Weipeng Zhou

Weipeng Zhou, Danielle Bitterman, Majid Afshar et al.

Large language models (LLMs) like ChatGPT have excited scientists across fields; in medicine, one source of excitement is the potential applications of LLMs trained on electronic health record (EHR) data. But there are tough questions we must first answer if health care institutions are interested in having LLMs trained on their own data; should they train an LLM from scratch or fine-tune it from an open-source model? For healthcare institutions with a predefined budget, what are the biggest LLMs they can afford? In this study, we take steps towards answering these questions with an analysis on dataset sizes, model sizes, and costs for LLM training using EHR data. This analysis provides a framework for thinking about these questions in terms of data scale, compute scale, and training budgets.

Nicholas J Dobbins, Bin Han, Weipeng Zhou et al.

Objective: Identifying study-eligible patients within clinical databases is a critical step in clinical research. However, accurate query design typically requires extensive technical and biomedical expertise. We sought to create a system capable of generating data model-agnostic queries while also providing novel logical reasoning capabilities for complex clinical trial eligibility criteria. Materials and Methods: The task of query creation from eligibility criteria requires solving several text-processing problems, including named entity recognition and relation extraction, sequence-to-sequence transformation, normalization, and reasoning. We incorporated hybrid deep learning and rule-based modules for these, as well as a knowledge base of the Unified Medical Language System (UMLS) and linked ontologies. To enable data-model agnostic query creation, we introduce a novel method for tagging database schema elements using UMLS concepts. To evaluate our system, called LeafAI, we compared the capability of LeafAI to a human database programmer to identify patients who had been enrolled in 8 clinical trials conducted at our institution. We measured performance by the number of actual enrolled patients matched by generated queries. Results: LeafAI matched a mean 43% of enrolled patients with 27,225 eligible across 8 clinical trials, compared to 27% matched and 14,587 eligible in queries by a human database programmer. The human programmer spent 26 total hours crafting queries compared to several minutes by LeafAI. Conclusions: Our work contributes a state-of-the-art data model-agnostic query generation system capable of conditional reasoning using a knowledge base. We demonstrate that LeafAI can rival an experienced human programmer in finding patients eligible for clinical trials.

Lingfei Qian, Weipeng Zhou, Yan Wang et al.

As the fundamental capability behind decision-making in finance, financial reasoning poses distinct challenges for LLMs. Although reinforcement learning (RL) have boosted generic reasoning, the progress in finance is hindered by the absence of empirical study of building effective financial chain-of-thought (CoT) corpus, a systematic comparison of different RL methods, and comprehensive benchmarks. To address these gaps, we introduce FinCoT, the first open high-fidelity CoT corpus for finance, distilled from seven QA datasets by a novel three-stage pipeline that incorporates domain supervision, iterative LLM refinement, and difficulty-aware filtering. Based on FinCoT, we develop Fin-o1, the first open financial reasoning models trained via supervised fine-tuning and GRPO-based RL. Our models outperform existing financial reasoning models and SOTA general models such as GPT-o1, DeepSeek-R1, and GPT-4.5. We also investigate the effectiveness of three different RL methods in improving domain-specific reasoning, offering the first such empirical study. We finally propose FinReason, the first financial reasoning benchmark covering multi-table analysis, long-context reasoning, and equation-based tasks, and evaluate 29 LLMs. Our extensive experiments reveal general reasoning models excel on standard benchmarks yet exhibit obvious performance degradation in financial contexts; even finance-tuned models like Dianjin-R1 and FinR1 degrade on lengthy documents. In contrast, our Fin-o1 models consistently outperform their backbones and larger GPT-o1 and DeepSeek-R1, confirming the effectiveness of our data building and model training strategy. Our study further shows that GRPO yields reliable gains whereas PPO and DPO do not, highlighting the need for targeted data and optimisation rather than scale alone.

Weipeng Zhou, Ryan J. Laundry, Paul L. Hebert et al.

Background: COVID-19 has become a challenge worldwide and properly planning of medical resources is the key to combating COVID-19. In the US Veteran Affairs Health Care System (VA), many of the enrollees are susceptible to COVID-19. Predicting the COVID-19 to allocate medical resources promptly becomes a critical issue. When the VA enrollees have COVID-19 symptoms, it is recommended that their first step should be to call the VA Call Center. For confirmed COVID-19 patients, the median time from the first symptom to hospital admission was seven days. By predicting the number of COVID-19 related calls, we could predict imminent surges in healthcare use and plan medical resources ahead. Objective: The study aims to develop a method to forecast the daily number of COVID-19 related calls for each of the 110 VA medical centers. Methods: In the proposed method, we pre-trained a model using a cluster of medical centers and fine-tuned it for individual medical centers. At the cluster level, we performed feature selection to select significant features and automatic hyper-parameter search to select optimal hyper-parameter value combinations for the model. Conclusions: This study proposed an accurate method to forecast the daily number of COVID-19 related calls for VA medical centers. The proposed method was able to overcome modeling challenges by grouping similar medical centers into clusters to enlarge the dataset for training models, and using hyper-parameter search to automatically find optimal hyper-parameter value combinations for models. With the proposed method, surges in health care can be predicted ahead. This allows health care practitioners to better plan medical resources and combat COVID-19.