Suppr超能文献

在美国精神分裂症患者中,通过自然语言处理识别出的认知障碍所带来的医疗资源利用负担。

Healthcare resource utilization burden associated with cognitive impairments identified through natural language processing among patients with schizophrenia in the United States.

作者信息

Vaccaro Jerome, Nili Mona, Xiang Pin, Nelson James K, Pack Cory, Thompson Randall, Vasey Joe, Parks Joseph

机构信息

RightPath HC, Millerton, NY, USA.

Boehringer Ingelheim Pharmaceutical Inc, Ridgefield, CT, USA.

出版信息

Schizophrenia (Heidelb). 2025 May 27;11(1):82. doi: 10.1038/s41537-025-00628-8.

Abstract

While cognitive impairments in schizophrenia are well documented in research, their identification and impact in clinical practice remain less well understood, despite their association with high patient burden and impact on long-term functional outcomes. In this study we aimed to identify documented cognitive impairments using natural language processing (NLP) and to characterize treatment patterns and healthcare resource utilization (HCRU) among patients with schizophrenia. This US retrospective cohort study used electronic health records (EHR) linked to administrative claims data from January 2016 through February 2023. Adult patients (≥18 years) with at least two schizophrenia diagnosis codes were included. Cognitive impairments were identified by NLP. Patient characteristics were assessed in the 12 months preceding the index date (first documented schizophrenia diagnosis). Treatment patterns and HCRU were measured over the 12 months after index date. A total of 79,326 patients were enrolled in the EHR cohort and 19,974 (25.2%) had documented cognitive impairments. Impairments in "Reasoning and Problem Solving" were identified most often (70.4%) followed by "Working Memory" (27.1%) and "Attention and Vigilance" (19.2%). In the EHR cohort, 11,293 patients (14.2%) had linked claims. Patients with documented cognitive impairments had more HCRU including outpatient visits, psychosocial interventions, and all-cause healthcare claims than patients without documented cognitive impairments (all p < 0.001). Patients with cognitive impairments had greater psychiatric pharmacy utilization than those without cognitive impairments. These observational data add to the limited published literature on cognitive impairments in patients with schizophrenia in the US. The low documented identification of cognitive impairments in this study underscores the importance of improving recognition and documentation of this important domain of schizophrenia. The association of cognitive impairments with high healthcare utilization further emphasizes the need for better treatment options for patients with schizophrenia.

摘要

虽然精神分裂症中的认知障碍在研究中有充分记录,但尽管它们与高患者负担相关且对长期功能结局有影响,但其在临床实践中的识别和影响仍了解较少。在本研究中,我们旨在使用自然语言处理(NLP)识别已记录的认知障碍,并描述精神分裂症患者的治疗模式和医疗资源利用(HCRU)情况。这项美国回顾性队列研究使用了2016年1月至2023年2月与行政索赔数据相关联的电子健康记录(EHR)。纳入了至少有两个精神分裂症诊断代码的成年患者(≥18岁)。通过NLP识别认知障碍。在索引日期(首次记录的精神分裂症诊断)前12个月评估患者特征。在索引日期后12个月测量治疗模式和HCRU。EHR队列中共纳入79,326名患者,其中19,974名(25.2%)有记录的认知障碍。“推理和解决问题”方面的障碍最常被识别(70.4%),其次是“工作记忆”(27.1%)和“注意力和警觉性”(19.2%)。在EHR队列中,11,293名患者(14.2%)有相关索赔。有记录的认知障碍患者比无记录的认知障碍患者有更多的HCRU,包括门诊就诊、心理社会干预和全因医疗索赔(所有p < 0.001)。有认知障碍的患者比无认知障碍的患者有更高的精神科药房利用率。这些观察数据增加了美国关于精神分裂症患者认知障碍的有限已发表文献。本研究中认知障碍的低记录识别强调了改善对精神分裂症这一重要领域的识别和记录的重要性。认知障碍与高医疗利用率的关联进一步强调了为精神分裂症患者提供更好治疗选择的必要性。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1449/12116770/24a3086aa958/41537_2025_628_Fig1_HTML.jpg

文献检索

告别复杂PubMed语法,用中文像聊天一样搜索,搜遍4000万医学文献。AI智能推荐,让科研检索更轻松。

立即免费搜索

文件翻译

保留排版,准确专业,支持PDF/Word/PPT等文件格式,支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述,25分钟生成高质量综述,智能提取关键信息,辅助科研写作。

立即免费体验