Citations

ABSTRACTBackgroundWe investigated mental health diagnoses (MHDs) in mycosis fungoides (MF) patients compared to the general population, evaluated risk factors, and studied survival outcomes in a large population database.MethodsMF patients from the Utah Cancer Registry diagnosed from 2001 to 2014 were matched with up to five general population individuals from the Utah Population Database. MHDs were retrospectively tracked in both populations (median follow‐up = 6.67 years). Risk factors for new MHDs among MF patients were studied using the Cox proportional hazards model. Overall survival (OS) and disease‐specific survival (DSS) were assessed using Kaplan–Meier analysis.ResultsThe incidence of anxiety disorders (HR = 1.99, 95% CI [1.16, 3.42]) and delirium/dementia disorders (HR = 2.43, 95% CI [1.05, 5.63]) was higher among MF patients than the matched general population. Among MF patients, Charlson Comorbidity Index (CCI) ≥ 2 and BMI < 18 kg/m2 were risk factors for new anxiety disorders. Radiation therapy, CCI ≥ 2, and female gender were risk factors for new delirium/dementia disorders. The 15‐year OS was worse for MF patients with versus without an MHD (36% vs. 81%, HR 2.62, 95%CI [1.24, 5.65]). The 15‐year DSS also worsened for MF patients with versus without an MHD (63% vs. 97%, HR 6.55, 95%CI [1.64, 26.2]).ConclusionsMF patients developed anxiety and delirium/dementia disorders at rates above the general population, and MHDs correlated with worse DSS and OS. Careful mental health monitoring may be an actionable step towards improving health‐related quality of life in this population.

Abstract Introduction COVID-19, a global health crisis, prompted rapid vaccine development. Bivalent vaccines by Pfizer-BioNTech and Moderna target both original and Omicron strains. Despite vaccination efforts, the persistence of adverse events underscores the importance of ongoing safety monitoring. Method We collected COVID-19 bivalent vaccine adverse event reports from the Vaccine Adverse Event Reporting System (VAERS) (September 15, 2022, to September 1, 2023). The Medical Dictionary for Regulatory Activities (MedDRA) categorized reported symptoms into corresponding concepts. Statistical analyses included zero-truncated Poisson regression for estimating symptom rates, logistic regression for identifying risk factors, and Spearman correlation for assessing non-parametric relationships between adverse events in different System Organ Classes (SOCs). Results Our analysis of COVID-19 bivalent vaccine adverse events identified significant correlations between SOCs. Notably, a positive correlation (ρ = 0.3) linked Infections (SOC 1) with Respiratory disorders (SOC 13), while a negative correlation (ρ=-0.3) connected Investigations (SOC 23) with Injury (SOC 24). Zero-truncated Poisson modeling estimated an average of 6.179 symptoms per individual, varying by age, gender, and vaccine. Gender and age significantly influence reported adverse events associated with COVID-19 bivalent vaccines. Females generally experienced higher odds for most SOCs compared to males, except for cardiac and product-related issues. Older adults showed a higher likelihood of symptoms across various SOCs, while children and adolescents had distinct susceptibility patterns. Additionally, Moderna and Pfizer vaccines were associated with different SOCs, with Moderna linked mainly to immune and skin disorders and Pfizer associated primarily with cardiac and metabolic issues. Conclusion In conclusion, our study aligned self-reported items with widely-accepted medical terminology and rigorously analyzed adverse events following COVID-19 bivalent vaccine using advanced statistical methods. The significant findings provide crucial insights, guiding evidence-based strategies and interventions for vaccine safety.

This cross-sectional study investigates the current landscape of generative artificial intelligence (GenAI) guidelines across ophthalmology journals.

Background: Electronic Health Records (EHRs) encompass valuable data essential for disease prediction. The application of artificial intelligence (AI), particularly deep learning, significantly enhances disease prediction by analyzing extensive EHR datasets to identify hidden patterns, facilitating early detection. Recently, numerous foundation models pretrained on extensive data have demonstrated efficacy in disease prediction using EHRs. However, there remains some unanswered questions on how to best utilize such models, especially with very small fine-tuning cohorts. Methods: We utilized Med-BERT, an EHR-specific foundation model, and reformulated the disease binary prediction task into a token prediction task and a next visit mask token prediction task to align with Med-BERT’s pretraining task format in order to improve the accuracy of pancreatic cancer (PaCa) prediction in both few-shot and fully supervised settings. Results: The reformulation of the task into a token prediction task, referred to as Med-BERT-Sum, demonstrated slightly superior performance in both few-shot scenarios and larger data samples. Furthermore, reformulating the prediction task as a Next Visit Mask Token Prediction task (Med-BERT-Mask) significantly outperformed the conventional Binary Classification (BC) prediction task (Med-BERT-BC) by 3% to 7% in few-shot scenarios with data sizes ranging from 10 to 500 samples. These findings highlight that aligning the downstream task with Med-BERT’s pretraining objectives substantially enhances the model’s predictive capabilities, thereby improving its effectiveness in predicting both rare and common diseases. Conclusions: Reformatting disease prediction tasks to align with the pretraining of foundation models enhances prediction accuracy, leading to earlier detection and timely intervention. This approach improves treatment effectiveness, survival rates, and overall patient outcomes for PaCa and potentially other cancers.

Abstract Advances in genomic medicine have accelerated the identification of mutations in disease- associated genes, but the pathogenicity of many mutations remains unknown, hindering their use in diagnostics and clinical decision-making. Predictive AI models have been generated to combat this issue, but current tools display low accuracy when tested against functionally validated datasets. We show that integrating detailed conformational data extracted from molecular dynamics simulations (MDS) into advanced AI-based models can increase their predictive power. We carried out an exhaustive mutational analysis of the disease gene PMM2 and subjected structural models of each variant to MDS. AI models trained on this dataset outperformed existing tools when predicting the known pathogenicity of mutations. Our best performing model, a neuronal networks model, was also able to predict the pathogenicity of several PMM2 mutations currently considered of unknown significance. We believe this new model will help alleviate the burden of unknown variants in genomic medicine.

Abstract Objective Human Papillomavirus (HPV) vaccine is an effective measure to prevent and control the diseases caused by HPV. However, widespread misinformation and vaccine hesitancy remain significant barriers to its uptake. This study focuses on the development of VaxBot-HPV, a chatbot aimed at improving health literacy and promoting vaccination uptake by providing information and answering questions about the HPV vaccine. Methods We constructed the knowledge base (KB) for VaxBot-HPV, which consists of 451 documents from biomedical literature and web sources on the HPV vaccine. We extracted 202 question-answer pairs from the KB and 39 questions generated by GPT-4 for training and testing purposes. To comprehensively understand the capabilities and potential of GPT-based chatbots, 3 models were involved in this study: GPT-3.5, VaxBot-HPV, and GPT-4. The evaluation criteria included answer relevancy and faithfulness. Results VaxBot-HPV demonstrated superior performance in answer relevancy and faithfulness compared to baselines. For test questions in KB, it achieved an answer relevancy score of 0.85 and a faithfulness score of 0.97. Similarly, it attained scores of 0.85 for answer relevancy and 0.96 for faithfulness on GPT-generated questions. Discussion VaxBot-HPV demonstrates the effectiveness of fine-tuned large language models in healthcare, outperforming generic GPT models in accuracy and relevance. Fine-tuning mitigates hallucinations and misinformation, ensuring reliable information on HPV vaccination while allowing dynamic and tailored responses. The specific fine-tuning, which includes context in addition to question-answer pairs, enables VaxBot-HPV to provide explanations and reasoning behind its answers, enhancing transparency and user trust. Conclusions This study underscores the importance of leveraging large language models and fine-tuning techniques in the development of chatbots for healthcare applications, with implications for improving medical education and public health communication.

Background: The incidence and mortality of anal squamous cell carcinoma (ASCC) are rising, with greater than 80% of cases linked to human papillomavirus (HPV), primarily HPV16. Post-treatment surveillance can be challenging due to the limitations of anoscopy, digital anal rectal exam (DARE), and imaging. Plasma tumor tissue modified viral (TTMV)-HPV DNA has shown strong sensitivity, specificity, and predictive value in detecting the recurrence of HPV-driven oropharyngeal cancer. Here, we investigate the ability of TTMV-HPV DNA for the early recurrence detection of ASCC. Methods: This retrospective clinical case series included 117 patients with HPV-driven ASCC across 7 U.S. centers, monitored with TTMV-HPV DNA during routine clinical care between March 2020 and June 2024. Physician-reported clinical data and biomarker testing data were combined to create a comprehensive, longitudinal dataset for evaluating test performance metrics. Results: Patients had a median age of 63 years and median post-diagnosis follow-up of 19 months. HPV status was primarily confirmed by TTMV-HPV DNA (52%) or p16 immunohistochemistry (39%). Of those tested for TTMV-HPV DNA pretreatment, 85% had a positive result. TTMV-HPV DNA clearance during or within three months post-treatment was associated with significantly better recurrence-free survival. The per-patient surveillance sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were 82.8%, 98.4%, 96.0%, and 92.5%. Of 24 patients with a documented recurrence and a positive TTMV-HPV DNA test, the test was the first evidence of recurrence in 14 patients (58.3%), with a median lead time of 59 days (range: 10–536). TTMV-HPV DNA accurately resolved 94.3% of cases with indeterminate clinical findings. Conclusions: TTMV-HPV DNA testing provides a sensitive and specific approach for detecting patients with recurrent ASCC and resolving the status of patients with indeterminate clinical findings.

(1) Background: Prostate cancer treatment efficacy is significantly influenced by androgen receptor (AR) signaling pathways. SLC22A3, a membrane transporter, has been linked to SNP rs9364554 risk loci for drug efficacy in prostate cancer. (2) Methods: We examined the location of SNP rs9364554 in the genome and utilized TCGA and other publicly available datasets to analyze the association of this SNP with SLC22A3 transcription levels. We verified onco-mining findings in prostate cancer cell lines using quantitative PCR and Western blots. Additionally, we employed electrophoretic mobility shift assay (EMSA) to detect the binding affinity of transcription factors to this SNP. The ChIP-Seq was used to analyze the enrichment of H3K27ac on the SLC22A3 promoter. (3) Results: In this study, we revealed that SNP rs9364554 resides in the SLC22A3 gene and affects its transcription. The downregulation of SLC22A3 is associated with drug resistance. More importantly, we found that this SNP has different binding affinities with transcription factors, specifically FOXA1 and AR, which significantly affects their regulation of SLC22A3 transcription. (4) Conclusions: Our findings highlight the potential of using this SNP as a biomarker for predicting chemotherapeutic outcomes and uncover possible mechanisms underlying drug resistance in advanced prostate cancers. More importantly, it provides a clinical foundation for targeting FOXA1 to enhance drug efficacy in prostate cancer patients.

Abstract Chemotherapy regimens for triple-negative breast cancer (TNBC) combine agents without knowing which agents drive response. Consequently, predictors derived from multi-agent regimens cannot be assumed to generalize to individual drugs or other regimens, motivating development of treatment-matched predictors. Here, we used TNBC patient-derived xenografts (PDXs) treated with carboplatin, docetaxel, or the combination to deconvolute drug-specific responses and identify associated molecular features. Combination treatment rarely improved upon the best single agent, with enhanced responses in only 13% of PDXs and antagonism in a comparable fraction. Proteogenomic analyses identified high cytokeratin-5 (KRT5) as a general marker of chemotherapy responsiveness and KRT5 immunohistochemistry discriminated responsive PDXs (AUROC, 0.83). To train treatment-specific predictors, we integrated these data with independent PDX and clinical cohorts with responses assessed after anthracycline-free platinum, taxane, or platinum-taxane therapy, ensuring response corresponded to the modeled treatment. Four feature selection strategies yielded largely nonoverlapping biomarker panels converging on treatment-relevant pathways. On independent test data, RNA-based predictors of complete response (CR) to platinum-based (carboplatin or cisplatin) and taxane-based (docetaxel or paclitaxel) chemotherapy achieved AUROCs of 0.80 and 0.86, respectively. For platinum-taxane regimens (carboplatin plus docetaxel or paclitaxel), proteomic-guided feature selection generated a 10-biomarker, protein- informed RNA predictor of pathologic complete response (pCR) that outperformed RNA-only feature selection and achieved an AUROC of 0.85 in an independent clinical cohort, while retaining practicality as an RNA-based assay. Treatment-matched integration of multi-omic PDX and clinical datasets provides a framework for chemotherapy-specific predictors with clinically relevant performance, supporting biomarker-guided precision selection and treatment optimization for patients with TNBC. Statement of significance Integration of multi-omic data from patient-derived xenografts with treatment-matched clinical cohorts yielded three retrospectively validated predictors of platinum, taxane, and platinum+taxane response, enabling biomarker-guided chemotherapy selection for patients with triple-negative breast cancer.

Abstract INTRODUCTION Immunotherapy has not improved survival in recurrent GBM (rGBM). Indoleamine 2,3 dioxygenase 1 (IDO1), highly expressed in ~90% of patients with malignant glioma, is a rate-limiting enzyme that catabolizes tryptophan (Trp) into kynurenine (Kyn) and enables immune escape. METHODS We hypothesized combining therapies targeting immunosuppressive pathways with cytotoxic and antiangiogenic therapies would overcome tumor-related immunosuppression. This was an open-label Phase II study of two regimens: Arm A consisted of retifanlimab (anti-PD1, 500mg IV Q4W) + bevacizumab (10mg/kg IV Q2W) + HFRT (3.5Gy/day x 10) in patients with IDH1/2-WT rGBM. Regimen B added the IDO inhibitor, epacadostat (400mg po BID), initiated prior to HFRT. Key inclusion criteria included dexamethasone ≤ 4 mg/day. The primary endpoint was overall survival (OS) at 9 months (OS-9). 24 evaluable patients were required to detect an OS-9 of 60% with 80% power, compared to 38% in historical controls (bevacizumab alone) by 1-sided 1-sample log rank test at alpha=0.1. RESULTS We previously reported Arm A. Here, we present results from Arm B. 25 of the 27 patients enrolled to regimen B were evaluable: median age 58years (23-71); 28% female; 23% MGMT promotor methylated; median KPS 90 (70 - 100); a median of 6 cycles of epacadostat as of May 2024 (1 - 13). 18 of 25 died with a median follow up 9.23 months. Median PFS was 7.52 months (95%CI: 5.52-9.43). Median OS was 9.5 months (95%CI 8.08-11.96). Regimen B met its primary endpoint with OS-9 of 61.07% (95%CI: 38.23-77.65%). There were 5 possible immune-related grade 3+ toxicities to date (2 ALT/AST increase; 3 rash). CONCLUSIONS Retifanlimab, epacadostat, HFRT, and bevacizumab in rGBM is well-tolerated, with encouraging OS and PFS at the time of submission. Arm B met its primary endpoint. Further studies are warranted to identify biomarkers to predict long-term responders.