Environmental factors affecting the BMI of older adults in the Philippines spatially assessed using machine learning
This study aimed to assess the environmental variables affecting the Body Mass Index of older adults at neighborhood levels (1 ha) while mapping probability distributions of normal, overweight-obese, and underweight older adults. We applied a data-driven method that integrates open-access remote sen...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-01-01
|
| Series: | Heliyon |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2405844024169356 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841526295271309312 |
|---|---|
| author | D.K. Mendoza A.B. Araza L.D. Groot M. Mensink R.C. Tan |
| author_facet | D.K. Mendoza A.B. Araza L.D. Groot M. Mensink R.C. Tan |
| author_sort | D.K. Mendoza |
| collection | DOAJ |
| description | This study aimed to assess the environmental variables affecting the Body Mass Index of older adults at neighborhood levels (1 ha) while mapping probability distributions of normal, overweight-obese, and underweight older adults. We applied a data-driven method that integrates open-access remote sensing products and geospatial data, along with the first nutritional survey in the Philippines with geo-locations conducted in 2021. We used ensemble machine learning of different presence-only and presence-absence models, all subjected to hyperparameter tuning and variable decorrelation. The cross-validated ensemble model was found to have AUC=0.76-0.93 and TSS =0.45-0.81, which indicates that the models are performing better than random chance. We found that neighborhoods with (a) short distances to the main city, (b) short distances to roads, and (c) with densest road network all drive overweight-obese cases. The latter (c) contrasts the findings in Western developed countries because of delimiting factors in a tropical developing country related to active public transport, crime, weather, the walkability of roads, and even the COVID-19 restrictions during the time of the surveys. The probability distribution maps revealed that the older adults in the Philippine case cities were mostly overweight-obese, especially within and nearby city centers. We finally showed priority neighborhoods for intervention and local policy implementation, providing valuable insights for local government units. |
| format | Article |
| id | doaj-art-ad673e1bcba34b26a7ed78c81136aa0c |
| institution | Kabale University |
| issn | 2405-8440 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Heliyon |
| spelling | doaj-art-ad673e1bcba34b26a7ed78c81136aa0c2025-01-17T04:49:52ZengElsevierHeliyon2405-84402025-01-01111e40904Environmental factors affecting the BMI of older adults in the Philippines spatially assessed using machine learningD.K. Mendoza0A.B. Araza1L.D. Groot2M. Mensink3R.C. Tan4Department of Science and Technology - Food and Nutrition Research Institute, Taguig, Metro Manila, PhilippinesEarth Systems and Global Change, Wageningen University and Research, Wageningen, the Netherlands; IMPACT R&D, 47 Razburg, San Agustin Bay, Laguna, Philippines; Corresponding author.Division of Human Nutrition and Health, Wageningen University and Research, Wageningen, the NetherlandsDivision of Human Nutrition and Health, Wageningen University and Research, Wageningen, the NetherlandsDepartment of Science and Technology - Food and Nutrition Research Institute, Taguig, Metro Manila, Philippines; Division of Human Nutrition and Health, Wageningen University and Research, Wageningen, the NetherlandsThis study aimed to assess the environmental variables affecting the Body Mass Index of older adults at neighborhood levels (1 ha) while mapping probability distributions of normal, overweight-obese, and underweight older adults. We applied a data-driven method that integrates open-access remote sensing products and geospatial data, along with the first nutritional survey in the Philippines with geo-locations conducted in 2021. We used ensemble machine learning of different presence-only and presence-absence models, all subjected to hyperparameter tuning and variable decorrelation. The cross-validated ensemble model was found to have AUC=0.76-0.93 and TSS =0.45-0.81, which indicates that the models are performing better than random chance. We found that neighborhoods with (a) short distances to the main city, (b) short distances to roads, and (c) with densest road network all drive overweight-obese cases. The latter (c) contrasts the findings in Western developed countries because of delimiting factors in a tropical developing country related to active public transport, crime, weather, the walkability of roads, and even the COVID-19 restrictions during the time of the surveys. The probability distribution maps revealed that the older adults in the Philippine case cities were mostly overweight-obese, especially within and nearby city centers. We finally showed priority neighborhoods for intervention and local policy implementation, providing valuable insights for local government units.http://www.sciencedirect.com/science/article/pii/S2405844024169356Body mass indexObesityMalnutritionMachine learningSpatial dataOlder persons |
| spellingShingle | D.K. Mendoza A.B. Araza L.D. Groot M. Mensink R.C. Tan Environmental factors affecting the BMI of older adults in the Philippines spatially assessed using machine learning Heliyon Body mass index Obesity Malnutrition Machine learning Spatial data Older persons |
| title | Environmental factors affecting the BMI of older adults in the Philippines spatially assessed using machine learning |
| title_full | Environmental factors affecting the BMI of older adults in the Philippines spatially assessed using machine learning |
| title_fullStr | Environmental factors affecting the BMI of older adults in the Philippines spatially assessed using machine learning |
| title_full_unstemmed | Environmental factors affecting the BMI of older adults in the Philippines spatially assessed using machine learning |
| title_short | Environmental factors affecting the BMI of older adults in the Philippines spatially assessed using machine learning |
| title_sort | environmental factors affecting the bmi of older adults in the philippines spatially assessed using machine learning |
| topic | Body mass index Obesity Malnutrition Machine learning Spatial data Older persons |
| url | http://www.sciencedirect.com/science/article/pii/S2405844024169356 |
| work_keys_str_mv | AT dkmendoza environmentalfactorsaffectingthebmiofolderadultsinthephilippinesspatiallyassessedusingmachinelearning AT abaraza environmentalfactorsaffectingthebmiofolderadultsinthephilippinesspatiallyassessedusingmachinelearning AT ldgroot environmentalfactorsaffectingthebmiofolderadultsinthephilippinesspatiallyassessedusingmachinelearning AT mmensink environmentalfactorsaffectingthebmiofolderadultsinthephilippinesspatiallyassessedusingmachinelearning AT rctan environmentalfactorsaffectingthebmiofolderadultsinthephilippinesspatiallyassessedusingmachinelearning |