Use of a Latent Topic Model for Characteristic Extraction from Health Checkup Questionnaire Data

OBJECTIVES

When patients complete questionnaires during health checkups, many of their responses are subjective, making topic extraction difficult. Therefore, the purpose of this study was to develop a model capable of extracting appropriate topics from subjective data in questionnaires conducted during health checkups.

METHODS

We employed a latent topic model to group the lifestyle habits of the study participants and represented their responses to items on health checkup questionnaires as a probability model. For the probability model, we used latent Dirichlet allocation to extract 30 topics from the questionnaires. According to the model parameters, a total of 4381 study participants were then divided into groups based on these topics. Results from laboratory tests, including blood glucose level, triglycerides, and estimated glomerular filtration rate, were compared between each group, and these results were then compared with those obtained by hierarchical clustering.

RESULTS

If a significant (p < 0.05) difference was observed in any of the laboratory measurements between groups, it was considered to indicate a questionnaire response pattern corresponding to the value of the test result. A comparison between the latent topic model and hierarchical clustering grouping revealed that, in the latent topic model method, a small group of participants who reported having subjective signs of urinary disorder were allocated to a single group.

CONCLUSIONS

The latent topic model is useful for extracting characteristics from a small number of groups from questionnaires with a large number of items. These results show that, in addition to chief complaints and history of past illness, questionnaire data obtained during medical checkups can serve as useful judgment criteria for assessing the conditions of patients.

Prevalence of Parkinson's disease and atypical parkinsonian syndromes in a rural Japanese district

OBJECTIVES

To investigate the prevalence of Parkinson's disease (PD) and atypical parkinsonian syndromes (APS) in a rural Japanese district.

METHOD

Collaboration with the medical institutions, the long-term care insurance system facilities, and the public health office.

RESULTS

The crude prevalence rates were 175 per 100,000 (95% CI: 143-206) for PD, 18 (8-28) for progressive supranuclear palsy, 17 (7-26) for multiple system atrophy (MSA), and 9 (2-16) for corticobasal degeneration. The age-adjusted prevalence rates were 109 per 100,000 (88-134), 10 (2-17), 13 (4-21), and 6 (0-12), for each condition. There was a preponderance of women with PD and of men with APS. Nine of the 116 PD patients and 7 of the 29 APS patients were newly diagnosed in this study.

CONCLUSIONS

There are high prevalence rates for PD and APS and suboptimal recognition of APS. This is the first epidemiological prevalence study of MSA from Japan.