Introduction: The objective of this multi-center retrospective cohort study was to devise a predictive tool known as RAPID-ED. This model identifies non-traumatic adult patients at significant risk for cardiac arrest within 48 hours post-admission from the emergency department. Methods: Data from 224,413 patients admitted through the emergency department (2016-2020) was analyzed, incorporating vital signs, lab tests, and administered therapies. A multivariable regression model was devised to anticipate early cardiac arrest. The efficacy of the RAPID-ED model was evaluated against traditional scoring systems like National Early Warning Score (NEWS) and Modified Early Warning Score (MEWS) and its predictive ability was gauged via the area under the receiver operating characteristic curve (AUC) in both hold-out validation set and external validation set. Results: RAPID-ED outperformed traditional models in predicting cardiac arrest with an AUC of 0.819 in the hold-out validation set and 0.807 in the external validation set. In this critical care update, RAPID-ED offers an innovative approach to assessing patient risk, aiding emergency physicians in post-discharge care decisions from the emergency department. High-risk score patients (≥13) may benefit from early ICU admission for intensive monitoring. Conclusion: As we progress with advancements in critical care, tools like RAPID-ED will prove instrumental in refining care strategies for critically ill patients, fostering an improved prognosis and potentially mitigating mortality rates.
Objectives: The aim of this study was to develop a deep-learning pipeline for the measurement of pericardial effusion (PE) based on raw echocardiography clips, as current methods for PE measurement can be operator-dependent and present challenges in certain situations. Methods: The proposed pipeline consisted of three distinct steps: moving window view selection (MWVS), automated segmentation, and width calculation from a segmented mask. The MWVS model utilized the ResNet architecture to classify each frame of the extracted raw echocardiography files into selected view types. The automated segmentation step then generated a mask for the PE area from the extracted echocardiography clip, and a computer vision technique was used to calculate the largest width of the PE from the segmented mask. The pipeline was applied to a total of 995 echocardiographic examinations. Results: The proposed deep-learning pipeline exhibited high performance, as evidenced by intraclass correlation coefficient (ICC) values of 0.867 for internal validation and 0.801 for external validation. The pipeline demonstrated a high level of accuracy in detecting PE, with an area under the receiving operating characteristic curve (AUC) of 0.926 (95% CI: 0.902-0.951) for internal validation and 0.842 (95% CI: 0.794-0.889) for external validation. Conclusion: The machine-learning pipeline developed in this study can automatically calculate the width of PE from raw ultrasound clips. The novel concepts of moving window view selection for image quality control and computer vision techniques for maximal PE width calculation seem useful in the field of ultrasound. This pipeline could potentially provide a standardized and objective approach to the measurement of PE, reducing operator-dependency and improving accuracy.
OBJECTIVE: We aimed to develop a deep learning artificial intelligence (AI) algorithm to detect impacted animal bones on lateral neck radiographs and to assess its effectiveness for improving the interpretation of lateral neck radiographs. METHODS: Lateral neck radiographs were retrospectively collected for patients with animal bone impaction between January 2010 and March 2020. Radiographs were then separated into training, validation, and testing sets. A total of 1733 lateral neck radiographs were used to develop the deep learning algorithm. The testing set was assessed for the stand-alone deep learning AI algorithm and for human readers (radiologists, radiology residents, emergency physicians, ENT physicians) with and without the aid of the AI algorithm. Another radiograph cohort, collected from April 1, 2020, to June 30, 2020, was analyzed to simulate clinical application by comparing the deep learning AI algorithm with radiologists' reports. RESULTS: In the testing set, the sensitivity, specificity, and accuracy of the AI model were 96%, 90%, and 93% respectively. Among the human readers, all physicians of different subspecialties achieved a higher accuracy with AI-assisted reading than without. In the simulation set, among the 20 cases positive for animal bones, the AI model accurately identified 3 more cases than the radiologists' reports. CONCLUSION: Our deep learning AI model demonstrated a higher sensitivity for detection of animal bone impaction on lateral neck radiographs without an increased false positive rate. The application of this model in a clinical setting may effectively reduce time to diagnosis, accelerate workflow, and decrease the use of CT.
This quality improvement study compares the diagnostic quality and completion time between ultrasonography operators guided by artificial intelligence vs those without such assistance.
Deep Learning , Humans , Ultrasonography , Algorithms
BACKGROUND: Machine learning models have demonstrated superior performance in predicting invasive bacterial infection (IBI) in febrile infants compared to commonly used risk stratification criteria in recent studies. However, the black-box nature of these models can make them difficult to apply in clinical practice. In this study, we developed and validated an explainable deep learning model that can predict IBI in febrile infants ≤ 60 days of age visiting the emergency department. METHODS: We conducted a retrospective study of febrile infants aged ≤ 60 days who presented to the pediatric emergency department of a medical center in Taiwan between January 1, 2011 and December 31, 2019. Patients with uncertain test results and complex chronic health conditions were excluded. IBI was defined as the growth of a pathogen in the blood or cerebrospinal fluid. We used a deep neural network to develop a predictive model for IBI and compared its performance to the IBI score and step-by-step approach. The SHapley Additive Explanations (SHAP) technique was used to explain the model's predictions at different levels. RESULTS: Our study included 1847 patients, 53 (2.7%) of whom had IBI. The deep learning model performed similarly to the IBI score and step-by-step approach in terms of sensitivity and negative predictive value, but provided better specificity (54%), positive predictive value (5%), and area under the receiver-operating characteristic curve (0.87). SHapley Additive exPlanations identified five influential predictive variables (absolute neutrophil count, body temperature, heart rate, age, and C-reactive protein). CONCLUSION: We have developed an explainable deep learning model that can predict IBI in febrile infants aged 0-60 days. The model not only performs better than previous scoring systems, but also provides insight into how it arrives at its predictions through individual features and cases.
Bacterial Infections , Deep Learning , Child , Infant , Humans , Retrospective Studies , Fever/diagnosis , Fever/microbiology , Bacterial Infections/diagnosis , Body Temperature
BACKGROUND: Hyperkalemia is a critical condition, especially in intensive care units. So far, there have been no accurate and noninvasive methods for recognizing hyperkalemia events on ambulatory electrocardiogram monitors. OBJECTIVE: This study aimed to improve the accuracy of hyperkalemia predictions from ambulatory electrocardiogram (ECG) monitors using a personalized transfer learning method; this would be done by training a generic model and refining it with personal data. METHODS: This retrospective cohort study used open source data from the Waveform Database Matched Subset of the Medical Information Mart From Intensive Care III (MIMIC-III). We included patients with multiple serum potassium test results and matched ECG data from the MIMIC-III database. A 1D convolutional neural network-based deep learning model was first developed to predict hyperkalemia in a generic population. Once the model achieved a state-of-the-art performance, it was used in an active transfer learning process to perform patient-adaptive heartbeat classification tasks. RESULTS: The results show that by acquiring data from each new patient, the personalized model can improve the accuracy of hyperkalemia detection significantly, from an average of 0.604 (SD 0.211) to 0.980 (SD 0.078), when compared with the generic model. Moreover, the area under the receiver operating characteristic curve level improved from 0.729 (SD 0.240) to 0.945 (SD 0.094). CONCLUSIONS: By using the deep transfer learning method, we were able to build a clinical standard model for hyperkalemia detection using ambulatory ECG monitors. These findings could potentially be extended to applications that continuously monitor one's ECGs for early alerts of hyperkalemia and help avoid unnecessary blood tests.
Hyperkalemia , Humans , Hyperkalemia/diagnosis , Hyperkalemia/epidemiology , Retrospective Studies , Precision Medicine , Intensive Care Units , Electrocardiography , Machine Learning
Purpose: To build machine learning models for predicting the risk of in-hospital death in patients with sepsis within 48 h, using only dynamic changes in the patient's vital signs. Methods: This retrospective observational cohort study enrolled septic patients from five emergency departments (ED) in Taiwan. We adopted seven variables, i.e., age, sex, systolic blood pressure, diastolic blood pressure, heart rate, respiratory rate, and body temperature. Results: Among all 353,253 visits, after excluding 159,607 visits (45%), the study group consisted of 193,646 ED visits. With a leading time of 6 h, the convolutional neural networks (CNNs), long short-term memory (LSTM), and random forest (RF) had accuracy rates of 0.905, 0.817, and 0.835, respectively, and the area under the receiver operating characteristic curve (AUC) was 0.840, 0.761, and 0.770, respectively. With a leading time of 48 h, the CNN, LSTM, and RF achieved accuracy rates of 0.828, 0759, and 0.805, respectively, and an AUC of 0.811, 0.734, and 0.776, respectively. Conclusion: By analyzing dynamic vital sign data, machine learning models can predict mortality in septic patients within 6 to 48 h of admission. The performance of the testing models is more accurate if the lead time is closer to the event.
Background: ST-segment elevation myocardial infarction (STEMI) is a leading cause of death worldwide. A shock index (SI), modified SI (MSI), delta-SI, and shock index-C (SIC) are known predictors of STEMI. This retrospective cohort study was designed to compare the predictive value of the SI, MSI, delta-SI, and SIC with thrombolysis in myocardial infarction (TIMI) risk scales. Method: Patients > 20 years old with STEMI who underwent percutaneous coronary intervention (PCI) were included. Receiver operating characteristic (ROC) curve analysis with the Youden index was performed to calculate the optimal cutoff values for these predictors. Results: Overall, 1552 adult STEMI cases were analyzed. The thresholds for the emergency department (ED) SI, MSI, SIC, and TIMI risk scales for in-hospital mortality were 0.75, 0.97, 21.00, and 5.5, respectively. Accordingly, ED SIC had better predictive power than the ED SI and ED MSI. The predictive power was relatively higher than TIMI risk scales, but the difference did not achieve statistical significance. After adjusting for confounding factors, the ED SI > 0.75, MSI > 0.97, SIC > 21.0, and TIMI risk scales > 5.5 were statistically and significantly associated with in-hospital mortality of STEMI. Compared with the ED SI and MSI, SIC (>21.0) had better sensitivity (67.2%, 95% CI, 58.6−75.9%), specificity (83.5%, 95% CI, 81.6−85.4%), PPV (24.8%, 95% CI, 20.2−29.6%), and NPV (96.9%, 95% CI, 96.0−97.9%) for in-hospital mortality of STEMI. Conclusions: SIC had better discrimination ability than the SI, MSI, and delta-SI. Compared with the TIMI risk scales, the ACU value of SIC was still higher. Therefore, SIC might be a convenient and rapid tool for predicting the outcome of STEMI.
Stroke is a leading cause of death, and air pollution is associated with stroke hospitalization. However, the susceptibility factors are unclear. Retrospective studies from 2014 to 2018 in Kaohsiung, Taiwan, were analyzed. Adult patients (>17 years) admitted to a medical center with stroke diagnosis were enrolled and patient characteristics and comorbidities were recorded. Air pollutant measurements, including those of particulate matter (PM) with aerodynamic diameters < 10 µm (PM10) and < 2.5 µm (PM2.5), nitrogen dioxide (NO2), and ozone (O3), were collected from air quality monitoring stations. During the study period, interquartile range (IQR) increments in PM2.5 on lag3 and lag4 were 12.3% (95% CI, 1.1−24.7%) and 11.5% (95% CI, 0.3−23.9%) concerning the risk of stroke hospitalization, respectively. Subgroup analysis revealed that the risk of stroke hospitalization after exposure to PM2.5 was greater for those with advanced age (≥80 years, interaction p = 0.045) and hypertension (interaction p = 0.034), after adjusting for temperature and humidity. A dose-dependent effect of PM2.5 on stroke hospitalization was evident. This is one of few studies focusing on the health effects of PM2.5 for patients with risk factors of stroke. We found that patients with risk factors, such as advanced age and hypertension, are more susceptible to PM2.5 impacts on stroke hospitalization.
COVID-19 tests have different turnaround times (TATs), accuracy levels, and limitations, which emergency physicians should be aware of. Nucleic acid amplification tests (NAATs) can be divided into standard high throughput tests and rapid molecular diagnostic tests at the point of care (POC). The standard NAAT has the advantages of high throughput and high accuracy with a TAT of 3-4 hours. The POC molecular test has the same advantages of high accuracy as standard high throughput PCR, but can be done in 13-45 minutes. Roche cobas Liat is the most commonly used machine in Taiwan, displaying 99%-100% sensitivity and 100% specificity, respectively. Abbott ID NOW is an isothermal PCR-based POC machine with a sensitivity of 79% and a specificity of 100%. A high rate of false positives and false negatives is associated with rapid antigen testing. Antibody testing is mostly used as part of public health surveys and for testing for immunity.
Wound infections after venomous snakebites are clinically important. Information regarding the nature and antibiotic susceptibilities of snake oral bacterial flora could support empiric antibiotic therapy. Wild venomous snakes were collected from southern Taiwan: a total of 30 each of Bungarus multicinctus, Naja atra, Protobothrops mucrosquamatus, and Trimeresurus stejnegeri; 3 Deinagkistrodon acutus; and 4 Daboia siamensis. The species and antibiotic susceptibilities of their oral bacteria were determined. Aerobic gram-negative bacteria, especially Pseudomonas aeruginosa and Proteus vulgaris, were the most abundant. Proteus vulgaris were more abundant in B. multicinctus, N. atra, and P. mucrosquamatus than in T. stejnegeri (40%, 43.3%, and 40% vs. 13.3%, respectively). The gram-negative species were less susceptible to first- and second-generation cephalosporins and ampicillin-sulbactam than to third-generation cephalosporins, fluoroquinolones, carbapenems, or piperacillin-tazobactam. The most abundant aerobic gram-positive species cultured was Enterococcus faecalis, which was more abundant in N. atra than in other snakes (p < 0.001) and was highly susceptible to ampicillin, high-level gentamicin, penicillin, teicoplanin, and vancomycin. Bacteroides fragilis and Clostridium species were the most common anaerobic bacteria. The anaerobic organisms were highly susceptible to metronidazole and piperacillin. As a reference for empiric antimicrobial therapy, third-generation cephalosporins, fluoroquinolones, carbapenems, or piperacillin-tazobactam can be initiated in venomous snakebites wound infections.
The level and composition of air pollution have changed during the coronavirus disease 2019 (COVID-19) pandemic. However, the association between air pollution and pediatric respiratory disease emergency department (ED) visits during the COVID-19 pandemic remains unclear. The study was retrospectively conducted between 2017 and 2020 in Kaohsiung, Taiwan, from 1 January 2020 to 1 May 2020, defined as the period of the COVID-19 pandemic, and 1 January 2017 to 31 May 2019, defined as the pre-COVID-19 pandemic period. We enrolled patients under 17 years old who visited the ED in a medical center and were diagnosed with respiratory diseases such as pneumonia, asthma, bronchitis, and acute pharyngitis. Measurements of particulate matter (PM) with aerodynamic diameters of <10 µm (PM10) and < 2.5 µm (PM2.5), nitrogen dioxide (NO2), and Ozone (O3) were collected. During the COVID-19 pandemic, an increase in the interquartile range of PM2.5, PM10, and NO2 levels was associated with increases of 72.5% (95% confidence interval [CI], 50.5−97.7%), 98.0% (95% CI, 70.7−129.6%), and 54.7% (95% CI, 38.7−72.6%), respectively, in the risk of pediatric respiratory disease ED visits on lag 1, which were greater than those in the pre-COVID-19 pandemic period. After adjusting for temperature and humidity, the risk of pediatric respiratory diseases after exposure to PM2.5 (inter p = 0.001) and PM10 (inter p < 0.001) was higher during the COVID-19 pandemic. PM2.5, PM10, and NO2 may play important roles in pediatric respiratory events in Kaohsiung, Taiwan. Compared with the pre-COVID-19 pandemic period, the levels of PM2.5 and PM10 were lower; however, the levels were related to a greater increase in ED during the COVID-19 pandemic.
Background. Out-of-hospital cardiac arrest (OHCA) remains a challenge for emergency physicians, given the poor prognosis. In 2020, MIRACLE2, a new and easier to apply score, was established to predict the neurological outcome of OHCA. Objective. The aim of this study is to compare the discrimination of MIRACLE2 score with cardiac arrest hospital prognosis (CAHP) score for OHCA neurologic outcomes. Methods. This retrospective cohort study was conducted between January 2015 and December 2019. Adult patients (>17 years) with cardiac arrest who were brought to the hospital by an emergency medical service crew were included. Deaths due to trauma, burn, drowning, resuscitation not initiated due to pre-ordered "do not resuscitate" orders, and patients who did not achieve return of spontaneous circulation were excluded. Receiver operating characteristic curve analysis with Youden Index was performed to calculate optimal cut-off values for both scores. Results. Overall, 200 adult OHCA cases were analyzed. The threshold of the MIRACLE2 score for favorable neurologic outcomes was 5.5, with an area under the curve (AUC) value of 0.70 (0.61−0.80, p < 0.001); the threshold of the CAHP score was 223.4, with an AUC of 0.77 (0.68−0.86, p < 0.001). On setting the MIRACLE2 score cut-off value, we documented 64.7% sensitivity (95% confidence interval [CI], 56.9−71.9%), 66.7.0% specificity (95% CI, 48.2−82.0%), 90.8% positive predictive value (PPV; 95% CI, 85.6−94.2%), and 27.2% negative predictive value (NPV; 95% CI, 21.4−33.9%). On establishing a CAHP cut-off value, we observed 68.2% sensitivity (95% CI, 60.2−75.5%), 80.6% specificity (95% CI, 62.5−92.6%), 94.6% PPV (95% CI, 88.6%−98.0%), and 33.8% NPV (95% CI, 23.2−45.7%) for unfavorable neurologic outcomes. Conclusions. The CAHP score demonstrated better discrimination than the MIRACLE2 score, affording superior sensitivity, specificity, PPV, and NPV; however, the CAHP score remains relatively difficult to apply. Further studies are warranted to establish scores with better discrimination and ease of application.
The authors would like to make corrections to their published paper [...].
Blood glucose (BG) monitoring is important for critically ill patients, as poor sugar control has been associated with increased mortality in hospitalized patients. However, constant BG monitoring can be resource-intensive and pose a healthcare burden in clinical practice. In this study, we aimed to develop a personalized machine-learning model to predict dysglycemia from electrocardiogram (ECG) data. We used the Medical Information Mart for Intensive Care III database as our source of data and obtained more than 20 ECG records from each included patient during a single hospital admission. We focused on lead II recordings, along with corresponding blood sugar data. We processed the data and used ECG features from each heartbeat as inputs to develop a one-class support vector machine algorithm to predict dysglycemia. The model was able to predict dysglycemia using a single heartbeat with an AUC of 0.92 ± 0.09, a sensitivity of 0.92 ± 0.10, and specificity of 0.84 ± 0.04. After applying 10 s majority voting, the AUC of the model's dysglycemia prediction increased to 0.97 ± 0.06. This study showed that a personalized machine-learning algorithm can accurately detect dysglycemia from a single-lead ECG.
Blood Glucose Self-Monitoring , Blood Glucose , Humans , Machine Learning , Electrocardiography, Ambulatory , Electrocardiography
[This corrects the article DOI: 10.3389/fped.2021.727466.].
The prognosis of out-of-hospital cardiac arrest (OHCA) is very poor. Although several pre-hospital factors are associated with survival, the different association of pre-hospital factors with OHCA outcomes in pediatric and adult groups remain unclear. To assess the association of pre-hospital factors with OHCA outcomes among pediatric and adult groups, a retrospective observational study was conducted using the emergency medical service (EMS) database in Kaohsiung from January 2015 to December 2019. Pre-hospital factors, underlying diseases, and OHCA outcomes were collected for the pediatric (Age ≤ 20) and adult groups. Kaplan-Meier type plots and multivariable logistic regression were used to analyze the association between pre-hospital factors and outcomes. In total, 7,461 OHCAs were analyzed. After adjusting for EMS response time, bystander CPR, attended by EMT-P, witness, and pre-hospital defibrillation, we found that age [odds ratio (OR) = 0.877, 95% confidence interval (CI): 0.764-0.990, p = 0.033], public location (OR = 7.681, 95% CI: 1.975-33.428, p = 0.003), and advanced airway management (AAM) (OR = 8.952; 95% CI, 1.414-66.081; p = 0.02) were significantly associated with survival till hospital discharge in pediatric OHCAs. The results of Kaplan-Meier type plots with log-rank test showed a significant difference between the pediatric and adult groups in survival for 2 h (p < 0.001), 24 h (p < 0.001), hospital discharge (p < 0.001), and favorable neurologic outcome (p < 0.001). AAM was associated with improved survival for 2 h (p = 0.015), 24 h (p = 0.023), and neurologic outcome (p = 0.018) only in the pediatric group. There were variations in prognostic factors between pediatric and adult patients with OHCA. The prognosis of the pediatric group was better than that of the adult group. Furthermore, AAM was independently associated with outcomes in pediatric patients, but not in adult patients. Age and public location of OHCA were independently associated with survival till hospital discharge in both pediatric and adult patients.
Over a quarter of patients presenting with abdominal pain at emergency departments (EDs) are diagnosed with nonspecific abdominal pain (NSAP) at discharge. This study investigated the risk factors associated with return ED visits in Taiwanese patients with NSAP after discharge. We divided patients into two groups: the study group comprising patients with ED revisits after the index ED visit, and the control group comprising patients without revisits. During the study period, 10,341 patients discharged with the impression of NSAP after ED management. A regression analysis found that older age (OR [95%CI]: 1.007 [1.003-1.011], p = 0.004), male sex (OR [95%CI]: 1.307 [1.036-1.650], p = 0.024), and use of NSAIDs (OR [95%CI]: 1.563 [1.219-2.003], p < 0.001) and opioids (OR [95%CI]: 2.213 [1.643-2.930], p < 0.001) during the index visit were associated with increased return ED visits. Computed tomography (CT) scans (OR [95%CI]: 0.605 [0.390-0.937], p = 0.021) were associated with decreased ED returns, especially for those who were older than 60, who had an underlying disease, or who required pain control during the index ED visit.
Background: The use of focused assessment with sonography in trauma (FAST) enables clinicians to rapidly screen for injury at the bedsides of patients. Pre-hospital FAST improves diagnostic accuracy and streamlines patient care, leading to dispositions to appropriate treatment centers. In this study, we determine the accuracy of artificial intelligence model-assisted free-fluid detection in FAST examinations, and subsequently establish an automated feedback system, which can help inexperienced sonographers improve their interpretation ability and image acquisition skills. Methods: This is a single-center study of patients admitted to the emergency room from January 2020 to March 2021. We collected 324 patient records for the training model, 36 patient records for validation, and another 36 patient records for testing. We balanced positive and negative Morison's pouch free-fluid detection groups in a 1:1 ratio. The deep learning (DL) model Residual Networks 50-Version 2 (ResNet50-V2) was used for training and validation. Results: The accuracy, sensitivity, and specificity of the model performance for ascites prediction were 0.961, 0.976, and 0.947, respectively, in the validation set and 0.967, 0.985, and 0.913, respectively, in the test set. Regarding feedback prediction, the model correctly classified qualified and non-qualified images with an accuracy of 0.941 in both the validation and test sets. Conclusions: The DL algorithm in ResNet50-V2 is able to detect free fluid in Morison's pouch with high accuracy. The automated feedback and instruction system could help inexperienced sonographers improve their interpretation ability and image acquisition skills.
Background: The shock index, pediatric age-adjusted (SIPA), defined as the maximum normal heart rate divided by the minimum normal systolic blood pressure by age, can help predict the risk of morbidity and mortality after pediatric trauma. This study investigated whether the SIPA can be used as an early index of prognosis for non-traumatic children visiting the pediatric emergency department (ED) and were directly admitted to the intensive care unit (ICU). We hypothesized that an increase in SIPA values in the first 24 h of ICU admission would correlate with mortality and adverse outcomes. Methods: This multicenter retrospective study enrolled non-traumatic patients aged 1-17 years who presented to the pediatric ED and were directly admitted to the ICU from January 1, 2016, to December 31, 2018, in Taiwan. The SIPA value was calculated at the time of arrival at the ED and 24 h after ICU admission. Cutoffs included SIPA values >1.2 (patient age: 1-6), >1.0 (patient age: 7-12), and >0.9 (patient age: 12-17). The utility of the SIPA and the trends in the SIPA during the first 24 h of ICU admission were analyzed to predict outcomes. Results: In total, 1,732 patients were included. Of these, 1,050 (60.6%) were under 6 years old, and the median Pediatric Risk of Mortality score was 7 (5-10). In total, 4.7% of the patients died, 12.9% received mechanical ventilator (MV) support, and 11.1% received inotropic support. The SIPA value at 24 h after admission was associated with increased mortality [odds ratio (OR): 4.366, 95% confidence interval (CI): 2.392-7.969, p < 0.001], MV support (OR: 1.826, 95% CI: 1.322-2.521, p < 0.001), inotropic support (OR: 2.306, 95% CI: 1.599-3.326, p < 0.001), and a long hospital length of stay (HLOS) (2.903 days, 95% CI: 1.734-4.271, p < 0.001). Persistent abnormal SIPA value was associated with increased mortality (OR: 2.799, 95% CI: 1.566-5.001, p = 0.001), MV support (OR: 1.457, 95% CI: 1.015-2.092, p = 0.041), inotropic support (OR: 1.875, 95% CI: 1.287-2.833, p = 0.001), and a long HLOS (3.2 days, 95% CI: 1.9-4.6, p < 0.001). Patients with abnormal to normal SIPA values were associated with decreased mortality (OR: 0.258, 95% CI: 0.106-0.627, p = 0.003), while patients with normal to abnormal SIPA values were associated with increased mortality (OR: 3.055, 95% CI: 1.472-5.930, p = 0.002). Conclusions: In non-traumatic children admitted to the ICU from the ED, increased SIPA values at 24 h after ICU admission predicted high mortality and bad outcomes. Monitoring the trends in the SIPA could help with prognostication and optimize early management.
