Original title: Mapping risk of gambling disorder in older adults: a neural network approach
The researchers used a neural networkA computer method that learns patterns from examples to make predictions., a computer method that learns patterns from examples, to study gambling disorder in adults aged 50 to 85. It distinguished people seeking treatment for gambling problems from healthy controls, with novelty seeking contributing most to that distinction. In the group with gambling disorder, overall psychological distress was most associated with how severe the disorder was. The study finds patterns in one clinic-based sample; it does not establish that the models are ready for clinical use.
Imagine sorting a pile of laundry into two baskets. Some clothes are easy to sort, but others have several clues that overlap, so no single clue settles where they belong. In this paper, the clues are people’s psychological and behavioral features, and the baskets are the group with gambling disorder and the healthy-control group; the computer learns which clues together best distinguish them.
Gambling-related harm in older adults may have different risk profiles than in younger people. Identifying factors linked to the disorder could help researchers develop age-sensitive ways to detect and understand it, though these models still need validation before clinical use.
The study was cross-sectional and based at one center, so it does not establish cause or show that the models work in other settings. The holdout estimates need caution because that subset included only 12 healthy controls. The authors say clinical use for age-sensitive detection and intervention remains preliminary and requires further validation.
Ask anything about this paper. Answers come from its abstract, and say so when the abstract doesn't cover your question.
Mapping risk of gambling disorder in older adults: a neural network approach — Roser Granero, Fernando Fernández‐Aranda, Isabel Baenas et al. — Frontiers in Psychiatry — doi:10.3389/fpsyt.2026.1936618
Abstract licence: CC BY
Explanation generated by Synthesis from the abstract — it is not the original paper.