Enhancing identification performance of cognitive impairment high-risk based on a semi-supervised learning method.

BACKGROUND: Cognitive assessment plays a pivotal role in the early detection of cognitive impairment, particularly in the prevention and management of cognitive diseases such as Alzheimer's and Lewy body dementia. Large-scale screening relies heavily on cognitive assessment scales as primary tools, with some low sensitivity and others expensive. Despite significant progress in machine learning for cognitive function assessment, its application in this particular screening domain remains underexplored, often requiring labor-intensive expert annotations. AIMS: This paper introduces a semi-supervised learning algorithm based on pseudo-label with putback (SS-PP), aiming to enhance model efficiency in predicting the high risk of cognitive impairment (HR-CI) by utilizing the distribution of unlabeled samples. DATA: The study involved 189 labeled samples and 215,078 unlabeled samples from real world. A semi-supervised classification algorithm was designed and evaluated by comparison with supervised methods composed by 14 traditional machine-learning methods and other advanced semi-supervised algorithms. RESULTS: The optimal SS-PP model, based on GBDT, achieved an AUC of 0.947. Comparative analysis with supervised learning models and semi-supervised methods demonstrated an average AUC improvement of 8% and state-of-art performance, repectively. CONCLUSION: This study pioneers the exploration of utilizing limited labeled data for HR-CI predictions and evaluates the benefits of incorporating physical examination data, holding significant implications for the development of cost-effective strategies in relevant healthcare domains.

Reliability and Validity of the Repeatable Battery for Assessment of Neuropsychological Status Scale in Evaluation of Vascular Cognitive Impairment in Elderly Han Population.

Introduction: Vascular cognitive impairment (VCI) and Alzheimer's disease are the most common cognitive impairment diseases in the elderly. This study aimed to apply the Repeatable Battery for Assessment of Neuropsychological Status (RBANS) scale to evaluate VCI in elderly patients and analyze its reliability and validity. Methods: We enrolled 278 VCI patients admitted to our hospital, from June 2017 to June 2018. The basic clinical information of each patient was documented, and the Mini-Mental State Examination (MMSE) and the RBANS scales were suggested to complete. Results: We found significant correlations between the RBANS total score and age, diabetes, hypertension, coronary heart disease and years of education. The internal consistency of the RBANS scale Cronbach αsuggested a good agreement with the total score and the single score at two time points. Moreover, the RBANS total score and the score of each dimension in the RBANS scale were positively correlated with the MMSE immediate memory, calculation ability, delayed memory, commanding ability, reading comprehension ability, command execution, sentence making, and pattern duplicating ability. Conclusion: In conclusion, the RBANS has good reliability and validity for the assessment of cognitive dysfunction in elderly VCI patients. It can be used as a routine clinical and research tool, for the simplicity in operation and superior acceptance.