The Veterans Health Administration (VHA) is committed to the sharing of Veteran's health information in its efforts to improve the patient-provider relationship in care delivery. The VHA has demonstrated this commitment with the initiation of MyHealtheVet (MHV) patient portal which also utilizes secure messaging between Veterans and their care teams as a way to improve communication. Clinical notes represent a key piece of patient information that could further enhance this relationship. In January 2013, the VA made Veterans' primary care provider's clinical notes available to their patients through the Blue Button feature within the MHV portal. Patient access to full text clinical notes has the potential to improve patient engagement and care. However, a recent study demonstrated that patients- especially those who are vulnerable (e.g., lower literacy, lower income)-can be perplexed by EHR notes. Inadvertently, this confusion and miscommunication may result in unintended increases in service utilization, and changes in perceptions that may disrupt patient-provider relationships. This proposal seeks to develop an innovative tool which will aid Veterans in the comprehension and effective use of their clinical notes to better their care outcomes. We will develop and evaluate NoteAid, a multi-component, intelligent natural language processing (NLP) system designed to translate medical jargon into consumer oriented concepts and provide patient-friendly links to related educational material from trusted resources. We expect that NoteAid will improve Veterans' comprehension of their EHR notes, which in turn will increase patient autonomy and self-management. No current HSR&D projects are evaluating this new innovation, and operational leaders are seeking guidance on how to further advance sharing of clinical information with Veterans.
Our Specific Aims are to:
Aim 1 : Develop a comprehensive EHR health knowledge resource-NoteKnow. It will link medical concepts (e.g., myocardial infarction) to the corresponding consumer oriented concepts (e.g., heart attack), along with definitions and high-quality educational material.
Aim 2 : Develop, implement, and assess NoteAid, a system that will decipher EHR notes and link them to NoteKnow. NoteAid will integrate innovative NLP approaches. We will assess the NoteAid system using expert walkthrough, usability testing, and task-driven cognitive evaluation.
Aim 3 : Evaluate NoteAid in a randomized comparison study. We will recruit 250 Veterans from the Worcester VA outpatient clinic. The Veterans will be randomly assigned to two groups: 1.) use of standard EHR notes; 2.) use of EHR notes with NoteAid support. The Study outcomes will be guided by Self- Determination Theory, including: 1.) perceived autonomy support of NoteAid and, 2.) the effect of NoteAid on Veteran outcomes (e.g., motivation and competence). Our integrated research team will include Veterans, physicians, a health educator, informaticians, a biostatistician, and health literacy and communication scientists. We will employ Veterans as co-investigators throughout the NoteAid study to ensure our focus on the end-user. Veterans will be engaged at multiple levels, including intervention refinement (usability tests) and creation (Veteran generated content). In both Aims 1 and 2, Veterans will drive the excellence of the NoteAid system, maximizing the potential of the system to support user comprehension in Aim 3. NoteAid will be a stand-alone and open-source tool that will be made available to national health IT organizations, healthcare providers and patients at the completion of this study. The potential impact of this system is high.
The Veterans Health Administration (VHA) is committed to the sharing health information to improve the patient-provider relationship in care delivery. The VHA is committed to MyHealtheVet (MHV), a patient portal which utilizes secure messaging between Veterans and their care teams. As of January 2013, Veterans' primary care provider's clinical notes were made available through the Blue Button feature of the MHV portal. While it is theorized that patient's access their physician's clinical notes may lead to empowerment, individuals are often confused by this documentation given the hard-to-comprehend medical abbreviations and jargon. This proposal seeks to develop an innovative system called NoteAid which links medical abbreviations and jargon to consumer-oriented terms, definitions, and educational materials in effort to improve the patient's comprehension. NoteAid will aid Veterans in their understanding of their own clinical notes, so that they can assist in their own care management while improving their health care outcomes.
|Lalor, John P; Wu, Hao; Chen, Li et al. (2018) ComprehENotes, an Instrument to Assess Patient Reading Comprehension of Electronic Health Record Notes: Development and Validation. J Med Internet Res 20:e139|
|Chen, Jinying; Druhl, Emily; Polepalli Ramesh, Balaji et al. (2018) A Natural Language Processing System That Links Medical Terms in Electronic Health Record Notes to Lay Definitions: System Development Using Physician Reviews. J Med Internet Res 20:e26|
|Li, Fei; Liu, Weisong; Yu, Hong (2018) Extraction of Information Related to Adverse Drug Events from Electronic Health Record Notes: Design of an End-to-End Model Based on Deep Learning. JMIR Med Inform 6:e12159|
|Zheng, Jiaping; Yu, Hong (2018) Assessing the Readability of Medical Documents: A Ranking Approach. JMIR Med Inform 6:e17|
|Chen, Jinying; Yu, Hong (2017) Unsupervised ensemble ranking of terms in electronic health record notes based on their importance to patients. J Biomed Inform 68:121-131|
|Chen, Jinying; Jagannatha, Abhyuday N; Fodeh, Samah J et al. (2017) Ranking Medical Terms to Support Expansion of Lay Language Resources for Patient Comprehension of Electronic Health Record Notes: Adapted Distant Supervision Approach. JMIR Med Inform 5:e42|
|Chen, Jinying; Zheng, Jiaping; Yu, Hong (2016) Finding Important Terms for Patients in Their Electronic Health Records: A Learning-to-Rank Approach Using Expert Annotations. JMIR Med Inform 4:e40|
|Jagannatha, Abhyuday N; Yu, Hong (2016) Bidirectional RNN for Medical Event Detection in Electronic Health Records. Proc Conf 2016:473-482|
|Zheng, Jiaping; Yu, Hong (2015) Methods for Linking EHR Notes to Education Materials. AMIA Jt Summits Transl Sci Proc 2015:209-15|
|Polepalli Ramesh, Balaji; Houston, Thomas; Brandt, Cynthia et al. (2013) Improving patients' electronic health record comprehension with NoteAid. Stud Health Technol Inform 192:714-8|