AUTHOR=Chen Yanru , Qian Xiaoling , Zhang Yuanyuan , Su Wenli , Huang Yanan , Wang Xinyu , Chen Xiaoli , Zhao Enhan , Han Lin , Ma Yuxia 

TITLE=Prediction Models for Conversion From Mild Cognitive Impairment to Alzheimer’s Disease: A Systematic Review and Meta-Analysis

JOURNAL=Frontiers in Aging Neuroscience

VOLUME=Volume 14 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/aging-neuroscience/articles/10.3389/fnagi.2022.840386

DOI=10.3389/fnagi.2022.840386

ISSN=1663-4365

ABSTRACT=Background and Purpose: Alzheimer's disease (AD) is a devastating neurodegenerative disorder with no cure and available treatments are only able to postpone the progression of the disease. Mild cognitive impairment (MCI) is considered to be a transitional stage preceding Alzheimer’s disease. Therefore, prediction models for conversion from mild cognitive impairment to Alzheimer’s disease is desperately required. These will allow early treatment of patients with MCI before they convert to AD. This study performed a systematic review and meta-analysis to summarize the reported risk prediction models and identify the most prevalent factors for conversion from MCI to AD. 
Methods: We systematically reviewed the studies from the databases of PubMed, CINAHL Plus, Web of Science, Embase and Cochrane Library was searched through September 2021. Two reviewers independently identified eligible articles and extracted data. We used the CHARMS (Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modelling Studies) checklist for risk of bias assessment.
Results: 18 articles describing the prediction models for conversion from MCI to AD were identified. The dementia conversion rate of elderly patients with mild cognitive impairment ranged from 14.49% to 61.50%. Models in 10 studies were developed using data from the ADNI (the Alzheimer’s Disease Neuroimaging Initiative). C-index/AUC of development Models were 0.718~ 0.929 and the validation models were 0.62 ~ 0.912. APOE4, gender, age, MMSE, CSF Aβ1–42, education, MRI, ADAS-cog, CDR score and the functional activities questionary (FAQ) score were the most common predictors included in the models.
Conclusion: In this systematic review, many prediction models have been developed and have good predictive performance, but the lack of external validation of models limited the extensive application in general population. In clinical practice, it is recommended that medical professionals adopt a comprehensive forecasting method rather than a single predictive factor to screen patients with high-risk of mild cognitive impairment. Future research should pay attention to improvement, calibration and validation of existing models while considering new variables, new methods and differences in risk profiles across populations.