How artificial intelligence could transform emergency department operations

Capturing artificial intelligence applications' value proposition in healthcare - a qualitative research study

Artificial intelligence (AI) applications pave the way for innovations in the healthcare (HC) industry. However, their adoption in HC organizations is still nascent as organizations often face a fragmented and incomplete picture of how they can capture the value of AI applications on a managerial level. To overcome adoption hurdles, HC organizations would benefit from understanding how they can capture AI applications' potential.We conduct a comprehensive systematic literature review and 11 semi-structured expert interviews to identify, systematize, and describe 15 business objectives that translate into six value propositions of AI applications in HC.Our results demonstrate that AI applications can have several business objectives converging into risk-reduced patient care, advanced patient care, self-management, process acceleration, resource optimization, and knowledge discovery.We contribute to the literature by extending research on value creation mechanisms of AI to the HC context and guiding HC organizations in evaluating their AI applications or those of the competition on a managerial level, to assess AI investment decisions, and to align their AI application portfolio towards an overarching strategy.

Assessing the precision of artificial intelligence in ED triage decisions: Insights from a study with ChatGPT

BACKGROUND

The rise in emergency department presentations globally poses challenges for efficient patient management. To address this, various strategies aim to expedite patient management. Artificial intelligence's (AI) consistent performance and rapid data interpretation extend its healthcare applications, especially in emergencies. The introduction of a robust AI tool like ChatGPT, based on GPT-4 developed by OpenAI, can benefit patients and healthcare professionals by improving the speed and accuracy of resource allocation. This study examines ChatGPT's capability to predict triage outcomes based on local emergency department rules.

METHODS

This study is a single-center prospective observational study. The study population consists of all patients who presented to the emergency department with any symptoms and agreed to participate. The study was conducted on three non-consecutive days for a total of 72 h. Patients' chief complaints, vital parameters, medical history and the area to which they were directed by the triage team in the emergency department were recorded. Concurrently, an emergency medicine physician inputted the same data into previously trained GPT-4, according to local rules. According to this data, the triage decisions made by GPT-4 were recorded. In the same process, an emergency medicine specialist determined where the patient should be directed based on the data collected, and this decision was considered the gold standard. Accuracy rates and reliability for directing patients to specific areas by the triage team and GPT-4 were evaluated using Cohen's kappa test. Furthermore, the accuracy of the patient triage process performed by the triage team and GPT-4 was assessed by receiver operating characteristic (ROC) analysis. Statistical analysis considered a value of p < 0.05 as significant.

RESULTS

The study was carried out on 758 patients. Among the participants, 416 (54.9%) were male and 342 (45.1%) were female. Evaluating the primary endpoints of our study - the agreement between the decisions of the triage team, GPT-4 decisions in emergency department triage, and the gold standard - we observed almost perfect agreement both between the triage team and the gold standard and between GPT-4 and the gold standard (Cohen's Kappa 0.893 and 0.899, respectively; p < 0.001 for each).

CONCLUSION

Our findings suggest GPT-4 possess outstanding predictive skills in triaging patients in an emergency setting. GPT-4 can serve as an effective tool to support the triage process.

Application of Machine Learning Techniques to Development of Emergency Medical Rapid Triage Prediction Models in Acute Care

Given the critical and complex features of medical emergencies, it is essential to develop models that enable prompt and suitable clinical decision-making based on considerable information. Emergency nurses are responsible for categorizing and prioritizing injuries and illnesses on the frontlines of the emergency room. This study aims to create an Emergency Medical Rapid Triage and Prediction Assistance model using electronic medical records and machine learning techniques. Patient information was retrieved from the emergency department of a large regional teaching hospital in Taiwan, and five supervised learning techniques were used to construct classification models for predicting critical outcomes. Of these models, the model using logistic regression had superior prediction performance, with an F1 score of 0.861 and an area under the receiver operating characteristic curve of 0.855. The Emergency Medical Rapid Triage and Prediction Assistance model demonstrated superior performance in predicting intensive care and hospitalization outcomes compared with the Taiwan Triage and Acuity Scale and three clinical early warning tools. The proposed model has the potential to assist emergency nurses in executing challenging triage assessments and emergency teams in treating critically ill patients promptly, leading to improved clinical care and efficient utilization of medical resources.

ChatGPT's performance before and after teaching in mass casualty incident triage

Since its initial launching, ChatGPT has gained significant attention from the media, with many claiming that ChatGPT's arrival is a transformative milestone in the advancement of the AI revolution. Our aim was to assess the performance of ChatGPT before and after teaching the triage of mass casualty incidents by utilizing a validated questionnaire specifically designed for such scenarios. In addition, we compared the triage performance between ChatGPT and medical students. Our cross-sectional study employed a mixed-methods analysis to assess the performance of ChatGPT in mass casualty incident triage, pre- and post-teaching of Simple Triage And Rapid Treatment (START) triage. After teaching the START triage algorithm, ChatGPT scored an overall triage accuracy of 80%, with only 20% of cases being over-triaged. The mean accuracy of medical students on the same questionnaire yielded 64.3%. Qualitative analysis on pre-determined themes on 'walking-wounded', 'respiration', 'perfusion', and 'mental status' on ChatGPT showed similar performance in pre- and post-teaching of START triage. Additional themes on 'disclaimer', 'prediction', 'management plan', and 'assumption' were identified during the thematic analysis. ChatGPT exhibited promising results in effectively responding to mass casualty incident questionnaires. Nevertheless, additional research is necessary to ensure its safety and efficacy before clinical implementation.

Using artificial intelligence to predict adverse outcomes in emergency department patients with hyperglycemic crises in real time

BACKGROUND

Hyperglycemic crises are associated with high morbidity and mortality. Previous studies have proposed methods to predict adverse outcomes of patients in hyperglycemic crises; however, artificial intelligence (AI) has never been used to predict adverse outcomes. We implemented an AI model integrated with the hospital information system (HIS) to clarify whether AI could predict adverse outcomes.

METHODS

We included 2,666 patients with hyperglycemic crises from emergency departments (ED) between 2009 and 2018. The patients were randomized into a 70%/30% split for AI model training and testing. Twenty-two feature variables from the electronic medical records were collected. The performance of the multilayer perceptron (MLP), logistic regression, random forest, Light Gradient Boosting Machine (LightGBM), support vector machine (SVM), and K-nearest neighbor (KNN) algorithms was compared. We selected the best algorithm to construct an AI model to predict sepsis or septic shock, intensive care unit (ICU) admission, and all-cause mortality within 1 month. The outcomes between the non-AI and AI groups were compared after implementing the HIS and predicting the hyperglycemic crisis death (PHD) score.

RESULTS

The MLP had the best performance in predicting the three adverse outcomes, compared with the random forest, logistic regression, SVM, KNN, and LightGBM models. The areas under the curves (AUCs) using the MLP model were 0.852 for sepsis or septic shock, 0.743 for ICU admission, and 0.796 for all-cause mortality. Furthermore, we integrated the AI predictive model with the HIS to assist decision making in real time. No significant differences in ICU admission or all-cause mortality were detected between the non-AI and AI groups. The AI model performed better than the PHD score for predicting all-cause mortality (AUC 0.796 vs. 0.693).

CONCLUSIONS

A real-time AI predictive model is a promising method for predicting adverse outcomes in ED patients with hyperglycemic crises. Further studies recruiting more patients are warranted.

Machine learning-based prediction of symptomatic intracerebral hemorrhage after intravenous thrombolysis for stroke: a large multicenter study

Background

This study aimed to compare the performance of different machine learning models in predicting symptomatic intracranial hemorrhage (sICH) after thrombolysis treatment for ischemic stroke.

Methods

This multicenter study utilized the Shenyang Stroke Emergency Map database, comprising 8,924 acute ischemic stroke patients from 29 comprehensive hospitals who underwent thrombolysis between January 2019 and December 2021. An independent testing cohort was further established, including 1,921 patients from the First People's Hospital of Shenyang. The structured dataset encompassed 15 variables, including clinical and therapeutic metrics. The primary outcome was the sICH occurrence post-thrombolysis. Models were developed using an 80/20 split for training and internal validation. Performance was assessed using machine learning classifiers, including logistic regression with lasso regularization, support vector machine (SVM), random forest, gradient-boosted decision tree (GBDT), and multilayer perceptron (MLP). The model boasting the highest area under the curve (AUC) was specifically employed to highlight feature importance.

Results

Baseline characteristics were compared between the training cohort (n = 6,369) and the external validation cohort (n = 1,921), with the sICH incidence being slightly higher in the training cohort (1.6%) compared to the validation cohort (1.1%). Among the evaluated models, the logistic regression with lasso regularization achieved the highest AUC of 0.87 (95% confidence interval [CI]: 0.79-0.95; p < 0.001), followed by the MLP model with an AUC of 0.766 (95% CI: 0.637-0.894; p = 0.04). The reference model and SVM showed AUCs of 0.575 and 0.582, respectively, while the random forest and GBDT models performed less optimally with AUCs of 0.536 and 0.436, respectively. Decision curve analysis revealed net benefits primarily for the SVM and MLP models. Feature importance from the logistic regression model emphasized anticoagulation therapy as the most significant negative predictor (coefficient: -2.0833) and recombinant tissue plasminogen activator as the principal positive predictor (coefficient: 0.5082).

Conclusion

After a comprehensive evaluation, the MLP model is recommended due to its superior ability to predict the risk of symptomatic hemorrhage post-thrombolysis in ischemic stroke patients. Based on decision curve analysis, the MLP-based model was chosen and demonstrated enhanced discriminative ability compared to the reference. This model serves as a valuable tool for clinicians, aiding in treatment planning and ensuring more precise forecasting of patient outcomes.

Revolutionizing healthcare: the role of artificial intelligence in clinical practice

INTRODUCTION

Healthcare systems are complex and challenging for all stakeholders, but artificial intelligence (AI) has transformed various fields, including healthcare, with the potential to improve patient care and quality of life. Rapid AI advancements can revolutionize healthcare by integrating it into clinical practice. Reporting AI's role in clinical practice is crucial for successful implementation by equipping healthcare providers with essential knowledge and tools.

RESEARCH SIGNIFICANCE

This review article provides a comprehensive and up-to-date overview of the current state of AI in clinical practice, including its potential applications in disease diagnosis, treatment recommendations, and patient engagement. It also discusses the associated challenges, covering ethical and legal considerations and the need for human expertise. By doing so, it enhances understanding of AI's significance in healthcare and supports healthcare organizations in effectively adopting AI technologies.

MATERIALS AND METHODS

The current investigation analyzed the use of AI in the healthcare system with a comprehensive review of relevant indexed literature, such as PubMed/Medline, Scopus, and EMBASE, with no time constraints but limited to articles published in English. The focused question explores the impact of applying AI in healthcare settings and the potential outcomes of this application.

RESULTS

Integrating AI into healthcare holds excellent potential for improving disease diagnosis, treatment selection, and clinical laboratory testing. AI tools can leverage large datasets and identify patterns to surpass human performance in several healthcare aspects. AI offers increased accuracy, reduced costs, and time savings while minimizing human errors. It can revolutionize personalized medicine, optimize medication dosages, enhance population health management, establish guidelines, provide virtual health assistants, support mental health care, improve patient education, and influence patient-physician trust.

CONCLUSION

AI can be used to diagnose diseases, develop personalized treatment plans, and assist clinicians with decision-making. Rather than simply automating tasks, AI is about developing technologies that can enhance patient care across healthcare settings. However, challenges related to data privacy, bias, and the need for human expertise must be addressed for the responsible and effective implementation of AI in healthcare.

Artificial intelligence and machine learning in prehospital emergency care: A scoping review

Our scoping review provides a comprehensive analysis of the landscape of artificial intelligence (AI) applications in prehospital emergency care (PEC). It contributes to the field by highlighting the most studied AI applications and identifying the most common methodological approaches across 106 included studies. The findings indicate a promising future for AI in PEC, with many unique use cases, such as prognostication, demand prediction, resource optimization, and the Internet of Things continuous monitoring systems. Comparisons with other approaches showed AI outperforming clinicians and non-AI algorithms in most cases. However, most studies were internally validated and retrospective, highlighting the need for rigorous prospective validation of AI applications before implementation in clinical settings. We identified knowledge and methodological gaps using an evidence map, offering a roadmap for future investigators. We also discussed the significance of explainable AI for establishing trust in AI systems among clinicians and facilitating real-world validation of AI models.

Needs and expectations for artificial intelligence in emergency medicine according to Canadian physicians

BACKGROUND

Artificial Intelligence (AI) is recognized by emergency physicians (EPs) as an important technology that will affect clinical practice. Several AI-tools have already been developed to aid care delivery in emergency medicine (EM). However, many EM tools appear to have been developed without a cross-disciplinary needs assessment, making it difficult to understand their broader importance to general-practice. Clinician surveys about AI tools have been conducted within other medical specialties to help guide future design. This study aims to understand the needs of Canadian EPs for the apt use of AI-based tools.

METHODS

A national cross-sectional, two-stage, mixed-method electronic survey of Canadian EPs was conducted from January-May 2022. The survey includes demographic and physician practice-pattern data, clinicians' current use and perceptions of AI, and individual rankings of which EM work-activities most benefit from AI.

RESULTS

The primary outcome is a ranked list of high-priority AI-tools for EM that physicians want translated into general use within the next 10 years. When ranking specific AI examples, 'automated charting/report generation', 'clinical prediction rules' and 'monitoring vitals with early-warning detection' were the top items. When ranking by physician work-activities, 'AI-tools for documentation', 'AI-tools for computer use' and 'AI-tools for triaging patients' were the top items. For secondary outcomes, EPs indicated AI was 'likely' (43.1%) or 'extremely likely' (43.7%) to be able to complete the task of 'documentation' and indicated either 'a-great-deal' (32.8%) or 'quite-a-bit' (39.7%) of potential for AI in EM. Further, EPs were either 'strongly' (48.5%) or 'somewhat' (39.8%) interested in AI for EM.

CONCLUSIONS

Physician input on the design of AI is essential to ensure the uptake of this technology. Translation of AI-tools to facilitate documentation is considered a high-priority, and respondents had high confidence that AI could facilitate this task. This study will guide future directions regarding the use of AI for EM and help direct efforts to address prevailing technology-translation barriers such as access to high-quality application-specific data and developing reporting guidelines for specific AI-applications. With a prioritized list of high-need AI applications, decision-makers can develop focused strategies to address these larger obstacles.

Modelling 30-day hospital readmission after discharge for COPD patients based on electronic health records

Chronic Obstructive Pulmonary Disease (COPD) is the third most common chronic disease in China with frequent exacerbations, resulting in increased hospitalization and readmission rate. COPD readmission within 30 days after discharge is an important indicator of care transitions, patient's quality of life and disease management. Identifying risk factors and improving 30-day readmission prediction help inform appropriate interventions, reducing readmissions and financial burden. This study aimed to develop a 30-day readmission prediction model using decision tree by learning from the data extracted from the electronic health record of COPD patients in Macao. Health records data of COPD inpatients from Kiang Wu Hospital, Macao, from January 1, 2018, to December 31, 2019 were reviewed and analyzed. A total of 782 hospitalizations for AECOPD were enrolled, where the 30-day readmission rate was 26.5% (207). A balanced dataset was randomly generated, where male accounted for 69.1% and mean age was 80.73 years old. Age, length of stay, history of tobacco smoking, hemoglobin, systemic steroids use, antibiotics use and number of hospital admission due to COPD in last 12 months were found to be significant risk factors for 30-day readmission of CODP patients (P < 0.01). A data-driven decision tree-based modelling approach with Bayesian hyperparameter optimization was developed. The mean precision-recall and AUC value for the classifier were 73.85, 73.7 and 0.7506, showing a satisfying prediction performance. The number of hospital admission due to AECOPD in last 12 months, smoke status and patients' age were the top factors for 30-day readmission in Macao population.

Discriminating Acute Respiratory Distress Syndrome from other forms of respiratory failure via iterative machine learning

Acute Respiratory Distress Syndrome (ARDS) is associated with high morbidity and mortality. Identification of ARDS enables lung protective strategies, quality improvement interventions, and clinical trial enrolment, but remains challenging particularly in the first 24 hours of mechanical ventilation. To address this we built an algorithm capable of discriminating ARDS from other similarly presenting disorders immediately following mechanical ventilation. Specifically, a clinical team examined medical records from 1263 ICU-admitted, mechanically ventilated patients, retrospectively assigning each patient a diagnosis of "ARDS" or "non-ARDS" (e.g., pulmonary edema). Exploiting data readily available in the clinical setting, including patient demographics, laboratory test results from before the initiation of mechanical ventilation, and features extracted by natural language processing of radiology reports, we applied an iterative pre-processing and machine learning framework. The resulting model successfully discriminated ARDS from non-ARDS causes of respiratory failure (AUC = 0.85) among patients meeting Berlin criteria for severe hypoxia. This analysis also highlighted novel patient variables that were informative for identifying ARDS in ICU settings.

Ethical considerations in implementing AI for mortality prediction in the emergency department: Linking theory and practice

Background

Artificial intelligence (AI) is predicted to be a solution for improving healthcare, increasing efficiency, and saving time and recourses. A lack of ethical principles for the use of AI in practice has been highlighted by several stakeholders due to the recent attention given to it. Research has shown an urgent need for more knowledge regarding the ethical implications of AI applications in healthcare. However, fundamental ethical principles may not be sufficient to describe ethical concerns associated with implementing AI applications.

Objective

The aim of this study is twofold, (1) to use the implementation of AI applications to predict patient mortality in emergency departments as a setting to explore healthcare professionals' perspectives on ethical issues in relation to ethical principles and (2) to develop a model to guide ethical considerations in AI implementation in healthcare based on ethical theory.

Methods

Semi-structured interviews were conducted with 18 participants. The abductive approach used to analyze the empirical data consisted of four steps alternating between inductive and deductive analyses.

Results

Our findings provide an ethical model demonstrating the need to address six ethical principles (autonomy, beneficence, non-maleficence, justice, explicability, and professional governance) in relation to ethical theories defined as virtue, deontology, and consequentialism when AI applications are to be implemented in clinical practice.

Conclusions

Ethical aspects of AI applications are broader than the prima facie principles of medical ethics and the principle of explicability. Ethical aspects thus need to be viewed from a broader perspective to cover different situations that healthcare professionals, in general, and physicians, in particular, may face when using AI applications in clinical practice.

Transcranial Doppler analysis based on computer and artificial intelligence for acute cerebrovascular disease

Cerebrovascular disease refers to damage to brain tissue caused by impaired intracranial blood circulation. It usually presents clinically as an acute nonfatal event and is characterized by high morbidity, disability, and mortality. Transcranial Doppler (TCD) ultrasonography is a non-invasive method for the diagnosis of cerebrovascular disease that uses the Doppler effect to detect the hemodynamic and physiological parameters of the major intracranial basilar arteries. It can provide important hemodynamic information that cannot be measured by other diagnostic imaging techniques for cerebrovascular disease. And the result parameters of TCD ultrasonography such as blood flow velocity and beat index can reflect the type of cerebrovascular disease and serve as a basis to assist physicians in the treatment of cerebrovascular diseases. Artificial intelligence (AI) is a branch of computer science which is used in a wide range of applications in agriculture, communications, medicine, finance, and other fields. In recent years, there are much research devoted to the application of AI to TCD. The review and summary of related technologies is an important work to promote the development of this field, which can provide an intuitive technical summary for future researchers. In this paper, we first review the development, principles, and applications of TCD ultrasonography and other related knowledge, and briefly introduce the development of AI in the field of medicine and emergency medicine. Finally, we summarize in detail the applications and advantages of AI technology in TCD ultrasonography including the establishment of an examination system combining brain computer interface (BCI) and TCD ultrasonography, the classification and noise cancellation of TCD ultrasonography signals using AI algorithms, and the use of intelligent robots to assist physicians in TCD ultrasonography and discuss the prospects for the development of AI in TCD ultrasonography.

Challenges in evaluating the accuracy of AI-containing digital triage systems: A systematic review

INTRODUCTION

Patient-operated digital triage systems with AI components are becoming increasingly common. However, previous reviews have found a limited amount of research on such systems' accuracy. This systematic review of the literature aimed to identify the main challenges in determining the accuracy of patient-operated digital AI-based triage systems.

METHODS

A systematic review was designed and conducted in accordance with PRISMA guidelines in October 2021 using PubMed, Scopus and Web of Science. Articles were included if they assessed the accuracy of a patient-operated digital triage system that had an AI-component and could triage a general primary care population. Limitations and other pertinent data were extracted, synthesized and analysed. Risk of bias was not analysed as this review studied the included articles' limitations (rather than results). Results were synthesized qualitatively using a thematic analysis.

RESULTS

The search generated 76 articles and following exclusion 8 articles (6 primary articles and 2 reviews) were included in the analysis. Articles' limitations were synthesized into three groups: epistemological, ontological and methodological limitations. Limitations varied with regards to intractability and the level to which they can be addressed through methodological choices. Certain methodological limitations related to testing triage systems using vignettes can be addressed through methodological adjustments, whereas epistemological and ontological limitations require that readers of such studies appraise the studies with limitations in mind.

DISCUSSION

The reviewed literature highlights recurring limitations and challenges in studying the accuracy of patient-operated digital triage systems with AI components. Some of these challenges can be addressed through methodology whereas others are intrinsic to the area of inquiry and involve unavoidable trade-offs. Future studies should take these limitations in consideration in order to better address the current knowledge gaps in the literature.

Deep Segmentation Networks for Segmenting Kidneys and Detecting Kidney Stones in Unenhanced Abdominal CT Images

Recent breakthroughs of deep learning algorithms in medical imaging, automated detection, and segmentation techniques for renal (kidney) in abdominal computed tomography (CT) images have been limited. Radiomics and machine learning analyses of renal diseases rely on the automatic segmentation of kidneys in CT images. Inspired by this, our primary aim is to utilize deep semantic segmentation learning models with a proposed training scheme to achieve precise and accurate segmentation outcomes. Moreover, this work aims to provide the community with an open-source, unenhanced abdominal CT dataset for training and testing the deep learning segmentation networks to segment kidneys and detect kidney stones. Five variations of deep segmentation networks are trained and tested both dependently (based on the proposed training scheme) and independently. Upon comparison, the models trained with the proposed training scheme enable the highly accurate 2D and 3D segmentation of kidneys and kidney stones. We believe this work is a fundamental step toward AI-driven diagnostic strategies, which can be an essential component of personalized patient care and improved decision-making in treating kidney diseases.

Machine learning-based suggestion for critical interventions in the management of potentially severe conditioned patients in emergency department triage

Providing timely intervention to critically ill patients is a challenging task in emergency departments (ED). Our study aimed to predict early critical interventions (CrIs), which can be used as clinical recommendations. This retrospective observational study was conducted in the ED of a tertiary hospital located in a Korean metropolitan city. Patient who visited ED from January 1, 2016, to December 31, 2018, were included. Need of six CrIs were selected as prediction outcomes, namely, arterial line (A-line) insertion, oxygen therapy, high-flow nasal cannula (HFNC), intubation, Massive Transfusion Protocol (MTP), and inotropes and vasopressor. Extreme gradient boosting (XGBoost) prediction model was built by using only data available at the initial stage of ED. Overall, 137,883 patients were included in the study. The areas under the receiver operating characteristic curve for the prediction of A-line insertion was 0·913, oxygen therapy was 0.909, HFNC was 0.962, intubation was 0.945, MTP was 0.920, and inotropes or vasopressor administration was 0.899 in the XGBoost method. In addition, an increase in the need for CrIs was associated with worse ED outcomes. The CrIs model was integrated into the study site's electronic medical record and could be used to suggest early interventions for emergency physicians.

Influence of artificial intelligence on the work design of emergency department clinicians a systematic literature review

Objective

This systematic literature review aims to demonstrate how Artificial Intelligence (AI) is currently used in emergency departments (ED) and how it alters the work design of ED clinicians. AI is still new and unknown to many healthcare professionals in emergency care, leading to unfamiliarity with its capabilities.

Method

Various criteria were used to establish the suitability of the articles to answer the research question. This study was based on 34 selected peer-reviewed papers on the use of Artificial Intelligence (AI) in the Emergency Department (ED), published in the last five years. Drawing on the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, all articles were scanned, read full-text, and analyzed afterward.

Results

The majority of the AI applications consisted of AI-based tools to aid with clinical decisions and to relieve overcrowded EDs of their burden. AI support was mostly offered during triage, the moment that sets the patient trajectory. There is ample evidence that AI-based applications could improve the clinical decision-making process.

Conclusion

The use of AI in EDs is still in its nascent stages. Many studies focus on the question of whether AI has clinical utility, such as decision support, improving resource allocation, reducing diagnostic errors, and promoting proactivity. Some studies suggest that AI-based tools essentially have the ability to outperform human skills. However, it is evident from the literature that current technology does not have the aims or power to do so. Nevertheless, AI-based tools can impact clinician work design in the ED by providing support with clinical decisions, which could ultimately help alleviate a portion of the increasing clinical burden.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12913-022-08070-7.

Artificial Intelligence in Chest Radiography Reporting Accuracy: Added Clinical Value in the Emergency Unit Setting Without 24/7 Radiology Coverage

OBJECTIVES

Chest radiographs (CXRs) are commonly performed in emergency units (EUs), but the interpretation requires radiology experience. We developed an artificial intelligence (AI) system (precommercial) that aims to mimic board-certified radiologists' (BCRs') performance and can therefore support non-radiology residents (NRRs) in clinical settings lacking 24/7 radiology coverage. We validated by quantifying the clinical value of our AI system for radiology residents (RRs) and EU-experienced NRRs in a clinically representative EU setting.

MATERIALS AND METHODS

A total of 563 EU CXRs were retrospectively assessed by 3 BCRs, 3 RRs, and 3 EU-experienced NRRs. Suspected pathologies (pleural effusion, pneumothorax, consolidations suspicious for pneumonia, lung lesions) were reported on a 5-step confidence scale (sum of 20,268 reported pathology suspicions [563 images × 9 readers × 4 pathologies]) separately by every involved reader. Board-certified radiologists' confidence scores were converted into 4 binary reference standards (RFSs) of different sensitivities. The RRs' and NRRs' performances were statistically compared with our AI system (trained on nonpublic data from different clinical sites) based on receiver operating characteristics (ROCs) and operating point metrics approximated to the maximum sum of sensitivity and specificity (Youden statistics).

RESULTS

The NRRs lose diagnostic accuracy to RRs with increasingly sensitive BCRs' RFSs for all considered pathologies. Based on our external validation data set, the AI system/NRRs' consensus mimicked the most sensitive BCRs' RFSs with areas under ROC of 0.940/0.837 (pneumothorax), 0.953/0.823 (pleural effusion), and 0.883/0.747 (lung lesions), which were comparable to experienced RRs and significantly overcomes EU-experienced NRRs' diagnostic performance. For consolidation detection, the AI system performed on the NRRs' consensus level (and overcomes each individual NRR) with an area under ROC of 0.847 referenced to the BCRs' most sensitive RFS.

CONCLUSIONS

Our AI system matched RRs' performance, meanwhile significantly outperformed NRRs' diagnostic accuracy for most of considered CXR pathologies (pneumothorax, pleural effusion, and lung lesions) and therefore might serve as clinical decision support for NRRs.

Artificial intelligence and machine learning in emergency medicine: a narrative review

AIM

The emergence and evolution of artificial intelligence (AI) has generated increasing interest in machine learning applications for health care. Specifically, researchers are grasping the potential of machine learning solutions to enhance the quality of care in emergency medicine.

METHODS

We undertook a narrative review of published works on machine learning applications in emergency medicine and provide a synopsis of recent developments.

RESULTS

This review describes fundamental concepts of machine learning and presents clinical applications for triage, risk stratification specific to disease, medical imaging, and emergency department operations. Additionally, we consider how machine learning models could contribute to the improvement of causal inference in medicine, and to conclude, we discuss barriers to safe implementation of AI.

CONCLUSION

We intend that this review serves as an introduction to AI and machine learning in emergency medicine.

Detecting brain lesions in suspected acute ischemic stroke with CT-based synthetic MRI using generative adversarial networks

Background

Difficulties in detecting brain lesions in acute ischemic stroke (AIS) have convinced researchers to use computed tomography (CT) to scan for and magnetic resonance imaging (MRI) to search for these lesions. This work aimed to develop a generative adversarial network (GAN) model for CT-to-MR image synthesis and evaluate reader performance with synthetic MRI (syn-MRI) in detecting brain lesions in suspected patients.

Methods

Patients with primarily suspected AIS were randomly assigned to the training (n=140) or testing (n=53) set. Emergency CT and follow-up MR images in the training set were used to develop a GAN model to generate syn-MR images from the CT data in the testing set. The standard reference was the manual segmentations of follow-up MR images. Image similarity was evaluated between syn-MRI and the ground truth using a 4-grade visual rating scale, the peak signal-to-noise ratio (PSNR), and the structural similarity index measure (SSIM). Reader performance with syn-MRI and CT was evaluated and compared on a per-patient (patient detection) and per-lesion (lesion detection) basis. Paired t-tests or Wilcoxon signed-rank tests were used to compare reader performance in lesion detection between the syn-MRI and CT data.

Results

Grade 2–4 brain lesions were observed on syn-MRI in 92.5% (49/53) of the patients, while the remaining syn-MRI data showed no lesions compared to the ground truth. The GAN model exhibited a weak PSNR of 24.30 dB but a favorable SSIM of 0.857. Compared with CT, syn-MRI led to an increase in the overall sensitivity from 38% (57/150) to 82% (123/150) in patient detection and from 4% (68/1,620) to 16% (262/1,620) in lesion detection (R=0.32, corrected P<0.001), but the specificity in patient detection decreased from 67% (6/9) to 33% (3/9). An additional 75% (70/93) of patients and 15% (77/517) of lesions missed on CT were detected on syn-MRI.

Conclusions

The GAN model holds potential for generating synthetic MR images from noncontrast CT data and thus could help sensitively detect individuals among patients with suspected AIS. However, the image similarity performance of the model needs to be improved, and further expert discrimination is strongly recommended.

Machine Learning Approaches for Predicting Acute Respiratory Failure, Ventilator Dependence, and Mortality in Chronic Obstructive Pulmonary Disease

Chronic obstructive pulmonary disease (COPD) is one of the leading causes of mortality and contributes to high morbidity worldwide. Patients with COPD have a higher risk for acute respiratory failure, ventilator dependence, and mortality after hospitalization compared with the general population. Accurate and early risk detection will provide more information for early management and better decision making. This study aimed to build prediction models using patients’ characteristics, laboratory data, and comorbidities for early detection of acute respiratory failure, ventilator dependence, and mortality in patients with COPD after hospitalization. We retrospectively collected the electronic medical records of 5061 patients with COPD in three hospitals of the Chi Mei Medical Group, Taiwan. After data cleaning, we built three prediction models for acute respiratory failure, ventilator dependence, and mortality using seven machine learning algorithms. Based on the AUC value, the best model for mortality was built by the XGBoost algorithm (AUC = 0.817), the best model for acute respiratory failure was built by random forest algorithm (AUC = 0.804), while the best model for ventilator dependence was built by LightGBM algorithm (AUC = 0.809). A web service application was implemented with the best models and integrated into the existing hospital information system for physician’s trials and evaluations. Our machine learning models exhibit excellent predictive quality and can therefore provide physicians with a useful decision-making reference for the adverse prognosis of COPD patients.

The Impact of Weather and Air Pollution on Viral Infection and Disease Outcome Among Pediatric Pneumonia Patients in Chongqing, China, from 2009 to 2018: A Prospective Observational Study

BACKGROUND

For pediatric pneumonia, the meteorological and air pollution indicators have been frequently investigated for their association with viral circulation but not for their impact on disease severity.

METHODS

We performed a 10-year prospective, observational study in 1 hospital in Chongqing, China, to recruit children with pneumonia. Eight commonly seen respiratory viruses were tested. Autoregressive distributed lag (ADL) and random forest (RF) models were used to fit monthly detection rates of each virus at the population level and to predict the possibility of severe pneumonia at the individual level, respectively.

RESULTS

Between 2009 and 2018, 6611 pediatric pneumonia patients were included, and 4846 (73.3%) tested positive for at least 1 respiratory virus. The patient median age was 9 months (interquartile range, 4‒20). ADL models demonstrated a decent fitting of detection rates of R2 > 0.7 for respiratory syncytial virus, human rhinovirus, parainfluenza virus, and human metapneumovirus. Based on the RF models, the area under the curve for host-related factors alone was 0.88 (95% confidence interval [CI], .87‒.89) and 0.86 (95% CI, .85‒.88) for meteorological and air pollution indicators alone and 0.62 (95% CI, .60‒.63) for viral infections alone. The final model indicated that 9 weather and air pollution indicators were important determinants of severe pneumonia, with a relative contribution of 62.53%, which is significantly higher than respiratory viral infections (7.36%).

CONCLUSIONS

Meteorological and air pollution predictors contributed more to severe pneumonia in children than did respiratory viruses. These meteorological data could help predict times when children would be at increased risk for severe pneumonia and when interventions, such as reducing outdoor activities, may be warranted.

Artificial Intelligence in Spine Care

Artificial intelligence is an exciting and growing field in medicine to assist in the proper diagnosis of patients. Although the use of artificial intelligence in orthopedics is currently limited, its utility in other fields has been extremely valuable and could be useful in orthopedics, especially spine care. Automated systems have the ability to analyze complex patterns and images, which will allow for enhanced analysis of imaging. Although the potential impact of artificial intelligence integration into spine care is promising, there are several limitations that must be overcome. Our goal is to review current advances that machine learning has been used for in orthopedics, and discuss potential application to spine care in the clinical setting in which there is a need for the development of automated systems.

Task-sharing with artificial intelligence: a design hypothesis for an Emergency Unit in sub-Saharan Africa

In sub-Saharan Africa, there is a significant unmet need for emergency care, with a shortage of trained providers. One model to increase the number of providers is to task-share: roles traditionally filled by clinicians are shared with lay workers who have received task-specific training. Separately, there has been much recent interest in the possible implications of artificial intelligence (AI) on healthcare. This paper proposes that, by combining the task-sharing model with AI, it is possible to design an Emergency Unit (EU) that shares the tasks currently undertaken by physicians and nurses with lay providers, with the activities of lay providers guided and supervised by AI. The proposed model would free emergency care clinicians to focus on higher-acuity and complex cases while AI-supervised routine care is provided by lay providers. The paper outlines the model for such an implementation and considers the potential benefits to patient care, as well as considering the risks, costs, effect on providers, and ethical questions. The paper concludes that AI and healthcare workers can operate as a team, with significant potential to augment human resources for health in sub-Saharan Africa.

Machine Learning and Syncope Management in the ED: The Future Is Coming

In recent years, machine learning (ML) has been promisingly applied in many fields of clinical medicine, both for diagnosis and prognosis prediction. Aims of this narrative review were to summarize the basic concepts of ML applied to clinical medicine and explore its main applications in the emergency department (ED) setting, with a particular focus on syncope management. Through an extensive literature search in PubMed and Embase, we found increasing evidence suggesting that the use of ML algorithms can improve ED triage, diagnosis, and risk stratification of many diseases. However, the lacks of external validation and reliable diagnostic standards currently limit their implementation in clinical practice. Syncope represents a challenging problem for the emergency physician both because its diagnosis is not supported by specific tests and the available prognostic tools proved to be inefficient. ML algorithms have the potential to overcome these limitations and, in the future, they could support the clinician in managing syncope patients more efficiently. However, at present only few studies have addressed this issue, albeit with encouraging results.

Artificial intelligence in emergency medicine: A scoping review

INTRODUCTION

Despite the growing investment in and adoption of artificial intelligence (AI) in medicine, the applications of AI in an emergency setting remain unclear. This scoping review seeks to identify available literature regarding the applications of AI in emergency medicine.

METHODS

The scoping review was conducted according to Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines for scoping reviews using Medline-OVID, EMBASE, CINAHL, and IEEE, with a double screening and extraction process. The search included articles published until February 28, 2020. Articles were excluded if they did not self-classify as studying an AI intervention, were not relevant to the emergency department (ED), or did not report outcomes or evaluation.

RESULTS

Of the 1483 original database citations, 395 were eligible for full-text evaluation. Of these articles, a total of 150 were included in the scoping review. The majority of included studies were retrospective in nature (n = 124, 82.7%), with only 3 (2.0%) prospective controlled trials. We found 37 (24.7%) interventions aimed at improving diagnosis within the ED. Among the 150 studies, 19 (12.7%) focused on diagnostic imaging within the ED. A total of 16 (10.7%) studies were conducted in the out-of-hospital environment (eg, emergency medical services, paramedics) with the remainder occurring either in the ED or the trauma bay. Of the 24 (16%) studies that had human comparators, there were 12 (8%) studies in which AI interventions outperformed clinicians in at least 1 measured outcome.

CONCLUSION

AI-related research is rapidly increasing in emergency medicine. There are several promising AI interventions that can improve emergency care, particularly for acute radiographic imaging and prediction-based diagnoses. Higher quality evidence is needed to further assess both short- and long-term clinical outcomes.

Deployment of artificial intelligence for radiographic diagnosis of COVID-19 pneumonia in the emergency department

OBJECTIVE

The coronavirus disease 2019 pandemic has inspired new innovations in diagnosing, treating, and dispositioning patients during high census conditions with constrained resources. Our objective is to describe first experiences of physician interaction with a novel artificial intelligence (AI) algorithm designed to enhance physician abilities to identify ground-glass opacities and consolidation on chest radiographs.

METHODS

During the first wave of the pandemic, we deployed a previously developed and validated deep-learning AI algorithm for assisted interpretation of chest radiographs for use by physicians at an academic health system in Southern California. The algorithm overlays radiographs with "heat" maps that indicate pneumonia probability alongside standard chest radiographs at the point of care. Physicians were surveyed in real time regarding ease of use and impact on clinical decisionmaking.

RESULTS

Of the 5125 total visits and 1960 chest radiographs obtained in the emergency department (ED) during the study period, 1855 were analyzed by the algorithm. Among these, emergency physicians were surveyed for their experiences on 202 radiographs. Overall, 86% either strongly agreed or somewhat agreed that the intervention was easy to use in their workflow. Of the respondents, 20% reported that the algorithm impacted clinical decisionmaking.

CONCLUSIONS

To our knowledge, this is the first published literature evaluating the impact of medical imaging AI on clinical decisionmaking in the emergency department setting. Urgent deployment of a previously validated AI algorithm clinically was easy to use and was found to have an impact on clinical decision making during the predicted surge period of a global pandemic.

A Human-Algorithm Integration System for Hip Fracture Detection on Plain Radiography: System Development and Validation Study

Background

Hip fracture is the most common type of fracture in elderly individuals. Numerous deep learning (DL) algorithms for plain pelvic radiographs (PXRs) have been applied to improve the accuracy of hip fracture diagnosis. However, their efficacy is still undetermined.

Objective

The objective of this study is to develop and validate a human-algorithm integration (HAI) system to improve the accuracy of hip fracture diagnosis in a real clinical environment.

Methods

The HAI system with hip fracture detection ability was developed using a deep learning algorithm trained on trauma registry data and 3605 PXRs from August 2008 to December 2016. To compare their diagnostic performance before and after HAI system assistance using an independent testing dataset, 34 physicians were recruited. We analyzed the physicians’ accuracy, sensitivity, specificity, and agreement with the algorithm; we also performed subgroup analyses according to physician specialty and experience. Furthermore, we applied the HAI system in the emergency departments of different hospitals to validate its value in the real world.

Results

With the support of the algorithm, which achieved 91% accuracy, the diagnostic performance of physicians was significantly improved in the independent testing dataset, as was revealed by the sensitivity (physician alone, median 95%; HAI, median 99%; P<.001), specificity (physician alone, median 90%; HAI, median 95%; P<.001), accuracy (physician alone, median 90%; HAI, median 96%; P<.001), and human-algorithm agreement [physician alone κ, median 0.69 (IQR 0.63-0.74); HAI κ, median 0.80 (IQR 0.76-0.82); P<.001. With the help of the HAI system, the primary physicians showed significant improvement in their diagnostic performance to levels comparable to those of consulting physicians, and both the experienced and less-experienced physicians benefited from the HAI system. After the HAI system had been applied in 3 departments for 5 months, 587 images were examined. The sensitivity, specificity, and accuracy of the HAI system for detecting hip fractures were 97%, 95.7%, and 96.08%, respectively.

Conclusions

HAI currently impacts health care, and integrating this technology into emergency departments is feasible. The developed HAI system can enhance physicians’ hip fracture diagnostic performance.

Man vs. machine: Predicting hospital bed demand from an emergency department

Background

The recent literature reports promising results from using intelligent systems to support decision making in healthcare operations. Using these systems may lead to improved diagnostic and treatment protocols and to predict hospital bed demand. Predicting hospital bed demand in emergency department (ED) attendances could help resource allocation and reduce pressure on busy hospitals. However, there is still limited knowledge on whether intelligent systems can operate as fully autonomous, user-independent systems.

Objective

Compare the performance of a computer-based algorithm and humans in predicting hospital bed demand (admissions and discharges) based on the initial SOAP (Subjective, Objective, Assessment, Plan) records of the ED.

Methods

This was a retrospective cohort study that compared the performance of humans and machines in predicting hospital bed demand from an ED. It considered electronic medical records (EMR) of 9030 patients (230 used as a testing set, and hence evaluated both by humans and by an algorithm, and 8800 used as a training set exclusively by the algorithm) who visited the ED of a tertiary care and teaching public hospital located in Porto Alegre, Brazil between January and December 2014. The machine role was played by Support Vector Machine Classifier and the human prediction was performed by four ED physicians. Predictions were compared in terms of sensitivity, specificity, accuracy, and area under the receiver operating characteristic curve (AUROC).

Results

All graders achieved similar accuracies. The accuracy by AUROC for the testing set was 0.82 [95% confidence interval (CI) of 0.77–0.87], 0.80 (95% CI: 0.75–0.85), 0.76 (95% CI: 0.71–0.81) for novice physicians, machine, experienced physicians, respectively. Processing time per test EMR was 0.00812±0.0009 seconds. In contrast, novice physicians took on average 156.80 seconds per test EMR, while experienced physicians took on average 56.40 seconds per test EMR.

Conclusions

Our data indicated that the system could predict patient admission or discharge states with 80% accuracy, which was similar the performance of novice and experienced physicians. These results suggested that the algorithm could operate as an autonomous and independent system to complete this task.

Exploring the Role of Artificial Intelligence in an Emergency and Trauma Radiology Department

Emergency and trauma radiologists, emergency department’s physicians and nurses, researchers, departmental leaders, and health policymakers have attempted to discover efficient approaches to enhance the provision of quality patient care. There are increasing expectations for radiology practices to deliver a dedicated emergency radiology service providing 24/7/365 on-site attending radiologist coverage. Emergency radiologists (ERs) are pressed to meet the demand of increased imaging volume, provide accurate reports, maintain a lower proportion of discrepancy rate, and with a rapid report turnaround time of finalized reports. Thus, rendering the radiologists overburdened. The demand for an increased efficiency in providing quality care to acute patients has led to the emergence of artificial intelligence (AI) in the field. AI can be used to assist emergency and trauma radiologists deal with the ever-increasing imaging volume and workload, as AI methods have typically demonstrated a variety of applications in medical image analysis and interpretation, albeit most programs are in a training or validation phase. This article aims to offer an evidence-based discourse about the evolving role of artificial intelligence in assisting the imaging pathway in an emergency and trauma radiology department. We hope to generate a multidisciplinary discourse that addresses the technical processes, the challenges in the labour-intensive process of training, validation and testing of an algorithm, the need for emphasis on ethics, and how an emergency radiologist’s role is pivotal in the execution of AI-guided systems within the context of an emergency and trauma radiology department. This exploratory narrative serves the present-day health leadership’s information needs by proposing an AI supported and radiologist centered framework depicting the work flow within a department. It is suspected that the use of such a framework, if efficacious, could provide considerable benefits for patient safety and quality of care provided. Additionally, alleviating radiologist burnout and decreasing healthcare costs over time.

Predicting patient outcomes in psychiatric hospitals with routine data: a machine learning approach

BACKGROUND

A common problem in machine learning applications is availability of data at the point of decision making. The aim of the present study was to use routine data readily available at admission to predict aspects relevant to the organization of psychiatric hospital care. A further aim was to compare the results of a machine learning approach with those obtained through a traditional method and those obtained through a naive baseline classifier.

METHODS

The study included consecutively discharged patients between 1st of January 2017 and 31st of December 2018 from nine psychiatric hospitals in Hesse, Germany. We compared the predictive performance achieved by stochastic gradient boosting (GBM) with multiple logistic regression and a naive baseline classifier. We tested the performance of our final models on unseen patients from another calendar year and from different hospitals.

RESULTS

The study included 45,388 inpatient episodes. The models' performance, as measured by the area under the Receiver Operating Characteristic curve, varied strongly between the predicted outcomes, with relatively high performance in the prediction of coercive treatment (area under the curve: 0.83) and 1:1 observations (0.80) and relatively poor performance in the prediction of short length of stay (0.69) and non-response to treatment (0.65). The GBM performed slightly better than logistic regression. Both approaches were substantially better than a naive prediction based solely on basic diagnostic grouping.

CONCLUSION

The present study has shown that administrative routine data can be used to predict aspects relevant to the organisation of psychiatric hospital care. Future research should investigate the predictive performance that is necessary to provide effective assistance in clinical practice for the benefit of both staff and patients.

Machine learning-based prediction of response to growth hormone treatment in Turner syndrome: the LG Growth Study

Background Growth hormone (GH) treatment has become a common practice in Turner syndrome (TS). However, there are only a few studies on the response to GH treatment in TS. The aim of this study is to predict the responsiveness to GH treatment and to suggest a prediction model of height outcome in TS. Methods The clinical parameters of 105 TS patients registered in the LG Growth Study (LGS) were retrospectively reviewed. The prognostic factors for the good responders were identified, and the prediction of height response was investigated by the random forest (RF) method, and also, multiple regression models were applied. Results In the RF method, the most important predictive variable for the increment of height standard deviation score (SDS) during the first year of GH treatment was chronologic age (CA) at start of GH treatment. The RF method also showed that the increment of height SDS during the first year was the most important predictor in the increment of height SDS after 3 years of treatment. In a prediction model by multiple regression, younger CA was the significant predictor of height SDS gain during the first year (32.4% of the variability). After 3 years of treatment, mid-parental height (MPH) and the increment of height SDS during the first year were identified as significant predictors (76.6% of the variability). Conclusions Both the machine learning approach and the multiple regression model revealed that younger CA at the start of GH treatment was the most important factor related to height response in patients with TS.

Using machine-learning risk prediction models to triage the acuity of undifferentiated patients entering the emergency care system: a systematic review

BACKGROUND

The primary objective of this review is to assess the accuracy of machine learning methods in their application of triaging the acuity of patients presenting in the Emergency Care System (ECS). The population are patients that have contacted the ambulance service or turned up at the Emergency Department. The index test is a machine-learning algorithm that aims to stratify the acuity of incoming patients at initial triage. This is in comparison to either an existing decision support tool, clinical opinion or in the absence of these, no comparator. The outcome of this review is the calibration, discrimination and classification statistics.

METHODS

Only derivation studies (with or without internal validation) were included. MEDLINE, CINAHL, PubMed and the grey literature were searched on the 14th December 2019. Risk of bias was assessed using the PROBAST tool and data was extracted using the CHARMS checklist. Discrimination (C-statistic) was a commonly reported model performance measure and therefore these statistics were represented as a range within each machine learning method. The majority of studies had poorly reported outcomes and thus a narrative synthesis of results was performed.

RESULTS

There was a total of 92 models (from 25 studies) included in the review. There were two main triage outcomes: hospitalisation (56 models), and critical care need (25 models). For hospitalisation, neural networks and tree-based methods both had a median C-statistic of 0.81 (IQR 0.80-0.84, 0.79-0.82). Logistic regression had a median C-statistic of 0.80 (0.74-0.83). For critical care need, neural networks had a median C-statistic of 0.89 (0.86-0.91), tree based 0.85 (0.84-0.88), and logistic regression 0.83 (0.79-0.84).

CONCLUSIONS

Machine-learning methods appear accurate in triaging undifferentiated patients entering the Emergency Care System. There was no clear benefit of using one technique over another; however, models derived by logistic regression were more transparent in reporting model performance. Future studies should adhere to reporting guidelines and use these at the protocol design stage.

REGISTRATION AND FUNDING

This systematic review is registered on the International prospective register of systematic reviews (PROSPERO) and can be accessed online at the following URL: https://www.crd.york.ac.uk/PROSPERO/display_record.php?ID=CRD42020168696This study was funded by the NIHR as part of a Clinical Doctoral Research Fellowship.

Machine Learning-Based Prediction Models for 30-Day Readmission after Hospitalization for Chronic Obstructive Pulmonary Disease

While machine learning approaches can enhance prediction ability, little is known about their ability to predict 30-day readmission after hospitalization for Chronic Obstructive Pulmonary Disease (COPD). We identified patients aged ≥40 years with unplanned hospitalization due to COPD in the Diagnosis Procedure Combination database, an administrative claims database in Japan, from 2011 through 2016 (index hospitalizations). COPD was defined by ICD-10-CM diagnostic codes, according to Centers for Medicare and Medicaid Services (CMS) readmission measures. The primary outcome was any readmission within 30 days after index hospitalization. In the training set (randomly-selected 70% of sample), patient characteristics and inpatient care data were used as predictors to derive a conventional logistic regression model and two machine learning models (lasso regression and deep neural network). In the test set (remaining 30% of sample), the prediction performances of the machine learning models were examined by comparison with the reference model based on CMS readmission measures. Among 44,929 index hospitalizations for COPD, 3413 (7%) were readmitted within 30 days after discharge. The reference model had the lowest discrimination ability (C-statistic: 0.57 [95% confidence interval (CI) 0.56-0.59]). The two machine learning models had moderate, significantly higher discrimination ability (C-statistic: lasso regression, 0.61 [95% CI 0.59-0.61], p = 0.004; deep neural network, 0.61 [95% CI 0.59-0.63], p = 0.007). Tube feeding duration, blood transfusion, thoracentesis use, and male sex were important predictors. In this study using nationwide administrative data in Japan, machine learning models improved the prediction of 30-day readmission after COPD hospitalization compared with a conventional model.

Urinary Stone Detection on CT Images Using Deep Convolutional Neural Networks: Evaluation of Model Performance and Generalization

Purpose

To investigate the diagnostic accuracy of cascading convolutional neural network (CNN) for urinary stone detection on unenhanced CT images and to evaluate the performance of pretrained models enriched with labeled CT images across different scanners.

Materials and Methods

This HIPAA-compliant, institutional review board-approved, retrospective clinical study used unenhanced abdominopelvic CT scans from 535 adults suspected of having urolithiasis. The scans were obtained on two scanners (scanner 1 [hereafter S1] and scanner 2 [hereafter S2]). A radiologist reviewed clinical reports and labeled cases for determination of reference standard. Stones were present on 279 (S1, 131; S2, 148) and absent on 256 (S1, 158; S2, 98) scans. One hundred scans (50 from each scanner) were randomly reserved as the test dataset, and the rest were used for developing a cascade of two CNNs: The first CNN identified the extent of the urinary tract, and the second CNN detected presence of stone. Nine variations of models were developed through the combination of different training data sources (S1, S2, or both [hereafter SB]) with (ImageNet, GrayNet) and without (Random) pretrained CNNs. First, models were compared for generalizability at the section level. Second, models were assessed by using area under the receiver operating characteristic curve (AUC) and accuracy at the patient level with test dataset from both scanners (n = 100).

Results

The GrayNet-pretrained model showed higher classifier exactness than did ImageNet-pretrained or Random-initialized models when tested by using data from the same or different scanners at section level. At the patient level, the AUC for stone detection was 0.92-0.95, depending on the model. Accuracy of GrayNet-SB (95%) was higher than that of ImageNet-SB (91%) and Random-SB (88%). For stones larger than 4 mm, all models showed similar performance (false-negative results: two of 34). For stones smaller than 4 mm, the number of false-negative results for GrayNet-SB, ImageNet-SB, and Random-SB were one of 16, three of 16, and five of 16, respectively. GrayNet-SB identified stones in all 22 test cases that had obstructive uropathy.

Conclusion

A cascading model of CNNs can detect urinary tract stones on unenhanced CT scans with a high accuracy (AUC, 0.954). Performance and generalization of CNNs across scanners can be enhanced by using transfer learning with datasets enriched with labeled medical images.© RSNA, 2019Supplemental material is available for this article. : An earlier incorrect version appeared online. This article was corrected on August 6, 2019.

Machine Learning-Based Prediction of Clinical Outcomes for Children During Emergency Department Triage

IMPORTANCE

While machine learning approaches may enhance prediction ability, little is known about their utility in emergency department (ED) triage.

OBJECTIVES

To examine the performance of machine learning approaches to predict clinical outcomes and disposition in children in the ED and to compare their performance with conventional triage approaches.

DESIGN, SETTING, AND PARTICIPANTS

Prognostic study of ED data from the National Hospital Ambulatory Medical Care Survey from January 1, 2007, through December 31, 2015. A nationally representative sample of 52 037 children aged 18 years or younger who presented to the ED were included. Data analysis was performed in August 2018.

MAIN OUTCOMES AND MEASURES

The outcomes were critical care (admission to an intensive care unit and/or in-hospital death) and hospitalization (direct hospital admission or transfer). In the training set (70% random sample), using routinely available triage data as predictors (eg, demographic characteristics and vital signs), we derived 4 machine learning-based models: lasso regression, random forest, gradient-boosted decision tree, and deep neural network. In the test set (the remaining 30% of the sample), we measured the models' prediction performance by computing C statistics, prospective prediction results, and decision curves. These machine learning models were built for each outcome and compared with the reference model using the conventional triage classification information.

RESULTS

Of 52 037 eligible ED visits by children (median [interquartile range] age, 6 [2-14] years; 24 929 [48.0%] female), 163 (0.3%) had the critical care outcome and 2352 (4.5%) had the hospitalization outcome. For the critical care prediction, all machine learning approaches had higher discriminative ability compared with the reference model, although the difference was not statistically significant (eg, C statistics of 0.85 [95% CI, 0.78-0.92] for the deep neural network vs 0.78 [95% CI, 0.71-0.85] for the reference; P = .16), and lower number of undertriaged critically ill children in the conventional triage levels 3 to 5 (urgent to nonurgent). For the hospitalization prediction, all machine learning approaches had significantly higher discrimination ability (eg, C statistic, 0.80 [95% CI, 0.78-0.81] for the deep neural network vs 0.73 [95% CI, 0.71-0.75] for the reference; P < .001) and fewer overtriaged children who did not require inpatient management in the conventional triage levels 1 to 3 (immediate to urgent). The decision curve analysis demonstrated a greater net benefit of machine learning models over ranges of clinical thresholds.

CONCLUSIONS AND RELEVANCE

Machine learning-based triage had better discrimination ability to predict clinical outcomes and disposition, with reduction in undertriaging critically ill children and overtriaging children who are less ill.

Strategies for improving physician documentation in the emergency department: a systematic review

BACKGROUND

Physician chart documentation can facilitate patient care decisions, reduce treatment errors, and inform health system planning and resource allocation activities. Although accurate and complete patient chart data supports quality and continuity of patient care, physician documentation often varies in terms of timeliness, legibility, clarity and completeness. While many educational and other approaches have been implemented in hospital settings, the extent to which these interventions can improve the quality of documentation in emergency departments (EDs) is unknown.

METHODS

We conducted a systematic review to assess the effectiveness of approaches to improve ED physician documentation. Peer reviewed electronic databases, grey literature sources, and reference lists of included studies were searched to March 2015. Studies were included if they reported on outcomes associated with interventions designed to enhance the quality of physician documentation.

RESULTS

Nineteen studies were identified that report on the effectiveness of interventions to improve physician documentation in EDs. Interventions included audit/feedback, dictation, education, facilitation, reminders, templates, and multi-interventions. While ten studies found that audit/feedback, dictation, pharmacist facilitation, reminders, templates, and multi-pronged approaches did improve the quality of physician documentation across multiple outcome measures, the remaining nine studies reported mixed results.

CONCLUSIONS

Promising approaches to improving physician documentation in emergency department settings include audit/feedback, reminders, templates, and multi-pronged education interventions. Future research should focus on exploring the impact of implementing these interventions in EDs with and without emergency medical record systems (EMRs), and investigating the potential of emerging technologies, including EMR-based machine-learning, to promote improvements in the quality of ED documentation.

Cross-sectional imaging of thoracic traumatic aortic injury

Aortic injury remains a major contributor to morbidity and mortality from acute thoracic trauma. While such injuries were once nearly uniformly fatal, the advent of cross-sectional imaging in recent years has facilitated rapid diagnosis and triage, greatly improving outcomes. In fact, cross-sectional imaging is now the diagnostic test of choice for traumatic aortic injury (TAI), specifically computed tomography angiography (CTA) in the acute setting and CTA or magnetic resonance angiography (MRA) in follow-up. In this review, we present an up-to-date discussion of acute traumatic thoracic aortic injury with a focus on optimal and emerging CT/MR techniques, imaging findings of TAI, and potential pitfalls.

Machine learning approaches for predicting disposition of asthma and COPD exacerbations in the ED

OBJECTIVE

The prediction of emergency department (ED) disposition at triage remains challenging. Machine learning approaches may enhance prediction. We compared the performance of several machine learning approaches for predicting two clinical outcomes (critical care and hospitalization) among ED patients with asthma or COPD exacerbation.

METHODS

Using the 2007-2015 National Hospital and Ambulatory Medical Care Survey (NHAMCS) ED data, we identified adults with asthma or COPD exacerbation. In the training set (70% random sample), using routinely-available triage data as predictors (e.g., demographics, arrival mode, vital signs, chief complaint, comorbidities), we derived four machine learning-based models: Lasso regression, random forest, boosting, and deep neural network. In the test set (the remaining 30% of sample), we compared their prediction ability against traditional logistic regression with Emergency Severity Index (ESI, reference model).

RESULTS

Of 3206 eligible ED visits, corresponding to weighted estimates of 13.9 million visits, 4% had critical care outcome and 26% had hospitalization outcome. For the critical care prediction, the best performing approach- boosting - achieved the highest discriminative ability (C-statistics 0.80 vs. 0.68), reclassification improvement (net reclassification improvement [NRI] 53%, P = 0.002), and sensitivity (0.79 vs. 0.53) over the reference model. For the hospitalization prediction, random forest provided the highest discriminative ability (C-statistics 0.83 vs. 0.64) reclassification improvement (NRI 92%, P < 0.001), and sensitivity (0.75 vs. 0.33). Results were generally consistent across the asthma and COPD subgroups.

CONCLUSIONS

Based on nationally-representative ED data, machine learning approaches improved the ability to predict disposition of patients with asthma or COPD exacerbation.