We propose the Multimodal Clinical Benchmark for Emergency Care (MC-BEC), a comprehensive benchmark for evaluating foundation models in Emergency Medicine using a dataset of 100K+ continuously monitored Emergency Department visits from 2020-2022. MC-BEC focuses on clinically relevant prediction tasks at timescales from minutes to days, including predicting patient decompensation, disposition, and emergency department (ED) revisit, and includes a standardized evaluation framework with train-test splits and evaluation metrics. The multimodal dataset includes a wide range of detailed clinical data, including triage information, prior diagnoses and medications, continuously measured vital signs, electrocardiogram and photoplethysmograph waveforms, orders placed and medications administered throughout the visit, free-text reports of imaging studies, and information on ED diagnosis, disposition, and subsequent revisits. We provide performance baselines for each prediction task to enable the evaluation of multimodal, multitask models. We believe that MC-BEC will encourage researchers to develop more effective, generalizable, and accessible foundation models for multimodal clinical data.

We propose the Multimodal Clinical Benchmark for Emergency Care (MC-BEC), a comprehensive benchmark for evaluating foundation models in Emergency Medicine using a dataset of 100K continuously monitored Emergency Department visits from 2020-2022. MC-BEC focuses on clinically relevant prediction tasks at timescales from minutes to days, including predicting patient decompensation, disposition, and emergency department (ED) revisit, and includes a standardized evaluation framework with train-test splits and evaluation metrics. The multimodal dataset includes a wide range of detailed clinical data, including triage information, prior diagnoses and medications, continuously measured vital signs, electrocardiogram and photoplethysmograph waveforms, orders placed and medications administered throughout the visit, free-text reports of imaging studies, and information on ED diagnosis, disposition, and subsequent revisits. We provide performance baselines for each prediction task to enable the evaluation of multimodal, multitask models. We believe that MC-BEC will encourage researchers to develop more effective, generalizable, and accessible foundation models for multimodal clinical data.

We propose the Multimodal Clinical Benchmark for Emergency Care (MC-BEC), a comprehensive benchmark for evaluating foundation models in Emergency Medicine using a dataset of 100K continuously monitored Emergency Department visits from 2020-2022. MC-BEC focuses on clinically relevant prediction tasks at timescales from minutes to days, including predicting patient decompensation, disposition, and emergency department (ED) revisit, and includes a standardized evaluation framework with train-test splits and evaluation metrics. The multimodal dataset includes a wide range of detailed clinical data, including triage information, prior diagnoses and medications, continuously measured vital signs, electrocardiogram and photoplethysmograph waveforms, orders placed and medications administered throughout the visit, free-text reports of imaging studies, and information on ED diagnosis, disposition, and subsequent revisits. We provide performance baselines for each prediction task to enable the evaluation of multimodal, multitask models. We believe that MC-BEC will encourage researchers to develop more effective, generalizable, and accessible foundation models for multimodal clinical data.

Emergency departments have been experiencing a significant strain for a long time, with visits only increasing. With the rise in flu, COVID-19 and RSV cases, in addition to an increase in psychiatric symptoms, emergency wait times can be agonizing. A place that is supposed to be known for its immediate access to care has instead become known for its stressful and harrowing delays. Even with the holiday season behind us – a time that is typically known for longer wait times – we're seeing a trend that these wait times are getting worse in general. For patients seeking urgent care, these delays can be excruciating, causing unnecessary anxiety and potentially worsening their health conditions.

Text summarization systems have made significant progress in recent years, but typically generate summaries in one single step. However, the one-shot summarization setting is sometimes inadequate, as the generated summary may contain hallucinations or overlook essential details related to the reader's interests. This paper addresses this limitation by proposing SummIt, an iterative text summarization framework based on large language models like ChatGPT. Our framework enables the model to refine the generated summary iteratively through self-evaluation and feedback, resembling humans' iterative process when drafting and revising summaries. Furthermore, we explore the potential benefits of integrating knowledge and topic extractors into the framework to enhance summary faithfulness and controllability. We automatically evaluate the performance of our framework on three benchmark summarization datasets. We also conduct a human evaluation to validate the effectiveness of the iterative refinements and identify a potential issue of over-correction.

Karim Karti is the former president of GE Health Imaging and the current CEO of RapidAI – a company founded more than 10 years ago by Dr. Greg Albers, one of the world's leading stroke researchers and director of the Stanford Stroke Center. For more than 20 years, most in healthcare believed doctors had less than three hours after a stroke to provide treatment. However, Dr. Albers' landmark research ultimately demonstrated that a thrombectomy (a procedure to remove blood clots) as late as 24 hours after stroke onset still benefited patients. Albers and Dr. Roland Bammer founded RapidAI to streamline the stroke workflow and get patients to treatment faster. Since then, their AI technology has been applied beyond stroke treatment, to aneurysm, pulmonary embolism and more.

Governor Northam announced that Virginians can now use COVIDCheck, a new online risk-assessment tool to check their symptoms and connect with the appropriate health care resource, including COVID-19 testing. "If you are feeling sick or think you may have been exposed to someone with COVID-19, it is important that you take action right away," said Governor Northam. "This online symptom-checking tool can help Virginians understand their personal risk for COVID-19 and get recommendations about what to do next from the safety of their homes. As we work to flatten the curve in our Commonwealth, telehealth services like this will be vital to relieving some of the strains on providers and health systems and making health care more convenient and accessible." COVIDCheck is a free, web-based, artificial intelligence-powered telehealth tool that can help individuals displaying symptoms associated with COVID-19 self-assess their risk and determine the best next steps, such as self-isolation, seeing a doctor, or seeking emergency care.