External Validation and Comparison of a General Ward Deterioration Index Between Diversely Different Health Systems.

OBJECTIVES: Implementing a predictive analytic model in a new clinical environment is fraught with challenges. Dataset shifts such as differences in clinical practice, new data acquisition devices, or changes in the electronic health record (EHR) implementation mean that the input data seen by a model can differ significantly from the data it was trained on. Validating models at multiple institutions is therefore critical. Here, using retrospective data, we demonstrate how Predicting Intensive Care Transfers and other UnfoReseen Events (PICTURE), a deterioration index developed at a single academic medical center, generalizes to a second institution with significantly different patient population. DESIGN: PICTURE is a deterioration index designed for the general ward, which uses structured EHR data such as laboratory values and vital signs. SETTING: The general wards of two large hospitals, one an academic medical center and the other a community hospital. SUBJECTS: The model has previously been trained and validated on a cohort of 165,018 general ward encounters from a large academic medical center. Here, we apply this model to 11,083 encounters from a separate community hospital. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: The hospitals were found to have significant differences in missingness rates (> 5% difference in 9/52 features), deterioration rate (4.5% vs 2.5%), and racial makeup (20% non-White vs 49% non-White). Despite these differences, PICTURE's performance was consistent (area under the receiver operating characteristic curve [AUROC], 0.870; 95% CI, 0.861-0.878), area under the precision-recall curve (AUPRC, 0.298; 95% CI, 0.275-0.320) at the first hospital; AUROC 0.875 (0.851-0.902), AUPRC 0.339 (0.281-0.398) at the second. AUPRC was standardized to a 2.5% event rate. PICTURE also outperformed both the Epic Deterioration Index and the National Early Warning Score at both institutions. CONCLUSIONS: Important differences were observed between the two institutions, including data availability and demographic makeup. PICTURE was able to identify general ward patients at risk of deterioration at both hospitals with consistent performance (AUROC and AUPRC) and compared favorably to existing metrics.

A deep learning framework for automated detection and quantitative assessment of liver trauma.

BACKGROUND: Both early detection and severity assessment of liver trauma are critical for optimal triage and management of trauma patients. Current trauma protocols utilize computed tomography (CT) assessment of injuries in a subjective and qualitative (v.s. quantitative) fashion, shortcomings which could both be addressed by automated computer-aided systems that are capable of generating real-time reproducible and quantitative information. This study outlines an end-to-end pipeline to calculate the percentage of the liver parenchyma disrupted by trauma, an important component of the American Association for the Surgery of Trauma (AAST) liver injury scale, the primary tool to assess liver trauma severity at CT. METHODS: This framework comprises deep convolutional neural networks that first generate initial masks of both liver parenchyma (including normal and affected liver) and regions affected by trauma using three dimensional contrast-enhanced CT scans. Next, during the post-processing step, human domain knowledge about the location and intensity distribution of liver trauma is integrated into the model to avoid false positive regions. After generating the liver parenchyma and trauma masks, the corresponding volumes are calculated. Liver parenchymal disruption is then computed as the volume of the liver parenchyma that is disrupted by trauma. RESULTS: The proposed model was trained and validated on an internal dataset from the University of Michigan Health System (UMHS) including 77 CT scans (34 with and 43 without liver parenchymal trauma). The Dice/recall/precision coefficients of the proposed segmentation models are 96.13/96.00/96.35% and 51.21/53.20/56.76%, respectively, in segmenting liver parenchyma and liver trauma regions. In volume-based severity analysis, the proposed model yields a linear regression relation of 0.95 in estimating the percentage of liver parenchyma disrupted by trauma. The model shows an accurate performance in avoiding false positives for patients without any liver parenchymal trauma. These results indicate that the model is generalizable on patients with pre-existing liver conditions, including fatty livers and congestive hepatopathy. CONCLUSION: The proposed algorithms are able to accurately segment the liver and the regions affected by trauma. This pipeline demonstrates an accurate performance in estimating the percentage of liver parenchyma that is affected by trauma. Such a system can aid critical care medical personnel by providing a reproducible quantitative assessment of liver trauma as an alternative to the sometimes subjective AAST grading system that is used currently.

Collaborative strategies for deploying artificial intelligence to complement physician diagnoses of acute respiratory distress syndrome.

There is a growing gap between studies describing the capabilities of artificial intelligence (AI) diagnostic systems using deep learning versus efforts to investigate how or when to integrate AI systems into a real-world clinical practice to support physicians and improve diagnosis. To address this gap, we investigate four potential strategies for AI model deployment and physician collaboration to determine their potential impact on diagnostic accuracy. As a case study, we examine an AI model trained to identify findings of the acute respiratory distress syndrome (ARDS) on chest X-ray images. While this model outperforms physicians at identifying findings of ARDS, there are several reasons why fully automated ARDS detection may not be optimal nor feasible in practice. Among several collaboration strategies tested, we find that if the AI model first reviews the chest X-ray and defers to a physician if it is uncertain, this strategy achieves a higher diagnostic accuracy (0.869, 95% CI 0.835-0.903) compared to a strategy where a physician reviews a chest X-ray first and defers to an AI model if uncertain (0.824, 95% CI 0.781-0.862), or strategies where the physician reviews the chest X-ray alone (0.808, 95% CI 0.767-0.85) or the AI model reviews the chest X-ray alone (0.847, 95% CI 0.806-0.887). If the AI model reviews a chest X-ray first, this allows the AI system to make decisions for up to 79% of cases, letting physicians focus on the most challenging subsets of chest X-rays.

A Comprehensive Comparison of Six Publicly Available Algorithms for Localization of QRS Complex on Electrocardiograph.

The QRS complex is the most prominent feature of the electrocardiogram (ECG) that is used as a marker to identify the cardiac cycles. Identification of QRS complex locations enables arrhythmia detection and heart rate variability estimation. Therefore, accurate and consistent localization of the QRS complex is an important component of automated ECG analysis which is necessary for the early detection of cardiovascular diseases. This study evaluates the performance of six popular publicly available QRS complex detection methods on a large dataset of over half a million ECGs in a diverse population of patients. We found that a deep-learning method that won first place in the 2019 Chinese physiological challenge (CPSC-1) outperforms the remaining five QRS complex detection methods with an F1 score of 98.8% and an absolute sdRR error of 5.5 ms. We also examined the stratified performance of the studied methods on various cardiac conditions. All six methods had a lower performance in the detection of QRS complexes in ECG signals of patients with pacemakers, complete atrioventricular block, or indeterminate cardiac axis. We also concluded that, in the presence of different cardiac conditions, CPSC-1 is more robust than Pan-Tompkins which is the most popular model for QRS complex detection. We expect that this study can potentially serve as a guide for researchers on the appropriate QRS detection method for their target applications.Clinical Relevance-This study highlights the overall performance of publicly available QRS detection algorithms in a large dataset of diverse patients. We showed that there are specific cardiac conditions that are associated with the poor performance of QRS detection algorithms and may adversely influence the performance of algorithms that rely on accurate and reliable QRS detection.

A hierarchical expert-guided machine learning framework for clinical decision support systems: an application to traumatic brain injury prognostication.

Prognosis of the long-term functional outcome of traumatic brain injury is essential for personalized management of that injury. Nonetheless, accurate prediction remains unavailable. Although machine learning has shown promise in many fields, including medical diagnosis and prognosis, such models are rarely deployed in real-world settings due to a lack of transparency and trustworthiness. To address these drawbacks, we propose a machine learning-based framework that is explainable and aligns with clinical domain knowledge. To build such a framework, additional layers of statistical inference and human expert validation are added to the model, which ensures the predicted risk score's trustworthiness. Using 831 patients with moderate or severe traumatic brain injury to build a model using the proposed framework, an area under the receiver operating characteristic curve (AUC) and accuracy of 0.8085 and 0.7488 were achieved, respectively, in determining which patients will experience poor functional outcomes. The performance of the machine learning classifier is not adversely affected by the imposition of statistical and domain knowledge "checks and balances". Finally, through a case study, we demonstrate how the decision made by a model might be biased if it is not audited carefully.

Teaching Python for Data Science: Collaborative development of a modular & interactive curriculum.

We are bioinformatics trainees at the University of Michigan who started a local chapter of Girls Who Code to provide a fun and supportive environment for high school women to learn the power of coding. Our goal was to cover basic coding topics and data science concepts through live coding and hands-on practice. However, we could not find a resource that exactly met our needs. Therefore, over the past three years, we have developed a curriculum and instructional format using Jupyter notebooks to effectively teach introductory Python for data science. This method, inspired by The Carpentries organization, uses bite-sized lessons followed by independent practice time to reinforce coding concepts, and culminates in a data science capstone project using real-world data. We believe our open curriculum is a valuable resource to the wider education community and hope that educators will use and improve our lessons, practice problems, and teaching best practices. Anyone can contribute to our Open Educational Resources on GitHub.

Automated Segmentation and Severity Analysis of Subdural Hematoma for Patients with Traumatic Brain Injuries.

Detection and severity assessment of subdural hematoma is a major step in the evaluation of traumatic brain injuries. This is a retrospective study of 110 computed tomography (CT) scans from patients admitted to the Michigan Medicine Neurological Intensive Care Unit or Emergency Department. A machine learning pipeline was developed to segment and assess the severity of subdural hematoma. First, the probability of each point belonging to the hematoma region was determined using a combination of hand-crafted and deep features. This probability provided the initial state of the segmentation. Next, a 3D post-processing model was applied to evolve the initial state and delineate the hematoma. The recall, precision, and Dice similarity coefficient of the proposed segmentation method were 78.61%, 76.12%, and 75.35%, respectively, for the entire population. The Dice similarity coefficient was 79.97% for clinically significant hematomas, which compared favorably to an inter-rater Dice similarity coefficient. In volume-based severity analysis, the proposed model yielded an F1, recall, and specificity of 98.22%, 98.81%, and 92.31%, respectively, in detecting moderate and severe subdural hematomas based on hematoma volume. These results show that the combination of classical image processing and deep learning can outperform deep learning only methods to achieve greater average performance and robustness. Such a system can aid critical care physicians in reducing time to intervention and thereby improve long-term patient outcomes.

Midline Shift vs. Mid-Surface Shift: Correlation with Outcome of Traumatic Brain Injuries.

Traumatic brain injury (TBI) is a major health and socioeconomic problem globally that is associated with a high level of mortality. Early and accurate diagnosis and prognosis of TBI is important in patient management and preventing any secondary injuries. Computer tomography (CT) imaging assists physicians in diagnosing injury and guiding treatment. One of the clinical parameters extracted from CT images is midline shift, a measure of linear displacement in brain structure, which is correlated with TBI patient outcomes. However, only a tiny fraction of the overall tissue displacement is quantified through this parameter. In this paper, a novel measurement of overall mid-surface shift is proposed that quantifies the total volume of brain tissue shifted across the midline. When compared to traditional midline shift, mid-surface shift has a stronger correlation with TBI patient outcomes.

Automated Kidney Segmentation for Traumatic Injured Patients through Ensemble Learning and Active Contour Modeling.

Traumatic abdominal injury can lead to multiple complications including laceration of major organs such as kidneys. Contrast-enhanced Computed Tomography (CT) is the primary imaging modality for evaluating kidney injury. However, the traditional visual examination of CT scans is time consuming, non-quantitative, prone to human error, and costly. In this work we propose a kidney segmentation method using machine learning and active contour modeling. We first detect an initialization mask inside the kidney and then evolve its boundary. This model is specifically developed and evaluated on trauma cases. Our experimental results show the average recall score of 92.6% and average Dice similarity value of 88.9%.

Fully Automated Spleen Localization And Segmentation Using Machine Learning And 3D Active Contours.

Automated segmentation of the spleen in CT volumes is difficult due to variations in size, shape, and position of the spleen within the abdominal cavity as well as similarity of intensity values among organs in the abdominal cavity. In this paper we present a method for automated localization and segmentation of the spleen within axial abdominal CT volumes using trained classification models, active contours, anatomical information, and adaptive features. The results show an average Dice score of 0.873 on patients experiencing various chest, abdominal, and pelvic traumas taken at different contrast phases.

Automated subdural hematoma segmentation for traumatic brain injured (TBI) patients.

Traumatic brain injury is a serious public health problem in the U.S. contributing to a large portion of permanent disability. However, its early management and treatment could limit the impact of the injury, save lives and reduce the burden of cost for patients as well as healthcare systems. Subdural hematoma is one of the most common types of TBI, which its visual detection and quantitative evaluation are time consuming and prone to error. In this study, we propose a fully auto-mated machine learning based approach for 3D segmentation of convexity subdural hematomas. Textural, statistical and geometrical features of sample points from intracranial region are extracted based on head Computed Tomography (CT) images. Then, a tree bagger classifier is implemented to classify each pixel as hematoma or no-hematoma. Our method yields sensitivity, specificity and area under the receiver operating curve (AUC) of 85:02%, 73:74% and 0:87 respectively.

A Review of Automated Methods for Detection of Myocardial Ischemia and Infarction Using Electrocardiogram and Electronic Health Records.

There is a growing body of research focusing on automatic detection of ischemia and myocardial infarction (MI) using computer algorithms. In clinical settings, ischemia and MI are diagnosed using electrocardiogram (ECG) recordings as well as medical context including patient symptoms, medical history, and risk factors-information that is often stored in the electronic health records. The ECG signal is inspected to identify changes in the morphology such as ST-segment deviation and T-wave changes. Some of the proposed methods compute similar features automatically while others use nonconventional features such as wavelet coefficients. This review provides an overview of the methods that have been proposed in this area, focusing on their historical evolution, the publicly available datasets that they have used to evaluate their performance, and the details of their algorithms for ECG and EHR analysis. The validation strategies that have been used to evaluate the performance of the proposed methods are also presented. Finally, the paper provides recommendations for future research to address the shortcomings of the currently existing methods and practical considerations to make the proposed technical solutions applicable in clinical practice.

Liver segmentation using location and intensity probabilistic atlases.

In a variety of injuries and illnesses, internal organs in the abdominal and pelvic regions, in particular liver, may be compromised. In the current practice, CT scans of liver are visually inspected to investigate the integrity of the organ. However, the size and complexity of the CT images limits the reliability of visual inspection to accurately assess the health of liver. Computer-aided image analysis can create fast and quantitative assessment of liver from the CT, in particular in the environments where access to skilled radiologists may be limited. In this paper we propose a hierarchical method based on probabilistic models of position and intensity of voxels for automated segmentation of liver that achieves the Dice similarity coefficient of higher than 89%.