Development and Performance of the Pulmonary Embolism Result Forecast Model (PERFORM) for Computed Tomography Clinical Decision Support

Efficient management of pulmonary embolism diagnosis using a two-step interconnected machine learning model based on electronic health records data

Pulmonary Embolism (PE) is a life-threatening clinical disease with no specific clinical symptoms and Computed Tomography Angiography (CTA) is used for diagnosis. Clinical decision support scoring systems like Wells and rGeneva based on PE risk factors have been developed to estimate the pre-test probability but are underused, leading to continuous overuse of CTA imaging. This diagnostic study aimed to propose a novel approach for efficient management of PE diagnosis using a two-step interconnected machine learning framework directly by analyzing patients' Electronic Health Records data. First, we performed feature importance analysis according to the result of LightGBM superiority for PE prediction, then four state-of-the-art machine learning methods were applied for PE prediction based on the feature importance results, enabling swift and accurate pre-test diagnosis. Throughout the study patients' data from different departments were collected from Sina educational hospital, affiliated with the Tehran University of medical sciences in Iran. Generally, the Ridge classification method obtained the best performance with an F1 score of 0.96. Extensive experimental findings showed the effectiveness and simplicity of this diagnostic process of PE in comparison with the existing scoring systems. The main strength of this approach centered on PE disease management procedures, which would reduce avoidable invasive CTA imaging and be applied as a primary prognosis of PE, hence assisting the healthcare system, clinicians, and patients by reducing costs and promoting treatment quality and patient satisfaction.

Modern imaging of acute pulmonary embolism

The first-choice imaging test for visualization of thromboemboli in the pulmonary vasculature in patients with suspected acute pulmonary embolism (PE) is multidetector computed tomography pulmonary angiography (CTPA) - a readily available and widely used imaging technique. Through technological advancements over the past years, alternative imaging techniques for the diagnosis of PE have become available, whilst others are still under investigation. In particular, the evolution of artificial intelligence (AI) is expected to enable further innovation in diagnostic management of PE. In this narrative review, current CTPA techniques and the emerging technology photon-counting CT (PCCT), as well as other modern imaging techniques of acute PE are discussed, including CTPA with iodine maps based on subtraction or dual-energy acquisition, single-photon emission CT (SPECT), magnetic resonance angiography (MRA), and magnetic resonance direct thrombus imaging (MRDTI). Furthermore, potential applications of AI are discussed.

Machine Learning-Based Predictive Models for Patients with Venous Thromboembolism: A Systematic Review

BACKGROUND

 Venous thromboembolism (VTE) is a chronic disorder with a significant health and economic burden. Several VTE-specific clinical prediction models (CPMs) have been used to assist physicians in decision-making but have several limitations. This systematic review explores if machine learning (ML) can enhance CPMs by analyzing extensive patient data derived from electronic health records. We aimed to explore ML-CPMs' applications in VTE for risk stratification, outcome prediction, diagnosis, and treatment.

METHODS

 Three databases were searched: PubMed, Google Scholar, and IEEE electronic library. Inclusion criteria focused on studies using structured data, excluding non-English publications, studies on non-humans, and certain data types such as natural language processing and image processing. Studies involving pregnant women, cancer patients, and children were also excluded. After excluding irrelevant studies, a total of 77 studies were included.

RESULTS

 Most studies report that ML-CPMs outperformed traditional CPMs in terms of receiver operating area under the curve in the four clinical domains that were explored. However, the majority of the studies were retrospective, monocentric, and lacked detailed model architecture description and external validation, which are essential for quality audit. This review identified research gaps and highlighted challenges related to standardized reporting, reproducibility, and model comparison.

CONCLUSION

 ML-CPMs show promise in improving risk assessment and individualized treatment recommendations in VTE. Apparently, there is an urgent need for standardized reporting and methodology for ML models, external validation, prospective and real-world data studies, as well as interventional studies to evaluate the impact of artificial intelligence in VTE.

Designing Chinese hospital emergency departments to leverage artificial intelligence-a systematic literature review on the challenges and opportunities

Artificial intelligence (AI) has witnessed rapid advances in the healthcare domain in recent years, especially in the emergency field, where AI is likely to radically reshape medical service delivery. Although AI has substantial potential to enhance diagnostic accuracy and operational efficiency in hospitals, research on its applications in Emergency Department building design remains relatively scarce. Therefore, this study aims to investigate Emergency Department facility design by identifying the challenges and opportunities of using AI. Two systematic literature reviews are combined, one in AI and the other in sensors, to explore their potential application to support decision-making, resource optimisation and patient monitoring. These reviews have then informed a discussion on integrating AI sensors in contemporary Emergency Department designs for use in China to support the evidence base on resuscitation units, emergency operating rooms and Emergency Department Intensive Care Unit (ED-ICU) design. We hope to inform the strategic implementation of AI sensors and how they might transform Emergency Department design to support medical staff and enhance the patient experience.

A machine learning model for diagnosing acute pulmonary embolism and comparison with Wells score, revised Geneva score, and Years algorithm

BACKGROUND

Acute pulmonary embolism (APE) is a fatal cardiovascular disease, yet missed diagnosis and misdiagnosis often occur due to non-specific symptoms and signs. A simple, objective technique will help clinicians make a quick and precise diagnosis. In population studies, machine learning (ML) plays a critical role in characterizing cardiovascular risks, predicting outcomes, and identifying biomarkers. This work sought to develop an ML model for helping APE diagnosis and compare it against current clinical probability assessment models.

METHODS

This is a single-center retrospective study. Patients with suspected APE were continuously enrolled and randomly divided into two groups including training and testing sets. A total of 8 ML models, including random forest (RF), Naïve Bayes, decision tree, K-nearest neighbors, logistic regression, multi-layer perceptron, support vector machine, and gradient boosting decision tree were developed based on the training set to diagnose APE. Thereafter, the model with the best diagnostic performance was selected and evaluated against the current clinical assessment strategies, including the Wells score, revised Geneva score, and Years algorithm. Eventually, the ML model was internally validated to assess the diagnostic performance using receiver operating characteristic (ROC) analysis.

RESULTS

The ML models were constructed using eight clinical features, including D-dimer, cardiac troponin T (cTNT), arterial oxygen saturation, heart rate, chest pain, lower limb pain, hemoptysis, and chronic heart failure. Among eight ML models, the RF model achieved the best performance with the highest area under the curve (AUC) (AUC = 0.774). Compared to the current clinical assessment strategies, the RF model outperformed the Wells score ( P = 0.030) and was not inferior to any other clinical probability assessment strategy. The AUC of the RF model for diagnosing APE onset in internal validation set was 0.726.

CONCLUSIONS

Based on RF algorithm, a novel prediction model was finally constructed for APE diagnosis. When compared to the current clinical assessment strategies, the RF model achieved better diagnostic efficacy and accuracy. Therefore, the ML algorithm can be a useful tool in assisting with the diagnosis of APE.

Artificial intelligence in the prediction of venous thromboembolism: A systematic review and pooled analysis

BACKGROUND

Accurate diagnostic and prognostic predictions of venous thromboembolism (VTE) are crucial for VTE management. Artificial intelligence (AI) enables autonomous identification of the most predictive patterns from large complex data. Although evidence regarding its performance in VTE prediction is emerging, a comprehensive analysis of performance is lacking.

AIMS

To systematically review the performance of AI in the diagnosis and prediction of VTE and compare it to clinical risk assessment models (RAMs) or logistic regression models.

METHODS

A systematic literature search was performed using PubMed, MEDLINE, EMBASE, and Web of Science from inception to April 20, 2021. Search terms included "artificial intelligence" and "venous thromboembolism." Eligible criteria were original studies evaluating AI in the prediction of VTE in adults and reporting one of the following outcomes: sensitivity, specificity, positive predictive value, negative predictive value, or area under receiver operating curve (AUC). Risks of bias were assessed using the PROBAST tool. Unpaired t-test was performed to compare the mean AUC from AI versus conventional methods (RAMs or logistic regression models).

RESULTS

A total of 20 studies were included. Number of participants ranged from 31 to 111 888. The AI-based models included artificial neural network (six studies), support vector machines (four studies), Bayesian methods (one study), super learner ensemble (one study), genetic programming (one study), unspecified machine learning models (two studies), and multiple machine learning models (five studies). Twelve studies (60%) had both training and testing cohorts. Among 14 studies (70%) where AUCs were reported, the mean AUC for AI versus conventional methods were 0.79 (95% CI: 0.74-0.85) versus 0.61 (95% CI: 0.54-0.68), respectively (p < .001). However, the good to excellent discriminative performance of AI methods is unlikely to be replicated when used in clinical practice, because most studies had high risk of bias due to missing data handling and outcome determination.

CONCLUSION

The use of AI appears to improve the accuracy of diagnostic and prognostic prediction of VTE over conventional risk models; however, there was a high risk of bias observed across studies. Future studies should focus on transparent reporting, external validation, and clinical application of these models.

Unmet Needs and Future Direction for Pulmonary Embolism Interventions

Venous thromboembolism (VTE) usually develops in the deep veins of the extremities. Pulmonary embolism (PE) is a type of VTE that is most commonly (∼90%) caused by a thrombus that originates from the deep veins of the lower extremities. PE is the third most common cause of death after myocardial infarction and stroke. In this review, the authors investigate and discuss the risk stratification and definitions of the aforementioned categories of PE and further explore the management of acute PE along with the types of catheter-based treatment options and their efficacy.

Fusion of imaging and non-imaging data for disease trajectory prediction for coronavirus disease 2019 patients

Purpose

Our study investigates whether graph-based fusion of imaging data with non-imaging electronic health records (EHR) data can improve the prediction of the disease trajectories for patients with coronavirus disease 2019 (COVID-19) beyond the prediction performance of only imaging or non-imaging EHR data.

Approach

We present a fusion framework for fine-grained clinical outcome prediction [discharge, intensive care unit (ICU) admission, or death] that fuses imaging and non-imaging information using a similarity-based graph structure. Node features are represented by image embedding, and edges are encoded with clinical or demographic similarity.

Results

Experiments on data collected from the Emory Healthcare Network indicate that our fusion modeling scheme performs consistently better than predictive models developed using only imaging or non-imaging features, with area under the receiver operating characteristics curve of 0.76, 0.90, and 0.75 for discharge from hospital, mortality, and ICU admission, respectively. External validation was performed on data collected from the Mayo Clinic. Our scheme highlights known biases in the model prediction, such as bias against patients with alcohol abuse history and bias based on insurance status.

Conclusions

Our study signifies the importance of the fusion of multiple data modalities for the accurate prediction of clinical trajectories. The proposed graph structure can model relationships between patients based on non-imaging EHR data, and graph convolutional networks can fuse this relationship information with imaging data to effectively predict future disease trajectory more effectively than models employing only imaging or non-imaging data. Our graph-based fusion modeling frameworks can be easily extended to other prediction tasks to efficiently combine imaging data with non-imaging clinical data.

AV, Mahale A. Multimodal medical tensor fusion network-based DL framework for abnormality prediction from the radiology CXRs and clinical text reports

Pulmonary disease is a commonly occurring abnormality throughout this world. The pulmonary diseases include Tuberculosis, Pneumothorax, Cardiomegaly, Pulmonary atelectasis, Pneumonia, etc. A timely prognosis of pulmonary disease is essential. Increasing progress in Deep Learning (DL) techniques has significantly impacted and contributed to the medical domain, specifically in leveraging medical imaging for analysis, prognosis, and therapeutic decisions for clinicians. Many contemporary DL strategies for radiology focus on a single modality of data utilizing imaging features without considering the clinical context that provides more valuable complementary information for clinically consistent prognostic decisions. Also, the selection of the best data fusion strategy is crucial when performing Machine Learning (ML) or DL operation on multimodal heterogeneous data. We investigated multimodal medical fusion strategies leveraging DL techniques to predict pulmonary abnormality from the heterogeneous radiology Chest X-Rays (CXRs) and clinical text reports. In this research, we have proposed two effective unimodal and multimodal subnetworks to predict pulmonary abnormality from the CXR and clinical reports. We have conducted a comprehensive analysis and compared the performance of unimodal and multimodal models. The proposed models were applied to standard augmented data and the synthetic data generated to check the model's ability to predict from the new and unseen data. The proposed models were thoroughly assessed and examined against the publicly available Indiana university dataset and the data collected from the private medical hospital. The proposed multimodal models have given superior results compared to the unimodal models.

Metaverse and Healthcare: Machine Learning-Enabled Digital Twins of Cancer

Medical digital twins, which represent medical assets, play a crucial role in connecting the physical world to the metaverse, enabling patients to access virtual medical services and experience immersive interactions with the real world. One serious disease that can be diagnosed and treated using this technology is cancer. However, the digitalization of such diseases for use in the metaverse is a highly complex process. To address this, this study aims to use machine learning (ML) techniques to create real-time and reliable digital twins of cancer for diagnostic and therapeutic purposes. The study focuses on four classical ML techniques that are simple and fast for medical specialists without extensive Artificial Intelligence (AI) knowledge, and meet the requirements of the Internet of Medical Things (IoMT) in terms of latency and cost. The case study focuses on breast cancer (BC), the second most prevalent form of cancer worldwide. The study also presents a comprehensive conceptual framework to illustrate the process of creating digital twins of cancer, and demonstrates the feasibility and reliability of these digital twins in monitoring, diagnosing, and predicting medical parameters.

Assessing the utility of a sliding-windows deep neural network approach for risk prediction of trauma patients

The risks of post trauma complications are regulated by the injury, comorbidities, and the clinical trajectories, yet prediction models are often limited to single time-point data. We hypothesize that deep learning prediction models can be used for risk prediction using additive data after trauma using a sliding windows approach. Using the American College of Surgeons Trauma Quality Improvement Program (ACS TQIP) database, we developed three deep neural network models, for sliding-windows risk prediction. Output variables included early- and late mortality and any of 17 complications. As patients moved through the treatment trajectories, performance metrics increased. Models predicted early- and late mortality with ROC AUCs ranging from 0.980 to 0.994 and 0.910 to 0.972, respectively. For the remaining 17 complications, the mean performance ranged from 0.829 to 0.912. In summary, the deep neural networks achieved excellent performance in the sliding windows risk stratification of trauma patients.

Machine Learning for the Prevalence and Severity of Coronary Artery Calcification in Nondialysis Chronic Kidney Disease Patients: A Chinese Large Cohort Study

PURPOSE

This study sought to determine whether machine learning (ML) can be used to better identify the risk factors and establish the prediction models for the prevalence and severity of coronary artery calcification (CAC) in nondialysis chronic kidney disease (CKD) patients and compare the performance of distinctive ML models with conventional logistic regression (LR) model.

MATERIALS AND METHODS

In all, 3701 Chinese nondialysis CKD patients undergoing noncontrast cardiac computed tomography (CT) scanning were enrolled from November 2013 to December 2017. CAC score derived from the cardiac CT was calculated with the calcium scoring software and was used to assess and stratify the prevalence and severity of CAC. Four ML models (LR, random forest, support vector machine, and k-nearest neighbor) and the corresponding feature ranks were conducted. The model that incorporated the independent predictors was shown as the receiver-operating characteristic (ROC) curve. Area under the curve (AUC) was used to present the prediction value. ML model performance was compared with the traditional LR model using pairwise comparisons of AUCs.

RESULTS

Of the 3701 patients, 943 (25.5%) patients had CAC. Of the 943 patients with CAC, 764 patients (20.6%) and 179 patients (4.8%) had an Agatston CAC score of 1 to 300 and ≥300, respectively. The primary cohort and the independent validation cohort comprised 2957 patients and 744 patients, respectively. For the prevalence of CAC, the AUCs of ML models were from 0.78 to 0.82 in the training data set and the internal validation cohort. For the severity of CAC, the AUCs of the 4 ML models were from 0.67 to 0.70 in the training data set and from 0.53 to 0.70 in the internal validation cohort. For the prevalence of CAC, the AUC was 0.80 (95% confidence interval [CI]: 0.77-0.83) for ML (LR) versus 0.80 (95% CI: 0.77-0.83) for the traditional LR model ( P =0.2533). For the severity of CAC, the AUC was 0.70 (95% CI: 0.63-0.77) for ML (LR) versus 0.70 (95% CI: 0.63-0.77) for traditional LR model ( P =0.982).

CONCLUSIONS

This study constructed prediction models for the presence and severity of CAC based on Agatston scores derived from noncontrast cardiac CT scanning in nondialysis CKD patients using ML, and showed ML LR had the best performance.

Graph-based Fusion Modeling and Explanation for Disease Trajectory Prediction

We propose a relational graph to incorporate clinical similarity between patients while building personalized clinical event predictors with a focus on hospitalized COVID-19 patients. Our graph formation process fuses heterogeneous data, i.e., chest X-rays as node features and non-imaging EHR for edge formation. While node represents a snap-shot in time for a single patient, weighted edge structure encodes complex clinical patterns among patients. While age and gender have been used in the past for patient graph formation, our method incorporates complex clinical history while avoiding manual feature selection. The model learns from the patient's own data as well as patterns among clinically-similar patients. Our visualization study investigates the effects of 'neighborhood' of a node on its predictiveness and showcases the model's tendency to focus on edge-connected patients with highly suggestive clinical features common with the node. The proposed model generalizes well by allowing edge formation process to adapt to an external cohort.

Overview of Noninterpretive Artificial Intelligence Models for Safety, Quality, Workflow, and Education Applications in Radiology Practice

Artificial intelligence has become a ubiquitous term in radiology over the past several years, and much attention has been given to applications that aid radiologists in the detection of abnormalities and diagnosis of diseases. However, there are many potential applications related to radiologic image quality, safety, and workflow improvements that present equal, if not greater, value propositions to radiology practices, insurance companies, and hospital systems. This review focuses on six major categories for artificial intelligence applications: study selection and protocoling, image acquisition, worklist prioritization, study reporting, business applications, and resident education. All of these categories can substantially affect different aspects of radiology practices and workflows. Each of these categories has different value propositions in terms of whether they could be used to increase efficiency, improve patient safety, increase revenue, or save costs. Each application is covered in depth in the context of both current and future areas of work. Keywords: Use of AI in Education, Application Domain, Supervised Learning, Safety © RSNA, 2022.

An Optimized Machine Learning Model Accurately Predicts In-Hospital Outcomes at Admission to a Cardiac Unit

Risk stratification at the time of hospital admission is of paramount significance in triaging the patients and providing timely care. In the present study, we aim at predicting multiple clinical outcomes using the data recorded during admission to a cardiac care unit via an optimized machine learning method. This study involves a total of 11,498 patients admitted to a cardiac care unit over two years. Patient demographics, admission type (emergency or outpatient), patient history, lab tests, and comorbidities were used to predict various outcomes. We employed a fully connected neural network architecture and optimized the models for various subsets of input features. Using 10-fold cross-validation, our optimized machine learning model predicted mortality with a mean area under the receiver operating characteristic curve (AUC) of 0.967 (95% confidence interval (CI): 0.963–0.972), heart failure AUC of 0.838 (CI: 0.825–0.851), ST-segment elevation myocardial infarction AUC of 0.832 (CI: 0.821–0.842), pulmonary embolism AUC of 0.802 (CI: 0.764–0.84), and estimated the duration of stay (DOS) with a mean absolute error of 2.543 days (CI: 2.499–2.586) of data with a mean and median DOS of 6.35 and 5.0 days, respectively. Further, we objectively quantified the importance of each feature and its correlation with the clinical assessment of the corresponding outcome. The proposed method accurately predicts various cardiac outcomes and can be used as a clinical decision support system to provide timely care and optimize hospital resources.

Predicting pulmonary embolism among hospitalized patients with machine learning algorithms

Background

Objective

Materials and Methods

Results

Conclusions

Development of a machine learning model using electrocardiogram signals to improve acute pulmonary embolism screening

Aims

Clinical scoring systems for pulmonary embolism (PE) screening have low specificity and contribute to computed tomography pulmonary angiogram (CTPA) overuse. We assessed whether deep learning models using an existing and routinely collected data modality, electrocardiogram (ECG) waveforms, can increase specificity for PE detection.

Methods and results

We create a retrospective cohort of 21 183 patients at moderate- to high suspicion of PE and associate 23 793 CTPAs (10.0% PE-positive) with 320 746 ECGs and encounter-level clinical data (demographics, comorbidities, vital signs, and labs). We develop three machine learning models to predict PE likelihood: an ECG model using only ECG waveform data, an EHR model using tabular clinical data, and a Fusion model integrating clinical data and an embedded representation of the ECG waveform. We find that a Fusion model [area under the receiver-operating characteristic curve (AUROC) 0.81 ± 0.01] outperforms both the ECG model (AUROC 0.59 ± 0.01) and EHR model (AUROC 0.65 ± 0.01). On a sample of 100 patients from the test set, the Fusion model also achieves greater specificity (0.18) and performance (AUROC 0.84 ± 0.01) than four commonly evaluated clinical scores: Wells' Criteria, Revised Geneva Score, Pulmonary Embolism Rule-Out Criteria, and 4-Level Pulmonary Embolism Clinical Probability Score (AUROC 0.50-0.58, specificity 0.00-0.05). The model is superior to these scores on feature sensitivity analyses (AUROC 0.66-0.84) and achieves comparable performance across sex (AUROC 0.81) and racial/ethnic (AUROC 0.77-0.84) subgroups.

Conclusion

Synergistic deep learning of ECG waveforms with traditional clinical variables can increase the specificity of PE detection in patients at least at moderate suspicion for PE.

Machine learning with D-dimer in the risk stratification for pulmonary embolism: a derivation and internal validation study

AIM

To develop a machine learning model to predict the diagnosis of pulmonary embolism (PE).

METHODS AND RESULTS

We undertook a derivation and internal validation study to develop a risk prediction model for use in patients being investigated for possible PE. The machine learning technique, generalized logistic regression using elastic net, was chosen following an assessment of seven machine learning techniques and on the basis that it optimized the area under the receiver operator characteristic curve (AUC) and Brier score. Models were developed both with and without the addition of D-dimer. A total of 3347 patients were included in the study of whom, 219 (6.5%) had PE. Four clinical variables (O2 saturation, previous deep venous thrombosis or PE, immobilization or surgery, and alternative diagnosis equal or more likely than PE) plus D-dimer contributed to the machine learning models. The addition of D-dimer improved the AUC by 0.16 (95% confidence interval 0.13-0.19), from 0.73 to 0.89 (0.87-0.91) and decreased the Brier score by 14% (10-18%). More could be ruled out with a higher positive likelihood ratio than by the Wells score combined with D-dimer, revised Geneva score combined with D-dimer, or the Pulmonary Embolism Rule-out Criteria score. Machine learning with D-dimer maintained a low-false-negative rate at a true-negative rate of nearly 53%, which was better performance than any of the other alternatives.

CONCLUSION

A machine learning model outperformed traditional risk scores for the risk stratification of PE in the emergency department. However, external validation is needed.

Free-breathing Accelerated Cardiac MRI Using Deep Learning: Validation in Children and Young Adults

Background Obtaining ventricular volumetry and mass is key to most cardiac MRI but challenged by long multibreath-hold acquisitions. Purpose To assess the image quality and performance of a highly accelerated, free-breathing, two-dimensional cine cardiac MRI sequence incorporating deep learning (DL) reconstruction compared with reference standard balanced steady-state free precession (bSSFP). Materials and Methods A DL algorithm was developed to reconstruct custom 12-fold accelerated bSSFP cardiac MRI cine images from coil sensitivity maps using 15 iterations of separable three-dimensional convolutions and data consistency steps. The model was trained, validated, and internally tested in 10, two, and 10 adult human volunteers, respectively, based on vendor partner-supplied fully sampled bSSFP acquisitions. For prospective external clinical validation, consecutive children and young adults undergoing cardiac MRI from September through December 2019 at a single children's hospital underwent both conventional and highly accelerated short-axis bSSFP cine acquisitions in one MRI examination. Two radiologists scored overall and volumetric three-dimensional mesh image quality of all short-axis stacks on a five-point Likert scale and manually segmented endocardial and epicardial contours. Scan times and image quality were compared using the Wilcoxon rank sum test. Measurement agreement was assessed with intraclass correlation coefficient and Bland-Altman analysis. Results Fifty participants (mean age, 16 years ± 4 [standard deviation]; range, 5-30 years; 29 men) were evaluated. The mean prescribed acquisition times of accelerated scans (non-breath-held) and bSSFP (excluding breath-hold time) were 0.9 minute ± 0.3 versus 3.0 minutes ± 1.9 (P < .001). Overall and three-dimensional mesh image quality scores were, respectively, 3.8 ± 0.6 versus 4.3 ± 0.6 (P < .001) and 4.0 ± 1.0 versus 4.4 ± 0.8 (P < .001). Raters had strong agreement between all bSSFP and DL measurements, with intraclass correlation coefficients of 0.76 to 0.97, near-zero mean differences, and narrow limits of agreement. Conclusion With slightly lower image quality yet much faster speed, deep learning reconstruction may allow substantially shorter acquisition times of cardiac MRI compared with conventional balanced steady-state free precession MRI performed for ventricular volumetry. © RSNA, 2021 Online supplemental material is available for this article.

Utilizing Artificial Intelligence in Critical Care: Adding A Handy Tool to Our Armamentarium

We have witnessed rapid advancement in technology over the last few decades. With the advent of artificial intelligence (AI), newer avenues have opened for researchers. AI has added an entirely new dimension to this technological boom. Researchers in medical science have been excited about the tantalizing prospect of utilizing AI for the benefit of patient care. Lately, we have come across studies trying to test and validate various models based on AI to improve patient care strategies in critical care medicine as well. Thus, in this review, we will attempt to succinctly review current literature discussing AI in critical care medicine and analyze its future utility based on prevailing evidence.

Patient-specific COVID-19 resource utilization prediction using fusion AI model

The strain on healthcare resources brought forth by the recent COVID-19 pandemic has highlighted the need for efficient resource planning and allocation through the prediction of future consumption. Machine learning can predict resource utilization such as the need for hospitalization based on past medical data stored in electronic medical records (EMR). We conducted this study on 3194 patients (46% male with mean age 56.7 (±16.8), 56% African American, 7% Hispanic) flagged as COVID-19 positive cases in 12 centers under Emory Healthcare network from February 2020 to September 2020, to assess whether a COVID-19 positive patient’s need for hospitalization can be predicted at the time of RT-PCR test using the EMR data prior to the test. Five main modalities of EMR, i.e., demographics, medication, past medical procedures, comorbidities, and laboratory results, were used as features for predictive modeling, both individually and fused together using late, middle, and early fusion. Models were evaluated in terms of precision, recall, F1-score (within 95% confidence interval). The early fusion model is the most effective predictor with 84% overall F1-score [CI 82.1–86.1]. The predictive performance of the model drops by 6 % when using recent clinical data while omitting the long-term medical history. Feature importance analysis indicates that history of cardiovascular disease, emergency room visits in the past year prior to testing, and demographic factors are predictive of the disease trajectory. We conclude that fusion modeling using medical history and current treatment data can forecast the need for hospitalization for patients infected with COVID-19 at the time of the RT-PCR test.

Leveraging the Electronic Health Record to Address the COVID-19 Pandemic

The coronavirus disease 2019 (COVID-19) pandemic continues its global spread. Coordinated effort on a vast scale is required to halt its progression and to save lives. Electronic health record (EHR) data are a valuable resource to mitigate the COVID-19 pandemic. We review how the EHR could be used for disease surveillance and contact tracing. When linked to "omics" data, the EHR could facilitate identification of genetic susceptibility variants, leading to insights into risk factors, disease complications, and drug repurposing. Real-time monitoring of patients could enable early detection of potential complications, informing appropriate interventions and therapy. We reviewed relevant articles from PubMed, MEDLINE, and Google Scholar searches as well as preprint servers, given the rapidly evolving understanding of the COVID-19 pandemic.

Time series analysis of the in-hospital diagnostic process in suspected pulmonary embolism evaluated by computed tomography: An explorative study

PURPOSE

This retrospective study aims to analyze the distribution of demand and the duration of the diagnostic workup of suspected pulmonary embolism (PE) using computed tomography pulmonary angiography (CTPA).

METHODS

Time data from physical examination to report creation were identified for each CTPA in 2013 and 2018 at a tertiary hospital. Multivariable multinomial logistic and linear regression models were used to evaluate differences between 3 time intervals (I1: 6am-2pm, I2: 2pm-10pm, I3: 10pm-6am). A cosinor model was applied to analyze the amount of CTPA per hour.

RESULTS

The relative demand for CTPA from the emergency room was lower in l1 compared to l2 and l3 (I1/I2: odds ratio (OR) 0.84, 95 % confidence interval (CI) 0.78-0.91; I1/I3: OR 0.80, 95 % CI 0.72-0.89; peak 4:23 pm). Requests for in-patients displayed a tendency towards I1 (I1/2: OR 1.15, 95 % CI 1.06-1.24; l1/l3: OR 1.19, 95 % CI 1.07-1.33; peak 1:54 pm). The time from CTPA request to study was shorter in I3 compared to I1 and I2 in 2013 (I1/I3: ratio 5.23, 95 % CI 3.38-8.10; I2/I3: ratio 3.50, 95 % CI 2.24-5.45) and 2018 (I1/I3: ratio 2.27, 95 % CI 1.60-3.22; I2/I3: ratio 2.11, 95 % CI 1.50-2.97). This applied similarly to fatal cases (I1/I3: ratio 2.91, 95 % CI 1.78-4.75; I2/I3: ratio 2.45, 95 % CI1.52-3.95).

CONCLUSIONS

The temporal distribution of demand for CTPA depends on the sector of patient care and the processing time differs substantially during the day. Time series analysis can reveal such coherences and may help to optimize workflows in radiology departments.

How artificial intelligence can help us 'Choose Wisely'

The overuse of low value medical tests and treatments drives costs and patient harm. Efforts to address overuse, such as Choosing Wisely campaigns, typically rely on passive implementation strategies- a form of low reliability system change. Embedding guidelines into clinical decision support (CDS) software is a higher leverage approach to provide ordering suggestions through an interface embedded within the clinical workflow. Growth in computing power is increasingly enabling artificial intelligence (AI) to augment such decision making tools. This article offers a roadmap of opportunities for AI-enabled CDS to reduce overuse, which are presented according to a patient’s journey of care.

The potential of artificial intelligence to improve patient safety: a scoping review

Artificial intelligence (AI) represents a valuable tool that could be used to improve the safety of care. Major adverse events in healthcare include: healthcare-associated infections, adverse drug events, venous thromboembolism, surgical complications, pressure ulcers, falls, decompensation, and diagnostic errors. The objective of this scoping review was to summarize the relevant literature and evaluate the potential of AI to improve patient safety in these eight harm domains. A structured search was used to query MEDLINE for relevant articles. The scoping review identified studies that described the application of AI for prediction, prevention, or early detection of adverse events in each of the harm domains. The AI literature was narratively synthesized for each domain, and findings were considered in the context of incidence, cost, and preventability to make projections about the likelihood of AI improving safety. Three-hundred and ninety-two studies were included in the scoping review. The literature provided numerous examples of how AI has been applied within each of the eight harm domains using various techniques. The most common novel data were collected using different types of sensing technologies: vital sign monitoring, wearables, pressure sensors, and computer vision. There are significant opportunities to leverage AI and novel data sources to reduce the frequency of harm across all domains. We expect AI to have the greatest impact in areas where current strategies are not effective, and integration and complex analysis of novel, unstructured data are necessary to make accurate predictions; this applies specifically to adverse drug events, decompensation, and diagnostic errors.

Physician understanding, explainability, and trust in a hypothetical machine learning risk calculator

OBJECTIVE

Implementation of machine learning (ML) may be limited by patients' right to "meaningful information about the logic involved" when ML influences healthcare decisions. Given the complexity of healthcare decisions, it is likely that ML outputs will need to be understood and trusted by physicians, and then explained to patients. We therefore investigated the association between physician understanding of ML outputs, their ability to explain these to patients, and their willingness to trust the ML outputs, using various ML explainability methods.

MATERIALS AND METHODS

We designed a survey for physicians with a diagnostic dilemma that could be resolved by an ML risk calculator. Physicians were asked to rate their understanding, explainability, and trust in response to 3 different ML outputs. One ML output had no explanation of its logic (the control) and 2 ML outputs used different model-agnostic explainability methods. The relationships among understanding, explainability, and trust were assessed using Cochran-Mantel-Haenszel tests of association.

RESULTS

The survey was sent to 1315 physicians, and 170 (13%) provided completed surveys. There were significant associations between physician understanding and explainability (P < .001), between physician understanding and trust (P < .001), and between explainability and trust (P < .001). ML outputs that used model-agnostic explainability methods were preferred by 88% of physicians when compared with the control condition; however, no particular ML explainability method had a greater influence on intended physician behavior.

CONCLUSIONS

Physician understanding, explainability, and trust in ML risk calculators are related. Physicians preferred ML outputs accompanied by model-agnostic explanations but the explainability method did not alter intended physician behavior.

Suspected Acute Pulmonary Embolism: Gestalt, Scoring Systems, and Artificial Intelligence

Pulmonary embolism (PE) remains a diagnostic challenge in 2021. As the pathology is potentially fatal and signs and symptoms are nonspecific, further investigations are classically required. Based on the Bayesian approach, clinical probability became the keystone of the diagnostic strategy to rule out PE in the case of a negative testing. Several clinical probability assessment methods are validated: gestalt, the Wells score, or the revised Geneva score. While the debate persists as to the best way to assess clinical probability, its assessment allows for the good interpretation of the investigation results and therefore directs the correct diagnostic strategy. The wide availability of computed tomography pulmonary angiography (CTPA) resulted in a major increase in investigations with a moderate increase in diagnosis, without any notable improvement in patient outcomes. This leads to a new challenge for PE diagnosis which is the limitation of the number of testing for suspected PE. We review different strategies recently developed to achieve this goal. The last challenge concerns the implementation in clinical practice. Two approaches are developed: simplification of the strategies versus the use of digital support tools allowing more sophisticated strategies. Artificial intelligence with machine-learning algorithms will probably be a future tool to guide the physician in this complex approach concerning acute PE suspicion.

Multimodal fusion with deep neural networks for leveraging CT imaging and electronic health record: a case-study in pulmonary embolism detection

Recent advancements in deep learning have led to a resurgence of medical imaging and Electronic Medical Record (EMR) models for a variety of applications, including clinical decision support, automated workflow triage, clinical prediction and more. However, very few models have been developed to integrate both clinical and imaging data, despite that in routine practice clinicians rely on EMR to provide context in medical imaging interpretation. In this study, we developed and compared different multimodal fusion model architectures that are capable of utilizing both pixel data from volumetric Computed Tomography Pulmonary Angiography scans and clinical patient data from the EMR to automatically classify Pulmonary Embolism (PE) cases. The best performing multimodality model is a late fusion model that achieves an AUROC of 0.947 [95% CI: 0.946–0.948] on the entire held-out test set, outperforming imaging-only and EMR-only single modality models.

Digital systems for improving outcomes in patients with primary immune defects

PURPOSE OF REVIEW

Healthcare has already been impacted by the fourth industrial revolution exemplified by tip of spear technology, such as artificial intelligence and quantum computing. Yet, there is much to be accomplished as systems remain suboptimal, and full interoperability of digital records is not realized. Given the footprint of technology in healthcare, the field of clinical immunology will certainly see improvements related to these tools.

RECENT FINDINGS

Biomedical informatics spans the gamut of technology in biomedicine. Within this distinct field, advances are being made, which allow for engineering of systems to automate disease detection, create computable phenotypes and improve record portability. Within clinical immunology, technologies are emerging along these lines and are expected to continue.

SUMMARY

This review highlights advancements in digital health including learning health systems, electronic phenotyping, artificial intelligence and use of registries. Technological advancements for improving diagnosis and care of patients with primary immunodeficiency diseases is also highlighted.

From Early Morphometrics to Machine Learning-What Future for Cardiovascular Imaging of the Pulmonary Circulation?

Imaging plays a cardinal role in the diagnosis and management of diseases of the pulmonary circulation. Behind the picture itself, every digital image contains a wealth of quantitative data, which are hardly analysed in current routine clinical practice and this is now being transformed by radiomics. Mathematical analyses of these data using novel techniques, such as vascular morphometry (including vascular tortuosity and vascular volumes), blood flow imaging (including quantitative lung perfusion and computational flow dynamics), and artificial intelligence, are opening a window on the complex pathophysiology and structure-function relationships of pulmonary vascular diseases. They have the potential to make dramatic alterations to how clinicians investigate the pulmonary circulation, with the consequences of more rapid diagnosis and a reduction in the need for invasive procedures in the future. Applied to multimodality imaging, they can provide new information to improve disease characterization and increase diagnostic accuracy. These new technologies may be used as sophisticated biomarkers for risk prediction modelling of prognosis and for optimising the long-term management of pulmonary circulatory diseases. These innovative techniques will require evaluation in clinical trials and may in themselves serve as successful surrogate end points in trials in the years to come.

Fusion of medical imaging and electronic health records using deep learning: a systematic review and implementation guidelines

Advancements in deep learning techniques carry the potential to make significant contributions to healthcare, particularly in fields that utilize medical imaging for diagnosis, prognosis, and treatment decisions. The current state-of-the-art deep learning models for radiology applications consider only pixel-value information without data informing clinical context. Yet in practice, pertinent and accurate non-imaging data based on the clinical history and laboratory data enable physicians to interpret imaging findings in the appropriate clinical context, leading to a higher diagnostic accuracy, informative clinical decision making, and improved patient outcomes. To achieve a similar goal using deep learning, medical imaging pixel-based models must also achieve the capability to process contextual data from electronic health records (EHR) in addition to pixel data. In this paper, we describe different data fusion techniques that can be applied to combine medical imaging with EHR, and systematically review medical data fusion literature published between 2012 and 2020. We conducted a systematic search on PubMed and Scopus for original research articles leveraging deep learning for fusion of multimodality data. In total, we screened 985 studies and extracted data from 17 papers. By means of this systematic review, we present current knowledge, summarize important results and provide implementation guidelines to serve as a reference for researchers interested in the application of multimodal fusion in medical imaging.

Management of Acute Pulmonary Embolism

Purpose of the Review

Over 100,000 cardiovascular-related deaths annually are caused by acute pulmonary embolism (PE). While anticoagulation has historically been the foundation for treatment of PE, this review highlights the recent rapid expansion in the interventional strategies for this condition.

Recent Findings

At the time of diagnosis, appropriate risk stratification helps to accurately identify patients who may be candidates for advanced therapeutic interventions. While systemic thrombolytics (ST) is the mostly commonly utilized intervention for high-risk PE, the risk profile of ST for intermediate-risk PE limits its use. Assessment of an individualized patient risk profile, often via a multidisciplinary pulmonary response team (PERT) model, there are various interventional strategies to consider for PE management. Novel therapeutic options include catheter-directed thrombolysis, catheter-based embolectomy, or mechanical circulatory support for certain high-risk PE patients. Current data has established safety and efficacy for catheter-based treatment of PE based on surrogate outcome measures. However, there is limited long-term data or prospective comparisons between treatment modalities and ST. While PE diagnosis has improved with modern cross-sectional imaging, there is interest in improved diagnostic models for PE that incorporate artificial intelligence and machine learning techniques.

Summary

In patients with acute pulmonary embolism, after appropriate risk stratification, some intermediate and high-risk patients should be considered for interventional-based treatment for PE.

Artificial Intelligence in the Intensive Care Unit

This article is one of ten reviews selected from the Annual Update in Intensive Care and Emergency Medicine 2020. Other selected articles can be found online at https://www.biomedcentral.com/collections/annualupdate2020. Further information about the Annual Update in Intensive Care and Emergency Medicine is available from http://www.springer.com/series/8901.

Pulmonary embolism rule out: positivity and factors affecting the yield of CT angiography

OBJECTIVE

CT pulmonary angiography (CTPA) is one of the most commonly ordered CT imaging tests. It is often believed to be overutilised with few recent studies showing a yield of less than 2%. This study aimed to determine the overall positivity rate of CTPA examinations and understand the factors that affect the yield of the CTPA examination.

METHODS

We retrospectively analysed 2713 patients who received the CTPA exam between 2016 and 2018. Type of study ordered (CTPA chest or CTPA chest with abdomen and pelvis CT), patient location (emergency department (ED), outpatient, inpatient, intensive care unit (ICU)) and patient characteristics-age, sex and body mass index (BMI) were recorded. A logistic regression analysis was performed to determine what factors affect the positivity rate of CT scans for pulmonary embolism (PE).

RESULTS

With 296 positive test results, the overall CTPA positivity was 10.9%. Male sex was associated with higher CTPA positivity, gender difference was maximum in 18-year to 35-year age group. Overweight and obese patients had significantly higher positivity as compared with BMI<25 (p<0.05). Higher positivity rate was seen in the BMI 25-40 group (11.9%) as compared with BMI>40 (10.1%) (p<0.05). Significant difference (p<0.001) was also found in CTPA examination yield from ICU (15.3%) versus inpatients (other than ICU) (12.4%) versus ED (9.6%), and outpatients (8.5%). The difference in CTPA yield based on the type of CT order (CTPA chest vs CTPA chest with CT abdomen and pelvis), patient's age and sex was not significant.

CONCLUSION

CTPA yield of 10.9% in this study is comparable to acceptable positivity rate for the USA and is higher than recent studies showing positivity of <2%. Patient characteristics like obesity and ICU or inpatient location are associated with higher rate of CT positivity.