Dr. Jiyeong Kim is a post-doctoral scholar at the Stanford Center for Digital Health and the Department of Dermatology School of Medicine. Dr. Kim is a computational epidemiologist, harnessing patient-and caregiver-generated health information and data to design patient-centered health interventions, which could be tailored to each patient group for improving patient engagement and better health outcomes.

In her work, Dr. Kim uses artificial intelligence, machine learning, and natural language processing to understand patients' and caregivers' genuine voices of care needs and needed support. As a multidisciplinary epidemiologist, Dr. Kim's work focuses on translational health data science, embracing the intersection of mental health and digital health and expanding to patient-provider communications and health disparities among cancer survivors and caregivers of individuals with chronic conditions (e.g., Alzheimer's Disease and Related Dementia).

Research Interest
-LLMs and generative AI to Listen to the Patient
-Generative AI-Assisted Enhanced Patient Care
-ML-based Disease Prediction Modeling
-Digital Mental Health Tools
-Patient-Generated Data and Precision Health

Professional Education

  • Doctor of Philosophy, University of California Davis (2023)
  • PhD, University of California, Davis, Public Health Sciences (2023)
  • MPH, Johns Hopkins Bloomberg School of Public Health, Public Health (2014)
  • BPharm, Chung-Ang University, Pharmacy (2007)

Stanford Advisors

All Publications

  • Telehealth Utilization and Associations in the United States During the Third Year of the COVID-19 Pandemic: Population-Based Survey Study in 2022. JMIR public health and surveillance Kim, J., Cai, Z. R., Chen, M. L., Onyeka, S., Ko, J. M., Linos, E. 2024; 10: e51279


    BACKGROUND: The COVID-19 pandemic rapidly changed the landscape of clinical practice in the United States; telehealth became an essential mode of health care delivery, yet many components of telehealth use remain unknown years after the disease's emergence.OBJECTIVE: We aim to comprehensively assess telehealth use and its associated factors in the United States.METHODS: This cross-sectional study used a nationally representative survey (Health Information National Trends Survey) administered to US adults (≥18 years) from March 2022 through November 2022. To assess telehealth adoption, perceptions of telehealth, satisfaction with telehealth, and the telehealth care purpose, we conducted weighted descriptive analyses. To identify the subpopulations with low adoption of telehealth, we developed a weighted multivariable logistic regression model.RESULTS: Among a total of 6252 survey participants, 39.3% (2517/6252) reported telehealth use in the past 12 months (video: 1110/6252, 17.8%; audio: 876/6252, 11.6%). The most prominent reason for not using telehealth was due to telehealth providers failing to offer this option (2200/3529, 63%). The most common reason for respondents not using offered telehealth services was a preference for in-person care (527/578, 84.4%). Primary motivations to use telehealth were providers' recommendations (1716/2517, 72.7%) and convenience (1516/2517, 65.6%), mainly for acute minor illness (600/2397, 29.7%) and chronic condition management (583/2397, 21.4%), yet care purposes differed by age, race/ethnicity, and income. The satisfaction rate was predominately high, with no technical problems (1829/2517, 80.5%), comparable care quality to that of in-person care (1779/2517, 75%), and no privacy concerns (1958/2517, 83.7%). Younger individuals (odd ratios [ORs] 1.48-2.23; 18-64 years vs ≥75 years), women (OR 1.33, 95% CI 1.09-1.61), Hispanic individuals (OR 1.37, 95% CI 1.05-1.80; vs non-Hispanic White), those with more education (OR 1.72, 95% CI 1.03-2.87; at least a college graduate vs less than high school), unemployed individuals (OR 1.25, 95% CI 1.02-1.54), insured individuals (OR 1.83, 95% CI 1.25-2.69), or those with poor general health status (OR 1.66, 95% CI 1.30-2.13) had higher odds of using telehealth.CONCLUSIONS: To our best knowledge, this is among the first studies to examine patient factors around telehealth use, including motivations to use, perceptions of, satisfaction with, and care purpose of telehealth, as well as sociodemographic factors associated with telehealth adoption using a nationally representative survey. The wide array of descriptive findings and identified associations will help providers and health systems understand the factors that drive patients toward or away from telehealth visits as the technology becomes more routinely available across the United States, providing future directions for telehealth use and telehealth research.

    View details for DOI 10.2196/51279

    View details for PubMedID 38669075

  • Human-AI interaction in skin cancer diagnosis: a systematic review and meta-analysis. NPJ digital medicine Krakowski, I., Kim, J., Cai, Z. R., Daneshjou, R., Lapins, J., Eriksson, H., Lykou, A., Linos, E. 2024; 7 (1): 78


    The development of diagnostic tools for skin cancer based on artificial intelligence (AI) is increasing rapidly and will likely soon be widely implemented in clinical use. Even though the performance of these algorithms is promising in theory, there is limited evidence on the impact of AI assistance on human diagnostic decisions. Therefore, the aim of this systematic review and meta-analysis was to study the effect of AI assistance on the accuracy of skin cancer diagnosis. We searched PubMed, Embase, IEE Xplore, Scopus and conference proceedings for articles from 1/1/2017 to 11/8/2022. We included studies comparing the performance of clinicians diagnosing at least one skin cancer with and without deep learning-based AI assistance. Summary estimates of sensitivity and specificity of diagnostic accuracy with versus without AI assistance were computed using a bivariate random effects model. We identified 2983 studies, of which ten were eligible for meta-analysis. For clinicians without AI assistance, pooled sensitivity was 74.8% (95% CI 68.6-80.1) and specificity was 81.5% (95% CI 73.9-87.3). For AI-assisted clinicians, the overall sensitivity was 81.1% (95% CI 74.4-86.5) and specificity was 86.1% (95% CI 79.2-90.9). AI benefitted medical professionals of all experience levels in subgroup analyses, with the largest improvement among non-dermatologists. No publication bias was detected, and sensitivity analysis revealed that the findings were robust. AI in the hands of clinicians has the potential to improve diagnostic accuracy in skin cancer diagnosis. Given that most studies were conducted in experimental settings, we encourage future studies to further investigate these potential benefits in real-life settings.

    View details for DOI 10.1038/s41746-024-01031-w

    View details for PubMedID 38594408

    View details for PubMedCentralID 8237239

  • Assessment of correctness, content omission, and risk of harm in large language model responses to dermatology continuing medical education questions. The Journal of investigative dermatology Cai, Z. R., Chen, M. L., Kim, J., Novoa, R. A., Barnes, L. A., Beam, A., Linos, E. 2024

    View details for DOI 10.1016/j.jid.2024.01.015

    View details for PubMedID 38310972

  • Prevalence and associations of poor mental health in the third year of COVID-19: U.S. population-based analysis from 2020 to 2022. Psychiatry research Kim, J., Linos, E., Rodriguez, C. I., Chen, M. L., Dove, M. S., Keegan, T. H. 2023; 330: 115622


    BACKGROUND: Poorer mental health was found early in the COVID-19 pandemic, yet mental health in the third year of COVID-19 has not been assessed on a general adult population level in the United States.METHODS: We used a nationally representative cross-sectional survey (Health Information National Trends Survey, HINTS 5 2020 n=3,865 and HINTS 6 2022 n=6,252). The prevalence of poor mental health was examined using a Patient Health Questionnaire-4 scale in 2020 and 2022. We also investigated the factors associated with poor mental health in 2022 using a weighted multivariable logistic regression adjusting for sociodemographic and health status characteristics to obtain the odds ratio (OR).OUTCOMES: The prevalence of poor mental health in adults increased from 2020 to 2022 (31.5% vs 36.3%, p=0.0005). U.S. adults in 2022 were 1.28 times as likely to have poor mental health than early in the pandemic. Moreover, individuals with food insecurity, housing instability, and low income had greater odds of poor mental health (ORs=1.78-2.55). Adults who were females, non-Hispanic Whites, or age 18-64 years were more likely to have poor mental health (ORs=1.46-4.15).INTERPRETATION: Mental health of U.S. adults worsened in the third year of COVID-19 compared to the beginning of the pandemic.

    View details for DOI 10.1016/j.psychres.2023.115622

    View details for PubMedID 38006717

  • Assessing Biases in Medical Decisions via Clinician and AI Chatbot Responses to Patient Vignettes. JAMA network open Kim, J., Cai, Z. R., Chen, M. L., Simard, J. F., Linos, E. 2023; 6 (10): e2338050

    View details for DOI 10.1001/jamanetworkopen.2023.38050

    View details for PubMedID 37847506

  • Effectiveness of Digital Mental Health Tools to Reduce Depressive and Anxiety Symptoms in Low- and Middle-Income Countries: Systematic Review and Meta-analysis. JMIR mental health Kim, J., Aryee, L. M., Bang, H., Prajogo, S., Choi, Y. K., Hoch, J. S., Prado, E. L. 2023; 10: e43066


    Depression and anxiety contribute to an estimated 74.6 million years of life with disability, and 80% of this burden occurs in low- and middle-income countries (LMICs), where there is a large gap in care.We aimed to systematically synthesize available evidence and quantify the effectiveness of digital mental health interventions in reducing depression and anxiety in LMICs.In this systematic review and meta-analysis, we searched PubMed, Embase, and Cochrane databases from the inception date to February 2022. We included randomized controlled trials conducted in LMICs that compared groups that received digital health interventions with controls (active control, treatment as usual, or no intervention) on depression or anxiety symptoms. Two reviewers independently extracted summary data reported in the papers and performed study quality assessments. The outcomes were postintervention measures of depression or anxiety symptoms (Hedges g). We calculated the pooled effect size weighted by inverse variance.Among 11,196 retrieved records, we included 80 studies in the meta-analysis (12,070 participants n=6052, 50.14% in the intervention group and n=6018, 49.85% in the control group) and 96 studies in the systematic review. The pooled effect sizes were -0.61 (95% CI -0.78 to -0.44; n=67 comparisons) for depression and -0.73 (95% CI -0.93 to -0.53; n=65 comparisons) for anxiety, indicating that digital health intervention groups had lower postintervention depression and anxiety symptoms compared with controls. Although heterogeneity was considerable (I2=0.94 for depression and 0.95 for anxiety), we found notable sources of variability between the studies, including intervention content, depression or anxiety symptom severity, control type, and age. Grading of Recommendations, Assessments, Development, and Evaluation showed that the evidence quality was overall high.Digital mental health tools are moderately to highly effective in reducing depression and anxiety symptoms in LMICs. Thus, they could be effective options to close the gap in depression and anxiety care in LMICs, where the usual mental health care is minimal.PROSPERO CRD42021289709;

    View details for DOI 10.2196/43066

    View details for PubMedID 36939820

    View details for PubMedCentralID PMC10131603

  • Incidence of Suicide Among Melanoma and Non-Keratinocyte Skin Cancer Patients in the US, 2000-2020. Journal of the American Academy of Dermatology Chen, M. L., Rezaei, S. J., Kim, J., Rodriguez, C., Swetter, S. M., O'Hara, R., Linos, E. 2024

    View details for DOI 10.1016/j.jaad.2024.05.028

    View details for PubMedID 38768863

  • Impact of COVID-19, cancer survivorship and patient-provider communication on mental health in the US Difference-In-Difference. Npj mental health research Kim, J., Linos, E., Dove, M. S., Hoch, J. S., Keegan, T. H. 2023; 2 (1): 14


    Poor mental health has been found to be more prevalent among those with cancer and is considered a public health crisis since COVID-19. This study assessed the impact of COVID-19 and cancer survivorship on mental health and investigated factors, including online patient-provider communications (OPPC; email/internet/tablet/smartphone), associated with poor mental health prior to and during the early COVID-19. Nationally representative Health Information National Trends Survey data during 2017-2020 (n = 15,871) was used. While the prevalence of poor mental health was high (40-42%), Difference-In-Difference analyses revealed that cancer survivorship and COVID-19 were not associated with poor mental health. However, individuals that used OPPC had 40% higher odds of poor mental health. Low socioeconomic status (low education/income), younger age (18-64 years), and female birth gender were also associated with poor mental health. Findings highlight the persistence of long-standing mental health inequities and identify that OPPC users might be those who need mental health support.

    View details for DOI 10.1038/s44184-023-00034-x

    View details for PubMedID 38609572

    View details for PubMedCentralID 2880195

  • Cancer survivors with sub-optimal patient-centered communication before and during the early COVID-19 pandemic. Patient education and counseling Kim, J., Fairman, N. P., Dove, M. S., Hoch, J. S., Keegan, T. H. 2023; 115: 107876


    OBJECTIVES: Patient-Centered Communication (PCC) is an essential element of patient-centered cancer care. Thus, this study aimed to examine the prevalence of and factors associated with optimal PCC among cancer survivors during COVID-19, which has been less studied.METHODS: We used national survey (Health Information National Trends Survey) among cancer survivors (n=2579) to calculate the prevalence (%) of optimal PCC in all 6 PCC domains and overall (mean) by time (before COVID-19, 2017-19 vs. COVID-19, 2020). Multivariable logistic regressions were performed to explore the associations of sociodemographic (age, birth gender, race/ethnicity, income, education, usual source of care), and health status (general health, depression/anxiety symptoms, time since diagnosis, cancer type) factors with optimal PCC.RESULTS: The prevalence of optimal PCC decreased during COVID-19 overall, with the greatest decrease in managing uncertainty (7.3%). Those with no usual source of care (odd ratios, ORs =1.53-2.29), poor general health (ORs=1.40-1.66), depression/anxiety symptoms (ORs=1.73-2.17) were less likely to have optimal PCC in most domains and overall PCC.CONCLUSIONS: We observed that the decreased prevalence of optimal PCC, and identified those with suboptimal PCC during COVID-19.PRACTICE IMPLICATIONS: More efforts to raise awareness and improve PCC are suggested, including education and guidelines, given the decreased prevalence during this public health emergency.

    View details for DOI 10.1016/j.pec.2023.107876

    View details for PubMedID 37406471

  • Factors Associated with Online Patient-Provider Communications Among Cancer Survivors in the United States during COVID: A Cross-Sectional Study. JMIR cancer Kim, J., Linos, E., Fishman, D. A., Dove, M. S., Hoch, J. S., Keegan, T. H. 2023


    BACKGROUND: Online Patient-Provider Communication (OPPC) is crucial in enhancing access to health information, self-care, and related health outcomes among cancer survivors. The necessity of OPPC increased during SARS/COVID-19 (COVID), yet investigations in vulnerable subgroups have been limited.OBJECTIVE: Thus, this study aimed to assess the prevalence of OPPC and sociodemographic and clinical characteristics associated with OPPC among cancer survivors and adults without a history of cancer during COVID vs. pre-COVID.METHODS: Nationally representative cross-sectional survey data (Health Information National Trends Survey, HINTS 5 2017-2020) was used among cancer survivors (n= 1,900) and adults without a history of cancer (n= 13, 292). COVID included data from February to June 2020. We calculated the prevalence of three types of OPPC, defined as using email/internet, tablet/smartphone, or Electronic Health Records (EHR) for patient-provider communication, in the past 12 months. To investigate the associations of sociodemographic and clinical factors with OPPC, multivariable-adjusted weighted logistic regression was performed to obtain odds ratios (OR) and 95% confidence intervals (95% CI).RESULTS: The average prevalence of OPPC increased from pre-COVID to COVID among cancer survivors (39.7% vs. 49.7%, email/internet; 32.2% vs. 37.9%, tablet/smartphone; 19.0% vs. 30.0%, EHR). Cancer survivors (OR=1.32, 95% CI 1.06-1.63) were slightly more likely to use email/internet communications than adults without a history of cancer prior to COVID. Among cancer survivors, email/internet (OR=1.61, 1.08-2.40) and EHR (OR=1.92, 1.22-3.02) were more likely to be used during COVID than pre-COVID. During COVID, subgroups of cancer survivors, including Hispanics (OR=0.26, 0.09-0.71 vs. non-Hispanic Whites), or those with the lowest income (OR=6.14, 1.99-18.92 $50,000 to <$75,000; OR=0.42, 1.56-11.28 ≥ $75,000 vs. <$20,000), with no usual source of care (OR=6.17, 2.12-17.99), or reporting depression (OR=0.33, 0.14-0.78) were less likely to use email/internet and those who were the oldest (OR=9.33, 2.18-40.01 age 35-49; OR=3.58, 1.20-10.70 age 50-64; OR=3.09, 1.09-8.76 age 65-74 vs. ≥75), unmarried (OR=2.26, 1.06-4.86) or had public/no health insurance (ORs=0.19-0.21 Medicare, Medicaid, or Other, vs. private) were less likely to use tablet/smartphone to communicate with providers. Cancer survivors with a usual source of care (OR=6.23, 1.66-23.39) or healthcare office visits within a year (ORs=7.55-8.25) were significantly more likely to use EHR to communicate. While not observed in cancer survivors, lower education level was associated with lower OPPC among adults without a history of cancer during COVID.CONCLUSIONS: Our findings identified vulnerable subgroups of cancer survivors who were left behind in online patient-provider communications which are becoming an increasing part of healthcare. Those vulnerable subgroups of cancer survivors with lower OPPC should be helped through multidimensional interventions to prevent further inequities.CLINICALTRIAL: Not applicable.

    View details for DOI 10.2196/44339

    View details for PubMedID 37074951

  • Characterizing risky alcohol use, cigarette smoking, e-cigarette use, and physical inactivity among cancer survivors in the USA-a cross-sectional study JOURNAL OF CANCER SURVIVORSHIP Kim, J., Keegan, T. H. 2022


    Unhealthy lifestyle behaviors are associated with inferior health outcomes among cancer survivors, including increased mortality. It is crucial to identify vulnerable subgroups, yet investigations have been limited. Thus, this study aimed to examine sociodemographic and clinical characteristics associated with risky health behaviors among cancer survivors.We used national, cross-sectional survey data (Health Information National Trends Survey, HINTS 2017-2020) for 2579 cancer survivors. We calculated the prevalence of risky alcohol use, current cigarette smoking, e-cigarette use, and not meeting physical activity guidelines. We performed weighted logistic regression to obtain multivariable-adjusted odds ratios (OR) for the association between each unhealthy behavior with sociodemographic and clinical characteristics.Overall, 25% showed risky alcohol use, 12% were current cigarette smokers, 3% were current e-cigarette users, and 68% did not meet physical activity guidelines. Cancer survivors who were males, non-Hispanic Whites or African Americans, without a college education, not married and with comorbidities or psychological distress were more likely to have unhealthy behaviors. Those with lung disease or depression were 2 times as likely to smoke cigarette or e-cigarettes and those with psychological distress were 1.6 times as likely to be physically inactive. Moreover, risky drinkers (OR = 1.75, 95% CI = 1.22-2.52) and e-cigarette smokers (OR = 16.40, 95% CI 3.29-81.89) were more likely to be current cigarette smokers.We identified vulnerable subpopulations of cancer survivors with multiple unhealthy lifestyle behaviors.Our findings inform clinicians and program and policy makers of the subgroups of cancer survivors to target for multiple health behavior interventions.

    View details for DOI 10.1007/s11764-022-01245-5

    View details for Web of Science ID 000840291700001

    View details for PubMedID 35963976

    View details for PubMedCentralID 2988633

  • Sociodemographic factors associated with HPV awareness/knowledge and cervical cancer screening behaviors among caregivers in the U.S BMC WOMENS HEALTH Kim, J., Dove, M. S., Dang, J. T. 2022; 22 (1): 335


    Family caregivers may be at a higher risk for several chronic diseases, including cancer. Cervical cancer is one of the most common causes of cancer death among women. Despite family caregivers' vulnerability, the status of their HPV awareness, knowledge, and preventive health behaviors, including cervical cancer screening, has been understudied. Thus, this study aimed to examine the sociodemographic factors associated with HPV awareness and knowledge and adherence to the cervical cancer screening guidelines among caregivers in the U.S.Nationally representative cross-sectional survey data were obtained from the Health Information National Trends Survey (HINTS 5, 2017-2020). Female caregivers aged 21-65 were included (N = 1190). Weighted multivariable logistic regression was performed to identify factors associated with HPV awareness (heard of HPV), knowledge (HPV can cause cervical cancer), and adherence to the United States Preventive Service Task Force 2018 cervical cancer screening guidelines by sociodemographic factors (age, race/ethnicity, education, household income, marital status,) and the intensity of caregiving.An estimated 79% of female caregivers were aware of HPV and 84% adhered to the cervical cancer screening guidelines. Caregivers who were older than 50 (OR = 3.62, 1.91-6.85, adherence of aged 21-50 vs. 51-65), Hispanics of race/ethnicity compared with Black/African Americans (OR = 3.14, 1.31-7.52, adherence of Black/African Americans vs. Hispanics), with a high school education or less (OR = 2.34, 1.14-4.82, adherence of Some college or more vs. High school education or less), and with intense caregiving duty (spending 35 h/week or more on caregiving) compared with light-duty (OR = 2.34, 1.10-5.00, adherence of 5-14 h vs. 35 h or more, weekly) had poor adherence to the cervical cancer screening guidelines. Caregivers who were older, racial minorities (Asian, Native Hawaiian/Pacific Islander, American Indian/Alaska Native, Multiple races), and less educated showed lower HPV awareness (Heard of HPV) than their counterparts.There are caregiving populations whose HPV awareness and cervical cancer screening adherence are low. To improve their awareness and knowledge of HPV and support their cervical cancer screening behaviors, we need to consider interventions that target those specific populations.

    View details for DOI 10.1186/s12905-022-01918-4

    View details for Web of Science ID 000837679800002

    View details for PubMedID 35941594

    View details for PubMedCentralID PMC9358833

  • The Rationale for Economic Evaluation in Speech and Language: Cost, Effectiveness, and Cost-effectiveness SEMINARS IN SPEECH AND LANGUAGE Hoch, J. S., Smith, B. P., Kim, J., Dewa, C. S. 2022; 43 (03): 208-217


    Economic evaluation studies the costs and outcomes of two or more alternative activities to estimate the relative efficiency of each course of action. Economic evaluation is both important and necessary in the management of speech and language issues. Economic evaluation can help focus attention on interventions that provide value for improving population health. The purpose of this article is to introduce readers to fundamental economic concepts. Readers are also introduced to common issues when conducting economic evaluations and how to address them in practice.

    View details for DOI 10.1055/s-0042-1750345

    View details for Web of Science ID 000827789000004

    View details for PubMedID 35858606