人工智能下社区儿童安全用药指导新模式的探索

Introduction: Whereas ample information describes medication errors (MEs) in children or in mixed pediatric and adult populations discharged with acute or chronic diseases from hospital to community settings, little is known about MEs in children and adolescents with chronic diseases discharged home, a major concern. To promote home medication safety, we trained parents of children discharged with chronic diseases to record ME with a tailored cell-phone eHealth app. Methods: In a 1-year prospective study, we used the app to monitor ME in patients with chronic diseases discharged home from a tertiary hospital in Rome, Italy. Univariate and multivariate analyses detected the ME incidence rate ratio (IRR). Results: Of the 310 parents enrolled, 194 used the app. The 41 MEs involved all drug management phases. The ME IRR was 0.46 errors per child. Children <1 year had the highest ME risk (1.69 vs. 0.35, p = 0.002). Children discharged from the cardiology unit had a statistically higher ME IRR than others (3.66, 95% confidence interval: 1.01–13.23%). Conclusions: The highest ME risk at home involves children with chronic diseases <1 year old. A significant ME IRR at home concerns children with heart diseases of any age. Parents find a tailored eHealth app for monitoring and reporting ME at home easy to use. At discharge, clinical teams need to identify age-related and disease-residual risks to target additional actions for monitoring ME, thus increasing medication safety at home.

BACKGROUND Owing to pharmacokinetic variations in pediatric patients, many antibiotics require weight-based dosing to ensure medication safety and antimicrobial stewardship. Despite the need for weight-based dosing, prescribers are not legally required to include the weight or diagnosis code on pediatric prescriptions that are necessary components to verify appropriateness. Clinical decision support system (CDSS) can help clinicians improve dosing appropriateness, but little is known about CDSS in a community pharmacy setting. To determine the impact of implementing CDSS in this setting, baseline information is necessary. OBJECTIVES This study aimed to determine both the percentage of pediatric antibiotic prescriptions without optimal patient information required to evaluate weight-based dosing and the baseline percentage of prescriptions dosed outside of guideline recommendations. METHODS A retrospective chart review was conducted at a locally owned community pharmacy in rural Southeast Missouri. Prescriptions written for patients less than 18 years old for guideline recommended antibiotics used for acute otitis media or acute pharyngitis dispensed between October 1, 2020, and May 10, 2021, were included in the analysis. Prescriptions were considered optimal if they included both patient weight and diagnosis code. Optimal prescriptions were evaluated for adherence to guideline recommended dosing. The primary outcomes included percentage of prescriptions without patient weight, diagnosis code, or both and the percentage of optimal prescriptions prescribed outside of guideline recommended dosing for the specified condition. RESULTS Of the 115 included prescriptions, 45 were missing a patient weight, diagnosis code, or both. Seventy prescriptions were considered optimal, and of those, 42 (60%) were prescribed outside of guideline recommended dosing. CONCLUSION Prescriptions were identified as missing important information at the time of dispensing. Of the optimal prescriptions, the majority were prescribed outside of current guideline recommended dosing, with subtherapeutic dosing being the most common.

No abstract available

Introduction: The American Academy of Pediatrics recommends using isotonic intravenous fluids (IVF) for maintenance needs to decrease the risk of hyponatremia. We conducted a quality improvement project to increase the use of isotonic maintenance IVF in pediatric patients admitted to three sites in a community hospital network to >85% within 12 months. Methods: We used improvement methodology to identify causes of continued hypotonic fluid use, which involved provider behavior and systems factors. We implemented interventions to address these factors including: (1) education; (2) clinical decision support; and (3) stocking automated medication dispensing systems with isotonic IVF. We compared isotonic IVF use before and after interventions in all admitted patients aged 28 days to 18 years who received maintenance IVFs at the rate of at least 10 mL/hour. We excluded admissions of patients with active chronic medical conditions like diabetic ketoacidosis. Balancing measures were the occurrence of adverse events from hypo- or hypernatremia. Data were analyzed using Laney P′ statistical process control charts. Results: Isotonic IVF use among patients requiring maintenance fluids at all three sites surpassed the goal of >85% within 12 months. There were no reports of hypo- or hypernatremia or other adverse outcomes related to the use of isotonic IVF. Conclusion: A combination of interventions aimed at provider behavior and systems factors was critical to successfully adopting the American Academy of Pediatrics guideline regarding the use of maintenance isotonic IVF in hospitalized children.

Annually, thousands of children in the United States experience serious preventable health care harm.1 Although children are at an increased risk of health care harm compared with adults, they also have an important protective factor: their families. Cognizant of this, we believe that improvements in pediatric safety could be accelerated through better utilization of patient and family partnerships. Patients and families play an important role in health care safety in the hospital and the community as contributors to, detectors of, and mitigators of medical error.2 Parents may not understand or have the skills to manage their children’s home medication regimen, resulting in errors. Families are, however, well placed to detect errors and are equipped with extensive knowledge and astute observations of the child and their conditions. Finally, informed and empowered families can be important advocates for their children and can prevent errors from reaching and subsequently harming their children, acting as error safety nets.3–5 In this article, we will discuss how unsafe health care continues to harm children and how families can influence care safety, giving both parent (J.W.) and health care professionals’ (P.R. and K.E.W.) perspectives. We will discuss promising examples of family partnership for safety in hospital, outpatient, and community settings for children with varying health needs. Additionally, we will discuss barriers to optimal partnering and how we might build on positive examples and better tap into families’ unique potential to coproduce safer care. Thousands of children in the United States continue to suffer … Address correspondence to Philippa Rees, BSc (Hons), MPhil, MBBCh, Institute of Child Health University College London, 1st Floor, 30 Guilford St, London WC1N 1EH. E-mail: p.rees{at}ucl.ac.uk

Introduction: Medication errors are a leading safety concern, especially for families with limited English proficiency and health literacy, and patients discharged on multiple medications with complex schedules. Integration of a multilanguage electronic discharge medication platform may help decrease medication errors. This quality improvement (QI) project’s primary aim (process measure) was to increase utilization in the electronic health record (EHR) of the integrated MedActionPlanPro (MAP) for cardiovascular surgery and blood and marrow transplant patients at hospital discharge and for the first clinic follow-up visit to 80% by July 2021. Methods: This QI project occurred between August 2020 and July 2021 on 2 subspecialty pediatric acute care inpatient units and respective outpatient clinics. An interdisciplinary team developed and implemented interventions, including integration of MAP within EHR; the team tracked and analyzed outcomes for discharge medication matching, and efficacy and safety MAP integration occurred with a go-live date of February 1, 2021. Statistical process control charts tracked progress. Results: Following the implementation of the QI interventions, there was an increase from 0% to 73% in the utilization of the integrated MAP in the EHR across the acute care cardiology unit-cardiovascular surgery/blood and marrow transplant units. The average user hours per patient (outcome measure) decreased 70% from the centerline of 0.89 hours during the baseline period to 0.27 hours. In addition, the medication matching between Cerner inpatient and MAP inpatient increased significantly from baseline to postintervention by 25.6% (P < 0.001). Conclusion: MAP integration into the EHR was associated with improved inpatient discharge medication reconciliation safety and provider efficiency.

Introduction: Emerging evidence supports the use of alternative dosing weights for medications in patients with obesity. Pediatric obesity presents a particular challenge because most medications are dosed based on patient weight. Additionally, building system-wide pediatric obesity safeguards is difficult due to pediatric obesity definitions of body mass index-percentile-for-age via the Center for Disease Control growth charts. We describe a quality initiative to increase appropriate medication dosing in inpatients with obesity. The specific aim was to increase appropriate dosing for 7 high-risk medications in inpatients with obesity ≥2 years old from 37% to >74% and to sustain for 1 year. Methods: The Institute for Healthcare Improvement model for improvement was used to plan interventions and track outcomes progress. Interventions included a literature review to establish internal dosing guidance, electronic health record (EHR) functionality to identify pediatric patients with obesity, a default selection for medication weight with an opt-out, and obtaining patient heights in the emergency department. Results: Appropriate dosing weight use in medication ordered for patients with obesity increased from 37% to 83.4% and was sustained above the goal of 74% for 12 months. Conclusions: Implementation of EHR-based clinical decision support has increased appropriate evidence-based dosing of medications in pediatric and adult inpatients with obesity. Future studies should investigate the clinical and safety implications of using alternative dosing weights in pediatric patients.

Abstract Background Health care systems face challenges of inconsistent quality, inefficiency, and rising costs. Fragmented applications of clinical decision support systems (CDSSs), clinical pathways (CPs), and diagnosis-related group (DRG) payment systems have limited their synergistic potential. Objective This study proposed a CDSS-CP-DRG closed-loop model enabled by digital health technologies; specifically, the CDSS optimized CP execution through real-time data, the CP standardized workflows to support DRG cost control, and DRG payment pressures drove iterative improvements in both technology and processes. This research aimed to validate the model’s effectiveness in clinical efficacy, cost control, and standardized diagnosis and treatment of bronchopneumonia in children and provide evidence for value-based health care transformation. Methods A total of 4543 children with bronchopneumonia were selected and divided into the experimental or control group based on whether the intelligent diagnosis and cost control system was used in the diagnostic process. Chi-square test, 1-way analysis of variance, paired t test, multiple regression analysis, and other mathematical statistical methods were used to verify the difference between the outcomes of the two groups of patients. Results This study demonstrated comparably high cure rates in both groups (P>.05). However, the experimental group exhibited a 0.4-day reduction in average length of stay, 12.3% lower total hospitalization costs, RMB 135.3 (US $19) higher medical insurance reimbursement surplus, and a reduction of 0.16 defined daily doses of antibiotic use intensity versus the control group (P<.05 for all significant differences). Conclusions The novel intelligent diagnosis and cost control system demonstrated significant improvement in clinical effect, cost control, and standardized treatment for pediatric bronchopneumonia, but the CP for pediatric pneumonia requiring intensive care still needs further attention and adjustment.

No abstract available

This paper presents a machine learning pipeline for pediatric type 1 diabetes that fuses continuous glucose monitoring, insulin delivery, and meal inputs to forecast short-term glycemia and deliver actionable recommendations through a safety-aware conversational interface. A stacked LSTM model trained on the AZT1D real-world dataset learns 12-step temporal contexts over 62 engineered features, with regularization, early stopping, and patient-wise validation; clinical evaluation reports MAE, RMSE, MARD, time-in-range, and error-grid analyses to align with bedside utility. The system operationalizes predictions into individualized guidance for dosing, nutrition timing, and activity via a pediatric-oriented chat UI, illustrating how sequence models can translate multi-modal diabetes telemetry into interpretable, point-of-care decision support in ML-enabled healthcare.

Artificial intelligence-based clinical decision support systems (AI-CDSS) are emerging tools leveraging machine learning and healthcare data to aid pharmacists in managing clinical complexity. They offer real-time insights for identifying high-risk prescriptions, preventing drug interactions, and aiming to improve patient outcomes. While the strength of AI-CDSS lies in data-driven support, human-centered design focusing on trust and usability is crucial for adoption. Applications of AI-CDSS extend to patient care (e.g., disease prediction, medication adherence) and pharmacy practice, including prioritizing prescription reviews (e.g., Lumio Medication) and early detection of cognitive impairment. Although AI-CDSS shows potential in optimizing pharmacy workflows and identifying drug-related issues, direct evidence of improved patient outcomes within the pharmacy remains limited. Implementation faces challenges like technical constraints and workflow misalignment. This paper synthesizes current research, highlighting the potential of AI-CDSS to transform pharmacy practice while acknowledging the need for further investigation into their impact on patient outcomes and the practical barriers to their widespread use.

OBJECTIVES Access to evidence-based self-management support in pediatric inflammatory bowel disease (IBD) is a significant challenge. Digital therapeutic solutions can increase access and provide data to patients and providers that would otherwise not be available. We have iteratively developed a mobile application, Self-Management Assistance with Recommended Treatment (SMART) IBD, that allows patients to access self-management support and record symptoms and medication adherence. METHODS We conducted a pilot and feasibility study for this digital therapeutic tool in which patients used SMART IBD for 30 days. RESULTS Results indicated that patients rated the app quality as good and accessed the app adequately overall, with some pages being used often. Medication adherence increased over the course of the study and was associated with sleep duration, mood, and stool consistency and blood content. CONCLUSIONS Overall, this study demonstrated adequate feasibility for the SMART IBD app and initial findings suggest that additional research is needed to explore the potential impact of this tool in clinical care.

There is a well-recognized need for a shift to proactive asthma care given the impact asthma has on overall healthcare costs. The demand for continuous monitoring of patient's adherence to the medication care plan, assessment of environmental triggers, and management of asthma can be challenging in traditional clinical settings and taxing on clinical professionals. Recent years have seen a robust growth of general purpose conversational systems. However, they lack the capabilities to support applications such an individual's health, which requires the ability to contextualize, learn interactively, and provide the proper hyper-personalization needed to hold meaningful conversations. In this paper, we present kBot, a knowledge-enabled personalized chatbot system designed for health applications and adapted to help pediatric asthmatic patients (age 8 to 15) to better control their asthma. Its core functionalities include continuous monitoring of the patient's medication adherence and tracking of relevant health signals and environment data. kBot takes the form of an Android application with a frontend chat interface capable of conversing in both text and voice, and a backend cloud-based server application that handles data collection, processing, and dialogue management. It achieves contextualization by piecing together domain knowledge from online sources and inputs from our clinical partners. The personalization aspect is derived from patient answering questionnaires and day-to-day conversations. kBot's preliminary evaluation focused on chatbot quality, technology acceptance, and system usability involved eight asthma clinicians and eight researchers. For both groups, kBot achieved an overall technology acceptance value of greater than 8 on the 11-point Likert scale and a mean System Usability Score (SUS) greater than 80. A demo of our kBot application is available at this URL: https://bit.ly/kBot\_demo.

The objective of this study was to design, code, and test the feasibility, acceptability, and preliminary efficacy of a digital therapeutic self-management tool for pediatric inflammatory bowel disease (IBD). The Self-Management Assistance for Recommended Treatment (SMART) portal development involved an iterative co-design process with a series of focus group/interview sessions with key stakeholders. Subsequently, a pilot, single-arm, open-label trial was conducted with 22 patients; medication adherence was the primary outcome. Usage data for the SMART portal were good, with patients demonstrating better engagement than parents. Results from the trial demonstrated improvement in medication adherence (M = 24%–31%; t = 7.94, P < 0.05) and self-management barriers as well as trends in health-related quality of life and symptoms. The SMART portal is a feasible digital therapeutic self-management tool for pediatric IBD that demonstrated preliminary efficacy in this pilot trial. Large, controlled trials are needed to definitively determine the clinical efficacy of this tool.

BACKGROUND Medication errors and adverse drug events are common in the pediatric population. Limited English proficiency and low health literacy have been associated with decreased medication adherence, increased medication errors, and worse health outcomes. This study explores parental factors affecting medication management in underserved communities. METHODS Using qualitative methods, we identified factors believed to affect medication management among parents. We conducted focus group discussions between December 2019 and September 2020. We recruited parents and healthcare professionals from local community partners and a tertiary care children's hospital. Sessions were recorded and transcribed. Three investigators created the coding scheme. Two investigators independently coded each focus group and organized results into themes using thematic analysis. RESULTS Eleven focus groups were held (n=45): 4 English-speaking parent groups (n=18), 3 Spanish-speaking parent groups (n=11), and 4 healthcare professional groups (n=16). We identified four main factors that could impact medication delivery: 1) limited health literacy among parents and feeling inadequate at medication administration (knowledge/skill gap), 2) poor communication between caregivers (regarding medication delivery, dosage, frequency, and purpose) and between providers (regarding what has been prescribed), 3) lack of pediatric medication education resources, and 4) personal attitudes and beliefs that influence one's medication-related decisions. CONCLUSIONS The compounding effect of these factors - knowledge, communication, resource, and personal belief - may put families living in underserved communities at greater risk for medication errors and suboptimal health outcomes. These findings can be used to guide future interventions and may help optimize medication delivery for pediatric patients.

Medication adherence is crucial for effective treatment outcomes, yet many patients struggle to follow prescribed regimens. This research study presents a novel smart medication management system designed to address this challenge. The proposed system incorporates automated dispensing, timely reminders, and machine learning-based dosage recommendations. By tracking patient adherence data and health parameters, the system can offer personalized dosage recommendations, enhancing treatment effectiveness. This comprehensive approach not only aids patients in maintaining medication schedules but also provides healthcare providers with valuable insights into patient adherence. The integration of automated features and machine learning capabilities positions this system as a significant advancement in medication management technology.

No abstract available

Integrating smart tags in healthcare, particularly relating to managing safe medications and electronic health records, reveals a substantial step forward for patient safety and medication management efficiency. Medication errors contribute to some of the most adverse consequences for patients. Implementing smart tags, such as RFID, QR codes and barcodes and wearable devices, the risk of errors can be minimized. Connecting smart tags to an electronic health record leads to access to real-time and accurate information to enhance trust that right medications are given to the right patient at the right time. The interaction between smart tags and electronic health records improves medication safety and optimizes work processes and increases patient adherence, and facilitates collaboration amongst and improving healthcare team communications. All to offer a more straightforward, trusted patient-centered delivery of health care.

A medical reminder system is a computer-based program that helps individualsmanage their health by reminding them of their medications, appointments, and other health-related tasks. These systems can be used by healthcareprofessionals, caregivers, and patients themselves to improve medication adherence and reduce the risk of adverse health outcomes. A medical reminder system is a computerized software application designed to help patients and healthcare providers manage medication schedules and treatment plans. It uses a variety of methods to remind patients about medication times and dosages as well as appointments with healthcareproviders. The system can also provide educational resources and tools to help patients better understand their treatment plans. The primary objective of the system is to improve patient adherence to medication regimens, reduce the risk of medication errors, and ultimately improve health outcomes. A medical reminder system has the potential to enhance patient self- management, reduce healthcare costs, and improve overall quality of care. However, further research is needed to evaluate the system's effectiveness and impact on patient outcomes.

Background: Ensuring antibiotics are prescribed only when necessary is crucial for maintaining their effectiveness and is a key focus of public health initiatives worldwide. In cases of sinusitis, among the most common reasons for antibiotic prescriptions in children, healthcare providers must distinguish between bacterial and viral causes based on clinical signs and symptoms. However, due to the overlap between symptoms of acute sinusitis and viral upper respiratory infections, antibiotics are often over-prescribed. Objectives: Currently, there are no electronic health record (EHR)-based methods, such as lab tests or ICD-10 codes, to retroactively assess the appropriateness of these prescriptions, making manual chart reviews the only available method for evaluation, which is time-intensive and not feasible at a large scale. In this study, we propose using natural language processing to automate this assessment. Methods: We developed, trained, and evaluated generative models to classify the appropriateness of antibiotic prescriptions in 300 clinical notes from pediatric patients with sinusitis seen at a primary care practice in the Children's Hospital of Philadelphia network. We utilized standard prompt engineering techniques, including few-shot learning and chain-of-thought prompting, to refine an initial prompt. Additionally, we employed Parameter-Efficient Fine-Tuning to train a medium-sized generative model Llama 3 70B-instruct. Results: While parameter-efficient fine-tuning did not enhance performance, the combination of few-shot learning and chain-of-thought prompting proved beneficial. Our best results were achieved using the largest generative model publicly available to date, the Llama 3.1 405B-instruct. On our test set, the model correctly identified 91.4% of the 35 notes where antibiotic prescription was appropriate and 71.4% of the 14 notes where it was not appropriate. However, notes that were insufficiently, vaguely, or ambiguously documented by physicians posed a challenge to our model, as none evaluation sets were accurately classified. Conclusion: Our generative model demonstrated strong performance in the challenging task of chart review. This level of performance may be sufficient for deploying the model within the EHR, where it can assist physicians in real-time to prescribe antibiotics in concordance with the guidelines, or for monitoring antibiotic stewardship on a large scale.

Medication non-adherence rates in children range between 50% and 80% in the United States. Due to multifaceted outpatient routines, children receiving hematopoietic stem cell transplant (HCT) are at especially high risk of non-adherence, which can be life-threatening. Although digital health interventions have been effective in improving non-adherence in many pediatric conditions, limited research has examined their benefits among families of children receiving HCT. To address this gap, we created the BMT4me© mobile health app, an innovative intervention serving as a “virtual assistant” to send medication-taking reminders for caregivers and to track, in real-time, the child’s medication taking, barriers to missed doses, symptoms or side effects, and other notes regarding their child’s treatment. In this randomized controlled trial, caregivers will be randomized to either the control (standard of care) group or the intervention (BMT4me© app) group at initial discharge post-HCT. Both groups will receive an electronic adherence monitoring device (i.e., medication event monitoring system “MEMS” cap, Medy Remote Patient Management “MedyRPM” medication adherence box) to store their child’s immunosuppressant medication. Caregivers who agree to participate will be asked to complete enrollment, weekly, and monthly parent-proxy measures of their child’s medication adherence until the child reaches Day 100 or complete taper from immunosuppression. Caregivers will also participate in a 15 to 30-minute exit interview at the conclusion of the study. Descriptive statistics and correlations will be used to assess phone activity and use behavior over time. Independent samples t-tests will examine the efficacy of the intervention to improve adherence monitoring and reduce readmission rates. The primary expected outcome of this study is that the BMT4me© app will improve the real-time monitoring and medication adherence in children receiving hematopoietic stem cell transplant following discharge, thus improving clinical outcomes.

In the field of medical education, the innovation and optimization of teaching methods have always been the key to improving the quality of education. The popularization of the WeChat platform has provided a broader application space for question banks, especially digital question banks. To improve the teaching quality of pediatric surgery, a digital question bank for pediatric surgery was constructed based on the WeChat platform and applied to the clinical teaching of pediatric surgery. We explore whether integrating the digital question bank into the WeChat platform can help improve examination scores and also explore students’ satisfaction. In this study, a clinical question bank covering pediatric surgery was established and then entered into the WeChat Official Accounts Platform. The instructor guides the medical students to use the WeChat platform for daily teaching activities and to complete the assessment of the digital question bank. A relevant evaluation system was established based on the big data results provided by the WeChat Official Account. This evaluation system was composed of the evaluation of instructors for the learning initiative and knowledge mastery of medical students and the evaluation of medical students for the teaching level of instructors and the digital question bank pattern. A digital question bank of pediatric surgery was successfully established. A total of about 3,200 questions in the question bank were uploaded to the WeChat Official Account of the pediatric surgery department of Qilu Hospital of Shandong University. Based on the digital question bank, partial clinical teaching tasks of pediatric surgery were completed, and the learning effects of medical students were evaluated. The question bank exhibited a favorable difficulty coefficient and discrimination, and the examination scores conformed to the normal distribution, indicating the higher scientific and effectiveness of this question bank. The questionnaire survey results demonstrated that most medical students maintained that the application of the new question bank based on the WeChat Official Accounts Platform can increase their learning interest in pediatrics, cultivate their clinical thinking, and enhance their clinical ability. A digital question bank of pediatric surgery was established for the first time based on the WeChat Official Accounts Platform. This digital question bank can be employed to evaluate the learning effects of medical students more scientifically, which contributes to improving teaching quality and teaching management. Overall, the new pediatric surgery question bank and the WeChat Official Accounts Platform can satisfy the development demands of pediatric surgery in the new era, exhibiting broad application prospects.

Abstract Background The opioid crisis has significantly impacted adolescents and their families. This is attributed in part to increased opioid prescriptions in pediatric emergency departments (EDs) due to acute pain conditions and injuries. Although EDs frequently prescribe opioids, no effective preventative interventions have been implemented to educate adolescents and their families on safe opioid use. This study evaluates the MedSMA℞T Families intervention, which consists of an engaging serious game, Adventures in PharmaCity, and a personalized Family Medication Safety Plan (FMSP) with the aim of reducing opioid misuse and promoting opioid medication safety. The MedSMA℞T Families intervention was developed to educate adolescents and adults prescribed opioids on safe practices such as opioid storage and disposal. Objective This study aimed to explore and characterize adolescents’ and parents’ experiences and perspectives on implementing the MedSMA℞T Families intervention in the ED to improve opioid education and safety among adolescents. Methods A total of 93 participants, including 16 children and 77 parents, were recruited from the pediatric ED at a tertiary academic hospital to play the MedSMA℞T game in the ED. A total of 16 participants, including 8 children and 8 parents, were followed up with interviews to gather qualitative feedback. Participants engaged with the MedSMA℞T game—Adventures in PharmaCity—and the FMSP. Data were collected through gameplay observation and 75-minute semistructured interviews via Zoom. Quantitative in-game data were analyzed using descriptive analysis and qualitative data were analyzed using thematic analysis with NVivo (version 14; Lumivero). Results Parents spent an average of 22.16 (SD 4.97) minutes playing the game, while children spent an average of 21.99 (SD 8.06) minutes. Families appreciated the game’s design and noted usability challenges and suggested enhancements for clearer gameplay instructions. Participants reported increased knowledge of opioid safety, highlighted the importance of communication with health care providers, and a desire for a mobile app to assist with medication management. The FMSP was perceived as valuable for promoting awareness of safe practices and connected well to the knowledge gained from the game. Conclusions The MedSMA℞T Families intervention was well received as a beneficial educational tool to educate adolescents and their families on safe opioid use. Additionally, it highlights a clear need for more accessible digital tools to increase opioid education. This feedback indicates a strong interest in improving educational resources to ensure safe opioid management within families.

PURPOSE To understand the views of parent participants in our larger pilot randomized controlled trial (RCT) about the Tool to Empower Parental TeLling and TaLking or the TELL Tool, a digital, psychoeducational and decision-support intervention; and to foster understanding about how pediatric nurse practitioners (PNPs) viewed integrating the TELL Tool into pediatric clinical settings. DESIGN AND METHODS In this qualitative descriptive study, a purposive sample of 10 parents and 10 PNPs completed in-depth, semi-structured interviews by Zoom. The recordings were auto transcribed, checked for accuracy, and analyzed for themes. The rigorous and accelerated data reduction (RADaR) technique was incorporated into the analytic plan. RESULTS Five themes emerged following analysis, including Perceptions, Optimal Time for Delivery, Most Appropriate Healthcare Provider to Counsel Parents about Disclosure, Challenges to Administering in Practice, and Recommendations for Implementing the TELL Tool into Pediatric Healthcare Settings. CONCLUSIONS Parents found the TELL Tool to be helpful and PNPs were supportive of incorporating the TELL Tool into clinical practice. Parents thought the TELL Tool increased their confidence about sharing information and appreciated its age-appropriate approach and language. PNPs perceived the tool as supporting their ability to provide anticipatory guidance and counseling/education to families seeking support in beginning and subsequent conversations with their children about their genetic origins. PRACTICE IMPLICATIONS The TELL Tool is an evidence-based intervention that can serve as a resource for PNPs while supporting parents as they navigate challenges about talking with their children about their genetic origins through gamete and embryo donation.

Background Electronic health record–based clinical decision support (CDS) tools can facilitate the adoption of evidence into practice. Yet, the impact of CDS beyond single-site implementation is often limited by dissemination and implementation barriers related to site- and user-specific variation in workflows and behaviors. The translation of evidence-based CDS from initial development to implementation in heterogeneous environments requires a framework that assures careful balancing of fidelity to core functional elements with adaptations to ensure compatibility with new contexts. Objective This study aims to develop and apply a framework to guide tailoring and implementing CDS across diverse clinical settings. Methods In preparation for a multisite trial implementing CDS for pediatric overweight or obesity in primary care, we developed the User-Centered Framework for Implementation of Technology (UFIT), a framework that integrates principles from user-centered design (UCD), human factors/ergonomics theories, and implementation science to guide both CDS adaptation and tailoring of related implementation strategies. Our transdisciplinary study team conducted semistructured interviews with pediatric primary care clinicians and a diverse group of stakeholders from 3 health systems in the northeastern, midwestern, and southeastern United States to inform and apply the framework for our formative evaluation. Results We conducted 41 qualitative interviews with primary care clinicians (n=21) and other stakeholders (n=20). Our workflow analysis found 3 primary ways in which clinicians interact with the electronic health record during primary care well-child visits identifying opportunities for decision support. Additionally, we identified differences in practice patterns across contexts necessitating a multiprong design approach to support a variety of workflows, user needs, preferences, and implementation strategies. Conclusions UFIT integrates theories and guidance from UCD, human factors/ergonomics, and implementation science to promote fit with local contexts for optimal outcomes. The components of UFIT were used to guide the development of Improving Pediatric Obesity Practice Using Prompts, an integrated package comprising CDS for obesity or overweight treatment with tailored implementation strategies. Trial Registration ClinicalTrials.gov NCT05627011; https://clinicaltrials.gov/study/NCT05627011

BACKGROUND Asthma is the most common chronic disease in children. Suboptimal asthma control is prevalent and causes significant health care costs. Electronic health records (EHRs) contain vast data which pose a major challenge for timely and efficient access to relevant information for clinical decision making. To address this challenge, a machine learning and natural language processing models-powered clinical decision support system (CDS) called Asthma-Guidance Prediction System (A-GPS) was developed. A-GPS automatically extracts and synthesizes pertinent patient data from EHRs for asthma management. To further enhance A-GPS, real-time patient data was added from a home spirometry device and mobile app system (AsthmaTuner), that remotely collected patient-reported outcomes for asthma control and lung function and delivered a clinician-prescribed Asthma Action Plan from EHR to patients. The goal of the study was to assess the feasibility and satisfaction of implementation of an integrated A-GPS with AsthmaTuner for remote asthma management within pediatric primary care. METHODS Study design was a parallel-group, non-blinded, dual-site, 2-arm pragmatic, randomized clinical trial (RCT) with 22 dyads (one clinician and one pediatric patient) at Mayo Clinic Health System and Mayo Clinic, Rochester, Minnesota. The primary endpoint was successful implementation of the integrated A-GPS with AsthmaTuner in primary care and study participants' satisfaction. CONCLUSION The technological integration and application of the integrated A-GPS and AsthmaTuner in primary care as a clinical CDS for remote asthma management was feasible. This protocol provides developers with a framework for the best practices for evaluating AI tools and enables digital technology via an RCT. TRIAL REGISTRATION Registered via ClinicalTrials.govNCT06062433 SIGNIFICANCE: We anticipate this study will establish a conceptual and operational framework for implementing AI-powered CDS in pediatric asthma management, with the goal that these methodological advancements will be expanded to the management of adults with asthma and other chronic complex diseases. Reporting a clinical trial protocol for the evaluation of an AI tool and following the reporting guidelines are valuable for establishing best practices evaluating AI tools, specifically for the developers and other key stakeholders who plan to evaluate AI models via RCTs in health care settings. We plan to communicate our trial results via publication and reporting in ClinicalTrials.gov database (NCT06062433). Authorship on publications will follow international standards for authorship (i.e., ICMJE).

Epilepsy, a chronic brain disorder characterized by abnormal brain activity that causes seizures and other symptoms, is typically treated using anti-epileptic drugs (AEDs) as the first-line therapy. However, due to the variations in their modes of action, identification of effective AEDs often relies on ad hoc trials, which is particularly challenging for pediatric patients. Thus, there is significant value in computational methods capable of assisting in the selection of AEDs, aiming to minimize unnecessary medication and improve treatment efficacy. In this study, we collected 7,507 medical records from 1,000 pediatric epilepsy patients and developed a computational clinical decision-supporting system for AED selection. This system leverages three multi-channel convolutional neural network (CNN) models tailored to three specific AEDs (vigabatrin, prednisolone, and clobazam). Each CNN model predicts whether a respective AED is effective on a given patient or not. The CNN models showed AUROCs of 0.90, 0.80, and 0.92 in 10-fold cross-validation, respectively. Evaluation on a hold-out test dataset further revealed positive predictive values (PPVs) of 0.92, 0.97, and 0.91 for the three respective CNN models, representing that suggested AEDs by our models would be effective in controlling epilepsy with a high accuracy and thereby reducing unnecessary medications for pediatric patients. Our CNN models in the system demonstrated high PPVs for the three AEDs, which signifies the potential of our approach to support the clinical decision-making by assisting doctors in recommending effective AEDs within the three AEDs for patients based on their medical history. This would result in a reduction in the number of unnecessary ad hoc attempts to find an effective AED for pediatric epilepsy patients.

Pharmacometrics could play a key role in shifting pediatric pharmacotherapy from dosing for an average patient to individualizing dosing. Clinicians can have these quantitative tools at their disposal without requiring significant training through the development of clinical decision support systems with easy‐to‐use interfaces that have a back‐end analysis engine or pharmacometric model that uses extensive electronic health record data to predict an individualized dose for each patient. There has been increased development of these clinical decision support systems recently, and for these tools to make the proper breakthrough into clinical practice, it is of utmost importance to perform rigorous testing to ensure adequate predictive performance. In this article, we walk through the components of a decision support tool and the testing required to determine its robustness using an example of a decision support tool we developed for vancomycin dosing in pediatrics.

Abstract Machine learning models may be integrated into clinical decision support (CDS) systems to identify children at risk of specific diagnoses or clinical deterioration to provide evidence-based recommendations. This use of artificial intelligence models in clinical decision support (AI-CDS) may have several advantages over traditional “rule-based” CDS models in pediatric care through increased model accuracy, with fewer false alerts and missed patients. AI-CDS tools must be appropriately developed, provide insight into the rationale behind decisions, be seamlessly integrated into care pathways, be intuitive to use, answer clinically relevant questions, respect the content expertise of the healthcare provider, and be scientifically sound. While numerous machine learning models have been reported in pediatric care, their integration into AI-CDS remains incompletely realized to date. Important challenges in the application of AI models in pediatric care include the relatively lower rates of clinically significant outcomes compared to adults, and the lack of sufficiently large datasets available necessary for the development of machine learning models. In this review article, we summarize key concepts related to AI-CDS, its current application to pediatric care, and its potential benefits and risks. Impact The performance of clinical decision support may be enhanced by the utilization of machine learning-based algorithms to improve the predictive performance of underlying models. Artificial intelligence-based clinical decision support (AI-CDS) uses models that are experientially improved through training and are particularly well suited toward high-dimensional data. The application of AI-CDS toward pediatric care remains limited currently but represents an important area of future research.

BACKGROUND General pediatric providers are the frontline for early peanut introduction discussions, but many feel ill-equipped to handle such discussions as guidelines have quickly changed. OBJECTIVE We hypothesized that a clinical decision support (CDS) tool could improve peanut introduction discussions. METHODS CDS tools were designed by stakeholders, improved through usability testing, and integrated into the current note templates. Based on queries of electronic health record (EHR), we did a pre-post performance evaluation of peanut introduction conversations, barriers for introduction, and percentage of 12-month WCC visits that had successfully introduced peanut. Providers completed surveys before and after intervention to assess awareness of early peanut introduction and comfort using CDS. RESULTS Providers' awareness of early peanut introduction guidelines increased from 17.8% to 66.7% after the CDS tool was implemented. 79.1% were comfortable using the tool. The CDS tool improved peanut introduction conversations at the 4-month well-child (WCC) care visit from 2.4% to 81.2%, at the 6-month WCC visit from 3.0% to 84.2%, and at the 12-month WCC visit from 2.7% to 82.9%. 56.6% of families had a plan to introduce peanut at the 4-month WCC visit. Of those who did not have a plan, the most common barrier was family's unawareness of the benefits of early peanut introduction. At the 12-month visit, 62.8% of families had introduced peanut without concerns. CONCLUSION A point-of-care CDS tool encouraged more discussions by general pediatric providers on early peanut introduction to all patients. CDS tools should be considered in quality improvement projects as an implementation method for the most up-to-date guidelines.

Abstract Background  Primary care pediatricians play an important role in genetic testing, including referrals, test ordering, responding to results, assessing risk, treatment, and managing care. As genetic testing rapidly evolves to include new tests identifying patients at risk for certain conditions, alert-based clinical decision support is insufficient in assisting pediatric primary care providers in working with patients, parents, genetics, and other specialties. Supporting pediatricians in the return of these results requires addressing gaps in genetics training and integrating genetics into practice with education, information resources, and specialized tools. Objectives  This study aimed to capture requirements for developing systems and processes to support primary care pediatricians in the return of genome-informed risk assessments. Methods  We performed a requirements analysis to inform the design of clinical decision support tools and processes for pediatric providers of patients who received a genome informed risk assessment, a novel test that combines polygenic risk scores with patient and family histories to deliver a risk assessment for common medical conditions. We developed an interview guide consisting of scenario presentations, questionnaires, and semi-structured questions to elicit provider responses on a broad set of requirements to manage results with patients and caregivers. Results  Twenty providers from 10 primary care pediatric practices within a single health system participated in the study. The findings demonstrated that providers feel responsible to be involved in the process of returning results but require a support system that integrates education, provider and patient information resources, effective communication with genetics, and electronic health record decision support tools that can accommodate a range of clinical scenarios and provider workflow preferences. Conclusion  Supporting providers with the return of genetic testing results such as the genome informed risk assessment requires a comprehensive approach to decision support consisting of education, communication, and a comprehensive and integrated set of electronic health record tools.