Bryant Lin
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Bryant Lin has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- Andrew Janss
Project: Music Heals Us, Guilford, CT 06437, USA
1 shared publication - Ann T. Nguyen
Stanford University, Stanford, California
1 shared publication - Aubrey Florom-Smith
Stanford University School of Medicine, Stanford, CA 94305, USA
1 shared publication - Augustine Wc Kang
Center for Alcohol and Addiction Studies, Brown University School of Public Health, Providence, RI, USA
1 shared publication - Chloe Sales
Chloe Sales is with the Center for Asian Health Research and Education, Stanford University School of Medicine, Stanford, CA. Yeuen Kim, Bryant Lin, and Latha Palaniappan are with the Department of Medicine, Division of Primary Care and Population Health, Stanford University School of Medicine. Gloria Kim is with the Department of Cardiovascular Medicine, Division of Primary Care and Population Health, Stanford University School of Medicine
1 shared publication - David H. Rehkopf
Department of Epidemiology and Population Health, Stanford University School of Medicine, Stanford, California
1 shared publication
Latest Publications
- Open Access
- 1 August 2026
- Published by AME Publishing Company in Chinese Clinical Oncology
- Vol. 15 (4) , 64
An interview-based study of Asian American non-smoker lung cancer in the United States
An interview-based study of Asian American non-smoker lung cancer in the United States
- 1 August 2026
- Published by AME Publishing Company in Chinese Clinical Oncology
- Vol. 15 (4) , 64
Open AccessAn interview-based study of Asian American non-smoker lung cancer in the United States
An interview-based study of Asian American non-smoker lung cancer in the United States
- Open Access
Structured Insight from Unstructured Data: Large Language Models for SDOH-Driven Diabetes Risk Prediction
Social determinants of health (SDOH) play a critical role in Type 2 Diabetes (T2D) management but are often absent from electronic health records and risk prediction models. Most individual-level SDOH data is collected through structured screening tools, which lack the flexibility to capture the complexity of patient experiences and unique needs of a clinic's population. This study explores the use of large language models (LLMs) to extract structured SDOH information from unstructured patient life stories and evaluate the predictive value of both the extracted features and the narratives themselves for assessing diabetes control. We collected unstructured interviews from 65 T2D patients aged 65 and older, focused on their lived experiences, social context, and diabetes management. These narratives were analyzed using LLMs with retrieval-augmented generation to produce concise, actionable qualitative summaries for clinical interpretation and structured quantitative SDOH ratings for risk prediction modeling. The structured SDOH ratings were used independently and in combination with traditional laboratory biomarkers as inputs to linear and tree-based machine learning models (Ridge, Lasso, Random Forest, and XGBoost) to demonstrate how unstructured narrative data can be applied in conventional risk prediction workflows. Finally, we evaluated several LLMs on their ability to predict a patient's level of diabetes control (low, medium, high) directly from interview text with A1C values redacted. LLMs achieved 60% accuracy in predicting diabetes control levels from interview text. This work demonstrates how LLMs can translate unstructured SDOH-related data into structured insights, offering a scalable approach to augment clinical risk models and decision-making.
Open AccessStructured Insight from Unstructured Data: Large Language Models for SDOH-Driven Diabetes Risk Prediction
Social determinants of health (SDOH) play a critical role in Type 2 Diabetes (T2D) management but are often absent from electronic health records and risk prediction models. Most individual-level SDOH data is collected through structured screening tools, which lack the flexibility to capture the complexity of patient experiences and unique needs of a clinic's population. This study explores the use of large language models (LLMs) to extract structured SDOH information from unstructured patient life stories and evaluate the predictive value of both the extracted features and the narratives themselves for assessing diabetes control. We collected unstructured interviews from 65 T2D patients aged 65 and older, focused on their lived experiences, social context, and diabetes management. These narratives were analyzed using LLMs with retrieval-augmented generation to produce concise, actionable qualitative summaries for clinical interpretation and structured quantitative SDOH ratings for risk prediction modeling. The structured SDOH ratings were used independently and in combination with traditional laboratory biomarkers as inputs to linear and tree-based machine learning models (Ridge, Lasso, Random Forest, and XGBoost) to demonstrate how unstructured narrative data can be applied in conventional risk prediction workflows. Finally, we evaluated several LLMs on their ability to predict a patient's level of diabetes control (low, medium, high) directly from interview text with A1C values redacted. LLMs achieved 60% accuracy in predicting diabetes control levels from interview text. This work demonstrates how LLMs can translate unstructured SDOH-related data into structured insights, offering a scalable approach to augment clinical risk models and decision-making.
- Open Access
- 9 November 2023
- Published by MDPI AG in Healthcare
- Vol. 11 (22) , 2929
Voices of Musicians: Virtual Live Bedside Music Concerts in Inpatient Care
The COVID-19 pandemic presented unprecedented challenges to patients, family members, and healthcare staff that resulted in increased stress and isolation and decreased quality of life. We evaluate the impact of a novel virtual concert program, the Vital Sounds Initiative (VSI) of Project: Music Heals Us (PMHU), which began at the beginning of the pandemic to combat patient isolation and provide employment to professional musicians. Using a qualitative analysis of VSI data, we examined post-concert written responses by musicians. These responses were coded by independent coders via inductive coding and thematic analysis. Between 7 April 2020 and 20 July 2022, 192 musicians played 2203 h of music for 11,222 audience members in 39 care facilities nationwide. A total of 114 musicians submitted a total of 658 responses. Three main themes (with corresponding subthemes) arose: (1) Patient Experience; (2) Musician Experience; (3) Caregiver (family or staff) Experience. The responses offered valuable insight into the overwhelmingly positive aspects of the virtual concerts. Overall, we found that VSI favorably impacts individuals at every level, including the patients, musician, and caregivers. These findings provide preliminary evidence for the benefits of virtual music concerts. Upscaling similar virtual music interventions/programs should be considered.
- 9 November 2023
- Published by MDPI AG in Healthcare
- Vol. 11 (22) , 2929
Open AccessVoices of Musicians: Virtual Live Bedside Music Concerts in Inpatient Care
The COVID-19 pandemic presented unprecedented challenges to patients, family members, and healthcare staff that resulted in increased stress and isolation and decreased quality of life. We evaluate the impact of a novel virtual concert program, the Vital Sounds Initiative (VSI) of Project: Music Heals Us (PMHU), which began at the beginning of the pandemic to combat patient isolation and provide employment to professional musicians. Using a qualitative analysis of VSI data, we examined post-concert written responses by musicians. These responses were coded by independent coders via inductive coding and thematic analysis. Between 7 April 2020 and 20 July 2022, 192 musicians played 2203 h of music for 11,222 audience members in 39 care facilities nationwide. A total of 114 musicians submitted a total of 658 responses. Three main themes (with corresponding subthemes) arose: (1) Patient Experience; (2) Musician Experience; (3) Caregiver (family or staff) Experience. The responses offered valuable insight into the overwhelmingly positive aspects of the virtual concerts. Overall, we found that VSI favorably impacts individuals at every level, including the patients, musician, and caregivers. These findings provide preliminary evidence for the benefits of virtual music concerts. Upscaling similar virtual music interventions/programs should be considered.
- Open Access
Increased Self-Reported Discrimination and Concern for Physical Assault Due to the COVID-19 Pandemic in Chinese, Vietnamese, Korean, Japanese, and Filipino Americans
Objectives: To investigate self-reported discrimination and concern for physical assault due to the COVID-19 pandemic among disaggregated Asian subgroups in the US. Methods: We conducted a nationwide survey to assess self-reported discrimination and concern for physical assault due to COVID-19 across racial/ethnic groups, including diverse subgroups of Asians. Results: Chinese respondents experienced the largest change (15% increase) in proportion of respondents reporting discrimination from 2019 to 2020 (P<.01). Chinese, Korean, Japanese, Vietnamese, and Other API showed up to 3.9 times increased odds of self-reported racial/ethnic discrimination due to COVID-19 and, with the addition of Filipino, experienced up to 5.4 times increased odds of concern for physical assault due to COVID-19 compared to Whites. Conclusions: Our study is the first to examine self-reported discrimination and concern for physical assault due to COVID-19 in subgroups of Asian Americans, finding that East (Chinese, Korean, Japanese) and Southeast (Vietnamese, Filipino) Asian Americans have been disproportionately affected. Future studies should disaggregate Asian subgroups to fully understand experiences of discrimination in diverse populations in the US.
Open AccessIncreased Self-Reported Discrimination and Concern for Physical Assault Due to the COVID-19 Pandemic in Chinese, Vietnamese, Korean, Japanese, and Filipino Americans
Objectives: To investigate self-reported discrimination and concern for physical assault due to the COVID-19 pandemic among disaggregated Asian subgroups in the US. Methods: We conducted a nationwide survey to assess self-reported discrimination and concern for physical assault due to COVID-19 across racial/ethnic groups, including diverse subgroups of Asians. Results: Chinese respondents experienced the largest change (15% increase) in proportion of respondents reporting discrimination from 2019 to 2020 (P<.01). Chinese, Korean, Japanese, Vietnamese, and Other API showed up to 3.9 times increased odds of self-reported racial/ethnic discrimination due to COVID-19 and, with the addition of Filipino, experienced up to 5.4 times increased odds of concern for physical assault due to COVID-19 compared to Whites. Conclusions: Our study is the first to examine self-reported discrimination and concern for physical assault due to COVID-19 in subgroups of Asian Americans, finding that East (Chinese, Korean, Japanese) and Southeast (Vietnamese, Filipino) Asian Americans have been disproportionately affected. Future studies should disaggregate Asian subgroups to fully understand experiences of discrimination in diverse populations in the US.