisted gynecologic surgery between November 2023 and April 2024. RSB was introduced in January 2024; 113 patients from the RSB-eligible era who received the block and 153 patients before RSB introduction served as the RSB and comparator groups, respectively. The primary outcome was LOS. Secondary outcomes included rescue intravenous fentanyl and rescue antiemetic use in the post-anesthesia care unit (PACU) and rescue analgesic administration on the general ward through postoperative day (POD) 2. Multivariable quasi-Poisson regression was used to adjust for potential confounders. Results: LOS was significantly shorter in the RSB group (median 3 [IQR 3–3] vs. 4 [3–5] days; p < 0.001; adjusted IRR 0.78, 95% CI 0.72–0.85). The RSB group also required less PACU rescue fentanyl (0.86 [0.68–1.38] vs. 1.17 [0.85–1.69] μg/kg; p < 0.001), fewer rescue antiemetics (3.5% vs. 11.8%; p = 0.029), and fewer ward rescue analgesics on POD 0 (52.2% vs. 68.6%; p = 0.009) and POD 1 (13.3% vs. 34.2%; p < 0.001). Conclusions: Preoperative ultrasound-guided RSB was associated with shorter LOS, reduced PACU opioid and antiemetic requirements, and fewer early ward rescue analgesics. Randomized trials are warranted to confirm these benefits.

Opiranserin injection (Unafra®, Vivozon Inc.) is a first-in-class, non-opioid analgesic for the management of moderate-to-severe postoperative pain. The active ingredient, opiranserin (code name: VVZ-149), is a synthetic molecule that simultaneously antagonizes glycine transporter 2 (GlyT2) and serotonin 2A receptors (5-HT2A), both of which play key roles in pain processing. Opiranserin exemplifies the application of ex vivo phenotypic screening combined with a bait-target approach to identify effective multi-target agents that overcome the limitations of conventional single-target analgesics. In this review, we aim to describe the discovery and optimization of opiranserin through efficacy-based screening using a bait-target approach, outline its pharmacological mechanisms of action as a drug with both central and peripheral activity, and summarize published clinical studies demonstrating its successful translation from preclinical efficacy to reductions in postoperative pain and opioid consumption. We also discuss the clinical implications and future research directions to enhance the therapeutic utility of opiranserin injection and maximize patient benefit within the framework of precision analgesia.

BACKGROUND: The oxygen reserve index (ORi) noninvasively measures oxygen levels within the mild hyperoxia range. To evaluate whether a degree of increase in the ORi during preoxygenation for general anesthesia is associated with the occurrence of postoperative pulmonary complications (PPCs). METHODS: We enrolled 154 patients who underwent preoperative pulmonary function tests and were scheduled for elective surgery under general anesthesia. We aimed to measure the increase in ORi during preoxygenation before general anesthesia and analyze its association with PPCs. RESULTS: PPCs occurred in 76 (49%) participants. Multivariate logistic regression analysis revealed that the three-minute preoxygenation ORi was significantly associated with PPCs (Odds ratio [OR]: 0.02, 95% CI [0.00-0.16], P < 0.001). The areas under the curve (AUC [95% CI]) in the receiver operating characteristic curve analysis for the three-minute preoxygenation ORi for PPCs were 0.64 (0.55-0.73). After a subgroup analysis, multivariate logistic regression showed that the three-minute preoxygenation ORi was significantly associated with PPCs among patients who underwent thoracic surgery (OR: 0.01, 95% CI [0.00-0.19], P = 0.006). The AUC of the three-minute preoxygenation ORi for PPCs was 0.72 (0.57-0.86) in patients who underwent thoracic surgery. CONCLUSIONS: A low ORi measured after 3 min of preoxygenation for general anesthesia was associated with an increased risk of PPCs, including those undergoing thoracic surgery. This study demonstrated the potential of ORi, measured after oxygen administration, as a tool for evaluating lung function that complements traditional lung function tests and scoring systems.

Background and Objective: Lung transplantation is the only life-extending therapy for end-stage pulmonary disease patients, but its risks necessitate an understanding of outcome predictors, with the frailty index and nutritional status being key assessment tools. This study aims to evaluate the relationship between preoperative frailty and nutritional indexes and the postoperative mortality rate in patients receiving lung transplants, and to determine which measure is a more potent predictor of outcomes. Materials and Methods: This study reviewed 185 adults who received lung transplants at a single medical center between January 2013 and May 2023. We primarily focused on postoperative 7-year overall survival. Other outcomes measured were short-term mortalities, acute rejection, kidney complications, infections, and re-transplantation. We compared the predictive abilities of preoperative nutritional and frailty indicators for survival using receiver operating characteristic curve analysis and identified factors affecting survival through regression analyses. Results: There were no significant differences in preoperative nutritional indicators between survivors and non-survivors. However, preoperative frailty indicators did differ significantly between these groups. Multivariate analysis revealed that the American Society of Anesthesiologists Class V, clinical frailty scale, and Charlson Comorbidity Index (CCI) were key predictors of 7-year overall survival. Of these, the CCI had the strongest predictive ability with an area under the curve of 0.755, followed by the modified frailty index at 0.731. Conclusions: Our study indicates that for critically ill patients undergoing lung transplantation, frailty indexes derived from preoperative patient history and functional autonomy are more effective in forecasting postoperative outcomes, including survival, than indexes related to preoperative nutritional status.