International psychogeriatrics · 2025
Brain morphological characteristics predicting clinical response to selective serotonin reuptake inhibitors or cholinesterase inhibitors: A study of electronic medical records in patients with cognitive disorders.
СтатьяНаблюдательное исследованиеПоддержка NIH: внешняя программаНазвание 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.
Onda Kengo, Chotiyanonta Jill S, Cowley Hannah P, Uchida Yuto, Nowrangi Milap A, Adams Roy, Lyketsos Constantine G, Zandi Peter P, Oishi Kenichi
Аннотация
OBJECTIVES: Current treatments for cognitive and neuropsychiatric symptoms in Alzheimer's disease and related dementias (ADRD), such as cholinesterase inhibitors (CEIs) and selective serotonin reuptake inhibitors (SSRIs), show inconsistent effectiveness, necessitating a personalized therapy approach. We aimed to develop predictive models using MRI-derived brain neuroanatomical features and clinical data to forecast responses to CEIs and SSRIs in ADRD patients.
DESIGN AND SETTING: This was a retrospective observational analysis of electronic health records (EHRs) and MRI data conducted within Johns Hopkins Medical Systems.
PARTICIPANTS: Cohort 1 comprised 179 patients prescribed CEIs or SSRIs for the first time with over a year of follow-up. Cohort 2 included 1244 patients with similar criteria to explore clinical characteristics linked to MRI features affecting treatment benefits.
MEASURES: Medication efficacy was assessed via a Likert scale based on EMR descriptions. We quantified brain volumes across 280 anatomical areas on T1-weighted MRIs and applied an elastic net model after harmonizing volumes with the ComBat model. Predictive model efficacy was evaluated using receiver operating characteristic (ROC) analysis.
RESULTS: Preserved volume in the nucleus basalis of Meynert correlated with better responses to both CEIs and SSRIs. Specific white matter volumes related to CEI benefits, while SSRI efficacy was linked to gray matter in the Nucleus Accumbens and frontal cortex. Area under ROC curve values were 0.82 for CEI and 0.75 for SSRI predictions. Older age and vascular factors were associated with reduced medication benefits.
CONCLUSIONS: MRI-derived neuroanatomical features effectively predict medication responses in ADRD, potentially enabling more tailored treatment strategies.
DESIGN AND SETTING: This was a retrospective observational analysis of electronic health records (EHRs) and MRI data conducted within Johns Hopkins Medical Systems.
PARTICIPANTS: Cohort 1 comprised 179 patients prescribed CEIs or SSRIs for the first time with over a year of follow-up. Cohort 2 included 1244 patients with similar criteria to explore clinical characteristics linked to MRI features affecting treatment benefits.
MEASURES: Medication efficacy was assessed via a Likert scale based on EMR descriptions. We quantified brain volumes across 280 anatomical areas on T1-weighted MRIs and applied an elastic net model after harmonizing volumes with the ComBat model. Predictive model efficacy was evaluated using receiver operating characteristic (ROC) analysis.
RESULTS: Preserved volume in the nucleus basalis of Meynert correlated with better responses to both CEIs and SSRIs. Specific white matter volumes related to CEI benefits, while SSRI efficacy was linked to gray matter in the Nucleus Accumbens and frontal cortex. Area under ROC curve values were 0.82 for CEI and 0.75 for SSRI predictions. Older age and vascular factors were associated with reduced medication benefits.
CONCLUSIONS: MRI-derived neuroanatomical features effectively predict medication responses in ADRD, potentially enabling more tailored treatment strategies.