Ritu Agarwal

Junjie Luo, Ritu Agarwal, Gordon Gao

Organizations routinely run experiments for A/B testing, yet the data generated from one experiment is underutilized to inform subsequent intervention design. Significant barriers exist to extracting actionable knowledge from prior experimental data to inform new interventions. We study whether tool-augmented agentic AI can automatically learn from experimental data to generate new interventions in subsequent experiments. Through two-stage field experiments in healthcare prescription messaging (693,139 patient visits), we compare a Human + Chatbot method (Stage 1: behavioral experts with conversational AI co-designing 13 message variants, 444,691 patient visits) against a Tool-Augmented Agentic AI method (Stage 2: AI autonomously extracting principles from Stage 1 data to generate 17 new variants, 248,448 patient visits). The Agentic AI method, equipped with analytical tools, structured Data-Information-Knowledge-Wisdom (DIKW) reasoning agents, and transparent evidence chains, produces superior interventions: the best AI-generated message achieved a 69.8% CTR (+6.5 percentage points over baseline). Critically, our results suggest that the value comes from domain-specific experimental data, not from general reasoning ability: frontier LLMs operating without experimental data failed to predict which interventions would succeed. The field experiments also revealed that general-purpose behavioral theories used for intervention design do not extend uniformly to specific healthcare contexts, motivating an agentic AI approach to theory audits at field-experiment scale. Our research shows that tool-augmented AI can learn from experimental data and generate improved domain-relevant interventions, transforming behavioral experimentation from one-shot evaluation into a scalable system for cumulative design learning.

Aishwarya Deep Shukla, Laksh Agarwal, Jie Mein et al.

The proliferation of fake reviews of doctors has potentially detrimental consequences for patient well-being and has prompted concern among consumer protection groups and regulatory bodies. Yet despite significant advancements in the fields of machine learning and natural language processing, there remains limited comprehension of the characteristics differentiating fraudulent from authentic reviews. This study utilizes a novel pre-labeled dataset of 38048 physician reviews to establish the effectiveness of large language models in classifying reviews. Specifically, we compare the performance of traditional ML models, such as logistic regression and support vector machines, to generative pre-trained transformer models. Furthermore, we use GPT4, the newest model in the GPT family, to uncover the key dimensions along which fake and genuine physician reviews differ. Our findings reveal significantly superior performance of GPT-3 over traditional ML models in this context. Additionally, our analysis suggests that GPT3 requires a smaller training sample than traditional models, suggesting its appropriateness for tasks with scarce training data. Moreover, the superiority of GPT3 performance increases in the cold start context i.e., when there are no prior reviews of a doctor. Finally, we employ GPT4 to reveal the crucial dimensions that distinguish fake physician reviews. In sharp contrast to previous findings in the literature that were obtained using simulated data, our findings from a real-world dataset show that fake reviews are generally more clinically detailed, more reserved in sentiment, and have better structure and grammar than authentic ones.

Yihong Guo, Junjie Luo, Guodong Gao et al.

Offline contextual bandits allow one to learn policies from historical/offline data without requiring online interaction. However, offline policy optimization that maximizes overall expected rewards can unintentionally amplify the reward disparities across groups. As a result, some groups might benefit more than others from the learned policy, raising concerns about fairness, especially when the resources are limited. In this paper, we study a group-sensitive fairness constraint in offline contextual bandits, reducing group-wise reward disparities that may arise during policy learning. We tackle the following common-parity requirements: the reward disparity is constrained within some user-defined threshold or the reward disparity should be minimized during policy optimization. We propose a constrained offline policy optimization framework by introducing group-wise reward disparity constraints into an off-policy gradient-based optimization procedure. To improve the estimation of the group-wise reward disparity during training, we employ a doubly robust estimator and further provide a convergence guarantee for policy optimization. Empirical results in synthetic and real-world datasets demonstrate that our method effectively reduces reward disparities while maintaining competitive overall performance.

Jeevesh Juneja, Ritu Agarwal

We analyze the Knowledge Neurons framework for the attribution of factual and relational knowledge to particular neurons in the transformer network. We use a 12-layer multi-lingual BERT model for our experiments. Our study reveals various interesting phenomena. We observe that mostly factual knowledge can be attributed to middle and higher layers of the network($\ge 6$). Further analysis reveals that the middle layers($6-9$) are mostly responsible for relational information, which is further refined into actual factual knowledge or the "correct answer" in the last few layers($10-12$). Our experiments also show that the model handles prompts in different languages, but representing the same fact, similarly, providing further evidence for effectiveness of multi-lingual pre-training. Applying the attribution scheme for grammatical knowledge, we find that grammatical knowledge is far more dispersed among the neurons than factual knowledge.

Ziqi Yang, Yuxuan Lu, Jennifer Bagdasarian et al.

Cancer surgery is a key treatment for gastrointestinal (GI) cancers, a group of cancers that account for more than 35% of cancer-related deaths worldwide, but postoperative complications are unpredictable and can be life-threatening. In this paper, we investigate how recent advancements in large language models (LLMs) can benefit remote patient monitoring (RPM) systems through clinical integration by designing RECOVER, an LLM-powered RPM system for postoperative GI cancer care. To closely engage stakeholders in the design process, we first conducted seven participatory design sessions with five clinical staff and interviewed five cancer patients to derive six major design strategies for integrating clinical guidelines and information needs into LLM-based RPM systems. We then designed and implemented RECOVER, which features an LLM-powered conversational agent for cancer patients and an interactive dashboard for clinical staff to enable efficient postoperative RPM. Finally, we used RECOVER as a pilot system to assess the implementation of our design strategies with four clinical staff and five patients, providing design implications by identifying crucial design elements, offering insights on responsible AI, and outlining opportunities for future LLM-powered RPM systems.

Krithika Ramesh, Daniel Smolyak, Zihao Zhao et al.

We present SynthTextEval, a toolkit for conducting comprehensive evaluations of synthetic text. The fluency of large language model (LLM) outputs has made synthetic text potentially viable for numerous applications, such as reducing the risks of privacy violations in the development and deployment of AI systems in high-stakes domains. Realizing this potential, however, requires principled consistent evaluations of synthetic data across multiple dimensions: its utility in downstream systems, the fairness of these systems, the risk of privacy leakage, general distributional differences from the source text, and qualitative feedback from domain experts. SynthTextEval allows users to conduct evaluations along all of these dimensions over synthetic data that they upload or generate using the toolkit's generation module. While our toolkit can be run over any data, we highlight its functionality and effectiveness over datasets from two high-stakes domains: healthcare and law. By consolidating and standardizing evaluation metrics, we aim to improve the viability of synthetic text, and in-turn, privacy-preservation in AI development.

Daniel Smolyak, Arshana Welivita, Margrét V. Bjarnadóttir et al.

Objective. Demographic groups are often represented at different rates in medical datasets. These differences can create bias in machine learning algorithms, with higher levels of performance for better-represented groups. One promising solution to this problem is to generate synthetic data to mitigate potential adverse effects of non-representative data sets. Methods. We build on recent advances in LLM-based synthetic data generation to create a pipeline where the synthetic data is generated separately for each demographic group. We conduct our study using MIMIC-IV and Framingham "Offspring and OMNI-1 Cohorts" datasets. We prompt GPT4-Turbo to create group-specific data, providing training examples and the dataset context. An exploratory analysis is conducted to ascertain the quality of the generated data. We then evaluate the utility of the synthetic data for augmentation of a training dataset in a downstream machine learning task, focusing specifically on model performance metrics across groups. Results. The performance of GPT4-Turbo augmentation is generally superior but not always. In the majority of experiments our method outperforms standard modeling baselines, however, prompting GPT-4-Turbo to produce data specific to a group provides little to no additional benefit over a prompt that does not specify the group. Conclusion. We developed a method for using LLMs out-of-the-box to synthesize group-specific data to address imbalances in demographic representation in medical datasets. As another "tool in the toolbox", this method can improve model fairness and thus health equity. More research is needed to understand the conditions under which LLM generated synthetic data is useful for non-representative medical data sets.

Junjie Luo, Rui Han, Arshana Welivita et al.

Understanding how patients perceive their physicians is essential to improving trust, communication, and satisfaction. We present a large language model (LLM)-based pipeline that infers Big Five personality traits and five patient-oriented subjective judgments. The analysis encompasses 4.1 million patient reviews of 226,999 U.S. physicians from an initial pool of one million. We validate the method through multi-model comparison and human expert benchmarking, achieving strong agreement between human and LLM assessments (correlation coefficients 0.72-0.89) and external validity through correlations with patient satisfaction (r = 0.41-0.81, all p<0.001). National-scale analysis reveals systematic patterns: male physicians receive higher ratings across all traits, with largest disparities in clinical competence perceptions; empathy-related traits predominate in pediatrics and psychiatry; and all traits positively predict overall satisfaction. Cluster analysis identifies four distinct physician archetypes, from "Well-Rounded Excellent" (33.8%, uniformly high traits) to "Underperforming" (22.6%, consistently low). These findings demonstrate that automated trait extraction from patient narratives can provide interpretable, validated metrics for understanding physician-patient relationships at scale, with implications for quality measurement, bias detection, and workforce development in healthcare.

Junjie Luo, Yihong Guo, Anqi Liu et al.

Messaging patients is a critical part of healthcare communication, helping to improve things like medication adherence and healthy behaviors. However, traditional mobile message design has significant limitations due to its inability to explore the high-dimensional design space. We develop PAME-AI, a novel approach for Patient Messaging Creation and Optimization using Agentic AI. Built on the Data-Information-Knowledge-Wisdom (DIKW) hierarchy, PAME-AI offers a structured framework to move from raw data to actionable insights for high-performance messaging design. PAME-AI is composed of a system of specialized computational agents that progressively transform raw experimental data into actionable message design strategies. We demonstrate our approach's effectiveness through a two-stage experiment, comprising of 444,691 patient encounters in Stage 1 and 74,908 in Stage 2. The best-performing generated message achieved 68.76% engagement compared to the 61.27% baseline, representing a 12.2% relative improvement in click-through rates. This agentic architecture enables parallel processing, hypothesis validation, and continuous learning, making it particularly suitable for large-scale healthcare communication optimization.

Junjie Luo, Abhimanyu Kumbara, Mansur Shomali et al.

Continuous glucose monitoring (CGM) combined with AI offers new opportunities for proactive diabetes management through real-time glucose forecasting. However, most existing models are task-specific and lack generalization across patient populations. Inspired by the autoregressive paradigm of large language models, we introduce CGM-LSM, a Transformer decoder-based Large Sensor Model (LSM) pretrained on 1.6 million CGM records from patients with different diabetes types, ages, and genders. We model patients as sequences of glucose time steps to learn latent knowledge embedded in CGM data and apply it to the prediction of glucose readings for a 2-hour horizon. Compared with prior methods, CGM-LSM significantly improves prediction accuracy and robustness: a 48.51% reduction in root mean square error in one-hour horizon forecasting and consistent zero-shot prediction performance across held-out patient groups. We analyze model performance variations across patient subgroups and prediction scenarios and outline key opportunities and challenges for advancing CGM foundation models.

Yizhi Liu, Weiguang Wang, Guodong Gordon Gao et al.

Electronic health records (EHRs) serve as an essential data source for the envisioned artificial intelligence (AI)-driven transformation in healthcare. However, clinician biases reflected in EHR notes can lead to AI models inheriting and amplifying these biases, perpetuating health disparities. This study investigates the impact of stigmatizing language (SL) in EHR notes on mortality prediction using a Transformer-based deep learning model and explainable AI (XAI) techniques. Our findings demonstrate that SL written by clinicians adversely affects AI performance, particularly so for black patients, highlighting SL as a source of racial disparity in AI model development. To explore an operationally efficient way to mitigate SL's impact, we investigate patterns in the generation of SL through a clinicians' collaborative network, identifying central clinicians as having a stronger impact on racial disparity in the AI model. We find that removing SL written by central clinicians is a more efficient bias reduction strategy than eliminating all SL in the entire corpus of data. This study provides actionable insights for responsible AI development and contributes to understanding clinician behavior and EHR note writing in healthcare.