Dataset Information

Heterogeneous multimodal biomarkers analysis for Alzheimer's disease via Bayesian network.

ABSTRACT: By 2050, it is estimated that the number of worldwide Alzheimer's disease (AD) patients will quadruple from the current number of 36 million, while no proven disease-modifying treatments are available. At present, the underlying disease mechanisms remain under investigation, and recent studies suggest that the disease involves multiple etiological pathways. To better understand the disease and develop treatment strategies, a number of ongoing studies including the Alzheimer's Disease Neuroimaging Initiative (ADNI) enroll many study participants and acquire a large number of biomarkers from various modalities including demographic, genotyping, fluid biomarkers, neuroimaging, neuropsychometric test, and clinical assessments. However, a systematic approach that can integrate all the collected data is lacking. The overarching goal of our study is to use machine learning techniques to understand the relationships among different biomarkers and to establish a system-level model that can better describe the interactions among biomarkers and provide superior diagnostic and prognostic information. In this pilot study, we use Bayesian network (BN) to analyze multimodal data from ADNI, including demographics, volumetric MRI, PET, genotypes, and neuropsychometric measurements and demonstrate our approach to have superior prediction accuracy.

SUBMITTER: Jin Y

PROVIDER: S-EPMC4992017 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundAlzheimer disease (AD) is the most common type of dementia with cognitive decline as one of the core symptoms in older adults. Numerous studies have suggested the value of psychosocial interventions to improve cognition in this population, but which one should be preferred are still matters of controversy. Consequently, we aim to compare and rank different psychosocial interventions in the management of mild to moderate AD with cognitive symptoms.MethodsWe did a network meta-analysis to identify both direct and indirect evidence in relevant studies. We searched MEDLINE, EMBASE, PsycINFO through the OVID database, CENTRAL through the Cochrane Library for clinical randomized controlled trials investigating psychosocial interventions of cognitive symptoms in patients with Alzheimer disease, published up to August 31, 2017. We included trials of home-based exercise(HE), group exercise(GE), walking program(WP), reminiscence therapy(RT), art therapy(AT) or the combination of psychosocial interventions and acetylcholinesterase inhibitor (ChEIs). We extracted the relevant information from these trials with a predefined data extraction sheet and assessed the risk of bias with the Cochrane risk of bias tool. The outcomes investigated were Mini-Mental State Examination (MMSE) and compliance. We did a pair-wise meta-analysis using the fixed-effects model and then did a random-effects network meta-analysis within a Bayesian framework.ResultsWe deemed 10 trials eligible, including 682 patients and 11 treatments. The quality of included study was rated as low in most comparison with Cochrane tools. Treatment effects from the network meta-analysis showed WP was better than control (SMD 4.89, 95% CI -0.07 to 10.00) while cognitive training and acetylcholinesterase inhibitor (CT + ChEIs) was significantly better than the other treatments, when compared with simple ChEIs treatment, assessed by MMSE. In terms of compliance, the pair-wise meta-analysis indicated that WP and HE are better than GE and AT, while CT + ChEIs, CST + ChEIs are better than other combined interventions.ConclusionOur study confirmed the effectiveness of psychosocial interventions for improving cognition or slowing down the progression of cognitive impairment in AD patients and recommended several interventions for clinical practice.

Dataset Information

Heterogeneous multimodal biomarkers analysis for Alzheimer's disease via Bayesian network.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets