Learning Health Systems最新文献_第8页

A machine learning approach to predicting inpatient mortality among pediatric acute gastroenteritis patients in Kenya 预测肯尼亚儿科急性肠胃炎患者住院死亡率的机器学习方法

IF 2.6 Q2 HEALTH POLICY & SERVICES

Learning Health Systems

Pub Date : 2024-12-26 DOI: 10.1002/lrh2.10478

Billy Ogwel, Vincent H. Mzazi, Bryan O. Nyawanda, Gabriel Otieno, Kirkby D. Tickell, Richard Omore

Background

Mortality prediction scores for children admitted with diarrhea are unavailable, early identification of at-risk patients for proper management remains a challenge. This study utilizes machine learning (ML) to develop a highly sensitive model for timelier identification of at-risk children admitted with acute gastroenteritis (AGE) for better management.

Methods

We used seven ML algorithms to build prognostic models for the prediction of mortality using de-identified data collected from children aged <5 years hospitalized with AGE at Siaya County Referral Hospital (SCRH), Kenya, between 2010 through 2020. Potential predictors included demographic, medical history, and clinical examination data collected at admission to hospital. We conducted split-sampling and employed tenfold cross-validation in the model development. We evaluated the sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and the area under the curve (AUC) for each of the models.

Results

During the study period, 12 546 children aged <5 years admitted at SCRH were enrolled in the inpatient disease surveillance, of whom 2271 (18.1%) had AGE and 164 (7.2%) subsequently died. The following features were identified as predictors of mortality in decreasing order: AVPU scale, Vesikari score, dehydration, sunken eyes, skin pinch, maximum number of vomits, unconsciousness, wasting, vomiting, pulse, fever, sunken fontanelle, restless, nasal flaring, diarrhea days, stridor, <90% oxygen saturation, chest indrawing, malaria, and stunting. The sensitivity ranged from 46.3%–78.0% across models, while the specificity and AUC ranged from 71.7% to 78.7% and 56.5%–82.6%, respectively. The random forest model emerged as the champion model achieving 78.0%, 76.6%, 20.6%, 97.8%, and 82.6% for sensitivity, specificity, PPV, NPV, and AUC, respectively.

Conclusions

This study demonstrates promising predictive performance of the proposed algorithm for identifying patients at risk of mortality in resource-limited settings. However, further validation in real-world clinical settings is needed to assess its feasibility and potential impact on patient outcomes.

背景：目前还没有腹泻入院儿童的死亡率预测评分，早期识别高危患者并进行适当管理仍然是一个挑战。本研究利用机器学习（ML）开发了一个高度敏感的模型，以便更及时地识别急性胃肠炎（AGE）入院的高危儿童，以便更好地管理。方法：我们使用7种ML算法构建预测死亡率的预后模型，使用2010年至2020年在肯尼亚Siaya县转诊医院（SCRH）收集的5岁AGE住院儿童的去识别数据。潜在的预测因素包括人口统计、病史和入院时收集的临床检查数据。我们在模型开发中进行了分裂抽样和十倍交叉验证。我们评估了每种模型的敏感性、特异性、阳性预测值（PPV）、阴性预测值（NPV）和曲线下面积（AUC）。结果在研究期间，12 546名5岁儿童被纳入SCRH住院疾病监测，其中年龄2271例（18.1%），随后死亡164例（7.2%）。以下特征被确定为死亡率的预测因子，其顺序由高到低依次为：AVPU量表、Vesikari评分、脱水、眼窝凹陷、皮肤捏痛、呕吐次数最多、意识不清、消瘦、呕吐、脉搏、发热、囟门凹陷、躁动、鼻肿胀、腹泻天数、喘鸣、90%氧饱和度、胸腔内缩、疟疾和发育迟缓。各模型的敏感性为46.3% ~ 78.0%，特异性和AUC分别为71.7% ~ 78.7%和56.5% ~ 82.6%。随机森林模型在敏感性、特异性、PPV、NPV和AUC方面分别达到78.0%、76.6%、20.6%、97.8%和82.6%，成为冠军模型。本研究表明，在资源有限的情况下，所提出的算法在识别有死亡风险的患者方面具有良好的预测性能。然而，需要在现实世界的临床环境中进一步验证，以评估其可行性和对患者预后的潜在影响。

{"title":"A machine learning approach to predicting inpatient mortality among pediatric acute gastroenteritis patients in Kenya","authors":"Billy Ogwel, Vincent H. Mzazi, Bryan O. Nyawanda, Gabriel Otieno, Kirkby D. Tickell, Richard Omore","doi":"10.1002/lrh2.10478","DOIUrl":"https://doi.org/10.1002/lrh2.10478","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Background</h3>\u0000 \u0000 <p>Mortality prediction scores for children admitted with diarrhea are unavailable, early identification of at-risk patients for proper management remains a challenge. This study utilizes machine learning (ML) to develop a highly sensitive model for timelier identification of at-risk children admitted with acute gastroenteritis (AGE) for better management.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Methods</h3>\u0000 \u0000 <p>We used seven ML algorithms to build prognostic models for the prediction of mortality using de-identified data collected from children aged <5 years hospitalized with AGE at Siaya County Referral Hospital (SCRH), Kenya, between 2010 through 2020. Potential predictors included demographic, medical history, and clinical examination data collected at admission to hospital. We conducted split-sampling and employed tenfold cross-validation in the model development. We evaluated the sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and the area under the curve (AUC) for each of the models.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Results</h3>\u0000 \u0000 <p>During the study period, 12 546 children aged <5 years admitted at SCRH were enrolled in the inpatient disease surveillance, of whom 2271 (18.1%) had AGE and 164 (7.2%) subsequently died. The following features were identified as predictors of mortality in decreasing order: AVPU scale, Vesikari score, dehydration, sunken eyes, skin pinch, maximum number of vomits, unconsciousness, wasting, vomiting, pulse, fever, sunken fontanelle, restless, nasal flaring, diarrhea days, stridor, <90% oxygen saturation, chest indrawing, malaria, and stunting. The sensitivity ranged from 46.3%–78.0% across models, while the specificity and AUC ranged from 71.7% to 78.7% and 56.5%–82.6%, respectively. The random forest model emerged as the champion model achieving 78.0%, 76.6%, 20.6%, 97.8%, and 82.6% for sensitivity, specificity, PPV, NPV, and AUC, respectively.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Conclusions</h3>\u0000 \u0000 <p>This study demonstrates promising predictive performance of the proposed algorithm for identifying patients at risk of mortality in resource-limited settings. However, further validation in real-world clinical settings is needed to assess its feasibility and potential impact on patient outcomes.</p>\u0000 </section>\u0000 </div>","PeriodicalId":43916,"journal":{"name":"Learning Health Systems","volume":"9 2","pages":""},"PeriodicalIF":2.6,"publicationDate":"2024-12-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/lrh2.10478","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143836302","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Setting the foundation for a national collaborative learning health system in acute TBI rehabilitation: CARE4TBI Year 1 experience 为急性创伤性脑损伤康复的全国协作学习医疗系统奠定基础：CARE4TBI 第一年的经验

IF 2.6 Q2 HEALTH POLICY & SERVICES

Learning Health Systems

Pub Date : 2024-12-16 DOI: 10.1002/lrh2.10454

Cynthia L. Beaulieu, Jennifer Bogner, Chad Swank, Kimberly Frey, Mary K. Ferraro, Candace Tefertiller, Timothy R. Huerta, John D. Corrigan, Erinn M. Hade

Introduction

A learning health system (LHS) approach is a collaborative model that continuously examines, evaluates, and re-evaluates data eventually transforming it into knowledge. High quantity of high-quality data are needed to establish this model. The purpose of this article is to describe the collaborative discovery process used to identify and standardize clinical data documented during daily multidisciplinary inpatient rehabilitation that would then allow access to these data to conduct comparative effectiveness research.

Methods

CARE4TBI is a prospective observational research study designed to capture clinical data within the standard inpatient rehabilitation documentation workflow at 15 TBI Model Systems Centers in the US. Three groups of stakeholders guided project development: therapy representative work group (TRWG) consisting of frontline therapists from occupational, physical, speech-language, and recreational therapies; rehabilitation leader representative group (RLRG); and informatics and information technology team (IIT). Over a 12-month period, the three work groups and research leadership team identified the therapeutic components captured within daily documentation throughout the duration of inpatient TBI rehabilitation.

Results

Data brainstorming among the groups created 98 distinct categories of data with each containing a range of data elements comprising a total of 850 discrete data elements. The free-form data were sorted into three large categories and through review and discussion, reduced to two categories of prospective data collection—session-level and therapy activity-level data. Twelve session data elements were identified, and 54 therapy activities were identified, with each activity containing discrete sub-categories for activity components, method of delivery, and equipment or supplies. A total of 561 distinct meaningful data elements were identified across the 54 activities.

Discussion

The CARE4TBI data discovery process demonstrated feasibility in identifying and capturing meaningful high quantity and high-quality treatment data across multiple disciplines and rehabilitation sites, setting the foundation for a LHS coalition for acute traumatic brain injury rehabilitation.

导言学习型医疗系统（LHS）是一种合作模式，它不断检查、评估和重新评估数据，最终将其转化为知识。建立这种模式需要大量高质量的数据。本文旨在描述合作发现过程，该过程用于识别和标准化多学科住院患者日常康复过程中记录的临床数据，从而获取这些数据以开展比较有效性研究。方法 CARE4TBI 是一项前瞻性观察研究，旨在获取美国 15 个 TBI 示范系统中心标准住院康复记录工作流程中的临床数据。项目开发由三组利益相关者指导：治疗代表工作组 (TRWG)，由来自职业、物理、语言和娱乐治疗的一线治疗师组成；康复领导代表小组 (RLRG)；信息学和信息技术小组 (IIT)。在为期 12 个月的时间里，三个工作组和研究领导小组确定了创伤性脑损伤住院康复期间日常文件中的治疗内容。结果各小组集思广益，创建了 98 个不同的数据类别，每个类别包含一系列数据元素，共 850 个离散数据元素。自由形式的数据被分为三个大类，通过审查和讨论，减少为两类前瞻性数据收集--疗程级数据和治疗活动级数据。确定了 12 个疗程数据元素和 54 项治疗活动，每项活动都包含活动组成部分、实施方法和设备或用品等离散子类别。在这 54 项活动中，共识别出 561 个不同的有意义数据元素。讨论 CARE4TBI 数据发现过程证明了在多个学科和康复场所识别和捕获有意义的大量高质量治疗数据的可行性，为急性脑外伤康复的 LHS 联盟奠定了基础。

{"title":"Setting the foundation for a national collaborative learning health system in acute TBI rehabilitation: CARE4TBI Year 1 experience","authors":"Cynthia L. Beaulieu, Jennifer Bogner, Chad Swank, Kimberly Frey, Mary K. Ferraro, Candace Tefertiller, Timothy R. Huerta, John D. Corrigan, Erinn M. Hade","doi":"10.1002/lrh2.10454","DOIUrl":"https://doi.org/10.1002/lrh2.10454","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Introduction</h3>\u0000 \u0000 <p>A learning health system (LHS) approach is a collaborative model that continuously examines, evaluates, and re-evaluates data eventually transforming it into knowledge. High quantity of high-quality data are needed to establish this model. The purpose of this article is to describe the collaborative discovery process used to identify and standardize clinical data documented during daily multidisciplinary inpatient rehabilitation that would then allow access to these data to conduct comparative effectiveness research.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Methods</h3>\u0000 \u0000 <p>CARE4TBI is a prospective observational research study designed to capture clinical data within the standard inpatient rehabilitation documentation workflow at 15 TBI Model Systems Centers in the US. Three groups of stakeholders guided project development: therapy representative work group (TRWG) consisting of frontline therapists from occupational, physical, speech-language, and recreational therapies; rehabilitation leader representative group (RLRG); and informatics and information technology team (IIT). Over a 12-month period, the three work groups and research leadership team identified the therapeutic components captured within daily documentation throughout the duration of inpatient TBI rehabilitation.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Results</h3>\u0000 \u0000 <p>Data brainstorming among the groups created 98 distinct categories of data with each containing a range of data elements comprising a total of 850 discrete data elements. The free-form data were sorted into three large categories and through review and discussion, reduced to two categories of prospective data collection—session-level and therapy activity-level data. Twelve session data elements were identified, and 54 therapy activities were identified, with each activity containing discrete sub-categories for activity components, method of delivery, and equipment or supplies. A total of 561 distinct meaningful data elements were identified across the 54 activities.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Discussion</h3>\u0000 \u0000 <p>The CARE4TBI data discovery process demonstrated feasibility in identifying and capturing meaningful high quantity and high-quality treatment data across multiple disciplines and rehabilitation sites, setting the foundation for a LHS coalition for acute traumatic brain injury rehabilitation.</p>\u0000 </section>\u0000 </div>","PeriodicalId":43916,"journal":{"name":"Learning Health Systems","volume":"9 2","pages":""},"PeriodicalIF":2.6,"publicationDate":"2024-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/lrh2.10454","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143836351","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Development and launch of a regional learning network to improve physical and mental health outcomes 发展和启动一个区域学习网络，以改善身心健康成果

IF 2.6 Q2 HEALTH POLICY & SERVICES

Learning Health Systems

Pub Date : 2024-12-09 DOI: 10.1002/lrh2.10462

Ndidi Unaka, Jeff Steller, Sarah Eaton, Brandy Seger, Jessica M. McClure, Mona Mansour, Kate Rich, Andrew F. Beck, Mary Carol Burkhardt, Nicole Lacasse, Crystal Robinson, Jeff Anderson

Background

Care gaps in routine and preventive care are common among youth. To close care gaps, health systems should take a population health approach and create opportunities for partnership, collaboration, shared learning, and scale via learning networks (LNs).

Methods

We describe the Pediatric Improvement Network for Quality (PINQ), a regional population health LN with the aim of closing well-child and mental and behavioral health (MBH) care gaps. We initially launched PINQ with 2 primary care domains: well-child care (WCC) and MBH and later added the third domain of PINQ focused on community MBH organizations. We defined measures for the primary care WCC (well-child visits for infants 0–15 months; lead screening by 2 years of age, childhood immunization status 3 completion) and MBH domains (depression screening in youth 12–17 years, 30-day follow-up for positive depression screen, mental health emergency department utilization) and established system-level key drivers.

Results

PINQ launched in September 2022 with 7 teams (5 in primary care WCC and 2 in primary care MBH domains, respectively). All teams participate in a monthly meeting that alternates between the Action Period call and Solutions Labs. We highlight two case studies that illustrate the impact of shared learning and quality improvement support on Improvement Team efforts.

Conclusion

We foresee PINQ as a means of moving the needle toward high quality, comprehensive health care for Greater Cincinnati youth. The next steps include growing PINQ by adding Improvement Teams and expanding the network focus to include other primary care-centric metrics and conditions.

背景：青少年在常规保健和预防性保健方面存在差距。为缩小保健差距，卫生系统应采取人口卫生方针，创造伙伴关系、协作、共享学习的机会，并通过学习网络扩大规模。方法：我们描述了儿科质量改善网络（PINQ），这是一个区域人口健康LN，旨在缩小儿童健康和心理和行为健康（MBH）护理差距。我们最初推出的PINQ有两个初级保健领域：儿童保健（WCC）和MBH，后来增加了PINQ的第三个领域，专注于社区MBH组织。我们定义了初级保健WCC(0-15个月婴儿的健康儿童访问；2岁前的先导筛查、儿童免疫接种状况（3完成）和MBH领域（12-17岁青少年抑郁症筛查、30天抑郁阳性随访、精神卫生急诊科利用）和已建立的系统级关键驱动因素。PINQ于2022年9月启动，共有7个团队（5个在初级保健WCC领域，2个在初级保健MBH领域）。所有团队都参加每月一次的会议，会议在行动期号召和解决方案实验室之间交替进行。我们重点介绍了两个案例研究，说明了共享学习和质量改进支持对改进团队工作的影响。结论：我们预见PINQ将为大辛辛那提青年提供高质量、全面的医疗保健服务。接下来的步骤包括通过增加改进小组来增加PINQ，并将网络重点扩大到包括其他以初级保健为中心的指标和条件。

{"title":"Development and launch of a regional learning network to improve physical and mental health outcomes","authors":"Ndidi Unaka, Jeff Steller, Sarah Eaton, Brandy Seger, Jessica M. McClure, Mona Mansour, Kate Rich, Andrew F. Beck, Mary Carol Burkhardt, Nicole Lacasse, Crystal Robinson, Jeff Anderson","doi":"10.1002/lrh2.10462","DOIUrl":"https://doi.org/10.1002/lrh2.10462","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Background</h3>\u0000 \u0000 <p>Care gaps in routine and preventive care are common among youth. To close care gaps, health systems should take a population health approach and create opportunities for partnership, collaboration, shared learning, and scale via learning networks (LNs).</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Methods</h3>\u0000 \u0000 <p>We describe the Pediatric Improvement Network for Quality (PINQ), a regional population health LN with the aim of closing well-child and mental and behavioral health (MBH) care gaps. We initially launched PINQ with 2 primary care domains: well-child care (WCC) and MBH and later added the third domain of PINQ focused on community MBH organizations. We defined measures for the primary care WCC (well-child visits for infants 0–15 months; lead screening by 2 years of age, childhood immunization status 3 completion) and MBH domains (depression screening in youth 12–17 years, 30-day follow-up for positive depression screen, mental health emergency department utilization) and established system-level key drivers.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Results</h3>\u0000 \u0000 <p>PINQ launched in September 2022 with 7 teams (5 in primary care WCC and 2 in primary care MBH domains, respectively). All teams participate in a monthly meeting that alternates between the Action Period call and Solutions Labs. We highlight two case studies that illustrate the impact of shared learning and quality improvement support on Improvement Team efforts.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Conclusion</h3>\u0000 \u0000 <p>We foresee PINQ as a means of moving the needle toward high quality, comprehensive health care for Greater Cincinnati youth. The next steps include growing PINQ by adding Improvement Teams and expanding the network focus to include other primary care-centric metrics and conditions.</p>\u0000 </section>\u0000 </div>","PeriodicalId":43916,"journal":{"name":"Learning Health Systems","volume":"9 2","pages":""},"PeriodicalIF":2.6,"publicationDate":"2024-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/lrh2.10462","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143835894","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Learning sites for health systems research: Reflections on five programs in Africa, Asia, and Central America 卫生系统研究的学习地点：对非洲、亚洲和中美洲五个规划的反思

IF 2.6 Q2 HEALTH POLICY & SERVICES

Learning Health Systems

Pub Date : 2024-12-04 DOI: 10.1002/lrh2.10475

Sophie Witter, Shophika Regmi, Joanna Raven, Jacinta Nzinga, Maria van der Merwe, Walter Flores, Lucia D'Ambruoso

Introduction

Learning sites have supported intervention development and testing in health care, but studies reflecting on lessons relating to their deployment for health policy and system research (HPSR) in low- and middle-income settings are limited.

Methods

This experience report draws from learning over three continents and five research and community engagement programs—the oldest starting in 2010—to reflect on the challenges and benefits of doing embedded HPSR in learning sites, and how those have been managed. Its objective is to generate better understanding of their potential and constraints. The report draws from team members' experiential insights and program publications.

Results

Challenges relating to initial engagement in the sites included building and maintaining trust, managing partner expectations, and negotiating priority topics and stakeholders. Once the embedded research was underway, sustaining engagement, and managing power dynamics within the group, supporting all participants in developing new skills and managing rapidly changing settings were important. Finally, the complexity of reflecting on action and assessing impact are outlined, along with potential approaches to managing all of these challenges and the variety of gains that have been noted across the programs.

Conclusions

We highlight the potential of learning sites to develop relationships, capacities, and local innovations which can strengthen health systems in the long term and some lessons in relation to how to do that, including the importance of stable, long-term funding as well as developing and recognizing facilitation skills among researchers. Supporting spaces for learning is particularly important when health systems face resource constraints and everyday or acute stressors and shocks.

学习网站支持了卫生保健干预措施的开发和测试，但反映与在低收入和中等收入环境中部署卫生政策和系统研究（HPSR）相关的经验教训的研究有限。方法本经验报告借鉴了在三大洲和五个研究和社区参与项目（最早于2010年开始）的经验，以反思在学习场所开展嵌入式HPSR的挑战和好处，以及如何管理这些挑战和好处。其目标是更好地了解它们的潜力和限制。该报告借鉴了团队成员的经验见解和项目出版物。结果与网站初始参与相关的挑战包括建立和维护信任，管理合作伙伴期望，以及协商优先主题和利益相关者。一旦嵌入式研究开始进行，保持参与，管理团队内部的权力动态，支持所有参与者发展新技能和管理快速变化的环境是很重要的。最后，概述了反思行动和评估影响的复杂性，以及管理所有这些挑战的潜在方法和各项目所取得的各种成果。我们强调了学习地点在发展关系、能力和地方创新方面的潜力，这些潜力可以长期加强卫生系统，并强调了如何做到这一点的一些经验教训，包括稳定、长期资助的重要性，以及发展和认可研究人员之间的促进技能。当卫生系统面临资源限制以及日常或急性压力和冲击时，支持学习空间尤为重要。

{"title":"Learning sites for health systems research: Reflections on five programs in Africa, Asia, and Central America","authors":"Sophie Witter, Shophika Regmi, Joanna Raven, Jacinta Nzinga, Maria van der Merwe, Walter Flores, Lucia D'Ambruoso","doi":"10.1002/lrh2.10475","DOIUrl":"https://doi.org/10.1002/lrh2.10475","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Introduction</h3>\u0000 \u0000 <p>Learning sites have supported intervention development and testing in health care, but studies reflecting on lessons relating to their deployment for health policy and system research (HPSR) in low- and middle-income settings are limited.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Methods</h3>\u0000 \u0000 <p>This experience report draws from learning over three continents and five research and community engagement programs—the oldest starting in 2010—to reflect on the challenges and benefits of doing embedded HPSR in learning sites, and how those have been managed. Its objective is to generate better understanding of their potential and constraints. The report draws from team members' experiential insights and program publications.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Results</h3>\u0000 \u0000 <p>Challenges relating to initial engagement in the sites included building and maintaining trust, managing partner expectations, and negotiating priority topics and stakeholders. Once the embedded research was underway, sustaining engagement, and managing power dynamics within the group, supporting all participants in developing new skills and managing rapidly changing settings were important. Finally, the complexity of reflecting on action and assessing impact are outlined, along with potential approaches to managing all of these challenges and the variety of gains that have been noted across the programs.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Conclusions</h3>\u0000 \u0000 <p>We highlight the potential of learning sites to develop relationships, capacities, and local innovations which can strengthen health systems in the long term and some lessons in relation to how to do that, including the importance of stable, long-term funding as well as developing and recognizing facilitation skills among researchers. Supporting spaces for learning is particularly important when health systems face resource constraints and everyday or acute stressors and shocks.</p>\u0000 </section>\u0000 </div>","PeriodicalId":43916,"journal":{"name":"Learning Health Systems","volume":"9 2","pages":""},"PeriodicalIF":2.6,"publicationDate":"2024-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/lrh2.10475","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143835719","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Analyzing electronic medical records to extract prepregnancy morbidities and pregnancy complications: Toward a learning health system 分析电子医疗记录以提取孕前发病率和妊娠并发症：迈向学习型卫生系统

IF 2.6 Q2 HEALTH POLICY & SERVICES

Learning Health Systems

Pub Date : 2024-11-26 DOI: 10.1002/lrh2.10473

Yitayeh Belsti, Lisa Moran, Aya Mousa, Rebecca Goldstein, Daniel Lorber Rolnik, Mahnaz Bahri Khomami, Mihiretu M. Kebede, Helena Teede, Joanne Enticott

Introduction

Preexisting and pregnancy-related medical conditions frequently co-occur, leading to multimorbidity (≥2 morbidities) in pregnant women, and much of this information is in semi-structured format in electronic medical records (EMRs). The aim was to advance the learning health system as a platform for automating information extraction from EMRs and to uncover the prevalence of common morbidities during pregnancy and their association with pregnancy-related complications.

Methods

This study included 48 502 pregnant women attending Monash Health maternity hospitals from 2016 to 2021. Natural language processing (NLP) was used to extract morbidities from semi-structured text in EMRs. Chi-squared tests were used to assess the association between morbidities of gestational diabetes mellitus (GDM) and other pregnancy complications. The k-means clustering algorithm identified clusters of comorbid conditions associated with GDM.

Results

The most common comorbidities during pregnancy were vitamin deficiency (14 019; 28.9%), overweight (13 918; 28.7%), obesity (11 026; 22.7%), anemia and other blood-related disorders (4821; 9.9%), mental health disorders (4314; 9.8%), asthma (4126; 8.5%), thyroid diseases (3576; 7.4%), endometrial disease (1927; 3.9%), cardiovascular disease (1525; 3.1%), and polycystic ovary syndrome (PCOS) (1464; 3.0%). While 22.5% of women had no medical conditions, 77.5% had one or more. Multimorbidity was associated with conditions including overweight, obesity, vitamin deficiency, thyroid disease, substance use, PCOS, GDM, and endometrial diseases. On cluster analysis, aged 35 years or older, overweight, vitamin deficiency, obesity, thyroid disease, asthma, uterine disease, other blood disorders, mental disorders, and PCOS were associated with GDM.

Conclusions

More than three-quarters of pregnant women in the Australian urban setting experienced one or more morbidities during pregnancy, which can be associated with adverse pregnancy outcomes. This project contributes to developing a learning health system infrastructure to deliver high-value maternal health care while reducing costs.

既往疾病和妊娠相关疾病经常同时发生，导致孕妇多重发病（≥2种发病），其中大部分信息以电子病历（emr）的半结构化格式存在。其目的是推进学习型卫生系统，使其成为从电子病历中自动提取信息的平台，并揭示妊娠期间常见疾病的患病率及其与妊娠相关并发症的关系。方法本研究纳入2016年至2021年在莫纳什健康妇产医院就诊的48 502名孕妇。使用自然语言处理（NLP）从emr的半结构化文本中提取发病率。卡方检验用于评估妊娠期糖尿病（GDM）发病率与其他妊娠并发症之间的关系。k-means聚类算法识别与GDM相关的合并症。结果妊娠期最常见的合并症为维生素缺乏(14 019例；28.9%)，超重(13 918；28.7%)，肥胖(11026例；22.7%)，贫血和其他血液相关疾病(4821；9.9%)、精神健康障碍(4314人；9.8%)，哮喘(4126；8.5%)，甲状腺疾病(3576；7.4%)，子宫内膜疾病(1927；3.9%)，心血管疾病(1525例；3.1%)，多囊卵巢综合征（PCOS） (1464；3.0%)。22.5%的妇女没有任何疾病，77.5%的妇女有一种或多种疾病。多发病与超重、肥胖、维生素缺乏、甲状腺疾病、药物使用、多囊卵巢综合征、GDM和子宫内膜疾病有关。在聚类分析中，年龄在35岁及以上、超重、维生素缺乏、肥胖、甲状腺疾病、哮喘、子宫疾病、其他血液疾病、精神疾病和多囊卵巢综合征与GDM相关。结论：澳大利亚城市环境中超过四分之三的孕妇在怀孕期间经历了一种或多种疾病，这可能与不良妊娠结局有关。该项目有助于发展学习型卫生系统基础设施，在降低成本的同时提供高价值的孕产妇保健服务。

{"title":"Analyzing electronic medical records to extract prepregnancy morbidities and pregnancy complications: Toward a learning health system","authors":"Yitayeh Belsti, Lisa Moran, Aya Mousa, Rebecca Goldstein, Daniel Lorber Rolnik, Mahnaz Bahri Khomami, Mihiretu M. Kebede, Helena Teede, Joanne Enticott","doi":"10.1002/lrh2.10473","DOIUrl":"https://doi.org/10.1002/lrh2.10473","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Introduction</h3>\u0000 \u0000 <p>Preexisting and pregnancy-related medical conditions frequently co-occur, leading to multimorbidity (≥2 morbidities) in pregnant women, and much of this information is in semi-structured format in electronic medical records (EMRs). The aim was to advance the learning health system as a platform for automating information extraction from EMRs and to uncover the prevalence of common morbidities during pregnancy and their association with pregnancy-related complications.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Methods</h3>\u0000 \u0000 <p>This study included 48 502 pregnant women attending Monash Health maternity hospitals from 2016 to 2021. Natural language processing (NLP) was used to extract morbidities from semi-structured text in EMRs. Chi-squared tests were used to assess the association between morbidities of gestational diabetes mellitus (GDM) and other pregnancy complications. The <i>k</i>-means clustering algorithm identified clusters of comorbid conditions associated with GDM.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Results</h3>\u0000 \u0000 <p>The most common comorbidities during pregnancy were vitamin deficiency (14 019; 28.9%), overweight (13 918; 28.7%), obesity (11 026; 22.7%), anemia and other blood-related disorders (4821; 9.9%), mental health disorders (4314; 9.8%), asthma (4126; 8.5%), thyroid diseases (3576; 7.4%), endometrial disease (1927; 3.9%), cardiovascular disease (1525; 3.1%), and polycystic ovary syndrome (PCOS) (1464; 3.0%). While 22.5% of women had no medical conditions, 77.5% had one or more. Multimorbidity was associated with conditions including overweight, obesity, vitamin deficiency, thyroid disease, substance use, PCOS, GDM, and endometrial diseases. On cluster analysis, aged 35 years or older, overweight, vitamin deficiency, obesity, thyroid disease, asthma, uterine disease, other blood disorders, mental disorders, and PCOS were associated with GDM.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Conclusions</h3>\u0000 \u0000 <p>More than three-quarters of pregnant women in the Australian urban setting experienced one or more morbidities during pregnancy, which can be associated with adverse pregnancy outcomes. This project contributes to developing a learning health system infrastructure to deliver high-value maternal health care while reducing costs.</p>\u0000 </section>\u0000 </div>","PeriodicalId":43916,"journal":{"name":"Learning Health Systems","volume":"9 2","pages":""},"PeriodicalIF":2.6,"publicationDate":"2024-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/lrh2.10473","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143836479","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Pre-implementation patient, provider, and administrator perspectives of remote measurement-based care in a safety net outpatient psychiatry department 实施前患者，提供者和管理者的观点远程测量为基础的护理在一个安全网门诊精神科

IF 2.6 Q2 HEALTH POLICY & SERVICES

Learning Health Systems

Pub Date : 2024-11-23 DOI: 10.1002/lrh2.10472

Lisa C. Rosenfeld, Miriam C. Tepper, Stephen H. Leff, Daisy Wang, Alice Zhang, Lia Tian, Eileen Huttlin, Carl Fulwiler, Rajendra Aldis, Philip Wang, Jennifer Stahr, Norah Mulvaney-Day, Margaret Lanca, Ana M. Progovac

Introduction

Psychiatric measurement-based care (MBC) can be more effective than usual care, but health systems face implementation challenges. Achieving attitudinal alignment before implementing MBC is critical, yet few studies incorporate perspectives from multiple stakeholders this early in planning. This analysis identifies alignment and themes in pre-implementation feedback from patients, providers, and administrators regarding a planned MBC implementation in a safety net psychiatry clinic.

Methods

We used interview guides informed by Conceptual Model of Implementation Research to gather qualitative pre-implementation attitudes about perceived Appropriateness, Acceptability, and Feasibility of an MBC measure (Computerized Adaptive Test—Mental Health; CAT-MH) from five patients, two providers, and six administrators. We applied rapid qualitative analysis methods to generate actionable feedback for department leadership still planning implementation. [Correction added on 22 January 2025, after first online publication: In the previous sentence, the word ‘general’ was replaced with the word ‘generate’.] We used a multistep process to generate thematic findings with potential relevance for other similar mental health settings.

Results

There was more attitudinal alignment across stakeholder groups regarding MBC's Acceptability and Feasibility than its Appropriateness. All three groups agreed that it was important to contextualize MBC for patients and providers, anticipate MBC's impact on patient–provider relationships, and consider the system's capacity to respond to patient needs unearthed by CAT-MH before implementation began. Our thematic analysis suggests: (1) Introducing MBC may complicate patient–provider relationships by adding a new and potentially conflicting input for decision making, that is, MBC data, to the more typical inputs of patient report and provider expertise; [Correction added on 22 January 2025, after first online publication: In the previous sentence, the word ‘complicated’ was replaced with the word ‘complicate’.] (2) MBC poses theoretical risks to health equity for safety net patients because of limitations in access to MBC tools themselves and the resources needed to respond to MBC data; and (3) Tension exists between individual- and system-level applications of MBC.

Conclusions

Our analysis highlights shifting treatment dynamics, equity considerations, and tension between individu

精神病学基于测量的护理（MBC）可能比常规护理更有效，但卫生系统面临实施挑战。在实施MBC之前实现态度一致是至关重要的，然而很少有研究在计划的早期就纳入了多个利益相关者的观点。本分析确定了从患者、提供者和管理人员那里获得的关于在安全网精神病学诊所计划实施MBC的实施前反馈的一致性和主题。方法采用实施研究概念模型的访谈指南，收集实施前对计算机化适应测试（MBC）的感知适当性、可接受性和可行性的定性态度。CAT-MH)来自5名患者、2名提供者和6名管理人员。我们采用快速定性分析方法，为部门领导制定实施计划提供可操作的反馈。[在首次在线发布后，于2025年1月22日进行了更正：在上一句中，将“general”一词替换为“generate”一词。我们使用了一个多步骤的过程来产生与其他类似心理健康环境潜在相关性的专题研究结果。结果利益相关者群体对MBC的可接受性和可行性的态度比对其适当性的态度更一致。所有三个小组都认为，在实施之前，将MBC置于患者和提供者的背景下，预测MBC对患者-提供者关系的影响，并考虑该系统对CAT-MH发现的患者需求的响应能力是很重要的。我们的专题分析表明：(1)引入MBC可能会使医患关系复杂化，因为它在更典型的患者报告和医生专业知识输入之外，增加了一个新的、可能存在冲突的决策输入，即MBC数据；[在首次在线发表后，于2025年1月22日更正：在上一句中，将“complicated”一词替换为“complicated”。(2)由于MBC工具本身的获取受限以及响应MBC数据所需的资源有限，MBC对安全网患者的健康公平构成了理论上的风险；(3) MBC在个人和系统层面的应用存在张力。结论：我们的分析强调了治疗动态的变化、公平的考虑以及个体和人群需求之间的紧张关系，这些都是我们的参与者在计划在安全网精神病学诊所实施MBC时所预期的。

{"title":"Pre-implementation patient, provider, and administrator perspectives of remote measurement-based care in a safety net outpatient psychiatry department","authors":"Lisa C. Rosenfeld, Miriam C. Tepper, Stephen H. Leff, Daisy Wang, Alice Zhang, Lia Tian, Eileen Huttlin, Carl Fulwiler, Rajendra Aldis, Philip Wang, Jennifer Stahr, Norah Mulvaney-Day, Margaret Lanca, Ana M. Progovac","doi":"10.1002/lrh2.10472","DOIUrl":"https://doi.org/10.1002/lrh2.10472","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Introduction</h3>\u0000 \u0000 <p>Psychiatric measurement-based care (MBC) can be more effective than usual care, but health systems face implementation challenges. Achieving attitudinal alignment before implementing MBC is critical, yet few studies incorporate perspectives from multiple stakeholders this early in planning. This analysis identifies alignment and themes in pre-implementation feedback from patients, providers, and administrators regarding a planned MBC implementation in a safety net psychiatry clinic.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Methods</h3>\u0000 \u0000 <p>We used interview guides informed by Conceptual Model of Implementation Research to gather qualitative pre-implementation attitudes about perceived Appropriateness, Acceptability, and Feasibility of an MBC measure (Computerized Adaptive Test—Mental Health; CAT-MH) from five patients, two providers, and six administrators. We applied rapid qualitative analysis methods to generate actionable feedback for department leadership still planning implementation. [Correction added on 22 January 2025, after first online publication: In the previous sentence, the word ‘general’ was replaced with the word ‘generate’.] We used a multistep process to generate thematic findings with potential relevance for other similar mental health settings.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Results</h3>\u0000 \u0000 <p>There was more attitudinal alignment across stakeholder groups regarding MBC's Acceptability and Feasibility than its Appropriateness. All three groups agreed that it was important to contextualize MBC for patients and providers, anticipate MBC's impact on patient–provider relationships, and consider the system's capacity to respond to patient needs unearthed by CAT-MH before implementation began. Our thematic analysis suggests: (1) Introducing MBC may complicate patient–provider relationships by adding a new and potentially conflicting input for decision making, that is, MBC data, to the more typical inputs of patient report and provider expertise; [Correction added on 22 January 2025, after first online publication: In the previous sentence, the word ‘complicated’ was replaced with the word ‘complicate’.] (2) MBC poses theoretical risks to health equity for safety net patients because of limitations in access to MBC tools themselves and the resources needed to respond to MBC data; and (3) Tension exists between individual- and system-level applications of MBC.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Conclusions</h3>\u0000 \u0000 <p>Our analysis highlights shifting treatment dynamics, equity considerations, and tension between individu","PeriodicalId":43916,"journal":{"name":"Learning Health Systems","volume":"9 2","pages":""},"PeriodicalIF":2.6,"publicationDate":"2024-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/lrh2.10472","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143836443","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

The Academic Community Early Psychosis Intervention Network: Toward building a novel learning health system across six US states 学术界早期精神病干预网络：在美国六个州建立一个新的学习健康系统

IF 2.6 Q2 HEALTH POLICY & SERVICES

Learning Health Systems

Pub Date : 2024-11-17 DOI: 10.1002/lrh2.10471

Jenifer L. Vohs, Vinod Srihari, Alexandra H. Vinson, Adrienne Lapidos, John Cahill, Stephan F. Taylor, Stephan Heckers, Ashley Weiss, Serena Chaudhry, Steve Silverstein, Ivy F. Tso, Nicholas J. K. Breitborde, Alan Breier

Introduction

Compared to usual care, specialty services for first-episode psychosis (FES) have superior patient outcomes. The Early Psychosis Intervention Network (EPINET), comprised of eight U.S. regional clinical networks, aims to advance the quality of FES care within the ethos of learning healthcare systems (LHS). Among these, the Academic Community (AC) EPINET was established to provide FES care, collect common data elements, leverage informatics, foster a culture of continuous learning and quality improvement, and engage in practice-based research.

Methods

We designed and implemented a novel LHS of university-affiliated FES programs within a hub (academic leadership team) and spoke (FES clinics) model. A series of site implementation meetings engaged stakeholders, setting the stage for a culture that values data collection and shared learning. We built clinical workflows to collect common data elements at enrollment and at consecutive 6-month intervals in parallel to an informatics workflow to deliver outcome visualizations and drive quality improvement efforts.

Results

All six clinical sites successfully implemented data capture workflows and engaged in the process of designing the informatics platform. Upon developing the structure, processes, and initial culture of the LHS, a total of 614 patients enrolled in AC-EPINET, with the most common primary diagnoses of schizophrenia (32.1%) and unspecified psychotic disorders (23.6%). Visualized outcomes were delivered to clinical teams who began to consider locally relevant quality improvement projects.

Conclusions

AC-EPINET is a novel LHS, with a simultaneous focus on science, informatics, incentives, and culture. The work of developing AC-EPINET thus far has highlighted the need for future LHS’ to be mindful of the complexities of data security issues, develop more automated informatic workflows, resource quality assurance efforts, and attend to building the cultural infrastructure with the input of all stakeholders.

导言：与常规护理相比，针对首发精神病（FES）的专科服务对患者的治疗效果更佳。早期精神病干预网络（EPINET）由八个美国地区临床网络组成，旨在学习型医疗保健系统（LHS）的精神下提高首次发病精神病（FES）护理的质量。其中，学术社区（AC）EPINET的成立旨在提供外展治疗护理、收集通用数据元素、利用信息学、培养持续学习和质量改进的文化，并参与基于实践的研究。方法我们在一个中心（学术领导小组）和辐条（FES 诊所）模式内，设计并实施了一个新颖的大学附属 FES 项目 LHS。一系列的现场实施会议吸引了利益相关者的参与，为建立重视数据收集和共享学习的文化奠定了基础。我们建立了临床工作流程，以便在入院时和连续 6 个月的间隔期收集通用数据元素，同时建立了信息学工作流程，以提供结果可视化并推动质量改进工作。结果所有六个临床研究机构都成功实施了数据采集工作流程，并参与了信息平台的设计过程。在开发了 LHS 的结构、流程和初始文化后，共有 614 名患者加入了 AC-EPINET，其中最常见的主要诊断为精神分裂症（32.1%）和不明原因的精神障碍（23.6%）。临床团队获得了可视化结果，并开始考虑开展与当地相关的质量改进项目。结论 AC-EPINET 是一种新型的 LHS，同时关注科学、信息学、激励机制和文化。迄今为止，AC-EPINET 的开发工作突出表明，未来的 LHS 需要注意数据安全问题的复杂性，开发更加自动化的信息工作流程，为质量保证工作提供资源，并在所有利益相关者的投入下关注文化基础设施的建设。

{"title":"The Academic Community Early Psychosis Intervention Network: Toward building a novel learning health system across six US states","authors":"Jenifer L. Vohs, Vinod Srihari, Alexandra H. Vinson, Adrienne Lapidos, John Cahill, Stephan F. Taylor, Stephan Heckers, Ashley Weiss, Serena Chaudhry, Steve Silverstein, Ivy F. Tso, Nicholas J. K. Breitborde, Alan Breier","doi":"10.1002/lrh2.10471","DOIUrl":"https://doi.org/10.1002/lrh2.10471","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Introduction</h3>\u0000 \u0000 <p>Compared to usual care, specialty services for first-episode psychosis (FES) have superior patient outcomes. The Early Psychosis Intervention Network (EPINET), comprised of eight U.S. regional clinical networks, aims to advance the quality of FES care within the ethos of learning healthcare systems (LHS). Among these, the Academic Community (AC) EPINET was established to provide FES care, collect common data elements, leverage informatics, foster a culture of continuous learning and quality improvement, and engage in practice-based research.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Methods</h3>\u0000 \u0000 <p>We designed and implemented a novel LHS of university-affiliated FES programs within a hub (academic leadership team) and spoke (FES clinics) model. A series of site implementation meetings engaged stakeholders, setting the stage for a culture that values data collection and shared learning. We built clinical workflows to collect common data elements at enrollment and at consecutive 6-month intervals in parallel to an informatics workflow to deliver outcome visualizations and drive quality improvement efforts.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Results</h3>\u0000 \u0000 <p>All six clinical sites successfully implemented data capture workflows and engaged in the process of designing the informatics platform. Upon developing the structure, processes, and initial culture of the LHS, a total of 614 patients enrolled in AC-EPINET, with the most common primary diagnoses of schizophrenia (32.1%) and unspecified psychotic disorders (23.6%). Visualized outcomes were delivered to clinical teams who began to consider locally relevant quality improvement projects.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Conclusions</h3>\u0000 \u0000 <p>AC-EPINET is a novel LHS, with a simultaneous focus on science, informatics, incentives, and culture. The work of developing AC-EPINET thus far has highlighted the need for future LHS’ to be mindful of the complexities of data security issues, develop more automated informatic workflows, resource quality assurance efforts, and attend to building the cultural infrastructure with the input of all stakeholders.</p>\u0000 </section>\u0000 </div>","PeriodicalId":43916,"journal":{"name":"Learning Health Systems","volume":"9 2","pages":""},"PeriodicalIF":2.6,"publicationDate":"2024-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/lrh2.10471","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143836438","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

VA's EHR transition and health professions trainee programs: Findings and impacts of a multistakeholder learning community VA的电子病历过渡和卫生专业培训项目：多利益相关者学习社区的发现和影响

IF 2.6 Q2 HEALTH POLICY & SERVICES

Learning Health Systems

Pub Date : 2024-10-23 DOI: 10.1002/lrh2.10460

Julian Brunner, Ellen A. Ahlness, Ekaterina Anderson, Brianne K. Molloy-Paolillo, Alexandre Braga, Sarah L. Cutrona, Christian D. Helfrich, Deborah Levy, Erin Matteau, Edward Walton, George Sayre, Seppo T. Rinne

Introduction

The Department of Veterans Affairs (VA) is undergoing an unprecedented electronic health record (EHR) transition, switching from its homegrown EHR to a commercial system. The transition affects nearly every clinical employee but is particularly disruptive to health professions trainees (HPTs)—an often-overlooked population in EHR transitions. To better understand and address trainee challenges with the EHR transition, we formed a multistakeholder learning community. In this study, we describe the findings of this learning community and the practices and policies developed in response.

Methods

In the qualitative study designed and executed by our learning community, we conducted 51 interviews with HPTs, program leaders, and preceptors before and multiple times after an EHR transition site's go-live (February 16, 2022 to April 7, 2023). We merged interview transcripts with 125 survey free-text responses from a survey conducted with preceptors 2 months post-go-live and conducted thematic analysis to identify key themes. To complement qualitative findings, we also include a quantitative survey finding, and, where applicable, we note policy and practice responses spurred by our learning community.

Results

Interviews yielded six key themes: (1) High satisfaction with HPT programs, despite negative impacts of the EHR transition; (2) early delays, then substantial improvements, in HPTs' EHR access; (3) persistent challenges with HPTs' EHR training and support, mitigated by local and national efforts; (4) the challenge of learning to use a rapidly evolving EHR during clinical training; (5) reduced visit volume as a continuing barrier to education; and (6) an impression that HPTs' relative lack of exposure to the prior EHR facilitated their proficiency with the new EHR.

Conclusions

Findings highlighted challenges for HPT programs related to the EHR transition, which spurred important changes including the creation of a national VA council to represent the needs of HPTs in the EHR transition, and improvements to HPTs' EHR training and access.

退伍军人事务部（VA）正在经历一场前所未有的电子健康记录（EHR）转型，从其自制的EHR系统转向商业系统。这种转变几乎影响到每一位临床员工，但对卫生专业培训生（hpt）的破坏性尤其大——这是一个在电子健康档案转变中经常被忽视的群体。为了更好地理解和应对培训生在电子病历转型过程中面临的挑战，我们组建了一个多利益相关方学习社区。在本研究中，我们描述了这个学习社区的发现，以及为此制定的实践和政策。在由我们的学习社区设计和执行的定性研究中，我们在EHR过渡网站（2022年2月16日至2023年4月7日）上线之前和之后多次采访了51位hpt、项目负责人和导师。我们将采访记录与125份调查问卷的自由文本回复合并在一起，这些回复来自于在上线2个月后与导师进行的调查，并进行了主题分析，以确定关键主题。为了补充定性的发现，我们还包括一个定量的调查发现，并且，在适用的情况下，我们注意到由我们的学习社区激发的政策和实践反应。结果访谈得出了六个关键主题：(1)尽管EHR转型带来了负面影响，但对HPT项目的满意度很高；(2) HPTs的电子病历获取出现早期延迟，然后出现实质性改善；(3) hpt的电子病历培训和支持面临的持续挑战，地方和国家的努力缓解了这一挑战；(4)在临床培训中学习使用快速发展的电子病历的挑战；(5)减少访问量成为教育的持续障碍；(6) hpt相对缺乏对先前EHR的接触有助于他们熟练使用新EHR的印象。研究结果强调了与EHR过渡相关的HPT项目面临的挑战，这促使了重要的变革，包括建立一个国家VA委员会来代表HPT在EHR过渡中的需求，以及改善HPT的EHR培训和获取。

{"title":"VA's EHR transition and health professions trainee programs: Findings and impacts of a multistakeholder learning community","authors":"Julian Brunner, Ellen A. Ahlness, Ekaterina Anderson, Brianne K. Molloy-Paolillo, Alexandre Braga, Sarah L. Cutrona, Christian D. Helfrich, Deborah Levy, Erin Matteau, Edward Walton, George Sayre, Seppo T. Rinne","doi":"10.1002/lrh2.10460","DOIUrl":"https://doi.org/10.1002/lrh2.10460","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Introduction</h3>\u0000 \u0000 <p>The Department of Veterans Affairs (VA) is undergoing an unprecedented electronic health record (EHR) transition, switching from its homegrown EHR to a commercial system. The transition affects nearly every clinical employee but is particularly disruptive to health professions trainees (HPTs)—an often-overlooked population in EHR transitions. To better understand and address trainee challenges with the EHR transition, we formed a multistakeholder learning community. In this study, we describe the findings of this learning community and the practices and policies developed in response.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Methods</h3>\u0000 \u0000 <p>In the qualitative study designed and executed by our learning community, we conducted 51 interviews with HPTs, program leaders, and preceptors before and multiple times after an EHR transition site's go-live (February 16, 2022 to April 7, 2023). We merged interview transcripts with 125 survey free-text responses from a survey conducted with preceptors 2 months post-go-live and conducted thematic analysis to identify key themes. To complement qualitative findings, we also include a quantitative survey finding, and, where applicable, we note policy and practice responses spurred by our learning community.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Results</h3>\u0000 \u0000 <p>Interviews yielded six key themes: (1) High satisfaction with HPT programs, despite negative impacts of the EHR transition; (2) early delays, then substantial improvements, in HPTs' EHR access; (3) persistent challenges with HPTs' EHR training and support, mitigated by local and national efforts; (4) the challenge of learning to use a rapidly evolving EHR during clinical training; (5) reduced visit volume as a continuing barrier to education; and (6) an impression that HPTs' relative lack of exposure to the prior EHR facilitated their proficiency with the new EHR.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Conclusions</h3>\u0000 \u0000 <p>Findings highlighted challenges for HPT programs related to the EHR transition, which spurred important changes including the creation of a national VA council to represent the needs of HPTs in the EHR transition, and improvements to HPTs' EHR training and access.</p>\u0000 </section>\u0000 </div>","PeriodicalId":43916,"journal":{"name":"Learning Health Systems","volume":"9 2","pages":""},"PeriodicalIF":2.6,"publicationDate":"2024-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/lrh2.10460","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143836444","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Thanks to our peer reviewers 感谢我们的同行评审员。

IF 2.6 Q2 HEALTH POLICY & SERVICES

Learning Health Systems

Pub Date : 2024-10-21 DOI: 10.1002/lrh2.10464

The publication of Issue 4 marks the completion of Volume 8 of Learning Health Systems. An international, trans-disciplinary, open access publication, the journal has advanced research and scholarship on learning health systems in partnership with our reviewers. With indexing in multiple major sources and an Impact Factor of 2.6, we have achieved a publication milestone that signals a sustainable, positive trajectory. Articles from the journal were downloaded over 123, 126 times in 2023.

Each year, the journal publishes a Special Issue; we have now published eight Special Issues: “Patient Empowerment and the Learning Health System” (v.1); “Ethical, Legal, and Social Implications of Learning Health Systems” (v.2); “Learning Health Systems: Connecting Research to Practice Worldwide” (v.3); “Human Phenomics and the Learning Health System” (v.4); “Collaborative Learning Health Systems: Science and Practice” (v.5); and “Education To Meet the Multidisciplinary Workforce Needs of Learning Health Systems” (v.6); “Transforming Health Through Computable Biomedical Knowledge (CBK)” (v.7); and “Envisioning Public Health As a Learning Health System” (v.8). Our talented guest editors have been instrumental in helping these Special Issues come to fruition.

In addition, we published a Supplement (“Focus on Research by AcademyHealth members”) in June 2024. The Supplement was a collaboration with the Department of Learning Health Sciences (University of Michigan), Academy Health, (LHS Interest Group), and John Wiley & Sons.

We are keenly aware that these achievements would not have happened without the dedicated efforts and insightful comments of all those individuals who accepted invitations to review submitted articles. With busy schedules and full commitments, these individuals found the time and energy to contribute their expertise to our authors to help ensure that their papers met (and often exceeded) the journal's high standards for publication.

Please accept our sincere gratitude for your outstanding efforts!

Charles P. Friedman, Editor in Chief

第 4 期的出版标志着《学习型卫生系统》第 8 卷的完成。作为一份国际性、跨学科、开放存取的出版物，该期刊与我们的审稿人合作，推动了学习型卫生系统的研究和学术发展。该期刊已被多个主要来源收录，影响因子达到 2.6，实现了一个出版里程碑，预示着期刊将继续保持良好的发展势头。2023 年，该期刊的文章下载量超过 123126 次。该期刊每年出版一期特刊，目前已出版了八期特刊：每年，本刊都会出版一期特刊；目前我们已经出版了八期特刊："患者赋权与学习型医疗系统"（第 1 期）；"学习型医疗系统的伦理、法律和社会影响"（第 2 期）；"学习型医疗系统：将全球研究与实践联系起来"（第 3 版）；"人类表型组学与学习型医疗系统"（第 4 版）；"协作学习型医疗系统：科学与实践"（第 5 版）、"满足学习型卫生系统多学科人才需求的教育"（第 6 版）、"通过可计算生物医学知识（CBK）改变健康"（第 7 版）和 "将公共卫生视为学习型卫生系统"（第 8 版）。此外，我们还于 2024 年 6 月出版了一份增刊（"聚焦 AcademyHealth 成员的研究"）。该增刊是与密歇根大学学习健康科学系（Department of Learning Health Sciences）、Academy Health（LHS Interest Group）和 John Wiley & Sons 合作出版的。我们深知，如果没有所有接受邀请审阅投稿的个人的不懈努力和独到见解，这些成就是不可能实现的。这些人工作繁忙、任务繁重，但仍抽出时间和精力为我们的作者贡献他们的专业知识，帮助确保他们的论文达到（甚至经常超过）期刊的高出版标准。请接受我们对你们杰出努力的衷心感谢！查尔斯-P-弗里德曼，主编

{"title":"Thanks to our peer reviewers","authors":"","doi":"10.1002/lrh2.10464","DOIUrl":"10.1002/lrh2.10464","url":null,"abstract":"<p>The publication of Issue 4 marks the completion of Volume 8 of <i>Learning Health Systems</i>. An international, trans-disciplinary, open access publication, the journal has advanced research and scholarship on learning health systems in partnership with our reviewers. With indexing in multiple major sources and an Impact Factor of 2.6, we have achieved a publication milestone that signals a sustainable, positive trajectory. Articles from the journal were downloaded over 123, 126 times in 2023.</p><p>Each year, the journal publishes a Special Issue; we have now published eight <i>Special Issues</i>: “Patient Empowerment and the Learning Health System” (v.1); “Ethical, Legal, and Social Implications of Learning Health Systems” (v.2); “Learning Health Systems: Connecting Research to Practice Worldwide” (v.3); “Human Phenomics and the Learning Health System” (v.4); “Collaborative Learning Health Systems: Science and Practice” (v.5); and “Education To Meet the Multidisciplinary Workforce Needs of Learning Health Systems” (v.6); “Transforming Health Through Computable Biomedical Knowledge (CBK)” (v.7); and “Envisioning Public Health As a Learning Health System” (v.8). Our talented guest editors have been instrumental in helping these <i>Special Issues</i> come to fruition.</p><p>In addition, we published a Supplement (“Focus on Research by AcademyHealth members”) in June 2024. The Supplement was a collaboration with the Department of Learning Health Sciences (University of Michigan), Academy Health, (LHS Interest Group), and John Wiley & Sons.</p><p>We are keenly aware that these achievements would not have happened without the dedicated efforts and insightful comments of all those individuals who accepted invitations to review submitted articles. With busy schedules and full commitments, these individuals found the time and energy to contribute their expertise to our authors to help ensure that their papers met (and often exceeded) the journal's high standards for publication.</p><p>Please accept our sincere gratitude for your outstanding efforts!</p><p><i>Charles P. Friedman</i>, Editor in Chief</p>","PeriodicalId":43916,"journal":{"name":"Learning Health Systems","volume":"8 4","pages":""},"PeriodicalIF":2.6,"publicationDate":"2024-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11493543/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142510012","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Assessing the harmonization of structured electronic health record data to reference terminologies and data completeness through data provenance 通过数据来源评估结构化电子健康记录数据与参考术语和数据完整性的协调性

IF 2.6 Q2 HEALTH POLICY & SERVICES

Learning Health Systems

Pub Date : 2024-10-21 DOI: 10.1002/lrh2.10468

Keith Marsolo, Lesley Curtis, Laura Qualls, Jennifer Xu, Yinghong Zhang, Thomas Phillips, C. Larry Hill, Gretchen Sanders, Judith C. Maro, Daniel Kiernan, Christine Draper, Kevin Coughlin, Sarah K. Dutcher, José J. Hernández-Muñoz, Monique Falconer

Introduction

(1) Assess the harmonization of structured electronic health record data (laboratory results and medications) to reference terminologies and characterize the severity of issues. (2) Identify issues of data completeness by comparing complementary data domains, stratifying by time, care setting, and provenance.

Methods

Queries were distributed to 3 Data Partners (DP). Using harmonization queries, we examined the top 200 laboratory results and medications by volume, identifying outliers and computing summary statistics. The completeness queries looked at 4 conditions of interest and related clinical concepts. Counts were generated for each condition, stratified by year, encounter type, and provenance. We analyzed trends over time within and across DPs.

Results

We found that the median number of codes associated with a given laboratory/medication name (and vice versa) generally met expectations, though there were DP-specific issues that resulted in outliers. In addition, there were drastic differences in the percentage of patients with a given concept depending on provenance.

Conclusions

The harmonization queries surfaced several mapping errors, as well as issues with overly specific codes and records with “null” codes. The completeness queries demonstrated having access to multiple types of data provenance provides more robust results compared with any single provenance type. Harmonization errors between source data and reference terminologies may not be widespread but do exist within CDMs, affecting tens of thousands or even millions of records. Provenance information can help identify potential completeness issues with EHR data, but only if it is represented in the CDM and then populated by DPs.

(1)评估结构化电子健康记录数据（实验室结果和药物）的一致性，以参考术语并描述问题的严重程度。(2)通过比较互补数据域，按时间、护理环境和来源分层，确定数据完整性问题。方法对3个数据伙伴（DP）进行问卷调查。使用协调查询，我们按体积检查了前200名的实验室结果和药物，确定了异常值并计算了汇总统计数据。完整性查询着眼于4种感兴趣的条件和相关的临床概念。对每种情况进行计数，按年份、遭遇类型和来源分层。我们分析了dp内部和dp之间的趋势。结果我们发现，与给定实验室/药物名称相关的代码中位数（反之亦然）通常符合预期，尽管存在导致异常值的dp特定问题。此外，根据来源不同，具有给定概念的患者百分比也有很大差异。协调查询出现了一些映射错误，以及过于具体的代码和“空”代码记录的问题。与任何单一来源类型相比，具有访问多种类型数据来源的完整性查询提供了更健壮的结果。源数据和参考术语之间的协调错误可能并不普遍，但在cdm中确实存在，影响到数万甚至数百万条记录。来源信息可以帮助识别EHR数据的潜在完整性问题，但前提是它在CDM中表示，然后由dp填充。

{"title":"Assessing the harmonization of structured electronic health record data to reference terminologies and data completeness through data provenance","authors":"Keith Marsolo, Lesley Curtis, Laura Qualls, Jennifer Xu, Yinghong Zhang, Thomas Phillips, C. Larry Hill, Gretchen Sanders, Judith C. Maro, Daniel Kiernan, Christine Draper, Kevin Coughlin, Sarah K. Dutcher, José J. Hernández-Muñoz, Monique Falconer","doi":"10.1002/lrh2.10468","DOIUrl":"https://doi.org/10.1002/lrh2.10468","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Introduction</h3>\u0000 \u0000 <p>(1) Assess the harmonization of structured electronic health record data (laboratory results and medications) to reference terminologies and characterize the severity of issues. (2) Identify issues of data completeness by comparing complementary data domains, stratifying by time, care setting, and provenance.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Methods</h3>\u0000 \u0000 <p>Queries were distributed to 3 Data Partners (DP). Using harmonization queries, we examined the top 200 laboratory results and medications by volume, identifying outliers and computing summary statistics. The completeness queries looked at 4 conditions of interest and related clinical concepts. Counts were generated for each condition, stratified by year, encounter type, and provenance. We analyzed trends over time within and across DPs.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Results</h3>\u0000 \u0000 <p>We found that the median number of codes associated with a given laboratory/medication name (and vice versa) generally met expectations, though there were DP-specific issues that resulted in outliers. In addition, there were drastic differences in the percentage of patients with a given concept depending on provenance.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Conclusions</h3>\u0000 \u0000 <p>The harmonization queries surfaced several mapping errors, as well as issues with overly specific codes and records with “null” codes. The completeness queries demonstrated having access to multiple types of data provenance provides more robust results compared with any single provenance type. Harmonization errors between source data and reference terminologies may not be widespread but do exist within CDMs, affecting tens of thousands or even millions of records. Provenance information can help identify potential completeness issues with EHR data, but only if it is represented in the CDM and then populated by DPs.</p>\u0000 </section>\u0000 </div>","PeriodicalId":43916,"journal":{"name":"Learning Health Systems","volume":"9 2","pages":""},"PeriodicalIF":2.6,"publicationDate":"2024-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/lrh2.10468","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143836407","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

首页上一页

2
3
4
5
6
7
8
9
...
10

下一页尾页