Lan Yao

Lan Yao

Auto-generated profile, based on publicly available information

Lan Yao


Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
7 September 2021 in Environmental Science and Pollution Research
Verified
Journal Article
Closed access
PDF file
LYLan Yao
Lan Yao
MLMinghui Li
Minghui Li
JWJim Y. Wan
Jim Y. Wan
SHScott C. Howard
Scott C. Howard
James E. BaileyJames E. Bailey
James E. Bailey
JGJoyce Carolyn Graff
Joyce Carolyn Graff

15 May 2025 in Journal of Medical Internet Research
Verified
Journal Article
Open access
YLYilan Li
Yilan Li
TGTianshu Gu
Tianshu Gu
CYChengyuan Yang
Chengyuan Yang
MLMinghui Li
Minghui Li
CWCong-Yi Wang
Cong-Yi Wang
DSDIANJUN SUN
DIANJUN SUN
Background: Cardiotoxicity is a major concern in heart disease research because it can lead to severe cardiac damage, including heart failure and arrhythmias. Objective: This study aimed to explore the ability of ChatGPT with GPT-4o to generate innovative research hypotheses to address 5 major challenges in cardiotoxicity research: the complexity of mechanisms, variability among patients, the lack of detection sensitivity, the lack of reliable biomarkers, and the limitations of animal models. Methods: ChatGPT with GPT-4o was used to generate multiple hypotheses for each of the 5 challenges. These hypotheses were then independently evaluated by 3 experts for novelty and feasibility. ChatGPT with GPT-4o subsequently selected the most promising hypothesis from each category and provided detailed experimental plans, including background, rationale, experimental design, expected outcomes, potential pitfalls, and alternative approaches. Results: ChatGPT with GPT-4o generated 96 hypotheses, of which 13 (14%) were rated as highly novel and 62 (65%) as moderately novel. The average group score of 3.85 indicated a strong level of innovation in these hypotheses. Literature searching identified at least 1 relevant publication for 28 (29%) of the 96 hypotheses. The selected hypotheses included using single-cell RNA sequencing to understand cellular heterogeneity, integrating artificial intelligence with genetic profiles for personalized cardiotoxicity risk prediction, applying machine learning to electrocardiogram data for enhanced detection sensitivity, using multi-omics approaches for biomarker discovery, and developing 3D bioprinted heart tissues to overcome the limitations of animal models. Our group’s evaluation of the 30 dimensions of the experimental plans for the 5 hypotheses selected by ChatGPT with GPT-4o revealed consistent strengths in the background, rationale, and alternative approaches, with most of the hypotheses (20/30, 67%) receiving scores of ≥4 in these areas. While the hypotheses were generally well received, the experimental designs were often deemed overly ambitious, highlighting the need for more practical considerations. Conclusions: Our study demonstrates that ChatGPT with GPT-4o can generate innovative and potentially impactful hypotheses for overcoming critical challenges in cardiotoxicity research. These findings suggest that artificial intelligence–assisted hypothesis generation could play a crucial role in advancing the field of cardiotoxicity, leading to more accurate predictions, earlier detection, and better patient outcomes.


Verified
Journal Article
Open access
PDF file
LYLan Yao
Lan Yao
JGJoyce Carolyn Graff
Joyce Carolyn Graff
Lotfi AleyaLotfi Aleya
Lotfi Aleya
JMJiamin Ma
Jiamin Ma
YCYanhong Cao
Yanhong Cao
DSDIANJUN SUN
DIANJUN SUN
Background: The greatest challenges are imposed on the overall capacity of disease management when the cases reach the maximum in each wave of the pandemic. Methods: The cases and deaths for the four waves of COVID-19 in 119 countries and regions (CRs) were collected. We compared the mortality across CRs where populations experience different economic and healthcare disparities. Findings: Among 119 CRs, 117, 112, 111, and 55 have experienced 1, 2, 3, and 4 waves of COVID-19 disease, respectively. The average mortality rates at the disease turning point were 0.036, 0.019. 0.017, and 0.015 for the waves 1, 2, 3, and 4, respectively. Among 49 potential factors, income level, gross national income (GNI) per capita, and school enrollment are positively correlated with the mortality rates in the first wave, but negatively correlated with the rates of the rest of the waves. Their values for the first wave are 0.253, 0.346 and 0.385, respectively. The r value for waves 2, 3, and 4 are −0.310, −0.293, −0.234; −0.263, −0.284, −0.282; and −0.330, −0.394, −0.048, respectively. In high-income CRs, the mortality rates in waves 2 and 3 were 29% and 28% of that in wave 1; while in upper-middle-income CRs, the rates for waves 2 and 3 were 76% and 79% of that in wave 1. The rates in waves 2 and 3 for lower-middle-income countries were 88% and 89% of that in wave 1, and for low-income countries were 135% and 135%. Furthermore, comparison among the largest case numbers through all waves indicated that the mortalities in upper- and lower-middle-income countries is 65% more than that of the high-income countries. Interpretation: Conclusions from the first wave of the COVID-19 pandemic do not apply to the following waves. The clinical outcomes in developing countries become worse along with the expansion of the pandemic.

3 November 2025 in The Science of Nature
Verified
Journal Article
Open access
PDF file
LYLan Yao
Lan Yao
TGTianshu Gu
Tianshu Gu
XLXuexin Li
Xuexin Li
YJYan Jiao
Yan Jiao
MLMinghui Li
Minghui Li
Weikuan GuWeikuan Gu
Weikuan Gu
DeepSeek and Grok 3 appear as strong competitors to AI models, particularly the widely accepted model, ChatGPT. The accuracy of the utilization of data in retracted scientific articles has proven to be a significant challenge for AI as an assistant in scientific research. It is critical to understand whether and how three AI models handle information from retracted articles when they answer scientific questions. We collected retracted articles and used AI models to generate questions and analyzed the answers. The answers were compared and evaluated among three AI models. Here we show that these three models utilized 84 out of 93 retracted articles in their answers about stem cells. ChatGPT4o retrieved 74 out of 93 (80%) articles and recognized the retract status for 46 (62%) of them. DeepSeek only found one retracted article and did not realize its retraction status. Grok 4 retrieved 69 (74%) articles and recognized the retraction status of 46 (67%) of them. In cases when the retracted articles were not identified, ChatGPT fabricated articles 5 times out of 19 (26%) for its answers. Grok 3 fabricated 15 articles out of 24 (63%) for its answers. In 82 times of 93 (88%) answers, DeepSeek fabricated the articles in various forms. The answering styles from ChatGPT4o, DeepSeek, and Grok 3 are characterized by accurate and straightforward, a tangential structure and guesswork, and comprehensive and detailed answers, respectively. Analysis with non-retracted articles revealed the similar patterns of these models. This study suggests that, while no model is perfect, DeepSeek performed the worst when facing in-depth scientific real-world challenges. Much improvement has to be made before any of these AI models become problem-free and valuable for scientists.

25 September 2021 in Journal of Personalized Medicine
Verified
Journal Article
Open access
PDF file
LYLan Yao
Lan Yao
WDWei Dong
Wei Dong
JWJim Y. Wan
Jim Y. Wan
SHScott C. Howard
Scott C. Howard
MLMinghui Li
Minghui Li
JGJoyce Carolyn Graff
Joyce Carolyn Graff
Data from the early stage of a novel infectious disease outbreak provide vital information in risk assessment, prediction, and precise disease management. Since the first reported case of COVID-19, the pattern of the novel coronavirus transmission in Wuhan has become the interest of researchers in epidemiology and public health. To thoroughly map the mechanism of viral spreading, we used the patterns of data at the early onset of COVID-19 from seven countries to estimate the time lag between peak days of cases and deaths. This study compared these data with those of Wuhan and estimated the natural history of disease across the infected population and the time lag. The findings suggest that comparative analyses of data from different regions and countries reveal the differences between peaks of cases and deaths caused by COVID-19 and the incomplete and underestimated cases in Wuhan. Different countries may show different patterns of cases peak days, deaths peak days, and peak periods. Error in the early COVID-19 statistics in Brazil was identified. This study provides sound evidence for policymakers to understand the local circumstances in diagnosing the health of a population and propose precise and timely public health interventions to control and prevent infectious diseases.