Prediction of cognitive conversion within the Alzheimer's disease continuum using deep learning.

IF 7.9 1区医学 Q1 CLINICAL NEUROLOGY

Alzheimer's Research & Therapy Pub Date : 2025-02-13 DOI:10.1186/s13195-025-01686-x

Siyu Yang, Xintong Zhang, Xinyu Du, Peng Yan, Jing Zhang, Wei Wang, Jing Wang, Lei Zhang, Huaiqing Sun, Yin Liu, Xinran Xu, Yaxuan Di, Jin Zhong, Caiyun Wu, Jan D Reinhardt, Yu Zheng, Ting Wu

{"title":"Prediction of cognitive conversion within the Alzheimer's disease continuum using deep learning.","authors":"Siyu Yang, Xintong Zhang, Xinyu Du, Peng Yan, Jing Zhang, Wei Wang, Jing Wang, Lei Zhang, Huaiqing Sun, Yin Liu, Xinran Xu, Yaxuan Di, Jin Zhong, Caiyun Wu, Jan D Reinhardt, Yu Zheng, Ting Wu","doi":"10.1186/s13195-025-01686-x","DOIUrl":null,"url":null,"abstract":"Background: Early diagnosis and accurate prognosis of cognitive decline in Alzheimer's disease (AD) is important to timely assignment to optimal treatment modes. We aimed to develop a deep learning model to predict cognitive conversion to guide re-assignment decisions to more intensive therapies where needed.Methods: Longitudinal data including five variable sets, i.e. demographics, medical history, neuropsychological outcomes, laboratory and neuroimaging results, from the Alzheimer's Disease Neuroimaging Initiative (ADNI) cohort were analyzed. We first developed a deep learning model to predicted cognitive conversion using all five variable sets. We then gradually removed variable sets to obtained parsimonious models for four different years of forecasting after baseline within acceptable frames of reduction in overall model fit (AUC remaining > 0.8).Results: A total of 607 individuals were included at baseline, of whom 538 participants were followed up at 12 months, 482 at 24 months, 268 at 36 months and 280 at 48 months. Predictive performance was excellent with AUCs ranging from 0.87 to 0.92 when all variable sets were considered. Parsimonious prediction models that still had a good performance with AUC 0.80-0.84 were established, each only including two variable sets. Neuropsychological outcomes were included in all parsimonious models. In addition, biomarker was included at year 1 and year 2, imaging data at year 3 and demographics at year 4. Under our pre-set threshold, the rate of upgrade to more intensive therapies according to predicted cognitive conversion was always higher than according to actual cognitive conversion so as to decrease the false positive rate, indicating the proportion of patients who would have missed upgraded treatment based on prognostic models although they actually needed it.Conclusions: Neurophysiological tests combined with other indicator sets that vary along the AD continuum can improve can provide aid for clinical treatment decisions leading to improved management of the disease.Trail registration information: ClinicalTrials.gov Identifier: NCT00106899 (Registration Date: 31 March 2005).","PeriodicalId":7516,"journal":{"name":"Alzheimer's Research & Therapy","volume":"17 1","pages":"41"},"PeriodicalIF":7.9000,"publicationDate":"2025-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11823042/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Alzheimer's Research & Therapy","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1186/s13195-025-01686-x","RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"CLINICAL NEUROLOGY","Score":null,"Total":0}

引用次数: 0

Abstract

Background: Early diagnosis and accurate prognosis of cognitive decline in Alzheimer's disease (AD) is important to timely assignment to optimal treatment modes. We aimed to develop a deep learning model to predict cognitive conversion to guide re-assignment decisions to more intensive therapies where needed.

Methods: Longitudinal data including five variable sets, i.e. demographics, medical history, neuropsychological outcomes, laboratory and neuroimaging results, from the Alzheimer's Disease Neuroimaging Initiative (ADNI) cohort were analyzed. We first developed a deep learning model to predicted cognitive conversion using all five variable sets. We then gradually removed variable sets to obtained parsimonious models for four different years of forecasting after baseline within acceptable frames of reduction in overall model fit (AUC remaining > 0.8).

Results: A total of 607 individuals were included at baseline, of whom 538 participants were followed up at 12 months, 482 at 24 months, 268 at 36 months and 280 at 48 months. Predictive performance was excellent with AUCs ranging from 0.87 to 0.92 when all variable sets were considered. Parsimonious prediction models that still had a good performance with AUC 0.80-0.84 were established, each only including two variable sets. Neuropsychological outcomes were included in all parsimonious models. In addition, biomarker was included at year 1 and year 2, imaging data at year 3 and demographics at year 4. Under our pre-set threshold, the rate of upgrade to more intensive therapies according to predicted cognitive conversion was always higher than according to actual cognitive conversion so as to decrease the false positive rate, indicating the proportion of patients who would have missed upgraded treatment based on prognostic models although they actually needed it.

Conclusions: Neurophysiological tests combined with other indicator sets that vary along the AD continuum can improve can provide aid for clinical treatment decisions leading to improved management of the disease.

Trail registration information: ClinicalTrials.gov Identifier: NCT00106899 (Registration Date: 31 March 2005).

查看原文本刊更多论文

利用深度学习预测阿尔茨海默病连续体中的认知转换。

背景：阿尔茨海默病（AD）认知能力下降的早期诊断和准确预后对于及时选择最佳治疗模式至关重要。我们的目标是开发一个深度学习模型来预测认知转换，以指导在需要时进行更强化治疗的重新分配决策。方法：对来自阿尔茨海默病神经影像学倡议（ADNI）队列的人口统计学、病史、神经心理结局、实验室和神经影像学结果等5个变量组的纵向数据进行分析。我们首先开发了一个深度学习模型，使用所有五个变量集来预测认知转换。然后，我们逐渐去除变量集，在总体模型拟合的可接受框架内，在基线后的四个不同年份的预测中获得简约模型（AUC剩余为bb0 0.8）。结果：基线时共纳入607人，其中538人在12个月时随访，482人在24个月时随访，268人在36个月时随访，280人在48个月时随访。当考虑所有变量集时，预测性能优异，auc范围为0.87至0.92。建立了AUC为0.80 ~ 0.84的简约预测模型，每个模型只包含两个变量集。神经心理学结果包括在所有节俭模型中。此外，在第1年和第2年纳入生物标志物，第3年纳入影像学数据，第4年纳入人口统计学数据。在我们设定的阈值下，为了降低假阳性率，根据预测的认知转换升级到更强化治疗的比率总是高于根据实际的认知转换升级到更强化治疗的比率，这表明有一部分患者虽然确实需要，但会错过基于预后模型的升级治疗。结论：神经生理测试结合其他指标可以改善阿尔茨海默病连续体，可以为临床治疗决策提供帮助，从而改善疾病的管理。试验注册信息：ClinicalTrials.gov标识符：NCT00106899（注册日期：2005年3月31日）。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Alzheimer's Research & Therapy 医学-神经病学

CiteScore

13.10

自引率

3.30%

发文量

172

审稿时长

>12 weeks

期刊介绍： Alzheimer's Research & Therapy is an international peer-reviewed journal that focuses on translational research into Alzheimer's disease and other neurodegenerative diseases. It publishes open-access basic research, clinical trials, drug discovery and development studies, and epidemiologic studies. The journal also includes reviews, viewpoints, commentaries, debates, and reports. All articles published in Alzheimer's Research & Therapy are included in several reputable databases such as CAS, Current contents, DOAJ, Embase, Journal Citation Reports/Science Edition, MEDLINE, PubMed, PubMed Central, Science Citation Index Expanded (Web of Science) and Scopus.