Publications

@misc{Chang2021iubmb,

title = {Meta-analysis of performance of existing machine learning models for detection of Alzheimer’s disease},

author = {Jose R Chang and Torbjörn E M Nordling},

url = {https://iubmb.npas.programs.sinica.edu.tw/},

year  = {2021},

date = {2021-04-01},

booktitle = {IUBMB Focused Meeting on Neurodegenerative Disease},

publisher = {Academia Sinica},

address = {Academia Sinica, Taipei, Taiwan},

abstract = {Differentiation between the early stages of Alzheimer's Disease (AD) and normal aging remains a challenging problem. Techniques, such as cerebrospinal fluid assays, magnetic resonance imaging, and positron electron tomography, have helped researchers in the detection of the lesions and changes commonly associated with AD in vivo. 

Here we report on our meta-analysis of the performance of machine learning methods using computational biomarkers for detection of mild cognitive impairment and Alzheimer's disease related dementia published 2012-2019. The best reported Bookmaker informedness (BM) score for binary, three-way and four-way classification are 0.994, 0.940 and 0.856; respectively. The reported sensitivity and specificity when doing a four-way classification by distinguishing early and late cognitive impairment is much poorer compared to a binary classification of AD related dementia and normal control. 

In conclusion, our analysis shows that the current models are not yet good enough for early diagnosis of AD.},

howpublished = {IUBMB Focused Meeting on Neurodegenerative Disease},

keywords = {Alzheimers disease, computational biomarkers, machine learning, meta analysis},

pubstate = {published},

tppubtype = {misc}

}