Multi-Task Learning for Alzheimer's Disease Diagnosis and Mini-Mental State Examination Score Prediction

Accurately diagnosing Alzheimer's disease is essential for improving elderly health.Meanwhile,accurate prediction of the mini-mental state examination score also can measure cognition impairment and track the progression of Alzheimer's disease.However,most of the existing methods perform Alzheimer's disease diagnosis and mini-mental state examination score prediction separately and ignore the relation between these two tasks.To address this challenging problem,we propose a novel multi-task learning method,which uses feature interaction to explore the relationship between Alzheimer's disease diagnosis and minimental state examination score prediction.In our proposed method,features from each task branch are firstly decoupled into candidate and non-candidate parts for interaction.Then,we propose feature sharing module to obtain shared features from candidate features and return shared features to task branches,which can promote the learning of each task.We validate the effectiveness of our proposed method on multiple datasets.In Alzheimer's disease neuroimaging initiative 1 dataset,the accuracy in diagnosis task and the root mean squared error in prediction task of our proposed method is 87.86%and 2.5,respectively.Experimental results show that our proposed method outperforms most state-of-the-art methods.Our proposed method enables accurate Alzheimer's disease diagnosis and mini-mental state examination score prediction.Therefore,it can be used as a reference for the clinical diagnosis of Alzheimer's disease,and can also help doctors and patients track disease progression in a timely manner.

Jidong cognitive impairment cohort study: objectives, design, and baseline screening

The risk of dementia increases in patients with cognitive impairment.However,it is not clear what factors contribute to the onset of dementia in those with cognitive impairment.In this prospective cohort study,we will investigate the every-five-year incidence of cognitive impairment and prognostic factors for cognitive impairment.The Jidong cognitive impairment cohort was established from April 2012 to August 2015,during which we recruited 5854 healthy participants(55.1%male)older than 45 years(mean,57 years).Participants received a health examination in the Staff Hospital,Jidong Oilfield Branch,China National Petroleum Corporation.Baseline data and blood samples were collected.Cognitive impairment was evaluated using the Mini-Mental State Examination,and was defined as a Mini-Mental State Examination score of less than 24.Dementia was assessed using the criteria of Diagnostic and Statistical Manual of Mental Disorders(Fourth edition),the International Working Group criteria,and the Mini-Mental State Examination score.The follow-up will continue until December 2024,during which a prognostic model will be constructed.The primary outcome is the presence/absence of dementia and the secondary outcome is quality of life.Baseline screening results showed the following:(1)Cognitive impairment was apparent in 320 participants(5.5%).These participants will be excluded from the Jidong cohort study,and the remaining participants will be followed up.(2)Of the 320 participants with cognitive impairment,there was a significantly higher prevalence of illiteracy than other education levels(35.9%,P<0.05).Age,arterial hypertension,alcohol consumption,and passive smoking differed significantly between the cognitive impairment and healthy groups(P<0.05).Multivariate logistic regression models showed that age(odds ratio[OR]=1.059,95%confidence interval[CI]:1.044-1.074)and arterial hypertension(OR=1.665,95%CI:1.143-2.427)were risk factors for mild cognitive impairment.With the increase of educational level(illiteracy,primary school,junior high school,high school,university,and above),cognitive impairment gradually decreased(OR<1,P<0.05).(3)This cohort study has initially screened for several risk factors for cognitive impairment at baseline,and subsequent prospective data will further describe,validate,and evaluate the effects of these risk factors on cognitive impairment and dementia.These results can provide clinical evidence for the early prevention of cognitive impairment and dementia.The study was approved by the Ethics Committee of Kailuan General Hospital of Tangshan City and the Medical Ethics Committee,Staff Hospital,Jidong Oilfield Branch,China National Petroleum Corporation on July 12,2013(approval No.2013 YILUNZI 1).

A preliminary study of the Six-Item Screener in detecting cognitive impairment

Objective The present retrospective study was to explore the clinical value of Six-Item Screener （SIS）, which is constituted by 6 items from mini-mental status examination （MMSE）, to identify cognitive impairment. Methods A total number of 1976 patients aged over 50 years, from the Memory Clinic of Huashan Hospital were employed in a battery of neuropsychological tests including MMSE. Subjects with severe conditions, unable to cooperate, or having been previously enrolled, were excluded from this study. The employed subjects were divided into 3 groups： subjective memory complaints （SMCs） （475 cases）, patients with mild cognitive impairment （MCI） （440 cases）, and patients with Alzheimer＇s disease （AD） （1061 cases, including 555 mild, 339 moderate, and 167 severe）. A total score of MMSE and a score of SIS composed of date, month, year, three-word delayed recall from MMSE were calculated. Data were analyzed based on educational background. Results The cut-off of SIS score was 〈 2 for illiterate, 〈 3 for elementary, and 〈 4 for junior high school or above. The sensitivity and specificity of SIS for detecting mild AD were 88.5% and 78.3%, respectively, with an overall accuracy of 83.8%, while for detecting MCI, the sensitivity and specificity were 34.3% and 90.1%, respectively, with an overall accuracy of 63.2%. Conclusion SIS is an effective and reliable instrument for dementia detection in outpatient department. However, it has limited value for MCI identification.