Journal of gerontological nursing · 2026
Detecting Mild Cognitive Impairment Using Follow-Up Call Speech and Electronic Health Record Data in Home Health Care Settings.
СтатьяНазвание и аннотация: Перевод пока не подготовлен
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Zolnoori Maryam, Zolnour Ali, Rashidi Sina, Spens Ian, Haghbin Yasaman, Vergez Sasha, Flaherty Grace, Onorato Nicole, Vasquez Felix, Noble James M, McDonald Margaret V
Аннотация
PURPOSE: Alzheimer's disease and related dementias often remain undiagnosed in home health care, where early symptoms are rarely documented in electronic health records (EHRs). The current study aimed to develop and evaluate a speech-based screening algorithm for detecting mild cognitive impairment (MCI) using routine follow-up calls.
METHOD: Speech data were collected from brief, semi-structured follow-up calls between nurse assistants and patients, Clinical Dementia Rating (CDR) interviews, and structured EHR data (Outcome and Assessment Information Set [OASIS]). Machine learning models were trained on these modalities individually and in combination. Model performance was evaluated using the area under the curve (AUC) of the receiver operating characteristic and secondary metrics.
RESULTS: Among 114 participants, the multimodal model combining follow-up call speech and OASIS variables achieved the best performance (AUC = 91.03), outperforming models based on CDR interviews (AUC = 80.67), follow-up calls alone (AUC = 81.09), and OASIS alone (AUC = 78.53). Patients with MCI showed greater comorbidity burden, higher rates of dual eligibility, and lower health literacy compared with cognitively healthy participants.
CONCLUSION: Speech collected from routine follow-up calls, when combined with structured clinical data, can enhance early detection of MCI in home health care. This multimodal, low-burden approach leverages existing care coordination workflows and holds promise for scalable cognitive screening in diverse, aging populations.
METHOD: Speech data were collected from brief, semi-structured follow-up calls between nurse assistants and patients, Clinical Dementia Rating (CDR) interviews, and structured EHR data (Outcome and Assessment Information Set [OASIS]). Machine learning models were trained on these modalities individually and in combination. Model performance was evaluated using the area under the curve (AUC) of the receiver operating characteristic and secondary metrics.
RESULTS: Among 114 participants, the multimodal model combining follow-up call speech and OASIS variables achieved the best performance (AUC = 91.03), outperforming models based on CDR interviews (AUC = 80.67), follow-up calls alone (AUC = 81.09), and OASIS alone (AUC = 78.53). Patients with MCI showed greater comorbidity burden, higher rates of dual eligibility, and lower health literacy compared with cognitively healthy participants.
CONCLUSION: Speech collected from routine follow-up calls, when combined with structured clinical data, can enhance early detection of MCI in home health care. This multimodal, low-burden approach leverages existing care coordination workflows and holds promise for scalable cognitive screening in diverse, aging populations.