HomeADScreen: Developing Alzheimer's disease and related dementia risk identification model in home healthcare.
HomeADScreen: Developing Alzheimer's disease and related dementia risk identification model in home healthcare.
复制标题
HomeADScreen：在家庭医疗保健中开发阿尔茨海默病和相关痴呆症风险识别模型。
DOI：
10.1016/j.ijmedinf.2023.105146
复制
发表时间：
2023
影响因子：
4.9
通讯作者：
Topaz,Maxim
中科院分区：
文献类型：
--
作者：
Zolnoori,Maryam;Barrón,Yolanda;Song,Jiyoun;Noble,James;Burgdorf,Julia;Ryvicker,Miriam;Topaz,Maxim
研究背景超过50%的阿尔茨海默病和相关痴呆（ADRD）患者仍未被确诊.这是具体的情况下，为家庭医疗保健（HHC）patients.ObjectivesThis研究的目的是在开发HomeADScreen，ADRD风险筛查模型建立在HHC患者的结构化数据和信息提取HHC clinical notes.MethodsThe研究的样本包括15,973 HHC患者没有诊断ADRD和8,901患者诊断为ADRD跨四个后续时间窗口。首先，我们应用两种自然语言处理方法，Word 2 Vec和主题建模方法，从临床笔记中提取ADRD风险因素。接下来，我们建立了风险识别模型的组合的结果和评估信息集（OASIS结构的数据收集在HHC设置）和临床记录的风险因素在四个时间windows.ResultsThe表现最好的机器学习算法达到了曲线下面积= 0.76的四年的风险预测时间窗口。在优化筛选ADRD患者的临界值（临界值= 0.31）后，我们实现了灵敏度= 0.75，F1评分= 0.63。对于第一年的时间窗，将临床记录衍生的风险因素添加到OASIS数据中，风险识别模型的整体性能提高了60%。我们观察到在其他时间窗口中增加模型整体性能的类似趋势。与ADRD风险增加相关的变量是“听力受损”和“患者使用电话的能力受损”。另一方面，“非西班牙裔白色”和“缺乏ofimpaired与以前的日常功能”与ADRD.ConclusionHomeADScreen的风险较低，有很强的潜力转化为临床实践，并协助HHC临床医生在评估患者的认知功能，并将他们进一步神经系统评估。
BackgroundMore than 50 % of patients with Alzheimer's disease and related dementia (ADRD) remain undiagnosed. This is specifically the case for home healthcare (HHC) patients.ObjectivesThis study aimed at developing HomeADScreen, an ADRD risk screening model built on the combination of HHC patients' structured data and information extracted from HHC clinical notes.MethodsThe study’s sample included 15,973 HHC patients with no diagnosis of ADRD and 8,901 patients diagnosed with ADRD across four follow-up time windows. First, we applied two natural language processing methods, Word2Vec and topic modeling methods, to extract ADRD risk factors from clinical notes. Next, we built the risk identification model on the combination of the Outcome and Assessment Information Set (OASIS-structured data collected in the HHC setting) and clinical notes-risk factors across the four-time windows.ResultsThe top-performing machine learning algorithm attained an Area under the Curve = 0.76 for a four-year risk prediction time window. After optimizing the cut-off value for screening patients with ADRD (cut-off-value = 0.31), we achieved sensitivity = 0.75 and an F1-score = 0.63. For the first-year time window, adding clinical note-derived risk factors to OASIS data improved the overall performance of the risk identification model by 60 %. We observed a similar trend of increasing the model's overall performance across other time windows. Variables associated with increased risk of ADRD were “hearing impairment” and “impaired patient ability in the use of telephone.” On the other hand, being “non-Hispanic White” and the “absence ofimpairment with prior daily functioning” were associated with a lower risk of ADRD.ConclusionHomeADScreen has a strong potential to be translated into clinical practice and assist HHC clinicians in assessing patients' cognitive function and referring them for further neurological assessment.