ReSmart-15 : An Information Gain based Questionnaire for Early Dementia Detection

Abstract

To build an efective questionnaire for detecting early dementia, we propose ReSmart-15 which is a dementia detection questionnaire that includes daily behavior-based questions in five categories (i.e., attention (3Q), spatial ability (3Q), spatiotemporal ability (3Q), memory (3Q), and thinking ability (3Q)). As for the evaluation, we first collected responses from two diferent screening tests with 87 participants. Then we used a machine learning method called "information gain" ranking to show the efectiveness of ReSmart-15 compared to another representative screening test. As a result, we found that the top 2 questions were from ReSmart-15, and 60 percent of ReSmart-15 questions were in the top 10.

Keywords

• eol>early dementia
• questionnaire
• information gain

1. Introduction

selection through information gain to rank the importance of all features and then filter out the low-ranking Existing screening tools for dementia have several lim- features. In information gain, each question in the quesitations. For example, Mini-Mental State Examination tionnaire was treated as a feature when it had diferent (MMSE) [ 1 ], one of the widely used tests for measuring importance in the prediction of a dementia diagnosis. In the clinical dementia rating scale (CDR) [ 2 ], is insensitive the same way, we computed the information gain to see to detecting the early stages of dementia [ 3 ], especially if ReSmart-15 is ranked higher than NMD-12 [ 8 ]. The for highly educated individuals [ 4, 5 ]. results show that most questions in ReSmart-15 were

Using a screening test with low specificity could lead to ranked higher than the NMD-12 questionnaire. This sugan incorrect diagnosis of dementia in elderly individuals. gests that ReSmart-15 was composed of influential quesTherefore, SED-11Q [ 6 ] aimed to investigate the state of tions filtered by information gain, which may increase daily activities performed in various aspects by including the accuracy of the early diagnosis of dementia. questions that dealt with social interactions and personality. In this study, inspired by the SED-11Q, we propose a questionnaire named ReSmart-15 by modifying the ex- 2. Method isting MMSE questionnaire for better detection of early dementia. The questionnaire consists of daily behavior- We collected audiences from SurveyMonkey2 to recruit based questions in five categories (i.e., attention (3Q), 87 participants (53 female) excluding four who dropped spatial ability (3Q), spatiotemporal ability (3Q), memory out. Their average age was 38.0 (=13.4, range=18-65). (3Q), and thinking ability (3Q)), which are explained by To show the efectiveness of ReSmart-15 compared to anCogniFit1 which designed cognitive assessment through other existing screening questionnaire for early dementia monitoring the patient’s cognitive rehabilitation process detection, we conducted a user study where participants [ 7 ]. were asked to submit their responses to 27 diferent ques

As for the evaluation, we collected responses from tions: 15 questions from ReSmart-15 and 12 questions 87 participants who were asked to answer 27 questions from NMD-12 [ 8 ]. It took 4 minutes and 25 seconds on from two diferent screening tests for dementia, ReSmart- average to complete the task. 15 and NMD-12 [ 8 ]. NMD-12 uses automated feature

3. Evaluation

To evaluate the importance of the questions in ReSmart

15 compared to NMD-12, where it uses the information gain (IG) ranking in machine learning [ 8 ]. Let () be an entropy, and () be the amount of information to

2https://www.surveymonkey.com/

4. Findings and Future Work make an exact classification based on the partition by questions , where is the data sample in the training set. Then, () and () can be calculated as follows: The purpose of this experiment was to select influential questions based on a machine learning technique called information gain. This technique treats each question () = − ∑︁ log2(), as a feature and each of them has a diferent level of =1 importance in the prediction of a dementia diagnosis.

As shown in Table 1, our experiment found that the top () = − ∑=︁1 |||| × ( ), 2ReqSumesatrito-1n5s qwueersetiofrnosmwRereeSminatrht-e1t5o,pa1n0d. 6T0hipsesrucgegnetsotsf that ReSmart-15 was composed of influential questions where is the number of classes, is the probability ifltered by information gain, which may increase the that an arbitrary tuple in belongs to class , and is accuracy of the early diagnosis of dementia. Furthermore, the number of distinct values in . In this study, we make information gain can be used to remove redundant or total two classes where each class represents whether unnecessary features with low importance (i.e., ReSmartthe user is in early dementia or not, which makes = 2. 13 and ReSmart-6), and can simplify the procedure of Also, each questionnaire in ReSmart-15 and NMD-12 can diagnosis. only be answered by either yes or no, which makes = 2. In the next experiment, to make our social robot as a For simplicity, we diagnose early dementia when the health care device, we would like to examine whether number of "yes" answers is 14 or more, i.e., more than the questions with the high impact selected by the mahalf of the total 27 questions. IG of each questionnaire chine learning the technique is likely to be more efective can be calculated by the diference between () and with a conversational voice-based interactive chatbot in(). terface where it is known to have several benefits. It has the potential to act as a doctor for people with de• Today, let’s improve memory! • What is the date today? mentia by providing deep learning chat and awareness combination of information. It helps users [ 9 ] to drive conversations with users rather than simple Q&A services, and to ease technical barriers and build intimacy.

We would like to experiment with a conversational voicebased user interface called Musio 3 as shown in Figure 1.

It is deployed with Muse, which has a natural language processing (NLP) engine. Musio introduces himself at ifrst and asks the questions (ReSmart-15) in a conversational format and we expect that Musio will relieve the users’ burden of testing their cognitive abilities by providing a user interface with a familiar voice [ 10 ]. 23 24 25 26 • (The user solves the problem)

• Yes, you did well.

References

[1] J. R. Cockrell , M. F. Folstein , Mini-mental state examination, Principles and practice of geriatric psychiatry ( 2002 ) 140 - 141 .

[2] J. C. Morris , The clinical dementia rating (CDR): Current version and , Young 41 ( 1991 ) 1588 - 1592 .

[3] J. Lawrence , D. Davidof , D. Katt-Lloyd , M. Auerbach , J. Hennen , A pilot program of improved methods for community-based screening for dementia , The American Journal of Geriatric Psychiatry 9 ( 2001 ) 205 - 211 .

[4] W. J. Lorentz , J. M. Scanlan , S. Borson , Brief screening tests for dementia , The Canadian Journal of Psychiatry 47 ( 2002 ) 723 - 733 .

[5] D. V. Espino , M. J. Lichtenstein , R. F. Palmer , H. P. Hazuda , Evaluation of the mini-mental state examination's internal consistency in a communitybased sample of mexican-american and europeanamerican elders: results from the san antonio longitudinal study of aging , Journal of the American Geriatrics Society 52 ( 2004 ) 822 - 827 .

[6] Y. Maki , T. Yamaguchi , H. Yamaguchi , Symptoms of early dementia-11 questionnaire (sed-11q): a brief informant-operated screening for dementia, Dementia and geriatric cognitive disorders extra 3 ( 2013 ) 131 - 142 .

[7] R. Jung , B. Son , H. Park , S. Kim, M. Wijaya , Resmart: Brain training games for enhancing cognitive health , in: Advances in Computer Vision and Computational Biology , Springer, 2021 , pp. 331 - 337 .

[8] P.-Y. Chiu , H. Tang , C.-Y. Wei, C. Zhang , G.-U. Hung, W. Zhou , Nmd-12: A new machine-learning derived screening instrument to detect mild cognitive impairment and dementia , PloS one 14 ( 2019 ) e0213430 .

[9] C.-L. Liu , S.-R. Chang , A pilot tool of the virtual scenario initial dementia cognitive screening (vsidcs) with a cultural exhibition for improving the standard traditional test , in: Healthcare , volume 9 , Multidisciplinary Digital Publishing Institute, 2021 , p. 1160 .

[10] S. Kim , J. Lee , G. Gweon , Comparing data from chatbot and web surveys: Efects of platform and conversational style on survey response quality , in: Proceedings of the 2019 CHI conference on human factors in computing systems , 2019 , pp. 1 - 12 .