Deep Learning-Based Localization and Detection of Malpositioned Nasogastric Tubes on Portable Supine Chest X-Rays in Intensive Care and Emergency Medicine: A Multi-center Retrospective Study.

Malposition of a nasogastric tube (NGT) can lead to severe complications. We aimed to develop a computer-aided detection (CAD) system to localize NGTs and detect NGT malposition on portable chest X-rays (CXRs). A total of 7378 portable CXRs were retrospectively retrieved from two hospitals between 2015 and 2020. All CXRs were annotated with pixel-level labels for NGT localization and image-level labels for NGT presence and malposition. In the CAD system, DeepLabv3 + with backbone ResNeSt50 and DenseNet121 served as the model architecture for segmentation and classification models, respectively. The CAD system was tested on images from chronologically different datasets (National Taiwan University Hospital (National Taiwan University Hospital)-20), geographically different datasets (National Taiwan University Hospital-Yunlin Branch (YB)), and the public CLiP dataset. For the segmentation model, the Dice coefficients indicated accurate delineation of the NGT course (National Taiwan University Hospital-20: 0.665, 95% confidence interval (CI) 0.630-0.696; National Taiwan University Hospital-Yunlin Branch: 0.646, 95% CI 0.614-0.678). The distance between the predicted and ground-truth NGT tips suggested accurate tip localization (National Taiwan University Hospital-20: 1.64 cm, 95% CI 0.99-2.41; National Taiwan University Hospital-Yunlin Branch: 2.83 cm, 95% CI 1.94-3.76). For the classification model, NGT presence was detected with high accuracy (area under the receiver operating characteristic curve (AUC): National Taiwan University Hospital-20: 0.998, 95% CI 0.995-1.000; National Taiwan University Hospital-Yunlin Branch: 0.998, 95% CI 0.995-1.000; CLiP dataset: 0.991, 95% CI 0.990-0.992). The CAD system also detected NGT malposition with high accuracy (AUC: National Taiwan University Hospital-20: 0.964, 95% CI 0.917-1.000; National Taiwan University Hospital-Yunlin Branch: 0.991, 95% CI 0.970-1.000) and detected abnormal nasoenteric tube positions with favorable performance (AUC: 0.839, 95% CI 0.807-0.869). The CAD system accurately localized NGTs and detected NGT malposition, demonstrating excellent potential for external generalizability.

End-tidal Carbon Dioxide Trajectory-based Prognostication of Out-of-hospital Cardiac Arrest.

Background: During cardiopulmonary resuscitation (CPR), end-tidal carbon dioxide (EtCO2) is primarily determined by pulmonary blood flow, thereby reflecting the blood flow generated by CPR. We aimed to develop an EtCO2 trajectory-based prediction model for prognostication at specific time points during CPR in patients with out-of-hospital cardiac arrest (OHCA). Methods: We screened patients receiving CPR between 2015-2021 from a prospectively collected database of a tertiary-care medical center. The primary outcome was survival to hospital discharge. We used group-based trajectory modeling to identify the EtCO2 trajectories. Multivariable logistic regression analysis was used for model development and internally validated using bootstrapping. We assessed performance of the model using the area under the receiver operating characteristic curve (AUC). Results: The primary analysis included 542 patients with a median age of 68.0 years. Three distinct EtCO2 trajectories were identified in patients resuscitated for 20 minutes (min): low (average EtCO2 10.0 millimeters of mercury [mm Hg]; intermediate (average EtCO2 26.5 mm Hg); and high (average EtCO2: 51.5 mm Hg). Twenty-min EtCO2 trajectory was fitted as an ordinal variable (low, intermediate, and high) and positively associated with survival (odds ratio 2.25, 95% confidence interval [CI] 1.07-4.74). When the 20-min EtCO2 trajectory was combined with other variables, including arrest location and arrest rhythms, the AUC of the 20-min prediction model for survival was 0.89 (95% CI 0.86-0.92). All predictors in the 20-min model remained statistically significant after bootstrapping. Conclusion: Time-specific EtCO2 trajectory was a significant predictor of OHCA outcomes, which could be combined with other baseline variables for intra-arrest prognostication. For this purpose, the 20-min survival model achieved excellent discriminative performance in predicting survival to hospital discharge.

Application of Phosphorylated Tau for Predicting Outcomes Among Sudden Cardiac Arrest Survivors.

BACKGROUND: Phosphorylated Tau (p-Tau), an early biomarker of neuronal damage, has emerged as a promising candidate for predicting neurological outcomes in cardiac arrest (CA) survivors. Despite its potential, the correlation of p-Tau with other clinical indicators remains underexplored. This study assesses the predictive capability of p-Tau and its effectiveness when used in conjunction with other predictors. METHODS: In this single-center retrospective study, 230 CA survivors had plasma and brain computed tomography scans collected within 24 h after the return of spontaneous circulation (ROSC) from January 2016 to June 2023. The patients with prearrest Cerebral Performance Category scores ≥ 3 were excluded (n = 33). The neurological outcomes at discharge with Cerebral Performance Category scores 1-2 indicated favorable outcomes. Plasma p-Tau levels were measured using an enzyme-linked immunosorbent assay, diastolic blood pressure (DBP) was recorded after ROSC, and the gray-to-white matter ratio (GWR) was calculated from brain computed tomography scans within 24 h after ROSC. RESULTS: Of 197 patients enrolled in the study, 54 (27.4%) had favorable outcomes. Regression analysis showed that higher p-Tau levels correlated with unfavorable neurological outcomes. The levels of p-Tau were significantly correlated with DBP and GWR. For p-Tau to differentiate between neurological outcomes, an optimal cutoff of 456 pg/mL yielded an area under the receiver operating characteristic curve of 0.71. Combining p-Tau, GWR, and DBP improved predictive accuracy (area under the receiver operating characteristic curve = 0.80 vs. 0.71, p = 0.008). CONCLUSIONS: Plasma p-Tau levels measured within 24 h following ROSC, particularly when combined with GWR and DBP, may serve as a promising biomarker of neurological outcomes in CA survivors, with higher levels predicting unfavorable outcomes.

Prognostic Impact of Heart Rhythm Shockability Trajectory in Out-of-Hospital Cardiac Arrest: A Multicenter Retrospective Study.

BACKGROUND: This study aimed to investigate the association between the temporal transitions in heart rhythms during cardiopulmonary resuscitation (CPR) and outcomes after out-of-hospital cardiac arrest. METHODS: This was an analysis of the prospectively collected databases in 3 academic hospitals in northern and central Taiwan. Adult patients with out-of-hospital cardiac arrest transported by emergency medical service between 2015 and 2022 were included. Favorable neurological recovery and survival to hospital discharge were the primary and secondary outcomes, respectively. Time-specific heart rhythm shockability was defined as the probability of shockable rhythms at a particular time point during CPR. The temporal changes in the time-specific heart rhythm shockability were calculated by group-based trajectory modeling. Multivariable logistic regression analyses were performed to examine the association between the trajectory group and outcomes. Subgroup analyses examined the effects of extracorporeal CPR in different trajectories. RESULTS: The study comprised 2118 patients. The median patient age was 69.1 years, and 1376 (65.0%) patients were male. Three distinct trajectories were identified: high-shockability (52 patients; 2.5%), intermediate-shockability (262 patients; 12.4%), and low-shockability (1804 patients; 85.2%) trajectories. The median proportion of shockable rhythms over the course of CPR for the 3 trajectories was 81.7% (interquartile range, 73.2%-100.0%), 26.7% (interquartile range, 16.7%-37.5%), and 0% (interquartile range, 0%-0%), respectively. The multivariable analysis indicated both intermediate- and high-shockability trajectories were associated with favorable neurological recovery (intermediate-shockability: adjusted odds ratio [aOR], 4.98 [95% CI, 2.34-10.59]; high-shockability: aOR, 5.40 [95% CI, 2.03-14.32]) and survival (intermediate-shockability: aOR, 2.46 [95% CI, 1.44-4.18]; high-shockability: aOR, 2.76 [95% CI, 1.20-6.38]). The subgroup analysis further indicated extracorporeal CPR was significantly associated with favorable neurological outcomes (aOR, 4.06 [95% CI, 1.11-14.81]) only in the intermediate-shockability trajectory. CONCLUSIONS: Heart rhythm shockability trajectories were associated with out-of-hospital cardiac arrest outcomes, which may be a supplementary factor in guiding the allocation of medical resources, such as extracorporeal CPR.

Multidimensional frailty in elderly emergency department patients: unveiling the prevalence and significance of social frailty.

PURPOSE: This study aimed to assess the prevalence and factors of physical, psychological, and social frailty among older adults in the emergency department, comparing these data with community population to understand emergency setting manifestations. METHODS: Conducted at the Emergency Department of National Taiwan University BioMedical Park Hospital, this prospective observational cohort study enrolled older adult patients over a three-month period. Frailty assessments included the Study of Osteoporotic Fractures scale for physical frailty, the Tilburg Frailty Indicator for psychological frailty, and the Makizako Social Frailty Index for social frailty. Data analysis involved a multivariable logistic model to determine the risk factors associated with each frailty type. RESULTS: Out of 991 older adult individuals seeking medical care, 207 participated in the study. The study found high prevalence rates of frailty: 46.38% for physical, 41.06% for psychological, and 48.79% for social frailty. Risk factors for frailty included older age and a history of falls. Interestingly, the prevalence of social frailty was notably higher than physical and psychological frailty. Gender and polypharmacy showed no significant association with any frailty type. CONCLUSION: This research reveals high physical, psychological, and social frailty among older ED patients, especially noting social frailty's prevalence. It highlights the importance for emergency care to adopt holistic care strategies that address older adults' multifaceted health challenges, suggesting a paradigm shift in current healthcare practices to better cater to the multifaceted needs of this vulnerable population.

RéSUMé: OBJECTIFS: Cette étude visait à évaluer la prévalence et les facteurs de la fragilité physique, psychologique et sociale chez les personnes âgées au service des urgences, en comparant ces données avec la population communautaire pour comprendre les manifestations en situation d'urgence. MéTHODES: Menée au service des urgences de l'hôpital BioMedical Park de l'Université nationale de Taiwan, cette étude prospective de cohorte observationnelle a recruté des patients adultes âgés sur une période de trois mois. Les évaluations de la fragilité comprenaient l'échelle de l'étude des fractures ostéoporotiques pour la fragilité physique, l'indicateur de la fragilité psychologique de Tilburg et l'indice de fragilité sociale de Makizako pour la fragilité sociale. L'analyse des données comportait un modèle logistique multivarié pour déterminer les facteurs de risque associés à chaque type de fragilité. RéSULTATS: Sur 991 personnes âgées ayant besoin de soins médicaux, 207 ont participé à l'étude. L'étude a révélé des taux de prévalence élevés de la fragilité : 46,38% pour le physique, 41,06% pour le psychologique et 48,79% pour la fragilité sociale. Les facteurs de risque de fragilité comprenaient un âge avancé et des antécédents de chute. Fait intéressant, la prévalence de la fragilité sociale était nettement plus élevée que la fragilité physique et psychologique. Le genre et la polypharmacie n'ont montré aucune association significative avec aucun type de fragilité. CONCLUSION: Cette recherche révèle une grande fragilité physique, psychologique et sociale chez les patients âgés aux urgences, en particulier la prévalence de la fragilité sociale. Il souligne l'importance pour les soins d'urgence d'adopter des stratégies de soins holistiques qui répondent aux défis de santé multiformes des personnes âgées, suggérant un changement de paradigme dans les pratiques de soins de santé actuelles pour mieux répondre aux besoins multiformes de cette population vulnérable.

Performance of Intra-arrest Echocardiography: A Systematic Review.

Introduction: Intra-arrest transthoracic echocardiography (TTE) and transesophageal echocardiography (TEE) have been introduced in adult patients with cardiac arrest (CA). Whether the diagnostic performance of TTE or TEE is superior during resuscitation is unclear. We conducted a systematic review following PRISMA guidelines. Methods: We searched databases from PubMed, Embase, and Google Scholar and evaluated articles with intra-arrest TTE and TEE in adult patients with non-traumatic CA. Two authors independently screened and selected articles for inclusion; they then dual-extracted study characteristics and target conditions (pericardial effusion, aortic dissection, pulmonary embolism, myocardial infarction, hypovolemia, left ventricular dysfunction, and sonographic cardiac activity). We performed quality assessment using the Quality Assessment of Diagnostic Accuracy Studies Version 2 criteria. Results: A total of 27 studies were included: 14 studies with 2,145 patients assessed TTE; and 16 with 556 patients assessed TEE. A high risk of bias or applicability concerns in at least one domain was present in 20 studies (74%). Both TTE and TEE found positive findings in nearly one-half of the patients. The etiology of CA was identified in 13% (271/2,145), and intervention was performed in 38% (102/271) of patients in the TTE group. In patients who received TEE, the etiology was identified in 43% (239/556), and intervention was performed in 28% (68/239). In the TEE group, a higher incidence regarding the etiology of CA was observed, particularly for those with aortic dissection. However, the outcome of those with aortic dissection in the TEE group was poor. Conclusion: While TEE could identify more causes of CA than TTE, sonographic cardiac activity was reported much more in the TTE group. The impact of TTE and TEE on the return of spontaneous circulation and further survival was still inconclusive in the current dataset.

Using Machine Learning with Impulse Oscillometry Data to Develop a Predictive Model for Chronic Obstructive Pulmonary Disease and Asthma.

We aimed to develop and validate a machine learning model using impulse oscillometry system (IOS) profiles for accurately classifying patients into three assessment-based categories: no airflow obstruction, asthma, and chronic obstructive pulmonary disease (COPD). Our research questions were as follows: (1) Can machine learning methods accurately classify obstructive disease states based solely on multidimensional IOS data? (2) Which IOS parameters and modeling algorithms provide the best discrimination? We used data for 480 patients (240 with COPD and 240 with asthma) and 84 healthy individuals for training. Physiological and IOS parameters were combined into six feature combinations. The classification algorithms tested were logistic regression, random forest, neural network, k-nearest neighbor, and support vector machine. The optimal feature combination for identifying individuals without pulmonary obstruction, with asthma, or with COPD included 15 IOS and physiological features. The neural network classifier achieved the highest accuracy (0.786). For discriminating between healthy and unhealthy individuals, two combinations of twenty-three features performed best in the neural network algorithm (accuracy of 0.929). When distinguishing COPD from asthma, the best combination included 15 features and the neural network algorithm achieved an accuracy of 0.854. This study provides compelling technical evidence and clinical justifications for advancing IOS data-driven models to aid in COPD and asthma management.

Interpretable Deep Learning System for Identifying Critical Patients Through the Prediction of Triage Level, Hospitalization, and Length of Stay: Prospective Study.

BACKGROUND: Triage is the process of accurately assessing patients' symptoms and providing them with proper clinical treatment in the emergency department (ED). While many countries have developed their triage process to stratify patients' clinical severity and thus distribute medical resources, there are still some limitations of the current triage process. Since the triage level is mainly identified by experienced nurses based on a mix of subjective and objective criteria, mis-triage often occurs in the ED. It can not only cause adverse effects on patients, but also impose an undue burden on the health care delivery system. OBJECTIVE: Our study aimed to design a prediction system based on triage information, including demographics, vital signs, and chief complaints. The proposed system can not only handle heterogeneous data, including tabular data and free-text data, but also provide interpretability for better acceptance by the ED staff in the hospital. METHODS: In this study, we proposed a system comprising 3 subsystems, with each of them handling a single task, including triage level prediction, hospitalization prediction, and length of stay prediction. We used a large amount of retrospective data to pretrain the model, and then, we fine-tuned the model on a prospective data set with a golden label. The proposed deep learning framework was built with TabNet and MacBERT (Chinese version of bidirectional encoder representations from transformers [BERT]). RESULTS: The performance of our proposed model was evaluated on data collected from the National Taiwan University Hospital (901 patients were included). The model achieved promising results on the collected data set, with accuracy values of 63%, 82%, and 71% for triage level prediction, hospitalization prediction, and length of stay prediction, respectively. CONCLUSIONS: Our system improved the prediction of 3 different medical outcomes when compared with other machine learning methods. With the pretrained vital sign encoder and repretrained mask language modeling MacBERT encoder, our multimodality model can provide a deeper insight into the characteristics of electronic health records. Additionally, by providing interpretability, we believe that the proposed system can assist nursing staff and physicians in taking appropriate medical decisions.

Outcome prediction of cardiac arrest with automatically computed gray-white matter ratio on computed tomography images.

BACKGROUND: This study aimed to develop an automated method to measure the gray-white matter ratio (GWR) from brain computed tomography (CT) scans of patients with out-of-hospital cardiac arrest (OHCA) and assess its significance in predicting early-stage neurological outcomes. METHODS: Patients with OHCA who underwent brain CT imaging within 12 h of return of spontaneous circulation were enrolled in this retrospective study. The primary outcome endpoint measure was a favorable neurological outcome, defined as cerebral performance category 1 or 2 at hospital discharge. We proposed an automated method comprising image registration, K-means segmentation, segmentation refinement, and GWR calculation to measure the GWR for each CT scan. The K-means segmentation and segmentation refinement was employed to refine the segmentations within regions of interest (ROIs), consequently enhancing GWR calculation accuracy through more precise segmentations. RESULTS: Overall, 443 patients were divided into derivation N=265, 60% and validation N=178, 40% sets, based on age and sex. The ROI Hounsfield unit values derived from the automated method showed a strong correlation with those obtained from the manual method. Regarding outcome prediction, the automated method significantly outperformed the manual method in GWR calculation (AUC 0.79 vs. 0.70) across the entire dataset. The automated method also demonstrated superior performance across sensitivity, specificity, and positive and negative predictive values using the cutoff value determined from the derivation set. Moreover, GWR was an independent predictor of outcomes in logistic regression analysis. Incorporating the GWR with other clinical and resuscitation variables significantly enhanced the performance of prediction models compared to those without the GWR. CONCLUSIONS: Automated measurement of the GWR from non-contrast brain CT images offers valuable insights for predicting neurological outcomes during the early post-cardiac arrest period.

Feasibility of predicting functional decline in the elderly through key posture information during sit-to-stand movement.

BACKGROUND: Early detection of functional decline in the elderly in day care centres facilitates timely implementation of preventive and treatment measures. RESEARCH QUESTION: Whether or not a predictive model can be developed by applying image recognition to analyze elderly individuals' posture during the sit-to-stand (STS) manoeuvre. METHODS: We enrolled sixty-six participants (24 males and 42 females) in an observational study design. To estimate posture key point information, we employed a region-based convolutional neural network model and utilized nine key points and their coordinates to calculate seven eigenvalues (X1-X7) that represented the motion curve features during the STS manoeuvre. One-way analysis of variance was performed to evaluate four STS strategies and four types of compensation strategies for three groups with different capacities (college students, community-dwelling elderly, and day care center elderly). Finally, a machine learning predictive model was established. RESULTS: Significant differences (p < 0.05) were observed in all eigenvalues except X2 (momentum transfer phase, p = 0.168) between participant groups; significant differences (p < 0.05) were observed in all eigenvalues except X2 (p = 0.219) and X3 (hip-rising phase, p = 0.286) between STS patterns; significant differences (p < 0.05) were observed in all eigenvalues except X2 (p = 0.842) and X3 (p = 0.074) between compensation strategies. The motion curve eigenvalues of the seven posture key points were used to build a machine learning model with 85% accuracy in capacity detection, 70% accuracy in pattern detection, and 85% accuracy in compensation strategy detection. SIGNIFICANCE: This study preliminarily demonstrates that eigenvalues can be used to detect STS patterns and compensation strategies adopted by individuals with different capacities. Our machine learning model has excellent predictive accuracy and may be used to develop inexpensive and effective systems to help caregivers to continuously monitor STS patterns and compensation strategies of elderly individuals as warning signs of functional decline.

Prognostic value of arterial carbon dioxide tension during cardiopulmonary resuscitation in out-of-hospital cardiac arrest patients receiving extracorporeal resuscitation.

BACKGROUND: Current guidelines on extracorporeal cardiopulmonary resuscitation (ECPR) recommend careful patient selection, but precise criteria are lacking. Arterial carbon dioxide tension (PaCO2) has prognostic value in out-of-hospital cardiac arrest (OHCA) patients but has been less studied in patients receiving ECPR. We studied the relationship between PaCO2 during cardiopulmonary resuscitation (CPR) and neurological outcomes of OHCA patients receiving ECPR and tested whether PaCO2 could help ECPR selection. METHODS: This single-centre retrospective study enrolled 152 OHCA patients who received ECPR between January 2012 and December 2020. Favorable neurological outcome (FO) at discharge was the primary outcome. We used multivariable logistic regression to determine the independent variables for FO and generalised additive model (GAM) to determine the relationship between PaCO2 and FO. Subgroup analyses were performed to test discriminative ability of PaCO2 in subgroups of OHCA patients. RESULTS: Multivariable logistic regression showed that PaCO2 was independently associated with FO after adjusting for other favorable resuscitation characteristics (Odds ratio [OR] 0.23, 95% Confidence Interval [CI] 0.08-0.66, p-value = 0.006). GAM showed a near-linear reverse relationship between PaCO2 and FO. PaCO2 < 70 mmHg was the cutoff point for predicting FO. PaCO2 also had prognostic value in patients with less favorable characteristics, including non-shockable rhythm (OR, 3.78) or low flow time > 60 min (OR, 4.66). CONCLUSION: PaCO2 before ECMO implementation had prognostic value for neurological outcomes in OHCA patients. Patients with PaCO2 < 70 mmHg had higher possibility of FO, even in those with non-shockable rhythm or longer low-flow duration. PaCO2 could serve as an ECPR selection criterion.

A novel scale for triage assessment of frailty in the emergency department (ED-FraS): a prospective videotaped study.

BACKGROUND: Rapid recognition of frailty in older patients in the ED is an important first step toward better geriatric care in the ED. We aimed to develop and validate a novel frailty assessment scale at ED triage, the Emergency Department Frailty Scale (ED-FraS). METHODS: We conducted a prospective cohort study enrolling adult patients aged 65 years or older who visited the ED at an academic medical center. The entire triage process was recorded, and triage data were collected, including the Taiwan Triage and Acuity Scale (TTAS). Five physician raters provided ED-FraS levels after reviewing videos. A modified TTAS (mTTAS) incorporating ED-FraS was also created. The primary outcome was hospital admission following the ED visit, and secondary outcomes included the ED length of stay (EDLOS) and total ED visit charges. RESULTS: A total of 256 patients were included. Twenty-seven percent of the patients were frail according to the ED-FraS. The majority of ED-FraS was level 2 (57%), while the majority of TTAS was level 3 (81%). There was a weak agreement between the ED-FraS and TTAS (kappa coefficient of 0.02). The hospital admission rate and charge were highest at ED-FraS level 5 (severely frail), whereas the EDLOS was longest at level 4 (moderately frail). The area under the Receiver Operating Characteristic curve (AUROC) in predicting hospital admission for the TTAS, ED-FraS, and mTTAS were 0.57, 0.62, and 0.63, respectively. The ED-FraS explained more variation in EDLOS (R2 = 0.096) compared with the other two methods. CONCLUSIONS: The ED-Fras tool is a simple and valid screening tool for identifying frail older adults in the ED. It also can complement and enhance ED triage systems. Further research is needed to test its real-time use at ED triage internationally.

The interaction of sex and age on outcomes in emergency medical services-treated out-of-hospital cardiac arrest: A 5-year multicenter retrospective analysis.

Background: Studies have established that sex and age influence outcomes following out-of-hospital cardiac arrest (OHCA). However, a knowledge gap exists regarding their interaction. This study aimed to investigate the interaction of age and sex and how they cooperatively influence OHCA outcomes. Methods: This retrospective cohort study included adult, nontraumatic OHCA patients admitted to a university hospital and its affiliated hospitals in Taiwan from January 2017 to December 2021. Data including sex, age, body mass index, cardiac rhythm, and resuscitation information in the emergency department (ED) were collected from medical records. The study outcomes encompassed survival to intensive care unit (ICU) admission, survival to hospital discharge, and a favorable neurological outcome. Multivariable logistic regression was performed to estimate the influence of sex on study outcomes. Results: We analyzed a total of 2,826 eligible subjects categorized into three groups: young (18-44 years, 149 males and 57 females), middle-aged (45-64 years, 524 males and 188 females), and old (≥65 years, 1,049 males and 859 females). Analysis of the effects of sex according to age stratification showed that old males had higher odds for survival to ICU admission (OR: 1.49, 95% CI: 1.21-1.83) and favorable neurological outcomes (OR: 2.74, 95% CI: 1.58-4.76) than did old females. Analysis of the effects of age according to sex stratification revealed that old males had lower odds for survival to hospital discharge (OR: 0.33, 95% CI: 0.21-0.51) and favorable neurological outcomes (OR: 0.26, 95% CI: 0.16-0.43) than did young males. Old females also showed the same trend as males, with lower odds for survival to hospital discharge (OR: 0.37, 95% CI: 0.17-0.78) and favorable neurological outcomes (OR: 0.11, 95% CI: 0.05-0.25) than did young females. Conclusions: The interaction between sex and age in patients with OHCA results in diverse outcomes. Within the same sex, age demonstrated varying effects on distinct outcomes.

Application of Machine Learning to Ultrasonography in Identifying Anatomical Landmarks for Cricothyroidotomy Among Female Adults: A Multi-center Prospective Observational Study.

We aimed to develop machine learning (ML)-based algorithms to assist physicians in ultrasound-guided localization of cricoid cartilage (CC) and thyroid cartilage (TC) in cricothyroidotomy. Adult female volunteers were prospectively recruited from two hospitals between September and December, 2020. Ultrasonographic images were collected via a modified longitudinal technique. You Only Look Once (YOLOv5s), Faster Regions with Convolutional Neural Network features (Faster R-CNN), and Single Shot Detector (SSD) were selected as the model architectures. A total of 488 women (mean age: 36.0 years) participated in the study, contributing to a total of 292,053 frames of ultrasonographic images. The derived ML-based algorithms demonstrated excellent discriminative performance for the presence of CC (area under the receiver operating characteristic curve [AUC]: YOLOv5s, 0.989, 95% confidence interval [CI]: 0.982-0.994; Faster R-CNN, 0.986, 95% CI: 0.980-0.991; SSD, 0.968, 95% CI: 0.956-0.977) and TC (AUC: YOLOv5s, 0.989, 95% CI: 0.977-0.997; Faster R-CNN, 0.981, 95% CI: 0.965-0.991; SSD, 0.982, 95% CI: 0.973-0.990). Furthermore, in the frames where the model could correctly indicate the presence of CC or TC, it also accurately localized CC (intersection-over-union: YOLOv5s, 0.753, 95% CI: 0.739-0.765; Faster R-CNN, 0.720, 95% CI: 0.709-0.732; SSD, 0.739, 95% CI: 0.726-0.751) or TC (intersection-over-union: YOLOv5s, 0.739, 95% CI: 0.722-0.755; Faster R-CNN, 0.709, 95% CI: 0.687-0.730; SSD, 0.713, 95% CI: 0.695-0.730). The ML-based algorithms could identify anatomical landmarks for cricothyroidotomy in adult females with favorable discriminative and localization performance. Further studies are warranted to transfer this algorithm to hand-held portable ultrasound devices for clinical use.

Deep Learning-based Diagnosis of Pulmonary Tuberculosis on Chest X-ray in the Emergency Department: A Retrospective Study.

Prompt and correct detection of pulmonary tuberculosis (PTB) is critical in preventing its spread. We aimed to develop a deep learning-based algorithm for detecting PTB on chest X-ray (CXRs) in the emergency department. This retrospective study included 3498 CXRs acquired from the National Taiwan University Hospital (NTUH). The images were chronologically split into a training dataset, NTUH-1519 (images acquired during the years 2015 to 2019; n = 2144), and a testing dataset, NTUH-20 (images acquired during the year 2020; n = 1354). Public databases, including the NIH ChestX-ray14 dataset (model training; 112,120 images), Montgomery County (model testing; 138 images), and Shenzhen (model testing; 662 images), were also used in model development. EfficientNetV2 was the basic architecture of the algorithm. Images from ChestX-ray14 were employed for pseudo-labelling to perform semi-supervised learning. The algorithm demonstrated excellent performance in detecting PTB (area under the receiver operating characteristic curve [AUC] 0.878, 95% confidence interval [CI] 0.854-0.900) in NTUH-20. The algorithm showed significantly better performance in posterior-anterior (PA) CXR (AUC 0.940, 95% CI 0.912-0.965, p-value < 0.001) compared with anterior-posterior (AUC 0.782, 95% CI 0.644-0.897) or portable anterior-posterior (AUC 0.869, 95% CI 0.814-0.918) CXR. The algorithm accurately detected cases of bacteriologically confirmed PTB (AUC 0.854, 95% CI 0.823-0.883). Finally, the algorithm tested favourably in Montgomery County (AUC 0.838, 95% CI 0.765-0.904) and Shenzhen (AUC 0.806, 95% CI 0.771-0.839). A deep learning-based algorithm could detect PTB on CXR with excellent performance, which may help shorten the interval between detection and airborne isolation for patients with PTB.

Prognostic implication of heart failure stage and left ventricular ejection fraction for patients with in-hospital cardiac arrest: a 16-year retrospective cohort study.

BACKGROUND: The 2022 AHA/ACC/HFSA guidelines for the management of heart failure (HF) makes therapeutic recommendations based on HF status. We investigated whether the prognosis of in-hospital cardiac arrest (IHCA) could be stratified by HF stage and left ventricular ejection fraction (LVEF). METHODS: This single-center retrospective study analyzed the data of patients who experienced IHCA between 2005 and 2020. Based on admission diagnosis, past medical records, and pre-arrest echocardiography, patients were classified into general IHCA, at-risk for HF, pre-HF, HF with preserved ejection fraction (HFpEF), and HF with mildly reduced ejection fraction or HF with reduced ejection fraction (HFmrEF-or-HFrEF) groups. RESULTS: This study included 2,466 patients, including 485 (19.7%), 546 (22.1%), 863 (35.0%), 342 (13.9%), and 230 (9.3%) patients with general IHCA, at-risk for HF, pre-HF, HFpEF, and HFmrEF-or-HFrEF, respectively. A total of 405 (16.4%) patients survived to hospital discharge, with 228 (9.2%) patients achieving favorable neurological recovery. Multivariable logistic regression analysis indicated that pre-HF and HFpEF were associated with better neurological (pre-HF, OR: 2.11, 95% confidence interval [CI]: 1.23-3.61, p = 0.006; HFpEF, OR: 1.90, 95% CI: 1.00-3.61, p = 0.05) and survival outcomes (pre-HF, OR: 2.00, 95% CI: 1.34-2.97, p < 0.001; HFpEF, OR: 1.91, 95% CI: 1.20-3.05, p = 0.007), compared with general IHCA. CONCLUSION: HF stage and LVEF could stratify patients with IHCA into different prognoses. Pre-HF and HFpEF were significantly associated with favorable neurological and survival outcomes after IHCA. Further studies are warranted to investigate whether HF status-directed management could improve IHCA outcomes.

Deep Learning-Based Localization and Detection of Malpositioned Endotracheal Tube on Portable Supine Chest Radiographs in Intensive and Emergency Medicine: A Multicenter Retrospective Study.

OBJECTIVES: We aimed to develop a computer-aided detection (CAD) system to localize and detect the malposition of endotracheal tubes (ETTs) on portable supine chest radiographs (CXRs). DESIGN: This was a retrospective diagnostic study. DeepLabv3+ with ResNeSt50 backbone and DenseNet121 served as the model architecture for segmentation and classification tasks, respectively. SETTING: Multicenter study. PATIENTS: For the training dataset, images meeting the following inclusion criteria were included: 1) patient age greater than or equal to 20 years; 2) portable supine CXR; 3) examination in emergency departments or ICUs; and 4) examination between 2015 and 2019 at National Taiwan University Hospital (NTUH) (NTUH-1519 dataset: 5,767 images). The derived CAD system was tested on images from chronologically (examination during 2020 at NTUH, NTUH-20 dataset: 955 images) or geographically (examination between 2015 and 2020 at NTUH Yunlin Branch [YB], NTUH-YB dataset: 656 images) different datasets. All CXRs were annotated with pixel-level labels of ETT and with image-level labels of ETT presence and malposition. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: For the segmentation model, the Dice coefficients indicated that ETT would be delineated accurately (NTUH-20: 0.854; 95% CI, 0.824-0.881 and NTUH-YB: 0.839; 95% CI, 0.820-0.857). For the classification model, the presence of ETT could be accurately detected with high accuracy (area under the receiver operating characteristic curve [AUC]: NTUH-20, 1.000; 95% CI, 0.999-1.000 and NTUH-YB: 0.994; 95% CI, 0.984-1.000). Furthermore, among those images with ETT, ETT malposition could be detected with high accuracy (AUC: NTUH-20, 0.847; 95% CI, 0.671-0.980 and NTUH-YB, 0.734; 95% CI, 0.630-0.833), especially for endobronchial intubation (AUC: NTUH-20, 0.991; 95% CI, 0.969-1.000 and NTUH-YB, 0.966; 95% CI, 0.933-0.991). CONCLUSIONS: The derived CAD system could localize ETT and detect ETT malposition with excellent performance, especially for endobronchial intubation, and with favorable potential for external generalizability.

The incidence, predictors, and causes of cardiac arrest in United States emergency departments.

Background: Emergency department cardiac arrest (EDCA) is a global public health challenge associated with high mortality rates and poor neurological outcomes. This study aimed to describe the incidence, risk factors, and causes of EDCA during emergency department (ED) visits in the U.S. Methods: This retrospective cohort study used data from the 2019 Nationwide Emergency Department Sample (NEDS). Adult ED visits with EDCA were identified using the cardiopulmonary resuscitation code. We used descriptive statistics and multivariable logistic regression, considering NEDS's complex survey design. The primary outcome measure was EDCA incidence. Results: In 2019, there were approximately 232,000 ED visits with cardiac arrest in the U.S. The incidence rate of EDCA was approximately 0.2%. Older age, being male, black race, low median household income, weekend ED visits, having Medicare insurance, and ED visits in non-summer seasons were associated with a higher risk of EDCA. Hispanic race was associated with a lower risk of EDCA. Certain comorbidities (e.g., diabetes and cancer), trauma centers, hospitals with a metropolitan and/or teaching program, and hospitals in the South were associated with a higher risk of EDCA. Depression, dementia, and hypothyroidism were associated with a lower risk of EDCA. Septicemia, acute myocardial infarction, and respiratory failure, followed by drug overdose, were the predominant causes of EDCA. Conclusions: Some patients were disproportionately affected by EDCA. Strategies should be developed to target these modifiable risk factors, specifically factors within ED's control, to reduce the subsequent disease burden.

Deep Learning-based Diagnosis and Localization of Pneumothorax on Portable Supine Chest X-ray in Intensive and Emergency Medicine: A Retrospective Study.

PURPOSE: To develop two deep learning-based systems for diagnosing and localizing pneumothorax on portable supine chest X-rays (SCXRs). METHODS: For this retrospective study, images meeting the following inclusion criteria were included: (1) patient age ≥ 20 years; (2) portable SCXR; (3) imaging obtained in the emergency department or intensive care unit. Included images were temporally split into training (1571 images, between January 2015 and December 2019) and testing (1071 images, between January 2020 to December 2020) datasets. All images were annotated using pixel-level labels. Object detection and image segmentation were adopted to develop separate systems. For the detection-based system, EfficientNet-B2, DneseNet-121, and Inception-v3 were the architecture for the classification model; Deformable DETR, TOOD, and VFNet were the architecture for the localization model. Both classification and localization models of the segmentation-based system shared the UNet architecture. RESULTS: In diagnosing pneumothorax, performance was excellent for both detection-based (Area under receiver operating characteristics curve [AUC]: 0.940, 95% confidence interval [CI]: 0.907-0.967) and segmentation-based (AUC: 0.979, 95% CI: 0.963-0.991) systems. For images with both predicted and ground-truth pneumothorax, lesion localization was highly accurate (detection-based Dice coefficient: 0.758, 95% CI: 0.707-0.806; segmentation-based Dice coefficient: 0.681, 95% CI: 0.642-0.721). The performance of the two deep learning-based systems declined as pneumothorax size diminished. Nonetheless, both systems were similar or better than human readers in diagnosis or localization performance across all sizes of pneumothorax. CONCLUSIONS: Both deep learning-based systems excelled when tested in a temporally different dataset with differing patient or image characteristics, showing favourable potential for external generalizability.