ArticleFrontiers in psychiatry2026
Machine learning for oral frailty factors in hospitalized schizophrenia patients: two-stage feature selection and SHAP analysis.
Article in Frontiers in psychiatry, 2026. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Not yet cited in PubMed.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
0 citing papers in PubMed.
No citing paper in PubMed yet.
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
8 authors.
Funding
No grant is acknowledged in the PubMed record.
Abstract
Background: Long-term hospitalized patients with schizophrenia (SZ) often experience significant oral health problems, and oral frailty (OF) can further exacerbate the decline in their quality of life. However, the status and key influencing factors contributing to OF in this population remain insufficiently explored. Most existing studies rely on traditional regression models, which are prone to overfitting when processing high-dimensional data, making accurate risk identification difficult. This study aims to clarify the current status of OF in this population in Southwest China, identify the influencing factors, and optimize the predictive model using machine learning (ML), thereby providing a basis for clinical practice. Methods: A total of 404 long-term hospitalized patients with SZ from three psychiatric hospitals in Southwest China were enrolled in this study. The Oral Frailty Index-8 was employed to assess OF. Nine feature selection methods and five ML models were employed to optimize the model through two-stage feature selection, while Shapley Additive Explanations (SHAP) were used to analyze the model's predictive logic. Results: The prevalence of OF in this population was determined to be 69.3%. The optimal model identified was the random forest, with the Area Under the Curve increasing to 0.779 following two-stage optimization. Compared to non-feature selection, performance improved by approximately 6.57%. SHAP analysis revealed that the Number of Teeth, Number of Psychiatric Hospitalizations, Self-discontinuation of Medication, Marital Status, and Age were core risk factors for OF. Conclusion: The prevalence of OF in long-term hospitalized patients with SZ is notably high. Two-stage feature selection enhances the accuracy of the predictive model, and the identified core factors can serve as a reference for developing individualized oral intervention programs in clinical practice.
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.