AUTHOR=Zheng Yu , Liu Yin , Wu Jiawen , Xie Yi , Yang Siyu , Li Wanting , Sun Huaiqing , He Qing , Wu Ting 

TITLE=Predicted Cognitive Conversion in Guiding Early Decision-Tailoring on Patients With Cognitive Impairment

JOURNAL=Frontiers in Aging Neuroscience

VOLUME=Volume 13 - 2021

YEAR=2022

URL=https://www.frontiersin.org/journals/aging-neuroscience/articles/10.3389/fnagi.2021.813923

DOI=10.3389/fnagi.2021.813923

ISSN=1663-4365

ABSTRACT=Background:
Cognitive decline is the most dominant and patient-oriented symptoms during the development of AD and MCI. This study was designed to test the feasibility of hybrid convolutional neural networks and long-short term memory (CNN-LSTM) modeling driven early decision-tailoring with the predicted long-term cognitive conversion in AD and MCI.

Methods:
AD or MCI patient characteristics covering demographic, clinical features and time-dependent neuropsychological related features were fused into the hybrid CNN-LSTM modeling to predict cognitive conversion based on a 4-point change in the Alzheimer’s disease assessment scale-cognition score. Treatment reassignment rates were estimated based on the actual and predicted cognitive conversion at 3-month and 6-month according to prespecified principle. That is, if patient’s ADAS-cog score declines less than 4 points or increases at either follow-up time point, the medical treatment recommended upon their diagnosis would be considered insufficient. Therefore, it is recommended to upgrade the medical treatment upon diagnosis. Actual and predicted treatment reassignment rates were compared in the general population and sub-populations categorized by age, gender, symptom severity and the intervention subtypes.

Results:
224 patients were included in the analysis. The hybrid CNN-LSTM model achieved the mean AUC of 0.735 (95%CI 0.701-0.769) at 3-month and 0.853 (95%CI 0.814-0.892) at 6-month in predicting cognitive conversion status. AUC at 6-month was significantly impacted when data collected at 3-month were withdrawn. The predicted cognitive conversion suggested a revision of medical treatment in 46.43% (104/224) of patients at 3-month and 54.02% (121/224) at 6-month as compared to 62.05% (139/224) at 3-month (p=0.001) and 62.50% (140/224) at 6-month (p=0.069) according to their actual cognitive conversion. No significant differences were detected between treatment reassignment rates estimated based on actual and predicted cognitive conversion in all directions at 6-month.

Conclusion:
With the utilization of the synergistic advances of deep learning modeling and featured longitudinal information, our hypothesis was preliminarily verified with the comparable predictive performance in cognitive conversion. Results provided the possibility of reassigned recommended treatment for those who may suffer from cognitive decline in the future. Considering the limited diversity of treatment strategies applied in the current study, the real-world medical situation needs further simulated.