Janelle S. Taylor
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Janelle S. Taylor has a total of 95 co-authors. Here are the top co-authors by number of shared publications:
- Nancy Vuckovic
Please send substantive, provocative, informative short essays (650 words or less) on our featured themes of “IRBs” and “the pragmatics of funding,” or on other topics of interest, to the SMA Contributing Editors Nancy Vuckovicor Janelle Taylor
28 shared publications Elizabeth K. Vig
Department of Medicine, University of Washington, Seattle
9 shared publicationsElizabeth K. Hopley
University of Washington
5 shared publicationsHelene Starks
University of Washington
5 shared publications- Ann M. O'Hare
University of Washington
4 shared publications - Elizabeth K. Vig
Division of Gerontology and Geriatric Medicine, University of Washington, Seattle, WA, USA
4 shared publications
Latest Publications
- Open Access
- 30 March 2026
- Published by JMIR Publications Inc. in JMIR Preprints
Using Natural Language Processing to Facilitate Qualitative Research: Dementia Experiences in EHR Free Text (Preprint)
BACKGROUND Electronic health records (EHRs) contain extensive unstructured free text that is difficult to incorporate into qualitative research at scale. Existing NLP approaches in health research primarily focus on structured data extraction or predictive modeling, leaving qualitative applications underdeveloped. OBJECTIVE To develop and evaluate an interpretable, rule based NLP pipeline to curate large EHR text corpora into analytically tractable sub corpora suitable for qualitative research. METHODS We applied a deterministic NLP algorithm (pyTAKES) to 161,111 free text EHR notes from 335 participants diagnosed with dementia in the Adult Changes in Thought (ACT) study. Using a concept dictionary informed by prior qualitative research and clinical expertise, we tagged notes with semantically meaningful concepts and applied filters (eg, concept density, note type, temporal proximity to diagnosis) to distill three focused sub corpora. We evaluated concept performance through manual review and assessed corpus relevance before and after filtration. RESULTS Sixty two percent of notes contained at least one concept match. Concept review demonstrated acceptable agreement between retrieved text and target phenomena. Filtering reduced the corpus by over 95% while increasing the proportion of caregiving relevant notes from 23.5% to 84.5%. Each sub corpus supported distinct qualitative research questions. CONCLUSIONS NLP methods can efficiently curate large EHR text corpora for qualitative analysis. This approach offers a reproducible and resource efficient alternative to black box machine learning models, enabling qualitative researchers to leverage EHR data at scale.
- 30 March 2026
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessUsing Natural Language Processing to Facilitate Qualitative Research: Dementia Experiences in EHR Free Text (Preprint)
BACKGROUND Electronic health records (EHRs) contain extensive unstructured free text that is difficult to incorporate into qualitative research at scale. Existing NLP approaches in health research primarily focus on structured data extraction or predictive modeling, leaving qualitative applications underdeveloped. OBJECTIVE To develop and evaluate an interpretable, rule based NLP pipeline to curate large EHR text corpora into analytically tractable sub corpora suitable for qualitative research. METHODS We applied a deterministic NLP algorithm (pyTAKES) to 161,111 free text EHR notes from 335 participants diagnosed with dementia in the Adult Changes in Thought (ACT) study. Using a concept dictionary informed by prior qualitative research and clinical expertise, we tagged notes with semantically meaningful concepts and applied filters (eg, concept density, note type, temporal proximity to diagnosis) to distill three focused sub corpora. We evaluated concept performance through manual review and assessed corpus relevance before and after filtration. RESULTS Sixty two percent of notes contained at least one concept match. Concept review demonstrated acceptable agreement between retrieved text and target phenomena. Filtering reduced the corpus by over 95% while increasing the proportion of caregiving relevant notes from 23.5% to 84.5%. Each sub corpus supported distinct qualitative research questions. CONCLUSIONS NLP methods can efficiently curate large EHR text corpora for qualitative analysis. This approach offers a reproducible and resource efficient alternative to black box machine learning models, enabling qualitative researchers to leverage EHR data at scale.
- Open Access
- 19 August 2025
- Published by Springer Nature in BioSocieties
- Vol. 21 (1) , 83-99
The nearness of the state: substitution practices at the ragged ends of life in the U.S
This essay examines two stories emerging from two different research projects, both based in Seattle, Washington (U.S.): one woman’s story of her eff
- 19 August 2025
- Published by Springer Nature in BioSocieties
- Vol. 21 (1) , 83-99
Open AccessThe nearness of the state: substitution practices at the ragged ends of life in the U.S
This essay examines two stories emerging from two different research projects, both based in Seattle, Washington (U.S.): one woman’s story of her eff
- 21 February 2025
- Published by Oxford University Press (OUP) in Academic Medicine
- Vol. 100 (5) , 541-546
Artificial Intelligence Meets Holistic Review: Promises and Pitfalls of Automating the Medical Education Admissions Process
Holistic review has been widely adopted in medical education as a means of promoting equity in the application process and diversity in the medical workforce. Artificial intelligence (AI) is a rapidly emerging technology already having an impact on the medical school and residency application process as students and faculty alike increasingly turn to AI tools to automate some steps in the preparation and evaluation of application materials. While AI may have the potential to improve the holistic admissions process by increasing efficiency and adding some measure of standardization among reviewers, the authors caution that this promise does not come without certain pitfalls. AI models may introduce new sources of bias and amplify existing ones, which, when combined with a lack of transparency regarding their use in the admissions process, may perpetuate the very inequities that holistic review seeks to minimize. The authors call for the medical education community to establish clear regulations to govern the acceptable use of AI in the admissions process and for a principled adoption of AI tools in a way that is sustainable for applicants and reviewers in the future.
- 21 February 2025
- Published by Oxford University Press (OUP) in Academic Medicine
- Vol. 100 (5) , 541-546
Artificial Intelligence Meets Holistic Review: Promises and Pitfalls of Automating the Medical Education Admissions Process
Holistic review has been widely adopted in medical education as a means of promoting equity in the application process and diversity in the medical workforce. Artificial intelligence (AI) is a rapidly emerging technology already having an impact on the medical school and residency application process as students and faculty alike increasingly turn to AI tools to automate some steps in the preparation and evaluation of application materials. While AI may have the potential to improve the holistic admissions process by increasing efficiency and adding some measure of standardization among reviewers, the authors caution that this promise does not come without certain pitfalls. AI models may introduce new sources of bias and amplify existing ones, which, when combined with a lack of transparency regarding their use in the admissions process, may perpetuate the very inequities that holistic review seeks to minimize. The authors call for the medical education community to establish clear regulations to govern the acceptable use of AI in the admissions process and for a principled adoption of AI tools in a way that is sustainable for applicants and reviewers in the future.
- 20 November 2024
- Published by Taylor & Francis in The American Journal of Bioethics
- Vol. 24 (12) , 35-37
Taking on Systems That Produce Moral Stress
- 20 November 2024
- Published by Taylor & Francis in The American Journal of Bioethics
- Vol. 24 (12) , 35-37
Taking on Systems That Produce Moral Stress
- Open Access
- 1 December 2023
- Published by Oxford University Press (OUP) in Innovation in Aging
- Vol. 7 (Supplement) , 878-879
HOUSING CONCERNS AND TRAJECTORIES OF KINLESS OLDER ADULTS WITH DEMENTIA
Housing preferences of older adults (e.g., to remain in residence, or relocate), housing options available, and housing needs related to changing physical and cognitive abilities are common concerns of aging. The challenges are possibly more complex for those living with dementia, who may have difficulty articulating housing preferences, and whose housing needs may include supportive care. For those with dementia who lack close kin, these challenges are likely significantly compounded. This paper focuses on the intersection of housing concerns for 64 participants in the Adult Changes in Thought (ACT) study who were kinless (no living spouse or children) when they developed dementia. All the ACT participants were 65+ when recruited. Everyone in this sample had received a research diagnosis, and their mean age at dementia onset (estimated at the midpoint between the research study that triggered the diagnostic evaluation, and the last research study before that -- usually one year before diagnosis) was 87 (Standard Deviation [SD] 7 years), with a median age of 86 and a range of 71-103.We present an analysis of their housing trajectories, as captured in chart notes from their medical records. We highlight multiple themes illustrating how housing intersects with health and social well-being and conclude by commenting on the potential of medical records for understanding and documenting issues related to housing.
- 1 December 2023
- Published by Oxford University Press (OUP) in Innovation in Aging
- Vol. 7 (Supplement) , 878-879
Open AccessHOUSING CONCERNS AND TRAJECTORIES OF KINLESS OLDER ADULTS WITH DEMENTIA
Housing preferences of older adults (e.g., to remain in residence, or relocate), housing options available, and housing needs related to changing physical and cognitive abilities are common concerns of aging. The challenges are possibly more complex for those living with dementia, who may have difficulty articulating housing preferences, and whose housing needs may include supportive care. For those with dementia who lack close kin, these challenges are likely significantly compounded. This paper focuses on the intersection of housing concerns for 64 participants in the Adult Changes in Thought (ACT) study who were kinless (no living spouse or children) when they developed dementia. All the ACT participants were 65+ when recruited. Everyone in this sample had received a research diagnosis, and their mean age at dementia onset (estimated at the midpoint between the research study that triggered the diagnostic evaluation, and the last research study before that -- usually one year before diagnosis) was 87 (Standard Deviation [SD] 7 years), with a median age of 86 and a range of 71-103.We present an analysis of their housing trajectories, as captured in chart notes from their medical records. We highlight multiple themes illustrating how housing intersects with health and social well-being and conclude by commenting on the potential of medical records for understanding and documenting issues related to housing.
- Open Access
- 21 February 2023
- Published by Oxford University Press (OUP) in The Journals of Gerontology, Series B: Psychological Sciences and Social Sciences
- Vol. 78 (6) , 1060-1072
Kinless Older Adults With Dementia: Qualitative Analysis of Data From the Adult Changes in Thought Study
Objectives: To examine the circumstances and needs of older adults who were “kinless,” defined as having no living spouse or children, when they developed dementia. Methods: We conducted a secondary analysis of information from the Adult Changes in Thought study. Among 848 participants diagnosed with dementia between 1994 and 2016, we identified 64 who had no living spouse or child at dementia onset. We then conducted a qualitative analysis of administrative documents pertaining to these participants: handwritten comments recorded after each study visit, and medical history documents containing clinical chart notes from participants’ medical records. Results: In this community-dwelling cohort of older adults diagnosed with dementia, 8.4% were kinless at dementia onset. Participants in this sample had an average age of 87 years old, half lived alone, and one third lived with unrelated persons. Through inductive content analysis, we identified 4 themes that describe their circumstances and needs: (1) life trajectories, (2) caregiving resources, (3) care needs and gaps, and (4) turning points in caregiving arrangements. Discussion: Our qualitative analysis reveals that the life trajectories that led members of the analytic cohort to be kinless at dementia onset were quite varied. This research highlights the importance of nonfamily caregivers and participants’ own roles as caregivers. Our findings suggest that clinicians and health systems may need to work with other parties to directly provide dementia caregiving support rather than rely on family, and address factors such as neighborhood affordability that particularly affect older adults who have limited family support.
- 21 February 2023
- Published by Oxford University Press (OUP) in The Journals of Gerontology, Series B: Psychological Sciences and Social Sciences
- Vol. 78 (6) , 1060-1072
Open AccessKinless Older Adults With Dementia: Qualitative Analysis of Data From the Adult Changes in Thought Study
Objectives: To examine the circumstances and needs of older adults who were “kinless,” defined as having no living spouse or children, when they developed dementia. Methods: We conducted a secondary analysis of information from the Adult Changes in Thought study. Among 848 participants diagnosed with dementia between 1994 and 2016, we identified 64 who had no living spouse or child at dementia onset. We then conducted a qualitative analysis of administrative documents pertaining to these participants: handwritten comments recorded after each study visit, and medical history documents containing clinical chart notes from participants’ medical records. Results: In this community-dwelling cohort of older adults diagnosed with dementia, 8.4% were kinless at dementia onset. Participants in this sample had an average age of 87 years old, half lived alone, and one third lived with unrelated persons. Through inductive content analysis, we identified 4 themes that describe their circumstances and needs: (1) life trajectories, (2) caregiving resources, (3) care needs and gaps, and (4) turning points in caregiving arrangements. Discussion: Our qualitative analysis reveals that the life trajectories that led members of the analytic cohort to be kinless at dementia onset were quite varied. This research highlights the importance of nonfamily caregivers and participants’ own roles as caregivers. Our findings suggest that clinicians and health systems may need to work with other parties to directly provide dementia caregiving support rather than rely on family, and address factors such as neighborhood affordability that particularly affect older adults who have limited family support.
- Open Access
- 14 December 2020
- Published by University Library System, University of Pittsburgh in Anthropology & Aging
- Vol. 41 (2) , 90-92
AFTERWORD. Situating Time, Futurity, and Aging in the Pandemic
AFTERWORD. Situating Time, Futurity, and Aging in the Pandemic
- 14 December 2020
- Published by University Library System, University of Pittsburgh in Anthropology & Aging
- Vol. 41 (2) , 90-92
Open AccessAFTERWORD. Situating Time, Futurity, and Aging in the Pandemic
AFTERWORD. Situating Time, Futurity, and Aging in the Pandemic
- Open Access
- 1 February 2020
- Published by Elsevier in American Journal of Kidney Diseases
- Vol. 75 (2) , 167-176
Experiences of US Nephrologists in the Delivery of Conservative Care to Patients With Advanced Kidney Disease: A National Qualitative Study
- 1 February 2020
- Published by Elsevier in American Journal of Kidney Diseases
- Vol. 75 (2) , 167-176
Open AccessExperiences of US Nephrologists in the Delivery of Conservative Care to Patients With Advanced Kidney Disease: A National Qualitative Study
- 31 December 2019
- Published by Rutgers University Press
- p. 126-138
8. Should Old Acquaintance Be Forgot? Friendship in the Face of Dementia
8. Should Old Acquaintance Be Forgot? Friendship in the Face of Dementia was published in Successful Aging as a Contemporary Obsession on page 126.
- 31 December 2019
- Published by Rutgers University Press
- p. 126-138
8. Should Old Acquaintance Be Forgot? Friendship in the Face of Dementia
8. Should Old Acquaintance Be Forgot? Friendship in the Face of Dementia was published in Successful Aging as a Contemporary Obsession on page 126.
- Open Access
- 1 October 2019
- Published by American Medical Association (AMA) in JAMA Internal Medicine
- Vol. 179 (10) , 1325-1333
Assessment of Self-reported Prognostic Expectations of People Undergoing Dialysis
Patients’ understanding of their prognosis and expected course of illness can profoundly shape their treatment goals and life choices.1 Such understanding is essential to the delivery of patient-centered care, shared decision-making, and advance care planning.2-4 Available evidence in people with cancer and older adults suggests that clinicians rarely share prognostic information5-9 and that patients often have overly optimistic expectations about the future.1,5-9
- 1 October 2019
- Published by American Medical Association (AMA) in JAMA Internal Medicine
- Vol. 179 (10) , 1325-1333
Open AccessAssessment of Self-reported Prognostic Expectations of People Undergoing Dialysis
Patients’ understanding of their prognosis and expected course of illness can profoundly shape their treatment goals and life choices.1 Such understanding is essential to the delivery of patient-centered care, shared decision-making, and advance care planning.2-4 Available evidence in people with cancer and older adults suggests that clinicians rarely share prognostic information5-9 and that patients often have overly optimistic expectations about the future.1,5-9