Purpose: This study aimed to optimize the consultation strategy and timing of physicist consultation for proton prostate patients, thereby improving patient experience and resource utilization in radiation oncology department. Methods: 96 prostate patients undergoing proton therapy were surveyed after physics consult conducted at two time points: (1) prior to simulation or (2) prior to treatment. Survey responses were further divided into two groups—one responding at their first physics consult, the other responding at second consult. Anxiety levels were measured using the six-item short-form Spielberger State-Trait Anxiety Inventory (STAI). Anxiety scores were calculated and analyzed to compare first- versus second consult groups, as well as physics consults performed at different timing. Patient feedback on useful information during consultations was categorized using K-Means clustering into five themes. Results: Anxiety scores were comparable between first (28.60 ± 8.94) and second (29.75 ± 10.33) consultations (p = 0.59). Similarly, anxiety scores for consultations prior to simulation (30.59 ± 9.93) and prior to treatment (28.04 ± 8.83) showed no significant difference (p = 0.22). Patients identified five key information categories: (1) Radiation Types and Delivery, (2) Treatment Plan and Procedure Details, (3) Mechanism and Effects of Proton Radiation, (4) Proton Beam Generation and Therapy Pathway, and (5) Dosimetry and Risk. Conclusions: For proton prostate patients, a single physics consultation prior to treatment covering identified patient concerns maintains similar anxiety score comparable to two consultations model. Streamlining the consultation process in this manner can optimize medical physicist time without increasing patient anxiety level. This approach may serve as a framework for improving patient education and communication strategies of physics consult for proton therapy.

Cancer remains the second leading cause of death in the United States, with nearly 1.9 million new cases and over 609,000 deaths annually. Research funded by the National Cancer Institute (NCI) plays a key role in advancing cancer treatments, diagnostics, and understanding. This study analyzes 24 years of NCI grant data to uncover funding trends and their broader implications. Using NIH RePORTER, we filtered and analyzed $36.07B of grants from 2000 to 2023. Leveraging BERTopic, a topic modeling algorithm, we clustered grant abstracts based on semantic similarities to identify major research themes. OpenAI’s GPT-4o-mini model was then used to generate topic labels. Our findings reveal key shifts in funding allocation. Total NCI funding has significantly increased since 2000, with notable growth in areas like Epigenetic Modifications in Cancer and P53 Pathways in HCC Liver Cancer, while topics such as Ethics of Cancer Research and Signal Transduction Pathways have seen less emphasis over time. Additionally, emerging areas like Natural Care Approaches for Cancer Patients exhibit high annual growth, reflecting new focuses in patient care. These insights enhance transparency in research funding, informing stakeholders about emerging therapies and underfunded research areas. This work highlights the link between funding and patient outcomes, demonstrating how NCI initiatives drive innovation in cancer care. By presenting trends, we aim to support equitable resource distribution, improve transparency, and enhance knowledge to guide future funding decisions. 

Investigators, funders, and the public desire knowledge on topics and trends in research funded by the federal government. Current efforts to categorize efforts are limited to manual categorization and naming of a few dozen grants at a time. We developed an automated pipeline within BERTopic (a topic modeling and representation technique) to extract and name research topics and applied this to $1.9B of NCI funding over 21 years in the radiological sciences to determine micro- and macro-scale research topics and funding trends. In our prior work by Nguyen et al., we used Word2Vec-based embeddings to represent grants, hierarchical/K-means clustering to group them, and iterative topic naming by humans to label them. Our current study builds on this with updated embedding, clustering, and generative-AI-driven naming methods. We mapped out 9202 grant abstracts from 2000-2020 using PubMedBERT-base embeddings, then clustered them into 60 clusters with HDBScan, and visualized them in two dimensions using UMAP to aid in interpretation. We employed a chaining strategy comparing c-TF-IDF and topic distributions to reduce cluster outliers. The resultant clusters were named via OpenAI's GPT-3.5 model. We used prompt tuning methods (role prompting, directive commanding) through three reinforcement phases to generate topic labels based on the most representative documents of each cluster. The three largest topics in descending order are related to PET/CT imaging, tumor cell imaging, and breast cancer computer-aided detection. We believe these results may (1) demonstrate the feasibility of using topic modeling to help funders and the public understand funding patterns in the field of radiation oncology (2) provide updated clustering and representation methodology which increases accuracy and decreases reliance on manual human validation.

Every year, thousands of cancer research abstracts are presented at the ASTRO Annual Meeting. As biomedical literature continues to grow, there is a need to better understand trends in this large corpus of unstructured text data to aid conference organizers and attendees. This study examines the effectiveness of natural language processing (NLP) techniques to organize and present conference research. We analyzed a dataset of 9,770 abstracts accepted to the ASTRO Annual Meeting conference from 2019 to 2023. Using the BERTopic Python package, we converted abstracts into PubMedBERT embeddings and clustered the embeddings into 100 topics with HDBScan clustering. We experimented with c-TF-IDF scores, centroid distance, or HDBScan probabilities as various distance metrics to identify representative documents of each topic. To generate topic names, we input representative documents and BERTopic-extracted keywords into OpenAI’s GPT-3.5 model, applying role prompting and directive commanding strategies across three reinforcement phases of prompt tuning. Manual validation of GPT-generated names was performed through surveys assessing quantitative agreement and comments. Our approach combining BERTopic with a PubMedBERT transformer model and HDBScan clustering successfully categorized 91% of ASTRO abstracts. The three largest topics encompassed thoracic malignancies, head and neck cancer radiation therapy, and prostate cancer, while the smallest topics centered around radiation oncology education and brain tumor treatments. Two-dimensional interactive visualization using the Altair package also uncovered meta-topics such as Education and Basic Science. GPT-generated names, obtained using 20 representative documents selected by c-TF-IDF scores and three prompt tuning stages, were preferred in validation over human-generated categories. These results demonstrate the potential of combining representative models and generative models to derive topics from abstracts that are more preferred than human-generated categories. Our methods for optimizing clustering and prompt tuning to produce the best organization and naming of biomedical text may also be applied to automated conference organization.

Publications are constantly being released as scientists and doctors continue to conduct new research. Keeping track of all publications released, even if narrow to a specific field, is onerous, requiring dedication of extensive time and resources. Our project uses LLMs (Large Language Models) to automate this process so that investigation of publication trends over decades is easily accessible to help inform future research. We extracted 4277 abstracts published from 2013 to 2023 from the International Journal of Radiation Oncology, Biology, and Physics. We leveraged the BERTopic (Bidirectional Encoder Representations from Transformers) framework, to cluster publications into a hundred topics based on PubMed pre-trained embeddings. In addition, we explored the parameter space of HDBSCAN (Hierarchical Density-Based Spatial Clustering of Applications with Noise), our chosen clustering method, in order to maximize the number of relevant topics and minimize the number of outliers. However, an outlier group that contained 18% of our abstracts still remained. To address this, we further processed abstracts in this group and assigned each of them to a topic using c-TF-IDF (class-based Term Frequency-Inverse Document Frequency) with more relaxed matching thresholds. We applied three different threshold levels and manually reviewed 30 randomly chosen outlier abstracts and graded them as strongly, moderately, or poorly aligned to the assigned topic. We found on our lowest threshold 76% of the abstracts were sorted to relevant topics. The verification we conduct on reduction helps ensure the quality of the clusters we produced and thus the accuracy of future analysis on underlying trends.

Neuroendocrine bladder cancer (NEBC) is a rare and aggressive urothelial tract cancer. NEBC is characterized by high metastatic potential and poor clinical prognosis. Neuroendocrine cancers often exhibit characteristic genetic changes including loss of tumor-suppressing genes like TP53 and RB1 and amplification or activating mutations in proto-oncogenes, e.g., MYC. However, not all bladder cancers with these characteristic mutations progress to NEBC, suggesting other occult genetic or epigenetic drivers of disease progression. To investigate the clonal origins of NEBC tumor heterogeneity, our lab developed a genetically engineered mouse model by introducing orthotopic mutations observed in human tumors (TP53, RB1, and MYC) in murine bladders by lentiviral delivery of Cre recombinase. We found some of the resulting tumors had high levels of the pioneer transcription factor, FOXA2. To further explore the role of this gene in NEBC development, we conducted an overexpression experiment in which FOXA2 was expressed in mouse-derived bladder cancer cell lines. We performed RNAseq (RNA sequencing) analysis in a panel of syngeneic murine NEBC lines, including samples with FOXA2 over expression and parental controls. In the course of this work, we developed an informatics pipeline to interrogate clonal heterogeneity at the transcriptional level in genetically identical syngeneic tumor lines – a method which we termed clonal phylogenies from RNAseq (CPR) data. My role in this project involved designing and implementing a bioinformatics pipeline to analyze both single-cell and bulk RNAseq data. By integrating cross-species comparisons with computational analysis, we aim to uncover novel molecular mechanisms driving NEBC emergence. While our research is ongoing, this approach highlights a new bioinformatics method allowing deeper insights into human cancer biology.