NYUTron is a large language model-based system that was developed with the objective of integrating clinical workflows centered around structured and unstructured notes and placing electronic orders in real time. The development team queried electronic health records from all NYU Langone facilities to generate two types of datasets: pre-training datasets ("NYU Notes", "NYU Notes–Manhattan", "NYU Notes–Brooklyn")...

This dataset consists of AI prompts used to improve the content and quality of medical documentation in a case study at NYU Langone Health. Both prompts were used with institutional instance of GPT-4. The first prompt checks for completeness of a clinical note, ensuring that comments from the patients, an all-encompassing description of the patient, a description of the appropriate exam, and an update...

The National Center for Advancing Translational Sciences (NCATS) has systematically compiled clinical, laboratory and diagnostic data from electronic health records to support COVID-19 research efforts via the National COVID Cohort Collaborative (N3C) Data Enclave. As of August 2, 2022, the repository contains information from over 15 million patients (including 5.8 million COVID-19 positive patients)...

With an emphasis on reaching historically underrepresented populations, the All of Us Research Program recruits adults aged 18 and above across the United States to share their health data to enable new insights into human health and research on precision medicine. Participants contribute electronic health records (EHR), survey responses, biospecimens, wearable devices (biometrics), and physical measurements....

Clinical data was extracted from electronic health records from patients treated for hip fractures by the Department of Orthopedic Surgery at NYU Langone Health between October 2014 and February 2020. A total of 1,590 patients aged 55 and older were included in the retrospective review with complete records for patient's sex; body mass index; comorbidities as measured with the Charlson Comorbidity...

The National Health Service Hospital Episode Statistics (NHS HES) include over 1 billion medical records of patients who attended outpatient appointments, were seen at accident and emergency (A&E) departments, or were admitted to NHS hospitals in England. This data is collected and curated on a monthly basis and has been used for purposes such as research and service evaluation. HES consists of the...

Data was abstracted from NYU Langone Health electronic health records, the Perlmutter Cancer Center Data Hub, and the NYU Langone Health SARS-CoV-2 Data Mart for all patients treated for breast cancer at Perlmutter Cancer Center either through telemedicine or in-person between February 1, 2020 and May 1, 2020 to determine the incidence of SARS-CoV-2 infection associated with treatment with cytotoxic...

This dataset was collected for a study to replicate previous work on hippocampal physiology predictive of successful encoding using an associative memory paradigm in a surgical intracranial electroencephalography (iEEG) group and extend those investigations to a chronic ambulatory iEEG population using RNS System devices (NeuroPace, Inc.). The primary objective was to compare the hippocampal gamma...

This dataset was collected for a combined retrospective and prospective cross-sectional study to establish risk factors for infection after treatment for intracerebral hemorrhage and subarachnoid hemorrhage and to determine the impact of those infections on long-term outcomes. Data was harvested from Tisch Hospital records from January 2013 to December 2014 retrospectively and from January 2015 to...

INSIGHT Clinical Research Network is a project founded by the Patient Centered Outcomes Research Institute (PCORI) and is part of the PCORnet program. The INSIGHT longitudinal datasets bring together New York City organizations including medical schools, medical centers, research support organizations, and practice-based research networks. Over 160 million patient encounters and 365 million diagnoses...