Aims: This study provides data on predicting changes in cognitive functions, behavioral independences and disturbances in dementia patients by differential modeling with logarithmic and linear regression. Methods: This longitudinal study included two data analysis groups. Group one: 24 dementia patients for identification of cognitive and behavioral changes over time in group data; group two: 15 dementia patients to ensure correlation of the group data applied to prediction of each individual's degree of cognitive and behavioral changes. Group one mini-mental state examination, functional independence measure and dementia behavior disturbance scale scores were assessed initially and 3 and 6 months thereafter during hospitalization and were regressed on the logarithm and linear of time. In group two, calculations of the scores were made for the first two scorings after admission to tailor logarithmic and linear regression formulae to fit an individual's degree of changes at 9 and 12 months. Results: Changes in data over time resembled both logarithmic and linear functions. However, the scores sampled at two baseline points based on logarithmic regression modeling estimated prediction of cognitive and behavioral changes more accurately than did linear regression modeling. Conclusion: This simple-to-use logarithmic modeling accurately predicted changes in cognitive functions, behavioral independence and disturbances in patients with dementia.

Aim This study aimed to use a convolutional neural network (CNN) to investigate the associations between the time of falling and multiple complicating factors, including age, dementia severity, lower extremity strength and physical function, among nursing home residents with Alzheimer's disease. Methods A total of 42 people with Alzheimer's disease were enrolled. We evaluated falling events from nursing home admission (baseline) to 300 days later. We assessed the knee extension strength and Functional Independence Measure locomotion item and carried out the Mini‐Mental State Examination at baseline. To predict falling, participants were categorized into three classes: those who fell within the first 150 (or 300) days from baseline or those who did not experience a fall within the study period. For each class, 1000 bootstrap datasets were generated using 42 actual sample datasets, and were used to propose a CNN algorithm and cross‐validate the algorithm. Results Eight (19.0%), 11 (26.2%) and 31 participants (73.8%) fell within 150 or 300 days after the baseline assessment or did not fall until 300 days or later, respectively. The highest accuracy rate of the CNN classification was 0.647 in the factor combination extracted from the Mini‐Mental State Examination score, knee extension strength and Functional Independence Measure locomotion item score. Conclusions A CNN based on multiple complicating factors could predict the time of falling in nursing home residents with Alzheimer's disease. Geriatr Gerontol Int 2020; ••: ••–••.

Objectives: It is difficult to predict behavioral disturbances in patients with Alzheimer's dementia because the order of appearance of behaviors is not clear. This study aimed to clarify the difficulty of the Dementia Behavior Disturbance Scale (DBDS) sub-items in patients with Alzheimer's disease and to compare changes in behavioral disorders after 6 months. Methods: The participants were inpatients with Alzheimer-type dementia hospitalized in participating hospitals for more than a year. They were assessed with the DBDS, the Mini-Mental State Examination (MMSE), and the Functional Independence Measure (FIM) twice: at the initial assessment and after 6 months. Rasch analysis for the sub-items of the DBDS determined the difficulty of behavioral disturbances. Results: The participants were 44 inpatients. There was no significant difference in the DBDS, MMSE, and FIM between the initial assessment and that after 6 months. Even though many participants increased or decreased for each assessment scale, there was no major change in the order of item difficulty of DBDS between the initial assessment and after 6 months. Conclusions:The systematic indication of the difficulty of behavioral disturbances in the DBDS is a new finding. It is possible to rank the difficulty of sub-items of the DBDS and infer behavioral disturbances that are likely to appear in the future. This is useful for clinical decision-making in dementia rehabilitation and care because it indicates the predictability of signs of dementia and behavioral disturbances that suggest the need for dementia intervention.