Free-Text Documentation of Dementia Symptoms in Home Healthcare: A Natural Language Processing Study.
Free-Text Documentation of Dementia Symptoms in Home Healthcare: A Natural Language Processing Study.
复制标题
DOI：
10.1177/2333721420959861
复制
发表时间：
2020-01
影响因子：
2.7
通讯作者：
Ryvicker M
中科院分区：
文献类型：
--
作者：
Topaz M;Adams V;Wilson P;Woo K;Ryvicker M
家庭保健 (HHC) 临床医生对与阿尔茨海默病和相关痴呆 (ADRD) 相关的症状记录知之甚少。本研究：(1) 开发了一种自然语言处理 (NLP) 算法，可识别 HHC 自由文本临床记录中常见的 ADRD 神经精神症状； (2) 描述了症状群以及有或没有这些症状的患者的住院或急诊科 (ED) 就诊率。我们检查了包含 -260 万条自由文本注释的语料库，涉及 89,459 名因任何诊断而入住非营利性 HHC 机构进行急性后护理的患者中的 112,237 次 HHC 发作。我们使用 NLP 软件（NimbleMiner）构建了六种神经精神症状的指标。结构化 HHC 评估数据用于识别已知的 ADRD 诊断并构建 HHC 期间住院/急诊室使用的衡量标准。 40% 的发作记录有神经精神症状。常见的症状包括记忆力受损、焦虑和/或情绪低落。三分之一没有 ADRD 诊断的病例有症状记录。出现一种或多种症状时，住院/急诊率会增加。 HHC 提供者应检查有神经精神症状但无 ADRD 诊断的发作，以确定 ADRD 诊断是否被遗漏或建议 ADRD 评估。 NLP 生成的症状指标可以帮助识别高危患者以进行针对性干预。
Little is known about symptom documentation related to Alzheimer’s disease and related dementias (ADRD) by home healthcare (HHC) clinicians. This study: (1) developed a natural language processing (NLP) algorithm that identifies common neuropsychiatric symptoms of ADRD in HHC free-text clinical notes; (2) described symptom clusters and hospitalization or emergency department (ED) visit rates for patients with and without these symptoms. We examined a corpus of −2.6 million free-text notes for 112,237 HHC episodes among 89,459 patients admitted to a non-profit HHC agency for post-acute care with any diagnosis. We used NLP software (NimbleMiner) to construct indicators of six neuropsychiatric symptoms. Structured HHC assessment data were used to identify known ADRD diagnoses and construct measures of hospitalization/ED use during HHC. Neuropsychiatric symptoms were documented for 40% of episodes. Common clusters included impaired memory, anxiety and/or depressed mood. One in three episodes without an ADRD diagnosis had documented symptoms. Hospitalization/ED rates increased with one or more symptoms present. HHC providers should examine episodes with neuropsychiatric symptoms but no ADRD diagnoses to determine whether ADRD diagnosis was missed or to recommend ADRD evaluation. NLP-generated symptom indicators can help to identify high-risk patients for targeted interventions.