Your privacy, your choice

We use essential cookies to make sure the site can function. We also use optional cookies for advertising, personalisation of content, usage analysis, and social media.

By accepting optional cookies, you consent to the processing of your personal data - including transfers to third parties. Some third parties are outside of the European Economic Area, with varying standards of data protection.

See our privacy policy for more information on the use of your personal data.

for further information and to change your choices.
Skip to main content

Table 1 Summary of the healthy ageing scale development steps

From: A novel explainable machine learning-based healthy ageing scale

Step number

Step description

Step 1

Selection of health categories and where applicable, subcategories.a

Step 2

Selection of dataset items that fall under each health category/subcategory.a,b

Step 3

Explanatory factor analysis performed for each health category/subcategory.b

Step 4

Selection of factors and items most relevant for describing healthy ageing of a person.a

Step 5

Design and development of web annotation application.a

Step 6

Annotation of healthy ageing for each person from this study.c

Step 7

Calculation of ground truth from healthy ageing annotation results.

Step 8

Machine learning model development using 6 different classification algorithms.

Step 9

Selection of best-performing model.

Step 10

Application of SHAP interpretation technique to individual model predictions.

  1. aTight cooperation with gerontology domain experts
  2. bIf the health category had one or multiple subcategories, the step was completed for each subcategory
  3. cAnnotations were performed by gerontology domain experts
Back to article page

BMC Medical Informatics and Decision Making

ISSN: 1472-6947

Contact us