Price transparency at the point of prescribing with real-time prescription benefits.

PURPOSE: Real-time prescription benefits (RTPB) shows prescribers patient-, medication-, and pharmacy-specific information on medication pricing, prior authorization requirements, and lower-cost alternatives. RTPB is intended to improve patient satisfaction and prescription fill rates by decreasing out-of-pocket costs for prescriptions. Therefore, we evaluated how RTPB affects prescribing patterns by examining acceptance and subsequent fill rates for RTPB alternative suggestions. METHODS: RTPB was implemented in February 2022 using external vendor interfaces. Prescribing data from March 2022 to March 2023 were analyzed. RTPB displayed alerts for medications requiring prior authorization or when alternative medications would result in cost savings. Patients were included if their prescription received an RTPB response and they had a subsequent encounter with pharmacy fill data. Primary outcomes were alert acceptance rates and prescription fill rates across RTPB alert groups, with a secondary outcome of monthly copay savings for accepted alerts. RESULTS: RTPB requests received a response for 88% of prescriptions, with price estimates provided for 77.9% of them. Lower-cost alternatives accounted for 67.2% of alerts, while prior authorization requirements represented 15% of alerts. Prescribers selected a lower-cost alternative 32% of the time. For those with an RTPB alert, patients filled prescriptions 68% of the time when an alternative was chosen, compared to 59% of the time when the original prescription was retained (odds ratio, 1.5; 95% confidence interval, 1.5-1.6; P < 0.001). Patients saved an average of $27.77 per month on copay costs when alternatives were selected. CONCLUSION: Implementation of RTPB was found to result in significant improvements in prescription fill rates and decrease patient copay costs, despite low alert acceptance rates.

Improving Medication Management for Inpatients with a Secondary Diagnosis of Parkinson Disease.

ABSTRACT: Patients who have Parkinson disease require individualized medication regimens to optimize care. A review of the medication management of patients admitted to a tertiary care hospital with a secondary diagnosis of Parkinson disease found significant departures from the patients' home regimen. Medication regimens are often altered by health care teams unfamiliar with Parkinson disease-specific care in order to conform to standard hospital medication orders and administration times, potentially resulting in increased patient falls, delirium, and mortality.A nurse-led multidisciplinary team consisting of pharmacy, nursing, informatics, neurology, and quality personnel implemented a quality improvement (QI) project between July 2020 and July 2022 to identify patients with Parkinson disease, including those with a secondary diagnosis and those undergoing deep brain stimulation, and customize medication management in order to reduce length of stay, mortality, falls, falls with harm, and 30-day readmissions. The QI project team also evaluated patient satisfaction with medication management.Among patients with a secondary diagnosis of Parkinson disease, the proportion who had medication histories conducted by a pharmacy staff member increased from a baseline of 53% to more than 75% per month. For all patients with Parkinson disease, those whose medication history was taken by a pharmacy staff member had orders matching their home regimen 89% of the time, whereas those who did not had orders matching the home regimen only 40% of the time. Among patients with a secondary diagnosis of Parkinson disease, the length-of-stay index decreased from a baseline of 1 to 0.94 and observed-to-expected mortality decreased from 1.03 to 0.78. The proportion of patients experiencing a fall decreased from an average of 5% to 4.08% per quarter, while the proportion of patients experiencing a fall with harm decreased from an average of 1% to 0.75% per quarter. The rate of 30-day readmissions decreased from 10.81% to 4.53% per quarter. Patient satisfaction scores were 1.95 points higher for patients who had medication histories taken by pharmacy than for those who did not (5 versus 3.05).

Latent Epstein-Barr virus infection collaborates with Myc over-expression in normal human B cells to induce Burkitt-like Lymphomas in mice.

Epstein-Barr virus (EBV) is an important cause of human lymphomas, including Burkitt lymphoma (BL). EBV+ BLs are driven by Myc translocation and have stringent forms of viral latency that do not express either of the two major EBV oncoproteins, EBNA2 (which mimics Notch signaling) and LMP1 (which activates NF-κB signaling). Suppression of Myc-induced apoptosis, often through mutation of the TP53 (p53) gene or inhibition of pro-apoptotic BCL2L11 (BIM) gene expression, is required for development of Myc-driven BLs. EBV+ BLs contain fewer cellular mutations in apoptotic pathways compared to EBV-negative BLs, suggesting that latent EBV infection inhibits Myc-induced apoptosis. Here we use an EBNA2-deleted EBV virus (ΔEBNA2 EBV) to create the first in vivo model for EBV+ BL-like lymphomas derived from primary human B cells. We show that cord blood B cells infected with both ΔEBNA2 EBV and a Myc-expressing vector proliferate indefinitely on a CD40L/IL21 expressing feeder layer in vitro and cause rapid onset EBV+ BL-like tumors in NSG mice. These LMP1/EBNA2-negative Myc-driven lymphomas have wild type p53 and very low BIM, and express numerous germinal center B cell proteins (including TCF3, BACH2, Myb, CD10, CCDN3, and GCSAM) in the absence of BCL6 expression. Myc-induced activation of Myb mediates expression of many of these BL-associated proteins. We demonstrate that Myc blocks LMP1 expression both by inhibiting expression of cellular factors (STAT3 and Src) that activate LMP1 transcription and by increasing expression of proteins (DNMT3B and UHRF1) known to enhance DNA methylation of the LMP1 promoters in human BLs. These results show that latent EBV infection collaborates with Myc over-expression to induce BL-like human B-cell lymphomas in mice. As NF-κB signaling retards the growth of EBV-negative BLs, Myc-mediated repression of LMP1 may be essential for latent EBV infection and Myc translocation to collaboratively induce human BLs.

The prospect of artificial intelligence to personalize assisted reproductive technology.

Infertility affects 1-in-6 couples, with repeated intensive cycles of assisted reproductive technology (ART) required by many to achieve a desired live birth. In ART, typically, clinicians and laboratory staff consider patient characteristics, previous treatment responses, and ongoing monitoring to determine treatment decisions. However, the reproducibility, weighting, and interpretation of these characteristics are contentious, and highly operator-dependent, resulting in considerable reliance on clinical experience. Artificial intelligence (AI) is ideally suited to handle, process, and analyze large, dynamic, temporal datasets with multiple intermediary outcomes that are generated during an ART cycle. Here, we review how AI has demonstrated potential for optimization and personalization of key steps in a reproducible manner, including: drug selection and dosing, cycle monitoring, induction of oocyte maturation, and selection of the most competent gametes and embryos, to improve the overall efficacy and safety of ART.

Why do users override alerts? Utilizing large language model to summarize comments and optimize clinical decision support.

OBJECTIVES: To evaluate the capability of using generative artificial intelligence (AI) in summarizing alert comments and to determine if the AI-generated summary could be used to improve clinical decision support (CDS) alerts. MATERIALS AND METHODS: We extracted user comments to alerts generated from September 1, 2022 to September 1, 2023 at Vanderbilt University Medical Center. For a subset of 8 alerts, comment summaries were generated independently by 2 physicians and then separately by GPT-4. We surveyed 5 CDS experts to rate the human-generated and AI-generated summaries on a scale from 1 (strongly disagree) to 5 (strongly agree) for the 4 metrics: clarity, completeness, accuracy, and usefulness. RESULTS: Five CDS experts participated in the survey. A total of 16 human-generated summaries and 8 AI-generated summaries were assessed. Among the top 8 rated summaries, five were generated by GPT-4. AI-generated summaries demonstrated high levels of clarity, accuracy, and usefulness, similar to the human-generated summaries. Moreover, AI-generated summaries exhibited significantly higher completeness and usefulness compared to the human-generated summaries (AI: 3.4 ± 1.2, human: 2.7 ± 1.2, P = .001). CONCLUSION: End-user comments provide clinicians' immediate feedback to CDS alerts and can serve as a direct and valuable data resource for improving CDS delivery. Traditionally, these comments may not be considered in the CDS review process due to their unstructured nature, large volume, and the presence of redundant or irrelevant content. Our study demonstrates that GPT-4 is capable of distilling these comments into summaries characterized by high clarity, accuracy, and completeness. AI-generated summaries are equivalent and potentially better than human-generated summaries. These AI-generated summaries could provide CDS experts with a novel means of reviewing user comments to rapidly optimize CDS alerts both online and offline.

Leveraging explainable artificial intelligence to optimize clinical decision support.

OBJECTIVE: To develop and evaluate a data-driven process to generate suggestions for improving alert criteria using explainable artificial intelligence (XAI) approaches. METHODS: We extracted data on alerts generated from January 1, 2019 to December 31, 2020, at Vanderbilt University Medical Center. We developed machine learning models to predict user responses to alerts. We applied XAI techniques to generate global explanations and local explanations. We evaluated the generated suggestions by comparing with alert's historical change logs and stakeholder interviews. Suggestions that either matched (or partially matched) changes already made to the alert or were considered clinically correct were classified as helpful. RESULTS: The final dataset included 2 991 823 firings with 2689 features. Among the 5 machine learning models, the LightGBM model achieved the highest Area under the ROC Curve: 0.919 [0.918, 0.920]. We identified 96 helpful suggestions. A total of 278 807 firings (9.3%) could have been eliminated. Some of the suggestions also revealed workflow and education issues. CONCLUSION: We developed a data-driven process to generate suggestions for improving alert criteria using XAI techniques. Our approach could identify improvements regarding clinical decision support (CDS) that might be overlooked or delayed in manual reviews. It also unveils a secondary purpose for the XAI: to improve quality by discovering scenarios where CDS alerts are not accepted due to workflow, education, or staffing issues.

Clinical compatibility of magnetic resonance imaging with magnetic intramedullary nails: a feasibility study.

INTRODUCTION: The use of magnetic resonance imaging (MRI) with a magnetic intramedullary lengthening nail in place is contraindicated per the manufacturer due to the concern of implant activation and migration. A prior in vitro study did not confirm these complications only noting that a 3.0 T MRI weakened the internal magnet. Therefore, a retrospective analysis of patients who underwent an MRI with a magnetic nail in place was performed to determine if any adverse effects occurred in the clinical setting. MATERIALS AND METHODS: A retrospective review of all patients who underwent an MRI with a magnetic lengthening nail in place was performed. The time spent being imaged in the MRI, number of times the patient entered the MRI suite, and the images obtained were recorded. Radiographs were performed before and after the MRI to determine if any hardware complications occurred. The patients were monitored for any adverse symptoms while they were in the suite. RESULTS: A total of 12 patients with 13 nails were identified. Two patients underwent imaging with a 3.0 T MRI while the remaining 10 underwent imaging with a 1.5 T MRI. Each patient entered the MRI suite 2.1 times and spent an average of 84.7 min being imaged in the MRI (range 21-494). No patients noted any adverse symptoms related to the nail while in the suite and no hardware complications were identified. CONCLUSION: MRI appears to be safe with a magnetic nail in place and did not result in any complications. Given the manufacturer's recommendations, informed consent should be obtained prior to an MRI being performed and a 3.0 T MRI should be avoided when possible if further activation of the nail is required.

A Randomized Trial of Two Remote Health Care Delivery Models on the Uptake of Genetic Testing and Impact on Patient-Reported Psychological Outcomes in Families With Pancreatic Cancer: The Genetic Education, Risk Assessment, and Testing (GENERATE) Study.

BACKGROUND & AIMS: Genetic testing uptake for cancer susceptibility in family members of patients with cancer is suboptimal. Among relatives of patients with pancreatic ductal adenocarcinoma (PDAC), The GENetic Education, Risk Assessment, and TEsting (GENERATE) study evaluated 2 online genetic education/testing delivery models and their impact on patient-reported psychological outcomes. METHODS: Eligible participants had ≥1 first-degree relative with PDAC, or ≥1 first-/second-degree relative with PDAC with a known pathogenic germline variant in 1 of 13 PDAC predisposition genes. Participants were randomized by family, between May 8, 2019, and June 1, 2021. Arm 1 participants underwent a remote interactive telemedicine session and online genetic education. Arm 2 participants were offered online genetic education only. All participants were offered germline testing. The primary outcome was genetic testing uptake, compared by permutation tests and mixed-effects logistic regression models. We hypothesized that Arm 1 participants would have a higher genetic testing uptake than Arm 2. Validated surveys were administered to assess patient-reported anxiety, depression, and cancer worry at baseline and 3 months postintervention. RESULTS: A total of 424 families were randomized, including 601 participants (n = 296 Arm 1; n = 305 Arm 2), 90% of whom completed genetic testing (Arm 1 [87%]; Arm 2 [93%], P = .014). Arm 1 participants were significantly less likely to complete genetic testing compared with Arm 2 participants (adjusted ratio [Arm1/Arm2] 0.90, 95% confidence interval 0.78-0.98). Among participants who completed patient-reported psychological outcomes questionnaires (Arm 1 [n = 194]; Arm 2 [n = 206]), the intervention did not affect mean anxiety, depression, or cancer worry scores. CONCLUSIONS: Remote genetic education and testing can be a successful and complementary option for delivering genetics care. (Clinicaltrials.gov, number NCT03762590).

Sensitivity of North American grassland birds to weather and climate variability.

Grassland birds in North America have declined sharply over the last 60 years, driven by the widespread loss and degradation of grassland habitats. Climate change is occurring more rapidly in grasslands relative to some other ecosystems, and exposure to extreme and novel climate conditions may affect grassland bird ecology and demographics. To determine the potential effects of weather and climate variability on grassland birds, we conducted a systematic review of relationships between temperature and precipitation and demographic responses in grassland bird species of North America. Based on 124 independent studies, we used a vote-counting approach to quantify the frequency and direction of significant effects of weather and climate variability on grassland birds. Grassland birds tended to experience positive and negative effects of higher temperatures and altered precipitation. Moderate, sustained increases in mean temperature and precipitation benefitted some species, but extreme heat, drought, and heavy rainfall often reduced abundance and nest success. These patterns varied among climate regions, temporal scales of temperature and precipitation (<1 or ≥1 month), and taxa. The sensitivity of grassland bird populations to extreme weather and altered climate variability will likely be mediated by regional climates, interaction with other stressors, life-history strategies of various species, and species' tolerances for novel climate conditions.

Sensibilidad de las aves norteamericanas de pastizales ante la variabilidad climática y el clima Resumen Las aves de los pastizales norteamericanos han declinado gravemente durante los últimos 60 años, principalmente debido a la pérdida generalizada y la degradación del hábitat. El cambio climático ocurre cada vez más rápido en los pastizales en relación con otros ecosistemas, y la exposición a las condiciones climáticas nuevas y extremas puede afectar la demografía y la ecología aviar en los pastizales. Realizamos un análisis sistemático de las relaciones entre la temperatura y la precipitación y las respuestas demográficas de las especies de aves de pastizales en Norteamérica para determinar los efectos potenciales del clima y la variabilidad climática sobre estas aves. Usamos un método de conteo de votos basado en 124 estudios independientes para cuantificar la frecuencia y dirección de los efectos significativos del clima y la variabilidad climática sobre las aves de pastizal. Las aves de pastizal tendieron a experimentar los efectos positivos y negativos de las altas temperaturas y la precipitación alterada. El incremento moderado y sostenido en las medias de temperatura y precipitación beneficiaron a algunas especies, pero el calor extremo, la sequía y las lluvias torrenciales redujeron con frecuencia la abundancia y el éxito de anidación. Estos patrones variaron entre las regiones climáticas, las escalas temporales de temperatura y precipitación (< 1 mes o ≥ 1 mes) y los taxones. La sensibilidad de las poblaciones de aves de pastizal ante el clima extremo y la variabilidad climática alterada probablemente será mediada por los climas regionales, la interacción con otros estresantes, las estrategias de vida de varias especies y la tolerancia de las especies a las condiciones climáticas nuevas.

TSH and FT4 Reference Interval Recommendations and Prevalence of Gestational Thyroid Dysfunction: Quantification of Current Diagnostic Approaches.

CONTEXT: Guidelines recommend use of population- and trimester-specific thyroid-stimulating hormone (TSH) and free thyroxine (FT4) reference intervals (RIs) in pregnancy. Since these are often unavailable, clinicians frequently rely on alternative diagnostic strategies. We sought to quantify the diagnostic consequences of current recommendations. METHODS: We included cohorts participating in the Consortium on Thyroid and Pregnancy. Different approaches were used to define RIs: a TSH fixed upper limit of 4.0 mU/L (fixed limit approach), a fixed subtraction from the upper limit for TSH of 0.5 mU/L (subtraction approach) and using nonpregnancy RIs. Outcome measures were sensitivity and false discovery rate (FDR) of women for whom levothyroxine treatment was indicated and those for whom treatment would be considered according to international guidelines. RESULTS: The study population comprised 52 496 participants from 18 cohorts. Compared with the use of trimester-specific RIs, alternative approaches had a low sensitivity (0.63-0.82) and high FDR (0.11-0.35) to detect women with a treatment indication or consideration. Sensitivity and FDR to detect a treatment indication in the first trimester were similar between the fixed limit, subtraction, and nonpregnancy approach (0.77-0.11 vs 0.74-0.16 vs 0.60-0.11). The diagnostic performance to detect overt hypothyroidism, isolated hypothyroxinemia, and (sub)clinical hyperthyroidism mainly varied between FT4 RI approaches, while the diagnostic performance to detect subclinical hypothyroidism varied between the applied TSH RI approaches. CONCLUSION: Alternative approaches to define RIs for TSH and FT4 in pregnancy result in considerable overdiagnosis and underdiagnosis compared with population- and trimester-specific RIs. Additional strategies need to be explored to optimize identification of thyroid dysfunction during pregnancy.

Luteal phase support in assisted reproductive technology.

Infertility affects one in six couples, with in vitro fertilization (IVF) offering many the chance of conception. Compared to the solitary oocyte produced during the natural menstrual cycle, the supraphysiological ovarian stimulation needed to produce multiple oocytes during IVF results in a dysfunctional luteal phase that can be insufficient to support implantation and maintain pregnancy. Consequently, hormonal supplementation with luteal phase support, principally exogenous progesterone, is used to optimize pregnancy rates; however, luteal phase support remains largely 'black-box' with insufficient clarity regarding the optimal timing, dosing, route and duration of treatment. Herein, we review the evidence on luteal phase support and highlight remaining uncertainties and future research directions. Specifically, we outline the physiological luteal phase, which is regulated by progesterone from the corpus luteum, and evaluate how it is altered by the supraphysiological ovarian stimulation used during IVF. Additionally, we describe the effects of the hormonal triggers used to mature oocytes on the degree of luteal phase support required. We explain the histological transformation of the endometrium during the luteal phase and evaluate markers of endometrial receptivity that attempt to identify the 'window of implantation'. We also cover progesterone receptor signalling, circulating progesterone levels associated with implantation, and the pharmacokinetics of available progesterone formulations to inform the design of luteal phase support regimens.

Revealing the dynamic landscape of drug-drug interactions through network analysis.

Introduction: The landscape of drug-drug interactions (DDIs) has evolved significantly over the past 60 years, necessitating a retrospective analysis to identify research trends and under-explored areas. While methodologies like bibliometric analysis provide valuable quantitative perspectives on DDI research, they have not successfully delineated the complex interrelations between drugs. Understanding these intricate relationships is essential for deciphering the evolving architecture and progressive transformation of DDI research structures over time. We utilize network analysis to unearth the multifaceted relationships between drugs, offering a richer, more nuanced comprehension of shifts in research focus within the DDI landscape. Methods: This groundbreaking investigation employs natural language processing, techniques, specifically Named Entity Recognition (NER) via ScispaCy, and the information extraction model, SciFive, to extract pharmacokinetic (PK) and pharmacodynamic (PD) DDI evidence from PubMed articles spanning January 1962 to July 2023. It reveals key trends and patterns through an innovative network analysis approach. Static network analysis is deployed to discern structural patterns in DDI research, while evolving network analysis is employed to monitor changes in the DDI research trend structures over time. Results: Our compelling results shed light on the scale-free characteristics of pharmacokinetic, pharmacodynamic, and their combined networks, exhibiting power law exponent values of 2.5, 2.82, and 2.46, respectively. In these networks, a select few drugs serve as central hubs, engaging in extensive interactions with a multitude of other drugs. Interestingly, the networks conform to a densification power law, illustrating that the number of DDIs grows exponentially as new drugs are added to the DDI network. Notably, we discovered that drugs connected in PK and PD networks predominantly belong to the same categories defined by the Anatomical Therapeutic Chemical (ATC) classification system, with fewer interactions observed between drugs from different categories. Discussion: The finding suggests that PK and PD DDIs between drugs from different ATC categories have not been studied as extensively as those between drugs within the same categories. By unearthing these hidden patterns, our study paves the way for a deeper understanding of the DDI landscape, providing valuable information for future DDI research, clinical practice, and drug development focus areas.

Beyond the Umbrella: A Systematic Review of the Interventions for the Prevention of and Reduction in the Incidence and Severity of Ovarian Hyperstimulation Syndrome in Patients Who Undergo In Vitro Fertilization Treatments.

Ovarian hyperstimulation syndrome (OHSS) is the main severe complication of ovarian stimulation for in vitro fertilization (IVF) cycles. The aim of the current study was to identify the interventions for the prevention of and reduction in the incidence and severity of OHSS in patients who undergo IVF not included in systematic reviews with meta-analyses of randomized controlled trials (RCTs) and assess and grade their efficacy and evidence base. The best available evidence for each specific intervention was identified, analyzed in terms of safety/efficacy ratio and risk of bias, and graded using the Oxford Centre for Evidence-Based Medicine (CEBM) hierarchy of evidence. A total of 15 interventions to prevent OHSS were included in the final analysis. In the IVF population not at a high risk for OHSS, follitropin delta for ovarian stimulation may reduce the incidence of early OHSS and/or preventive interventions for early OHSS. In high-risk patients, inositol pretreatment, ovulation triggering with low doses of urinary hCG, and the luteal phase administration of a GnRH antagonist may reduce OHSS risk. In conclusion, even if not supported by systematic reviews with homogeneity of the RCTs, several treatments/strategies to reduce the incidence and severity of OHSS have been shown to be promising.

Association between perinatal mortality and morbidity and customised and non-customised birthweight centiles in Denmark, Finland, Norway, Wales, and England: comparative, population based, record linkage study.

Objectives: To compare the risk of adverse perinatal outcomes according to infants who are born small for gestational age (SGA; <10th centile) or large for gestational age (LGA; >90th centile), as defined by birthweight centiles that are non-customised (ie, standardised by sex and gestational age only) and customised (by sex, gestational age, maternal weight, height, parity, and ethnic group). Design: Comparative, population based, record linkage study with meta-analysis of results. Setting: Denmark, Finland, Norway, Wales, and England (city of Bradford), 1986-2019. Participants: 2 129 782 infants born at term in birth registries. Main outcome measures: Stillbirth, neonatal death, infant death, admission to neonatal intensive care unit, and low Apgar score (<7) at 5 minutes. Results: Relative to those infants born average for gestational age (AGA), both SGA and LGA births were at increased risk of all five outcomes, but observed relative risks were similar irrespective of whether non-customised or customised charts were used. For example, for SGA versus AGA births, when non-customised and customised charts were used, relative risks pooled over countries were 3.60 (95% confidence interval 3.29 to 3.93) versus 3.58 (3.02 to 4.24) for stillbirth, 2.83 (2.18 to 3.67) versus 3.32 (2.05 to 5.36) for neonatal death, 2.82 (2.07 to 3.83) versus 3.17 (2.20 to 4.56) for infant death, 1.66 (1.49 to 1.86) versus 1.54 (1.30 to 1.81) for low Apgar score at 5 minutes, and (based on Bradford data only) 1.97 (1.74 to 2.22) versus 1.94 (1.70 to 2.21) for admission to the neonatal intensive care unit. The estimated sensitivity of combined SGA or LGA births to identify the three mortality outcomes ranged from 31% to 34% for non-customised charts and from 34% to 38% for customised charts, with a specificity of 82% and 80% with non-customised and customised charts, respectively. Conclusions: These results suggest an increased risk of adverse perinatal outcomes of a similar magnitude among SGA or LGA term infants when customised and non-customised centiles are used. Use of customised charts for SGA/LGA births-over and above use of non-customised charts for SGA/LGA births-is unlikely to provide benefits in terms of identifying term births at risk of these outcomes.

Evaluation of inpatient medication guidance from an artificial intelligence chatbot.

PURPOSE: To analyze the clinical completeness, correctness, usefulness, and safety of chatbot and medication database responses to everyday inpatient medication-use questions. METHODS: We evaluated the responses from an artificial intelligence chatbot, a medication database, and clinical pharmacists to 200 real-world medication-use questions. Answer quality was rated by a blinded group of pharmacists, providers, and nurses. Chatbot and medication database responses were deemed "acceptable" if the mean reviewer rating was within 3 points of the mean rating for pharmacists' answers. We used descriptive statistics for reviewer ratings and Kendall's coefficient to evaluate interrater agreement. RESULTS: The medication database generated responses to 194 (97%) questions, with 88% considered acceptable for clinical correctness, 76% considered acceptable for completeness, 83% considered acceptable for safety, and 81% considered acceptable for usefulness compared to pharmacists' answers. The chatbot responded to only 160 (80%) questions, with 85% considered acceptable for clinical correctness, 65% considered acceptable for completeness, 71% considered acceptable for safety, and 68% considered acceptable for usefulness. CONCLUSION: Traditional search methods using a drug database provide more clinically correct, complete, safe, and useful answers than a chatbot. When the chatbot generated a response, the clinical correctness was similar to that of a drug database; however, it was not rated as favorably for clinical completeness, safety, or usefulness. Our results highlight the need for ongoing training and continued improvements to artificial intelligence chatbots for them to be incorporated reliably into the clinical workflow. With continued improvement in chatbot functionality, chatbots could be a useful pharmacist adjunct, providing healthcare providers with quick and reliable answers to medication-use questions.