Machine learning models to evaluate mortality in pediatric patients with pneumonia in the intensive care unit.

OBJECTIVES: This study aimed to predict mortality in children with pneumonia who were admitted to the intensive care unit (ICU) to aid decision-making. STUDY DESIGN: Retrospective cohort study conducted at a single tertiary hospital. PATIENTS: This study included children who were admitted to the pediatric ICU at the National Taiwan University Hospital between 2010 and 2019 due to pneumonia. METHODOLOGY: Two prediction models were developed using tree-structured machine learning algorithms. The primary outcomes were ICU mortality and 24-h ICU mortality. A total of 33 features, including demographics, underlying diseases, vital signs, and laboratory data, were collected from the electronic health records. The machine learning models were constructed using the development data set, and performance matrices were computed using the holdout test data set. RESULTS: A total of 1231 ICU admissions of children with pneumonia were included in the final cohort. The area under the receiver operating characteristic curves (AUROCs) of the ICU mortality model and 24-h ICU mortality models was 0.80 (95% confidence interval [CI], 0.69-0.91) and 0.92 (95% CI, 0.86-0.92), respectively. Based on feature importance, the model developed in this study tended to predict increased mortality for the subsequent 24 h if a reduction in the blood pressure, peripheral capillary oxygen saturation (SpO2), or higher partial pressure of carbon dioxide (PCO2) were observed. CONCLUSIONS: This study demonstrated that the machine learning models for predicting ICU mortality and 24-h ICU mortality in children with pneumonia have the potential to support decision-making, especially in resource-limited settings.

Clinical characteristics of hospitalized children with community-acquired pneumonia and respiratory infections: Using machine learning approaches to support pathogen prediction at admission.

BACKGROUND: Acute respiratory infections (ARIs) are common in children. We developed machine learning models to predict pediatric ARI pathogens at admission. METHODS: We included hospitalized children with respiratory infections between 2010 and 2018. Clinical features were collected within 24 h of admission to construct models. The outcome of interest was the prediction of 6 common respiratory pathogens, including adenovirus, influenza virus types A and B, parainfluenza virus (PIV), respiratory syncytial virus (RSV), and Mycoplasma pneumoniae (MP). Model performance was estimated using area under the receiver operating characteristic curve (AUROC). Feature importance was measured using Shapley Additive exPlanation (SHAP) values. RESULTS: A total of 12,694 admissions were included. Models trained with 9 features (age, event pattern, fever, C-reactive protein, white blood cell count, platelet count, lymphocyte ratio, peak temperature, peak heart rate) achieved the best performance (AUROC: MP 0.87, 95% CI 0.83-0.90; RSV 0.84, 95% CI 0.82-0.86; adenovirus 0.81, 95% CI 0.77-0.84; influenza A 0.77, 95% CI 0.73-0.80; influenza B 0.70, 95% CI 0.65-0.75; PIV 0.73, 95% CI 0.69-0.77). Age was the most important feature to predict MP, RSV and PIV infections. Event patterns were useful for influenza virus prediction, and C-reactive protein had the highest SHAP value for adenovirus infections. CONCLUSION: We demonstrate how artificial intelligence can assist clinicians identify potential pathogens associated with pediatric ARIs upon admission. Our models provide explainable results that could help optimize the use of diagnostic testing. Integrating our models into clinical workflows may lead to improved patient outcomes and reduce unnecessary medical costs.

Unraveling the molecular mechanism of collagen flexibility during physiological warmup using molecular dynamics simulation and machine learning.

Physiological warmup plays an important role in reducing the injury risk in different sports. In response to the associated temperature increase, the muscle and tendon soften and become easily stretched. In this study, we focused on type I collagen, the main component of the Achilles tendon, to unveil the molecular mechanism of collagen flexibility upon slight heating and to develop a model to predict the strain of collagen sequences. We used molecular dynamics approaches to simulate the molecular structures and mechanical behavior of the gap and overlap regions in type I collagen at 307 K, 310 K, and 313 K. The results showed that the molecular model in the overlap region is more sensitive to temperature increases. Upon increasing the temperature by 3 degrees Celsius, the end-to-end distance and Young's modulus of the overlap region decreased by 5% and 29.4%, respectively. The overlap region became more flexible than the gap region at higher temperatures. GAP-GPA and GNK-GSK triplets are critical for providing molecular flexibility upon heating. A machine learning model developed from the molecular dynamics simulation results showed good performance in predicting the strain of collagen sequences at a physiological warmup temperature. The strain-predictive model could be applied to future collagen designs to obtain desirable temperature-dependent mechanical properties.

Deep Learning for Detecting Supraspinatus Calcific Tendinopathy on Ultrasound Images.

Background: The aim of the study was to evaluate the feasibility of convolutional neural network (CNN)-based deep learning (DL) algorithms to dichotomize shoulder ultrasound (US) images with or without supraspinatus calcific tendinopathy (SSCT). Methods: This was a retrospective study pertaining to US examinations that had been performed by 18 physiatrists with 3-20 years of experience. 133,619 US images from 7836 consecutive patients who had undergone shoulder US examinations between January 2017 and June 2019 were collected. Only images with longitudinal or transverse views of supraspinatus tendons (SSTs) were included. During the labeling process, two physiatrists with 6-and 10-year experience in musculoskeletal US independently classified the images as with or without SSCT. DenseNet-121, a pre-trained model in CNN, was used to develop a computer-aided system to identify US images of SSTs with and without calcifications. Testing accuracy, sensitivity, and specificity calculated from the confusion matrix was used to evaluate the models. Results: A total of 2462 images were used for developing the DL algorithm. The longitudinal-transverse model developed with a CNN-based DL algorithm was better for the diagnosis of SSCT when compared with the longitudinal and transverse models (accuracy: 91.32%, sensitivity: 87.89%, and specificity: 94.74%). Conclusion: The developed DL model as a computer-aided system can assist physicians in diagnosing SSCT during the US examination.

High-Dimensional Phase Space Reconstruction with a Convolutional Neural Network for Structural Health Monitoring.

In order to accurately diagnose the health of high-order statically indeterminate structures, most existing structural health monitoring (SHM) methods require multiple sensors to collect enough information. However, comprehensive data collection from multiple sensors for high degree-of-freedom structures is not typically available in practice. We propose a method that reconciles the two seemingly conflicting difficulties. Takens' embedding theorem is used to augment the dimensions of data collected from a single sensor. Taking advantage of the success of machine learning in image classification, high-dimensional reconstructed attractors were converted into images and fed into a convolutional neural network (CNN). Attractor classification was performed for 10 damage cases of a 3-story shear frame structure. Numerical results show that the inherently high dimension of the CNN model allows the handling of higher dimensional data. Information on both the level and the location of damage was successfully embedded. The same methodology will allow the extraction of data with unsupervised CNN classification to be consistent with real use cases.