Empowering Clinical Trial Design through AI: A Randomized Evaluation of PowerGPT

Sample size calculations for power analysis are critical for clinical research and trial design, yet their complexity and reliance on statistical expertise create barriers for many researchers. We introduce PowerGPT, an AI-powered system integrating large language models (LLMs) with statistical engines to automate test selection and sample size estimation in trial design. In a randomized trial to evaluate its effectiveness, PowerGPT significantly improved task completion rates (99.3% vs. 88.9% for test selection, 99.3% vs. 77.8% for sample size calculation) and accuracy (94.1% vs. 55.4% in sample size estimation, p < 0.001), while reducing average completion time (4.0 vs. 9.3 minutes, p < 0.001). These gains were consistent across various statistical tests and benefited both statisticians and non-statisticians as well as bridging expertise gaps. Already under deployment across multiple institutions, PowerGPT represents a scalable AI-driven approach that enhances accessibility, efficiency, and accuracy in statistical power analysis for clinical research.

Suicide Risk Modeling with Uncertain Diagnostic Records

Motivated by the pressing need for suicide prevention through improving behavioral healthcare, we use medical claims data to study the risk of subsequent suicide attempts for patients who were hospitalized due to suicide attempts and later discharged. Understanding the risk behaviors of such patients at elevated suicide risk is an important step towards the goal of "Zero Suicide". An immediate and unconventional challenge is that the identification of suicide attempts from medical claims contains substantial uncertainty: almost 20\% of "suspected" suicide attempts are identified from diagnostic codes indicating external causes of injury and poisoning with undermined intent. It is thus of great interest to learn which of these undetermined events are more likely actual suicide attempts and how to properly utilize them in survival analysis with severe censoring. To tackle these interrelated problems, we develop an integrative Cox cure model with regularization to perform survival regression with uncertain events and a latent cure fraction. We apply the proposed approach to study the risk of subsequent suicide attempt after suicide-related hospitalization for adolescent and young adult population, using medical claims data from Connecticut. The identified risk factors are highly interpretable; more intriguingly, our method distinguishes the risk factors that are most helpful in assessing either susceptibility or timing of subsequent attempt. The predicted statuses of the uncertain attempts are further investigated, leading to several new insights on suicide event identification.

Exploring difference in public perceptions on HPV vaccine between gender groups from Twitter using deep learning

In this study, we proposed a convolutional neural network model for gender prediction using English Twitter text as input. Ensemble of proposed model achieved an accuracy at 0.8237 on gender prediction and compared favorably with the state-of-the-art performance in a recent author profiling task. We further leveraged the trained models to predict the gender labels from an HPV vaccine related corpus and identified gender difference in public perceptions regarding HPV vaccine. The findings are largely consistent with previous survey-based studies.