Browsing by Subject "Electronic health records (EHRs)"

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    A large language model for electronic health records
    (Springer Nature, 2022-12-26) Yang, Xi; Chen, Aokun; PourNejatian, Nima; Shin, Hoo Chang; Smith, Kaleb E.; Parisien, Christopher; Compas, Colin; Martin, Cheryl; Costa, Anthony B.; Flores, Mona G.; Zhang, Ying; Magoc, Tanja; Harle, Christopher A.; Lipori, Gloria; Mitchell, Duane A.; Hogan, William R.; Shenkman, Elizabeth A.; Bian, Jiang; Wu, Yonghui; Health Policy and Management, Richard M. Fairbanks School of Public Health
    There is an increasing interest in developing artificial intelligence (AI) systems to process and interpret electronic health records (EHRs). Natural language processing (NLP) powered by pretrained language models is the key technology for medical AI systems utilizing clinical narratives. However, there are few clinical language models, the largest of which trained in the clinical domain is comparatively small at 110 million parameters (compared with billions of parameters in the general domain). It is not clear how large clinical language models with billions of parameters can help medical AI systems utilize unstructured EHRs. In this study, we develop from scratch a large clinical language model—GatorTron—using >90 billion words of text (including >82 billion words of de-identified clinical text) and systematically evaluate it on five clinical NLP tasks including clinical concept extraction, medical relation extraction, semantic textual similarity, natural language inference (NLI), and medical question answering (MQA). We examine how (1) scaling up the number of parameters and (2) scaling up the size of the training data could benefit these NLP tasks. GatorTron models scale up the clinical language model from 110 million to 8.9 billion parameters and improve five clinical NLP tasks (e.g., 9.6% and 9.5% improvement in accuracy for NLI and MQA), which can be applied to medical AI systems to improve healthcare delivery. The GatorTron models are publicly available at: https://catalog.ngc.nvidia.com/orgs/nvidia/teams/clara/models/gatortron_og
  • Thumbnail Image
    Item
    Evolving availability and standardization of patient attributes for matching
    (Oxford University Press, 2023-10-12) Deng, Yu; Gleason, Lacey P.; Culbertson, Adam; Chen, Xiaotian; Bernstam, Elmer V.; Cullen, Theresa; Gouripeddi, Ramkiran; Harle, Christopher; Hesse, David F.; Kean, Jacob; Lee, John; Magoc, Tanja; Meeker, Daniella; Ong, Toan; Pathak, Jyotishman; Rosenman, Marc; Rusie, Laura K.; Shah, Akash J.; Shi, Lizheng; Thomas, Aaron; Trick, William E.; Grannis, Shaun; Kho, Abel; Health Policy and Management, Richard M. Fairbanks School of Public Health
    Variation in availability, format, and standardization of patient attributes across health care organizations impacts patient-matching performance. We report on the changing nature of patient-matching features available from 2010-2020 across diverse care settings. We asked 38 health care provider organizations about their current patient attribute data-collection practices. All sites collected name, date of birth (DOB), address, and phone number. Name, DOB, current address, social security number (SSN), sex, and phone number were most commonly used for cross-provider patient matching. Electronic health record queries for a subset of 20 participating sites revealed that DOB, first name, last name, city, and postal codes were highly available (>90%) across health care organizations and time. SSN declined slightly in the last years of the study period. Birth sex, gender identity, language, country full name, country abbreviation, health insurance number, ethnicity, cell phone number, email address, and weight increased over 50% from 2010 to 2020. Understanding the wide variation in available patient attributes across care settings in the United States can guide selection and standardization efforts for improved patient matching in the United States.
  • Thumbnail Image
    Item
    Progress in Healthcare: Securing a New Common Norm in Medical Technology
    (2016-04-08) Gookins, Alexandra
    In the modern age of Healthcare Technology, there are vast changes in patient records. In the 1960s, the first use of EHRs (Electronic Health Records) was implemented in the Mayo Clinic of Rochester, Minnesota. (Earl) However, EHRs continue to enhance at a rapid rate and are becoming one of the fastest growing industries worldwide. The problem that arises with keeping confidential patient information on the cloud or servers is the access to hackers looking to steal information for misuse and causing detrimental harm to patients’ privacy. Thus, HIMSS (Healthcare Information and Management Systems Society) has continued to put rules and regulations into effect across the board of EHR systems. The issue is that these security measures do not fall on to the EHR system software creators but the medical practices themselves. (Health IT) But who in these practices or hospitals are going to regulate these significant measures? Many do not know that there is a software on the market today what will handle these tedious adjustments for the safety of the businesses and patients. Software companies like HIPAA One will do just that. (HIPAA One) These small companies will work with your current EHRs in compliance with the federally regulated HIPAA laws to ensure practices and hospitals alike are providing safety of patient information by using security risk assessment tools. However, numerous users of electronic health records do not use these critical tools because there are not well known. I have observed many EHR systems, leading me to believe the importance of an EHR software that will integrate HIPAA compliant technology without a middle man such as HIPAA One; putting this responsibility on software designers instead of practices. 1. Earl, Elizabeth. Health IT & CIO Review. 16 Februrary 2015. 01 March 2016. . 2. Health IT. n.d. https://www.healthit.gov/providers-professionals/security-risk-assessment-tool. 01 March 2016. 3. HIPAA One. n.d. 05 March 2016.