Background: Worldwide, sepsis is the leading cause of death in hospitals. If mortality rates in patients with sepsis can be predicted early, medical resources can be allocated efficiently. We constructed machine learning (ML) models to predict the mortality of patients with sepsis in a hospital emergency department. Methods: This study prospectively collected nationwide data from an ongoing multicenter cohort of patients with sepsis identified in the emergency department. Patients were enrolled from 19 hospitals between September 2019 and December 2020. For acquired data from 3,657 survivors and 1,455 deaths, six ML models (logistic regression, support vector machine, random forest, extreme gradient boosting [XGBoost], light gradient boosting machine, and categorical boosting [CatBoost]) were constructed using fivefold cross-validation to predict mortality. Through these models, 44 clinical variables measured on the day of admission were compared with six sequential organ failure assessment (SOFA) components (PaO 2 /FIO 2 [PF], platelets (PLT), bilirubin, cardiovascular, Glasgow Coma Scale score, and creatinine).The confidence interval (CI) was obtained by performing 10,000 repeated measurements via random sampling of the test dataset. All results were explained and interpreted using Shapley’s additive explanations (SHAP). Results: Of the 5,112 participants, CatBoost exhibited the highest area under the curve (AUC) of 0.800 (95% CI, 0.756–0.840) using clinical variables. Using the SOFA components for the same patient, XGBoost exhibited the highest AUC of 0.678 (95% CI, 0.626–0.730). As interpreted by SHAP, albumin, lactate, blood urea nitrogen, and international normalization ratio were determined to significantly affect the results. Additionally, PF and PLTs in the SOFA component significantly influenced the prediction results. Conclusion Newly established ML-based models achieved good prediction of mortality in patients with sepsis. Using several clinical variables acquired at the baseline can provide more accurate results for early predictions than using SOFA components. Additionally, the impact of each variable was identified.

Objective: Adenomyosis impacts pregnancy outcomes, although there is a lack of consensus regarding the actual effects. It is likely, however, that the severity of adenomyosis or ultrasound findings or timing of diagnosis can have different effects on adverse pregnancy outcomes (APOs). Methods: In this study, we aimed to investigate the impact of the timing of adenomyosis diagnosis on pregnancy outcomes. Singleton pregnant women who delivered between 2017 and 2022 were analyzed based on the timing of adenomyosis diagnosis, using a national database. The final cohort was classified into three groups: 1) group 1, without adenomyosis; 2) group 2, those diagnosed with adenomyosis before pregnancy; and 3) group 3, those diagnosed with adenomyosis during pregnancy. Results: A total of 1,226,475 cases were ultimately included in this study. Women with a diagnosis of adenomyosis had a significantly higher risk of APOs including hypertensive disorder during pregnancy (HDP), gestational diabetes mellitus (GDM), postpartum hemorrhage, placental abruption, preterm birth, and delivery of a small-for-gestational-age infant even after adjusting for covariates. In particular, concerning HDP, the risk was highest in group 3 (group 2: adjusted odds ratio [aOR], 1.15 vs. group 3: aOR, 1.36). However, the highest GDM risk was in group 2 (GDM; group 2: aOR, 1.24 vs. group 3: aOR, 1.04). Conclusion The increased risk of APO differed depending on the timing of adenomyosis diagnosis. Therefore, efforts for more careful monitoring and prevention of APOs may be necessary when such women become pregnant.

Background: Surgical resection is the standard treatment for early-stage lung cancer. Since postoperative lung function is related to mortality, predicted postoperative lung function is used to determine the treatment modality. The aim of this study was to evaluate the predictive performance of linear regression and machine learning models. Methods: We extracted data from the Clinical Data Warehouse and developed three sets: set I, the linear regression model; set II, machine learning models omitting the missing data: and set III, machine learning models imputing the missing data. Six machine learning models, the least absolute shrinkage and selection operator (LASSO), Ridge regression, ElasticNet, Random Forest, eXtreme gradient boosting (XGBoost), and the light gradient boosting machine (LightGBM) were implemented. The forced expiratory volume in 1 second measured 6 months after surgery was defined as the outcome. Five-fold cross-validation was performed for hyperparameter tuning of the machine learning models. The dataset was split into training and test datasets at a 70:30 ratio. Implementation was done after dataset splitting in set III. Predictive performance was evaluated by R2 and mean squared error (MSE) in the three sets. Results: A total of 1,487 patients were included in sets I and III and 896 patients were included in set II. In set I, the R2 value was 0.27 and in set II, LightGBM was the best model with the highest R2 value of 0.5 and the lowest MSE of 154.95. In set III, LightGBM was the best model with the highest R2 value of 0.56 and the lowest MSE of 174.07. Conclusion The LightGBM model showed the best performance in predicting postoperative lung function.

Aortic dissection is one of the causes of acute ischemic stroke. Endovascular recanalization therapy (EVT) has emerged as an essential treatment for acute ischemic stroke due to large artery occlusion. However, it is rarely performed in the situation of hidden aortic dissection (AD). Two patients presented to the emergency room with focal neurologic deficits. The first patient was diagnosed with right internal carotid artery (ICA) occlusion. Angiography revealed that the ICA was occluded by the dissection flap. After a stent deployment in the proximal ICA, the antegrade flow was restored. The patient was diagnosed with AD on chest computed tomography (CT) after EVT. For the second patient, intraarterial thrombectomy was performed to treat left middle cerebral artery occlusion. AD was first detected on echocardiography, which was performed after EVT. Herein, we report successful endovascular recanalization therapy performed in two patients with acute ischemic stroke in the situation of undiagnosed aortic dissection. We also reviewed previous case reports and relevant literature.

Background/Aims: It remains unclear which maintenance treatment modality is most appropriate for mild gastroesophageal reflux disease (GERD).We aimed to compare on-demand treatment with continuous treatment using a proton pump inhibitor (PPI) in the maintenance treatment for patients with non-erosive GERD or mild erosive esophagitis. Methods: Patients whose GERD symptoms improved after 4 weeks of standard dose PPI treatment were prospectively enrolled at 25 hospitals.Subsequently, the enrolled patients were randomly assigned to either an on-demand or a continuous maintenance treatment group, and followed in an 8-week interval for up to 24 weeks. Results: A total of 304 patients were randomized to maintenance treatment (continuous, n = 151 vs on-demand, n = 153). The primary outcome, the overall proportion of unwillingness to continue the assigned maintenance treatment modality, failed to confirm the noninferiority of on-demand treatment (45.9%) compared to continuous treatment (36.1%). Compared with the on-demand group, the GERD symptom and health-related quality of life scores significantly more improved and the overall satisfaction score was significantly higher in the continuous treatment group, particularly at week 8 and week 16 of maintenance treatment. Work impairment scores were not different in the 2 groups, but the prescription cost was less in the on-demand group. Serum gastrin levels significantly elevated in the continuous treatment group, but not in the on-demand group. Conclusions Continuous treatment seems to be more appropriate for the initial maintenance treatment of non-erosive GERD or mild erosive esophagitis than on-demand treatment. Stepping down to on-demand treatment needs to be considered after a sufficient period of continuous treatment.

Colonoscopic polypectomy is effective in decreasing the incidence and mortality of colorectal cancer (CRC). Premalignant polyps discovered during colonoscopy are associated with the risk of metachronous advanced neoplasia. Postpolypectomy surveillance is the most important method for managing advanced metachronous neoplasia. A more efficient and evidence-based guideline for postpolypectomy surveillance is required because of the limited medical resources and concerns regarding colonoscopy complications. In these consensus guidelines, an analytic approach was used to address all reliable evidence to interpret the predictors of CRC or advanced neoplasia during surveillance colonoscopy. The key recommendations state that the high-risk findings for metachronous CRC following polypectomy are as follows: adenoma ≥10 mm in size; 3 to 5 (or more) adenomas; tubulovillous or villous adenoma; adenoma containing high-grade dysplasia; traditional serrated adenoma; sessile serrated lesion containing any grade of dysplasia; serrated polyp of at least 10 mm in size; and 3 to 5 (or more) sessile serrated lesions. More studies are needed to fully comprehend the patients who are most likely to benefit from surveillance colonoscopy and the ideal surveillance interval to prevent metachronous CRC.

Mannitol, derived from mannose sugar, is crucial in treating patients with elevated intracranial pressure (ICP). Its dehydrating properties at the cellular and tissue levels increase plasma osmotic pressure, which is studied for its potential to reduce ICP through osmotic diuresis. While clinical guidelines support mannitol use in these cases, the best approach for its application continues to be debated. Important aspects needing further investigation include: 1) bolus administration versus continuous infusion, 2) ICP-based dosing versus scheduled bolus, 3) identifying the optimal infusion rate, 4) determining the appropriate dosage, 5) establishing fluid replacement plans for urinary loss, and 6) selecting monitoring techniques and thresholds to assess effectiveness and ensure safety.Due to the lack of adequate high-quality prospective research data, a comprehensive review of recent studies and clinical trials is crucial. This assessment aims to bridge the knowledge gap, improve understanding of effective mannitol use in elevated ICP patients, and provide insights for future research. In conclusion, this review aspires to contribute to the ongoing discourse on mannitol application. By integrating the latest findings, this review will offer valuable insights into the function of mannitol in decreasing ICP, thereby informing better therapeutic approaches and enhancing patient outcomes.

While there is no level I recommendation for intracranial pressure (ICP) monitoring, it is typically indicated for patients with severe traumatic brain injury (TBI) with a Glasgow Coma Scale (GCS) score of 3–8 (class II). Even for moderate TBI patients with GCS 9–12, ICP monitoring should be considered for risk of increased ICP. The impact of ICP monitoring on patient outcomes is still not well-established, but recent studies reported a reduction of early mortality (class III) in TBI patients. There is no standard protocol for the application of ICP monitoring. In cases where cerebrospinal fluid drainage is required, an external ventricular drain is commonly used. In other cases, parenchymal ICP monitoring devices are generally employed. Subdural or non-invasive forms are not suitable for ICP monitoring. The mean value of ICP is the parameter recommended for observation in many guidelines. In TBI, values above 22 mmHg are associated with increased mortality. However, recent studies proposed various parameters including cumulative time with ICP above 20 mmHg (pressuretime dose), pressure reactivity index, ICP waveform characteristics (pulse amplitude of ICP, mean ICP wave amplitude), and the compensatory reserve of the brain (reserve-amplitudepressure), which are useful in predicting patient outcomes and guiding treatment. Further research is required for validation of these parameters compared to simple ICP monitoring.

Objective: : The aim of this study was to verify the equivalence and effectiveness of the tablet-administered Korean Repeatable Battery for the Assessment of Neuropsychological Status (K-RBANS) for the prevention and early detection of dementia. Methods: : Data from 88 psychiatry and neurology patient samples were examined to evaluate the equivalence between tablet and paper administrations of the K-RBANS using a non-randomly equivalent group design. We calculated the prediction scores of the tablet-administered K-RBANS based on demographics and covariate-test scores for focal tests using norm samples and tested format effects. In addition, we compared the receiver operating characteristic curves to confirm the effectiveness of the K-RBANS for preventing and detecting dementia. Results: : In the analysis of raw scores, line orientation showed a significant difference (t=-2.94, p<0.001), and subtests showed small to large effect sizes (0.04–0.86) between paper- and tablet-administered K-RBANS. To investigate the format effect, we compared the predicted scaled scores of the tablet sample to the scaled scores of the norm sample. Consequently, a small effect size (d≤0.20) was observed in most of the subtests, except word list and story recall, which showed a medium effect size (d=0.21), while picture naming and subtests of delayed memory showed significant differences in the one-sample t-test. In addition, the area under the curve of the total scale index (TSI) (0.827; 95% confidence interval, 0.738–0.916) was higher than that of the five indices, ranging from 0.688 to 0.820. The sensitivity and specificity of TSI were 80% and 76%, respectively. Conclusion : The overall results of this study suggest that the tablet-administered K-RBANS showed significant equivalence to the norm sample, although some subtests showed format effects, and it may be used as a valid tool for the brief screening of patients with neuropsychological disorders in Korea.

Desmoid fibromatosis is a very slowly growing benign fibroblast tumor. Locally aggressive and non-metastasizing, it is a well-differentiated, unencapsulated monoclonal myofibroblastic proliferation that has a tendency for local invasion and recurrence. About 15% of all desmoidtype fibromatosis develops within the head and neck. The majority of head and neck desmoid tumor is located in the neck, but less frequently in the face, scalp, oral cavity, mandible, paranasal sinuses, orbit, ear and other structures. We report a very rare case in a 55-year-old female of a desmoid fibromatosis arising from the lateral nasal wall of anterior portion of uncinated process. We discuss the clinicopathologic features and successful treatment of nasal desmoid tumor with a literature review.