Integrating and Adopting AI in the Radiology Workflow: A Primer for Standards and Integrating the Healthcare Enterprise (IHE) Profiles.

The deployment of artificial intelligence (AI) solutions in radiology practice creates new demands on existing imaging workflow. Accommodating custom integrations creates a substantial operational and maintenance burden. These custom integrations also increase the likelihood of unanticipated problems. Standards-based interoperability facilitates AI integration with systems from different vendors into a single environment by enabling seamless exchange between information systems in the radiology workflow. Integrating the Healthcare Enterprise (IHE) is an initiative to improve how computer systems share information across health care domains, including radiology. IHE integrates existing standards-such as Digital Imaging and Communications in Medicine, Health Level Seven, and health care lexicons and ontologies (ie, LOINC, RadLex, SNOMED Clinical Terms)-by mapping data elements from one standard to another. IHE Radiology manages profiles (standards-based implementation guides) for departmental workflow and information sharing across care sites, including profiles for scaling AI processing traffic and integrating AI results. This review focuses on the need for standards-based interoperability to scale AI integration in radiology, including a brief review of recent IHE profiles that provide a framework for AI integration. This review also discusses challenges and additional considerations for AI integration, including technical, clinical, and policy perspectives.

From Bench to Bedside With Large Language Models: AJR Expert Panel Narrative Review.

Large language models (LLMs) hold immense potential to revolutionize radiology. However, their integration into practice requires careful consideration. Artificial intelligence (AI) chatbots and general-purpose LLMs have potential pitfalls related to privacy, transparency, and accuracy, limiting their current clinical readiness. Thus, LLM-based tools must be optimized for radiology practice to overcome these limitations. While research and validation for radiology applications remain in their infancy, commercial products incorporating LLMs are becoming available alongside promises of transforming practice. To help radiologists navigate this landscape, this AJR Expert Panel Narrative Review provides a multidimensional perspective on LLMs, encompassing considerations from bench (development and optimization) to bedside (use in practice). At present, LLMs are not autonomous entities that can replace expert decision-making, and radiologists remain responsible for the content of their reports. Patient-facing tools, particularly medical AI chatbots, require additional guardrails to ensure safety and prevent misuse. Still, if responsibly implemented, LLMs are well-positioned to transform efficiency and quality in radiology. Radiologists must be well-informed and proactively involved in guiding the implementation of LLMs in practice to mitigate risks and maximize benefits to patient care.

Environmental Sustainability and AI in Radiology: A Double-Edged Sword.

According to the World Health Organization, climate change is the single biggest health threat facing humanity. The global health care system, including medical imaging, must manage the health effects of climate change while at the same time addressing the large amount of greenhouse gas (GHG) emissions generated in the delivery of care. Data centers and computational efforts are increasingly large contributors to GHG emissions in radiology. This is due to the explosive increase in big data and artificial intelligence (AI) applications that have resulted in large energy requirements for developing and deploying AI models. However, AI also has the potential to improve environmental sustainability in medical imaging. For example, use of AI can shorten MRI scan times with accelerated acquisition times, improve the scheduling efficiency of scanners, and optimize the use of decision-support tools to reduce low-value imaging. The purpose of this Radiology in Focus article is to discuss this duality at the intersection of environmental sustainability and AI in radiology. Further discussed are strategies and opportunities to decrease AI-related emissions and to leverage AI to improve sustainability in radiology, with a focus on health equity. Co-benefits of these strategies are explored, including lower cost and improved patient outcomes. Finally, knowledge gaps and areas for future research are highlighted.

Value Creation Through Artificial Intelligence and Cardiovascular Imaging: A Scientific Statement From the American Heart Association.

Multiple applications for machine learning and artificial intelligence (AI) in cardiovascular imaging are being proposed and developed. However, the processes involved in implementing AI in cardiovascular imaging are highly diverse, varying by imaging modality, patient subtype, features to be extracted and analyzed, and clinical application. This article establishes a framework that defines value from an organizational perspective, followed by value chain analysis to identify the activities in which AI might produce the greatest incremental value creation. The various perspectives that should be considered are highlighted, including clinicians, imagers, hospitals, patients, and payers. Integrating the perspectives of all health care stakeholders is critical for creating value and ensuring the successful deployment of AI tools in a real-world setting. Different AI tools are summarized, along with the unique aspects of AI applications to various cardiac imaging modalities, including cardiac computed tomography, magnetic resonance imaging, and positron emission tomography. AI is applicable and has the potential to add value to cardiovascular imaging at every step along the patient journey, from selecting the more appropriate test to optimizing image acquisition and analysis, interpreting the results for classification and diagnosis, and predicting the risk for major adverse cardiac events.

Efficient healthcare with large language models: optimizing clinical workflow and enhancing patient care.

PURPOSE: This article explores the potential of large language models (LLMs) to automate administrative tasks in healthcare, alleviating the burden on clinicians caused by electronic medical records. POTENTIAL: LLMs offer opportunities in clinical documentation, prior authorization, patient education, and access to care. They can personalize patient scheduling, improve documentation accuracy, streamline insurance prior authorization, increase patient engagement, and address barriers to healthcare access. CAUTION: However, integrating LLMs requires careful attention to security and privacy concerns, protecting patient data, and complying with regulations like the Health Insurance Portability and Accountability Act (HIPAA). It is crucial to acknowledge that LLMs should supplement, not replace, the human connection and care provided by healthcare professionals. CONCLUSION: By prudently utilizing LLMs alongside human expertise, healthcare organizations can improve patient care and outcomes. Implementation should be approached with caution and consideration to ensure the safe and effective use of LLMs in the clinical setting.

A randomized trial of mailed outreach with behavioral economic interventions to improve liver cancer surveillance.

BACKGROUND: Surveillance rates for HCC remain limited in patients with cirrhosis. We evaluated whether opt-out mailed outreach increased uptake with or without a $20 unconditional incentive. METHODS: This was a pragmatic randomized controlled trial in an urban academic health system including adult patients with cirrhosis or advanced fibrosis, at least 1 visit to a specialty practice in the past 2 years and no surveillance in the last 7 months. Patients were randomized in a 1:2:2 ratio to (1) usual care, (2) a mailed letter with a signed order for an ultrasound, or (3) a mailed letter with an order and a $20 unconditional incentive. The main outcome was the proportion with completion of ultrasound within 6 months. RESULTS: Among the 562 patients included, the mean age was 62.1 (SD 11.1); 56.8% were male, 51.1% had Medicare, and 40.6% were Black. At 6 months, 27.6% (95% CI: 19.5-35.7) completed ultrasound in the Usual care arm, 54.5% (95% CI: 47.9-61.0) in the Letter + Order arm, and 54.1% (95% CI: 47.5-60.6) in the Letter + Order + Incentive arm. There was a significant increase in the Letter + Order arm compared to Usual care (absolute difference of 26.9%; 95% CI: 16.5-37.3; p<0.001), but no significant increase in the Letter + Order + Incentive arm compared to Letter + Order (absolute difference of -0.4; 95% CI: -9.7 to 8.8; p=0.93). CONCLUSIONS: There was an increase in HCC surveillance from mailed outreach with opt-out framing and a signed order slip, but no increase in response to the financial incentive.

Quality Improvement Report: Design and Implementation of a Radiology E-Consult Service.

Electronic consultations (e-consults) mediated through an electronic health record system or web-based platform allow synchronous or asynchronous physician-to-physician communication. E-consults have been explored in various clinical specialties, but relatively few instances in the literature describe e-consults to connect health care providers directly with radiologists.The authors outline how a radiology department can implement an e-consult service and review the development of such a service in a large academic health system. They describe the logistics, workflow, turnaround time expectations, stakeholder management, and pilot implementation and highlight challenges and lessons learned.

Exploring the Clinical Translation of Generative Models Like ChatGPT: Promise and Pitfalls in Radiology, From Patients to Population Health.

Generative artificial intelligence (AI) tools such as GPT-4, and the chatbot interface ChatGPT, show promise for a variety of applications in radiology and health care. However, like other AI tools, ChatGPT has limitations and potential pitfalls that must be considered before adopting it for teaching, clinical practice, and beyond. We summarize five major emerging use cases for ChatGPT and generative AI in radiology across the levels of increasing data complexity, along with pitfalls associated with each. As the use of AI in health care continues to grow, it is crucial for radiologists (and all physicians) to stay informed and ensure the safe translation of these new technologies.

Management of spontaneous coronary artery dissection: Trends over time.

BACKGROUND: Spontaneous coronary artery dissection (SCAD) is an increasingly recognized cause of acute coronary syndrome. Guidance regarding the optimal management of patients with SCAD has been published over the past 10 years, but the impact on clinical practice has not been evaluated. The present study aims to examine if approaches to invasive management, medical therapy, and vascular imaging have changed over time. METHODS: This is a retrospective cohort study of 157 patients treated for SCAD between 2005 and 2019 at an academic health system in Philadelphia, Pennsylvania. We aimed to examine change in management over time, including rates of coronary revascularization, discharge medications, and vascular imaging. RESULTS: Conservative management of SCAD increased over time from 35% before 2013 to 89% in 2019, p < 0.001. Revascularization was associated with younger age, pregnancy-associated SCAD, and lesions of the left main artery, left anterior descending artery, and multiple vessels, p < 0.05 for all. Partial imaging for extracoronary vascular abnormalities ranged from 33% before 2013 to 71% in 2018, p = 0.146. The rate of comprehensive vascular imaging (cross-sectional head to pelvis imaging) remained low in all time categories (10-18%) and did not change over time. Patients who underwent comprehensive imaging were more likely to be diagnosed with fibromuscular dysplasia (FMD) compared to those with partial imaging (63% vs 15%, p < 0.001). CONCLUSION: Management of spontaneous coronary artery dissection has changed over time. More patients are being managed conservatively and undergo screening for extracoronary vascular abnormalities such as FMD. Future efforts should focus on improving rates of comprehensive vascular screening.

Improved Fine-Tuning of In-Domain Transformer Model for Inferring COVID-19 Presence in Multi-Institutional Radiology Reports.

Building a document-level classifier for COVID-19 on radiology reports could help assist providers in their daily clinical routine, as well as create large numbers of labels for computer vision models. We have developed such a classifier by fine-tuning a BERT-like model initialized from RadBERT, its continuous pre-training on radiology reports that can be used on all radiology-related tasks. RadBERT outperforms all biomedical pre-trainings on this COVID-19 task (P<0.01) and helps our fine-tuned model achieve an 88.9 macro-averaged F1-score, when evaluated on both X-ray and CT reports. To build this model, we rely on a multi-institutional dataset re-sampled and enriched with concurrent lung diseases, helping the model to resist to distribution shifts. In addition, we explore a variety of fine-tuning and hyperparameter optimization techniques that accelerate fine-tuning convergence, stabilize performance, and improve accuracy, especially when data or computational resources are limited. Finally, we provide a set of visualization tools and explainability methods to better understand the performance of the model, and support its practical use in the clinical setting. Our approach offers a ready-to-use COVID-19 classifier and can be applied similarly to other radiology report classification tasks.

Automated deidentification of radiology reports combining transformer and "hide in plain sight" rule-based methods.

OBJECTIVE: To develop an automated deidentification pipeline for radiology reports that detect protected health information (PHI) entities and replaces them with realistic surrogates "hiding in plain sight." MATERIALS AND METHODS: In this retrospective study, 999 chest X-ray and CT reports collected between November 2019 and November 2020 were annotated for PHI at the token level and combined with 3001 X-rays and 2193 medical notes previously labeled, forming a large multi-institutional and cross-domain dataset of 6193 documents. Two radiology test sets, from a known and a new institution, as well as i2b2 2006 and 2014 test sets, served as an evaluation set to estimate model performance and to compare it with previously released deidentification tools. Several PHI detection models were developed based on different training datasets, fine-tuning approaches and data augmentation techniques, and a synthetic PHI generation algorithm. These models were compared using metrics such as precision, recall and F1 score, as well as paired samples Wilcoxon tests. RESULTS: Our best PHI detection model achieves 97.9 F1 score on radiology reports from a known institution, 99.6 from a new institution, 99.5 on i2b2 2006, and 98.9 on i2b2 2014. On reports from a known institution, it achieves 99.1 recall of detecting the core of each PHI span. DISCUSSION: Our model outperforms all deidentifiers it was compared to on all test sets as well as human labelers on i2b2 2014 data. It enables accurate and automatic deidentification of radiology reports. CONCLUSIONS: A transformer-based deidentification pipeline can achieve state-of-the-art performance for deidentifying radiology reports and other medical documents.

Imaging Informatics Fellowship Curriculum: Building Consensus on the Most Critical Topics and the Future of the Informatics Fellowship.

The existing fellowship imaging informatics curriculum, established in 2004, has not undergone formal revision since its inception and inaccurately reflects present-day radiology infrastructure. It insufficiently equips trainees for today's informatics challenges as current practices require an understanding of advanced informatics processes and more complex system integration. We sought to address this issue by surveying imaging informatics fellowship program directors across the country to determine the components and cutline for essential topics in a standardized imaging informatics curriculum, the consensus on essential versus supplementary knowledge, and the factors individual programs may use to determine if a newly developed topic is an essential topic. We further identified typical program structural elements and sought fellowship director consensus on offering official graduate trainee certification to imaging informatics fellows. Here, we aim to provide an imaging informatics fellowship director consensus on topics considered essential while still providing a framework for informatics fellowship programs to customize their individual curricula.

Predicting Patient Demographics From Chest Radiographs With Deep Learning.

BACKGROUND: Deep learning models are increasingly informing medical decision making, for instance, in the detection of acute intracranial hemorrhage and pulmonary embolism. However, many models are trained on medical image databases that poorly represent the diversity of the patients they serve. In turn, many artificial intelligence models may not perform as well on assisting providers with important medical decisions for underrepresented populations. PURPOSE: Assessment of the ability of deep learning models to classify the self-reported gender, age, self-reported ethnicity, and insurance status of an individual patient from a given chest radiograph. METHODS: Models were trained and tested with 55,174 radiographs in the MIMIC Chest X-ray (MIMIC-CXR) database. External validation data came from two separate databases, one from CheXpert and another from a multihospital urban health care system after institutional review board approval. Macro-averaged area under the curve (AUC) values were used to evaluate performance of models. Code used for this study is open-source and available at https://github.com/ai-bias/cxr-bias, and pixelstopatients.com/models/demographics. RESULTS: Accuracy of models to predict gender was nearly perfect, with 0.999 (95% confidence interval: 0.99-0.99) AUC on held-out test data and 0.994 (0.99-0.99) and 0.997 (0.99-0.99) on external validation data. There was high accuracy to predict age and ethnicity, ranging from 0.854 (0.80-0.91) to 0.911 (0.88-0.94) AUC, and moderate accuracy to predict insurance status, with AUC ranging from 0.705 (0.60-0.81) on held-out test data to 0.675 (0.54-0.79) on external validation data. CONCLUSIONS: Deep learning models can predict the age, self-reported gender, self-reported ethnicity, and insurance status of a patient from a chest radiograph. Visualization techniques are useful to ensure deep learning models function as intended and to demonstrate anatomical regions of interest. These models can be used to ensure that training data are diverse, thereby ensuring artificial intelligence models that work on diverse populations.

Ensemble Approaches to Recognize Protected Health Information in Radiology Reports.

Natural language processing (NLP) techniques for electronic health records have shown great potential to improve the quality of medical care. The text of radiology reports frequently constitutes a large fraction of EHR data, and can provide valuable information about patients' diagnoses, medical history, and imaging findings. The lack of a major public repository for radiological reports severely limits the development, testing, and application of new NLP tools. De-identification of protected health information (PHI) presents a major challenge to building such repositories, as many automated tools for de-identification were trained or designed for clinical notes and do not perform sufficiently well to build a public database of radiology reports. We developed and evaluated six ensemble models based on three publically available de-identification tools: MIT de-id, NeuroNER, and Philter. A set of 1023 reports was set aside as the testing partition. Two individuals with medical training annotated the test set for PHI; differences were resolved by consensus. Ensemble methods included simple voting schemes (1-Vote, 2-Votes, and 3-Votes), a decision tree, a naïve Bayesian classifier, and Adaboost boosting. The 1-Vote ensemble achieved recall of 998 / 1043 (95.7%); the 3-Votes ensemble had precision of 1035 / 1043 (99.2%). F1 scores were: 93.4% for the decision tree, 71.2% for the naïve Bayesian classifier, and 87.5% for the boosting method. Basic voting algorithms and machine learning classifiers incorporating the predictions of multiple tools can outperform each tool acting alone in de-identifying radiology reports. Ensemble methods hold substantial potential to improve automated de-identification tools for radiology reports to make such reports more available for research use to improve patient care and outcomes.

Development and Implementation of a Multisite Registry Using Structured Templates for Actionable Findings in the Kidney.

PURPOSE: The aim of this study was to scale structured report templates categorizing actionable renal findings across health systems and create a centralized registry of patient and report data. METHODS: In January 2017, three academic radiology departments agreed to prospectively include identical structured templates categorizing the malignant likelihood of renal findings in ≥90% of all adult ultrasound, MRI, and CT reports, a new approach for two sites. Between November 20, 2017, and September 30, 2019, deidentified HL7 report data were transmitted to a centralized ACR registry. An automated algorithm extracted categories. Radiologists were requested to addend reports with missing or incomplete templates after the first month. Separately, each site submitted patient sociodemographic and clinical data 12 months before and at least 3 months after enrollment. RESULTS: A total of 164,982 eligible radiology reports were transmitted to the registry; 4,159 (2.5%) were excluded because of missing categories or radiologist names. The final cohort included 160,823 examinations on 102,619 unique patients. Mean template use before and after addendum requests was 99.3% and 99.9% at SITE1, 86.5% and 94.6% at SITE2, and 91.4% and 96.0% at SITE3. Matching patient sociodemographic and clinical data were obtained on 96.9% of reports from SITE1, 94.2% from SITE2, and 96.0% from SITE3. Regulatory, cultural, and technology barriers to the creation of a multisite registry were identified. CONCLUSIONS: Barriers to the adoption of unified structured report templates for actionable kidney findings can be addressed. Deidentified report and patient data can be securely transmitted to an external registry. These data can facilitate the collection of diverse evidence-based population imaging outcomes.

Economic impact of selective use of contrast for routine follow-up MRI of patients with multiple sclerosis.

BACKGROUND AND PURPOSE: Imaging and autopsy studies show intracranial gadolinium deposition in patients who have undergone serial contrast-enhanced MRIs. This observation has raised concerns when using contrast administration in patients who receive frequent MRIs. To address this, we implemented a contrast-conditional protocol wherein gadolinium is administered only for multiple sclerosis (MS) patients with imaging evidence of new disease activity on precontrast imaging. In this study, we explore the economic impact of our new MRI protocol. METHODS: We compared scanner time and Medicare reimbursement using our contrast-conditional methodology versus that of prior protocols where all patients received gadolinium. RESULTS: For 422 patients over 4 months, the contrast-conditional protocol amounted to 60% decrease in contrast injection and savings of approximately 20% of MRI scanner time. If the extra scanner time was used for performing MS follow-up MRIs in additional patients, the contrast-conditional protocol would amount to net revenue loss of $21,707 (∼3.7%). CONCLUSIONS: Implementation of a new protocol to limit contrast in MS follow-up MRIs led to a minimal decrease in revenue when controlled for scanner time utilized and is outweighed by other benefits, including substantial decreased gadolinium administration, increased patient comfort, and increased availability of scanner time, which depending on type of studies performed could result in additional financial benefit.