Objectives/Goals: The study’s objective was to use real-world data to compare machine learning approaches for predicting colorectal cancer (CRC) screening status: (1) a Random Forest model optimized for overall accuracy and (2) Feasible Solution Algorithm (FSA) models focused on interpretability and identifying subgroups at risk of being unscreened. Methods/Study Population: The data included 22,549 adults aged 45–75 who visited a UK King’s Daughters Medical Center (UKKD) primary care site between 12/1/2023–11/30/2024, across five Appalachian counties. Patients with total colectomy, colon cancer, advanced illness, hospice care, dementia, and/or frailty were excluded. After complete-case analysis, 18,533 records remained and were split 80/20 for training/testing. Two machine learning methods, random forests and FSA, were applied to identify key predictors of CRC screening status. Within the FSA framework, logistic regression models were fitted using the training data, and model performance metrics were subsequently evaluated using the testing dataset. Results/Anticipated Results: Overall (n=22,549), 65.6% of patients completed CRC screening. The mean age was 59 years (SD = 8.2); most were White (97%), 40% had Medicare insurance, and 68% had multiple non-primary care provider (PCP) visits. The Random Forest model demonstrated the highest overall accuracy of 69% and had notably high sensitivity, correctly identifying approximately 9 of 10 screened patients. On the other hand, the FSA model offered greater specificity (65%) and interpretability, with the 2-predictor model identifying smokers and those with 0 non-PCP visits as the vulnerable subgroups who are least likely to be screened. Discussion/Significance of Impact: FSA identified smoking status, insurance type, number of non-PCP clinic visits, and age as key factors relating to CRC screening behavior. These findings can help clinicians and public health teams identify unscreened patients, guide targeted outreach, and advance translational strategies to improve population health.

OBJECTIVES/SPECIFIC AIMS: Despite advancements in therapies, such as surgery, irradiation (IR) and chemotherapy, outcome for patients suffering from glioblastoma remains fatal; the median survival rate is only about 15 months. Even with novel therapeutic targets, networks and signaling pathways being discovered, monotherapy with such agents targeting such pathways has been disappointing in clinical trials. Poor prognosis for GBM can be attributed to several factors, including failure of drugs to cross the blood-brain-barrier (BBB), tumor heterogeneity, metastasis and angiogenesis. Development of tumor resistance, particularly to temozolomide (TMZ), creates a substantial clinical challenge.The primary focus of our work is to rationally develop novel combination therapies and dose regimens that mitigate resistance development. Specifically, our aim is to combine TMZ with small molecule inhibitors that are either currently in clinical trials or are approved drugs for other cancer types, and which target the disease at various resistance signaling pathways that are induced in response to TMZ monotherapy. METHODS/STUDY POPULATION: To accomplish this objective, an integrated PKPD modeling approach is used. The approach is largely based on the work of Cardilin, et al, 2018. A PK model for each drug is first defined. This is subsequently linked to a PD model description of tumor growth dynamics in the presence of a single drug or combinations of drugs. A key outcome of these combined PKPD models are tumor static concentration (TSC) curves of dual or triple combination drug regimens that identify combination drug exposures predicted to arrest tumor growth. This approach has been applied to TMZ in combination with abemaciclib (a dual CDK4/6 small molecule inhibitor) based on data from a published study evaluating abemaciclib efficacy in combination with TMZ in a glioblastoma xenograft model (Raub, et al, 2015). RESULTS/ANTICIPATED RESULTS: A PKPD model was developed to predict tumor growth kinetics for TMZ and abemaciclib monotherapy, as well as combination therapy. Population PK models in immune deficient NSG mice for temozolomide and abemaciclib were developed based on data obtained from original and published studies. Subsequently, the PK model was linked to tumor volume data obtained from U87-MG GBM subcutaneous xenografts, again using both original data as well as data from the Raub, et al, 2015 study. Model parameters quantifying tumor volume dynamics were precisely estimated (coefficient of variation < 30%). The developed PKPD model was used to calculate plasma concentrations of TMZ and abemaciclib that would arrest tumor growth, as well as combinations of concentrations of the two drugs that would accomplish the same endpoint. This so-called TSC curve for the TMZ and abemaciclib combination pair evidenced an additive effect of the two agents when administered together. These results will be presented. In addition, results from on-going PKPD studies of TMZ in combination with two other small molecule inhibitors, RG7388, an MDM2 inhibitor, and GDC0068, an AKT inhibitor, will also be presented. DISCUSSION/SIGNIFICANCE OF IMPACT: Our long-term goals are to further elucidate SOC-induced responses in GBM and establish combination treatment regimens that are safe and significantly improve therapeutic efficacy. Collectively, our studies will broadly influence chemotherapy of GBM by establishing a process to rationally design combination approaches that mitigate resistance development. These studies will ultimately provide opportunities to study other targeted agents tailored to individual molecular signatures of GBM, as well as other tumor types.

OBJECTIVES/SPECIFIC AIMS: To demonstrate that olanzapine recapitulates the effect of increased lateral hypothalamic (LH) GABAergic activity in the DRN and the DBB. This will provide a potential neural substrate for the observed increase in consumption of food and weight gain. METHODS/STUDY POPULATION: (1) We will examine electrophysiological activity of the DRN and the DBB in response to optogenetic stimulation of LH fibers to these nuclei. (2) We will identify the behavioral phenotype of stimulating these same projections using optogenetic techniques. (3a) Identify the behavioral phenotype of mice possessing cre-loxp-dependent knockout (KO) of LH GABAergic activity, DRN serotonergic activity, and inhibition of DBB cholinergic activity. (3b) Using these mice, we will establish behavioral response to olanzapine in ad libitum feeding and fast-refeeding condition. (4) Using baseline and post-treatment body mass index (BMI), PANSS, and side effect profile scores from a recently completed prospective cohort study of treatment-naive schizophrenic patients receiving atypical antipsychotics for 1 year, we will sequence multiple single nucleotide polymorphisms and explore the correlation of serotonergic, dopaminergic, and cholinergic receptor mutations with the increase in BMI and changes in PANSS score and side effect scores. RESULTS/ANTICIPATED RESULTS: (1) Our preliminary data indicates that the LH exclusively sends GABAergic input to the DBB, and the large majority of its projections to the DRN are GABAergic. (2) We have identified that stimulating LH–>DBB projections produces intense feeding and drinking behavior, a real-time place preference for laser stimulation, and a conditioned place preference for laser stimulation. Preliminary data shows that the LH->DRN also produces feeding behavior. (3a) Our lab has demonstrated that transgenic mice with LH-specific GABA release KO are smaller, have increased anxiety-like behaviors such a repetitive grooming and open field aversion, and have reduced feeding after fasting conditions. We expect the DRN serotonergic KO mice to have increased body weight and reduced anxiety-like behaviors. (3b) Our pilot study demonstrated that the LH GABA KO mice administered olanzapine have a greater consumption of food over 1 hour than controls (n=7, 5, respectively; p=0.08). DRN serotonergic KO mice and mice with inhibition of choline will have an increased baseline feeding behavior, but will not be affected by olanzapine. (4) We believe that SNPs in serotonergic receptors such as 5HT2C, and those affecting dopaminergic and cholinergic receptors, will be more common in schizophrenic patients with increased BMI than those without. Further, we believe that a reduction in the PANSS items reflecting anxiety and aversiveness will correlate with increased BMI, since we postulate that mimicking LH GABAergic activity will produce its previously demonstrated anxiolytic effects. DISCUSSION/SIGNIFICANCE OF IMPACT: Identifying the important role for a reward-oriented feeding center in the brain in producing antipsychotic weight gain will allow a more comprehensive, ethologically sound approach to behavioral modification therapy in these patients. It will lend mechanistic credence to weight control therapies which have used token economy, opioid antagonism, and other inhibition-promoting therapies. This study will also increase the validity for testing further the use of selective serotonin agonists which prevent weight gain such as lorcaserin.

OBJECTIVES/GOALS: The purpose of this study is to determine critical recovery support factors (SDOH, postpartum and post-discharge continuity of care), to optimize continuity of recovery and to determine the best intervention among postpartum and parenting women for treatment retention. METHODS/STUDY POPULATION: Through a mixed methods approach, we will review retrospective hospital discharge data to identify hospital-based gaps in treatment. We will conduct key informant interviews with postpartum women, treatment providers and stakeholders to broaden understanding of critical recovery factors from lived experiences and test a parent-centered evidence-based intervention for a comprehensive and targeted approach to recovery. RESULTS/ANTICIPATED RESULTS: This research will lead to new understanding of critical maternal recovery support factors for sustaining treatment retention for 6-12 months after childbirth and to improve long term maternal health outcomes. DISCUSSION/SIGNIFICANCE: The recovery journey and postpartum period are challenging and lack specific recovery support evidence. Recovery support and continuity of care protocols are unclear after childbirth. Maternal opioid-related overdose deaths occur 6-12 months after childbirth. Therefore, this study will impact and inform recovery retention strategies.

ABSTRACT IMPACT: Identifying the causative antigen in membranous glomerulopathy cohorts enables the development of serum assays to detect and monitor disease progression without the need for invasive kidney biopsies. OBJECTIVES/GOALS: Primary membranous glomerulopathy is caused by the formation of autoantibody immune complexes which deposit in the glomerulus and obstruct kidney function. Causative antigens remain to be identified in roughly 20% of cases. Our goal is to identify the antigen in these cohorts, so that non-invasive assays can be developed for disease monitoring. METHODS/STUDY POPULATION: Renal biopsy tissue from known antigen cases (PLA2R, THSD7A), and unknown cases were included in the analysis. Renal biopsy tissue from formalin fixed paraffin embedded tissue was cut at a thickness of 10 µm onto Leica PET-membrane frame slides. These slides were then stained with hematoxylin. The glomeruli were microdissected into microcentrifuge tubes using a Leica DM6000B microscope. The microdissected glomeruli were lysed in 2% SDS and 0.1M DTT at 99 degrees Celsius for 1 hour and processed by filter assisted sample preparation (FASP). Digested peptides were analyzed by liquid chromatography-mass spectrometry using an Orbitrap Fusion Lumos using data-dependent acquisition. RESULTS/ANTICIPATED RESULTS: Mass spectrometry data collected from the laser captured glomeruli was searched against the human proteome fasta database from Uniprot using MaxQuant. IBAQ values were used for quantitation and statistical analysis. Null hypothesis significance testing was performed for each protein by comparing each sample group to the rest of the samples in the data set. In the control groups, the causative antigens PLA2R and THSD7A were detected and quantified with the largest magnitude fold change in their respective category, validating the experimental design. Using this approach, the proteins SAP, NELL1, and NCAM1 were identified and subsequently validated as causative antigens in distinct patient cohorts. DISCUSSION/SIGNIFICANCE OF FINDINGS: Here, we share the results of our efforts to comprehensively identify the spectrum of causative antigens in membranous glomerulopathy. In this context, antigen discovery is an essential first step for the development of non-invasive assays to inform prognosis, monitor response to treatment, and better understand disease etiology.

Objectives/Goals: The Fanconi anemia (FA) pathway is responsible for faithful DNA damage repair. FA mutations are common in multiple types of cancer, including HPV-negative head and neck cancers. We sought to identify synthetic lethal genes within this pathway to target treatment of FA-mutant tumors through siRNA- and chemical-compound-based screens. Methods/Study Population: First, we completed siRNA-based and chemical compound-based screening assays to identify gene targets that reduce patient derived Fanconi pathway mutant cell (FA-D2) viability compared to Fanconi pathway proficient cells (FA-D2 + FANCD2). Five aurora kinase (AURK) inhibitors from the compound screen were chosen for further evaluation. Cell lines were treated with AURK inhibitors or siRNA-based AURK knockdown to assess viability, proliferation, DNA repair, and cell cycle progression differences. Patient mutational, mRNA expression, and outcome data were accessed through The Cancer Genome Atlas (TCGA) portal and the Caris CODEai portal. We stratified patients by tumor AURKA and AURKB mRNA levels and assessed differences in patient survival, tumor grade, and DNA repair proficiency. Results/Anticipated Results: In both screens, AURKA came up as a target to selectively reduce the growth of FA-D2 cells compared to FA-D2 + FANCD2 cells. All five AURK inhibitors identified showed selective growth inhibition (~50–75%) in FA-D2 cells at low nanomolar doses. We narrowed our selection to hesperadin, an AURKB-specific inhibitor, which showed the highest selectivity. siRNA knockdown of AURKA and AURKB decreased cell viability by 50% and 20%, respectively. Patients with FA-mutated tumors from the TCGA pan-cancer dataset had high AURKA (twofold) and AURKB (threefold) mRNA expression. AURKA and AURKB tumor mRNA expression was significantly associated with poor patient survival. Homologous recombination deficiency scores were increased ~5-fold (p Discussion/Significance of Impact: We hypothesize that in FA-deficient backgrounds, loss of AURKA or AURKB leads to heightened genomic instability due to cell cycle dysregulation and accumulated DNA damage. Our findings warrant investigation of the therapeutic potential for AURK inhibitors, specifically hesperadin, in FA-mutant head and neck cancers.

OBJECTIVES/SPECIFIC AIMS: Pelvic organ prolapse, a disorder in which the muscles of the pelvic floor are weakened over time, affects over a million women each year in the United States. A quarter of these women undergo a reconstructive procedure, increasingly using polypropylene mesh as mechanical reinforcement to the pelvic floor. However, the number of complications such as chronic pain and mesh erosion/exposure in women with vaginal mesh implants were reported at rates as high as 10%–20%. This indicates a limited understanding of the host response to mesh in vaginal tissue and strategies to reduce these complications. Utilizing a novel surgical technique in New Zealand white rabbits, we implant mesh analogously to human implantation and evaluate changes in the immunologic response at early (14 d) and tissue remodeling outcomes at late stages (90 and 180 d) of implantation. The mesh-tissue complex was removed from each rabbit and processed for histological staining as well as immunolabeling of immune cells, such as macrophages. Extracellular matrix protease assays and mechanical integrity of the tissue also evaluate the overall inflammatory response associated with each implant. METHODS/STUDY POPULATION: Commercially available polypropylene mesh was used to investigate the modulation of the immune response. An adapted radio frequency glow discharge method is used to create a stable negative charge on the surface of the mesh, followed by the sequential deposition of polycationic and polyanionic polymers to provide a stable, conformal, nanoscale coating. It is well known macrophages are characterized on a spectrum ranging from a proinflammatory M1 phenotype to an M2 anti-inflammatory phenotype. Interleukin-4, an immunomodulatory cytokine known to promote the M2 phenotype, is incorporated into the coating to be released in a controlled manner upon implantation. Utilizing a novel surgical technique in New Zealand white rabbits, we implant mesh using the “gold standard” abdominal sacrocolpopexy procedure and evaluate changes in the immunologic response at early (14 d) and tissue remodeling outcomes at late stages (90 and 180 d) of implantation. The procedure begins with an initial hysterectomy removing the uterus followed by creating space along the vaginal wall on both sides between the bladder and the rectum. Two 3×10 cm2 pieces of mesh are secured along both sides of the vaginal wall. The remaining flaps at the top are then secured to a ligament in the sacral/lumbar space, creating the support to the pelvic organs. Upon closing the incision, a partial thickness defect is made in the abdominal wall, and mesh is implanted inside to repair the abdominal muscle. Both of these implantations of mesh allow for the assessment of the immune response in the pelvic area (relevant for prolapse patients) and in the abdominal area (relevant for translation from hernia repair).The mesh-tissue complex was removed from each rabbit and processed for histological staining as well as immunolabeling of immune cells, such as macrophages. Extracellular matrix protease assays and mechanical integrity of the tissue also evaluate the overall inflammatory response associated with each implant. RESULTS/ANTICIPATED RESULTS: The results of this study show that implants into vaginal tissues elicited an increased host inflammatory response at 14 days as compared with those in the abdominal wall. However, at chronic time points the inflammatory response in the vagina was reduced as compared to that in the abdominal cavity. The present study also demonstrates the scale-up of a previous methodology for a nanoscale coating. We present a nanometer thickness, tunable, and uniform coating capable of releasing bioactive interleukin-4. We evaluated the biological functionality of the coated mesh via bioactivity studies and in vivo implantation. An ideal mesh would provide mechanical support to the pelvic floor while decreasing the inflammatory response and increasing integration with the surrounding native tissue. DISCUSSION/SIGNIFICANCE OF IMPACT: We developed an in vivo model clinically relevant to understanding the early host response to mesh in an anatomically relevant area, the vaginal microenvironment. Previous studies have been conducted in a rodent abdominal defect model while other work has been done in a nonhuman primate vaginal model, but the host response is only observed at later time points (>3 mo). Thus, we developed a rabbit model to investigate early responses and a novel coating to actively working towards improved tissue integration.

OBJECTIVES/GOALS: This study seeks to determine the relationship between fear of COVID-19 infection and care-seeking behaviors including provider visit and telemedicine utilization among vulnerable adolescent and young adults in Baltimore, Maryland METHODS/STUDY POPULATION: Participants enrolled in the COVID-19 Youth study were 13-25 years old and recruited from four existing sexual health studies based in Baltimore, MD which focused on 1) PID, 2) HIV, 3) emerging sexually transmitted infections, and 4) a dyadic STI prevention, respectively. Participants agreed to be re-contacted for future studies and completed a telephone survey developed to inquire about the impacts of COVID-19 on care seeking behaviors. Bivariate analyses tested for correlations between fear of COVID-19 infection, demographic variables, and care-seeking behaviors. Multivariable logistic regression modeled associations between fear of COVID-19 infection and care-seeking behaviors. RESULTS/ANTICIPATED RESULTS: Adjusted multivariable logistic regression revealed a statistically significant association between fear of COVID-19 infection and having a provider visit; AYA who feared COVID-19 were at greater than two times increased odds of a provider visit compared to AYA who did not fear COVID-19 infection (OR: 2.37, 95%CI: 1.02, 6.15). Among those with a provider visit, fear of COVID-19 infection was associated with two-fold increased odds of having a telemedicine visit vs. an in-person visit (OR: 2.23, 95%CI: 1.09, 4.51), however this was not statistically significant in the adjusted model. There were however significant associations detected in the adjusted model for HIV status, insurance type and telemedicine utilization respectively. DISCUSSION/SIGNIFICANCE: This study demonstrates the ongoing need for health services during the recent pandemic and overall willingness of AYA to utilize telemedicine. Given the sexual health disparities faced by AYA, who bear more than half of the 50 million STI cases in the US, optimizing services for AYA is essential and consistent with new laws expanding telehealth use.

OBJECTIVES/GOALS: The goal of this study is to identify if ocular graft versus host disease (oGVHD) patients treated with a systemic JAK inhibitor have a change in their tear cytokine profile (a possible bio-marker) and oGVHD score. oGHVD is a severe inflammatory dry eye disease and major cause of morbidity after a hematopoietic stem cell transplant. METHODS/STUDY POPULATION: Janus Kinase (JAK) is an upstream regulator of cytokine production. A JAK 1/2 inhibitor, Ruxolitinib, was recently FDA approved for the treatment of chronic GVHD. We propose that JAK inhibition results incytokine changes in tears and improvement of oGVHD. To study this, we will quantify tear cytokines in patients with oGVHD, with and without systemic JAK inhibition treatment. Patients with ‘definite’ oGVHD based on the international chronic oGVHD diagnostic criteria (ICOGVHD) whom we have collected tears will be grouped based on JAK inhibition treatment. Tear cytokines are analyzed using Iso spark Meteor bulk quantitative proteomic analysis. RESULTS/ANTICIPATED RESULTS: Seven patients were identified from our patient cohort who met inclusion criteria (oGVHD; tears collected while on Ruxolitinib), five patients were identified whom we have collected tears with oGVHD who have not taken ruxolitinib. The following 10 cytokines will be analyzed in the tears by the Iso spark Meteor bulk quantitative proteomic analysis: GM-CSF, IFN-g, IL-2, IL-4, IL-5, IL-6, IL-8, IL-10, IL-17A, TNF-a. The change in cytokine levels will be compared with the ICOGVHD score, corneal fluorescein staining, schirmers test (measurement of tear production), conjunctival injection score, ocular surface disease index score (validated symptomatic score of dry eye disease). DISCUSSION/SIGNIFICANCE: OGVHD is a major cause of morbidity for patients who undergo a hematopoietic stem cell transplant and is the result of a highly complex immune process including dysregulation of pro-inflammatory cytokines. It is critical to understand the effect of cytokine changes on the eyes to potentially identify a biomarker and possible treatment targets.

OBJECTIVES/GOALS: Allopregnanolone (ALLO), a modulator of GABAA receptors, may be useful as a treatment for human and canine benzodiazepine-refractory status epilepticus (SE). Our objective was to develop a phamacokinetic-pharmacodynamic (PKPD) model relating ALLO plasma concentrations to electroencephalographic (EEG) effects in dogs. METHODS/STUDY POPULATION: Four healthy dogs and one dog with epilepsy that had implanted intracranial electrodes were utilized. ALLO doses ranging from 1-6 mg/kg were administered IV over 5 min. EEG data were collected during four IM doses (1-2 mg/kg). Blood samples were collected up to 6 hr following dosing. ALLO concentrations were measured using HPLC-MS/MS. Power density was determined in EEG bands using a custom algorithm. A two-compartment link PKPD model was developed to describe the relation between ALLO plasma concentration and change in EEG power in the alpha, beta, delta and theta bands. RESULTS/ANTICIPATED RESULTS: ALLO caused a rapid increase in absolute power density in all EEG bands measured (1-4, >4 – 8, >8 – 12, >12 – 25, and >25 – 100 Hz). The onset of effect was rapid (1-3 min) and demonstrated by frequency band and dose analysis. Concentration-EEG data were best fit by a two-compartment PK model and sigmoidal Emax PD indirect link model. The beta frequency band was most sensitive, showing increases in power at the lowest ALLO concentrations. The EC50 concentration for the beta frequency was ~270 ng/mL. The EC50 values for effects on the other frequency bands were ~500-700 ng /mL. In conclusion, IV ALLO causes a rapid effect on EEG that can be used to determine minimal plasma concentrations associated with target engagement. DISCUSSION/SIGNIFICANCE OF IMPACT: Dose selection for future clinical trials will use the effective concentrations determined here in conjunction with studies in animal status epilepticus models. Studies are planned in client owned dogs with epilepsy to evaluate clinical efficacy in dogs and as nonclinical proof-of-concept evidence supporting translational studies in people. CONFLICT OF INTEREST DESCRIPTION: Michael Rogawski and Dorota Zolkowska are named as inventors on patent applications claiming use of neuroactive steroids including allopregnanolone and ganaxolone in the treatment of status epilepticus.

This paper is part of the Environmental Scan of Adaptive Capacity and Preparedness of Clinical and Translational Science Award (CTSA) hubs, illuminating challenges, practices, and lessons learned related to CTSA hubs’ efforts of engaging community partners to reduce the spread of the virus, address barriers to COVID-19 testing, identify treatments to improve health outcomes, and advance community participation in research. CTSA researchers, staff, and community partners collaborated to develop evidence-based, inclusive, accessible, and culturally appropriate strategies and resources helping community members stay healthy, informed, and connected during the pandemic. CTSA institutions have used various mechanisms to advance co-learning and co-sharing of knowledge, resources, tools, and experiences between academic professionals, patients, community partners, and other stakeholders. Forward-looking and adaptive decision-making structures are those that prioritize sustained relationships, mutual trust and commitment, ongoing communication, proactive identification of community concerns and needs, shared goals and decision making, as well as ample appreciation of community members and their contributions to translational research. There is a strong need for further community-engaged research and workforce training on how to build our collective and individual adaptive capacity to sustain and improve processes and outcomes of engagement with and by communities—in all aspects of translational science.

Objectives/Goals: The need for accessible medical information has never been greater. Existing research and clinical documents are often too complex for the public to understand. This study aimed to evaluate the use of AI algorithms to convert research and clinical materials into language that is more easily understood while maintaining accuracy and informativeness. Methods/Study Population: We abstracted 21 half-page texts from informed consents, clinical documents, abstracts, and health-related websites. Each original text was then rewritten using 3 AI algorithms (resulting in 63 new, rewritten texts). Participants were given a set of 3 randomly selected surveys. Each survey contained the original text and an AI-rewritten text. Participants were then asked to answer 5 questions using a Likert scale 1-5 about the readability, clarity, and content of the two texts, their overall score of the new text, and which text they preferred. The study was IRB-approved. Participants were given a $10 gift card. Results/Anticipated Results: 68 participants (69.6% non-white, 65.2% female, mean age 58.3) completed the study task. 3 AI Algorithms were tested: * ConBART [Cripwell 2023]: context-aware method for text simplification * UL+Decoder [Flores 2023]: Flesh-Kincaid readability-driven method for text simplification * UBclear [House-made]: Iteratively improves readability with self-correction and retrieval-augmented generation. ConBART and UL+Decoder scored similarly across readability, clarity, and detail-fidelity metrics, but were preferred over original texts less than 50% of the time. UBclear scored higher in readability, clarity, detail, and overall score. Importantly, UBclear text was preferred over the original text 80% of the time, showing stronger alignment with human judgments of clarity, readability, and fidelity. Discussion/Significance of Impact: Our pilot study shows that AI can simplify existing research and medical care documents, potentially contributing to inclusivity and transparency in research and clinical care. “UBclear” was superior to the other 2 AI methodologies in readability, accessibility, and clarity while also being preferred over original texts and competing AI versions.