Suitability of machine learning models for prediction of clinically defined Stage III/IV periodontitis from questionnaires and demographic data in Danish cohorts.

AIM: To evaluate if, and to what extent, machine learning models can capture clinically defined Stage III/IV periodontitis from self-report questionnaires and demographic data. MATERIALS AND METHODS: Self-reported measures of periodontitis, demographic data and clinically established Stage III/IV periodontitis status were extracted from two Danish population-based cohorts (The Copenhagen Aging and Midlife Biobank [CAMB] and The Danish Health Examination Survey [DANHES]) and used to develop cross-validated machine learning models for the prediction of clinically established Stage III/IV periodontitis. Models were trained using 10-fold cross-validations repeated three times on the CAMB dataset (n = 1476), and the resulting models were validated in the DANHES dataset (n = 3585). RESULTS: The prevalence of Stage III/IV periodontitis was 23.2% (n = 342) in the CAMB dataset and 9.3% (n = 335) in the DANHES dataset. For the prediction of clinically established Stage III/IV periodontitis in the CAMB cohort, models reached area under the receiver operating characteristics (AUROCs) of 0.67-0.69, sensitivities of 0.58-0.64 and specificities of 0.71-0.80. In the DANHES cohort, models derived from the CAMB cohort achieved AUROCs of 0.64-0.70, sensitivities of 0.44-0.63 and specificities of 0.75-0.84. CONCLUSIONS: Applying cross-validated machine learning algorithms to demographic data and self-reported measures of periodontitis resulted in models with modest capabilities for the prediction of Stage III/IV periodontitis in two Danish cohorts.

Root growth and N dynamics in response to multi-year experimental warming, summer drought and elevated CO2 in a mixed heathland-grass ecosystem.

Ecosystems exposed to elevated CO2 are often found to sequester more atmospheric carbon due to increased plant growth. We exposed a Danish heath ecosystem to elevated CO2, elevated temperature and extended summer drought alone and in all combinations in order to study whether the expected increased growth would be matched by an increase in root nutrient uptake of NH4+-N and NO3- -N. Root growth was significantly increased by elevated CO2. The roots, however, did not fully compensate for the higher growth with a similar increase in nitrogen uptake per unit of root mass. Hence the nitrogen concentration in roots was decreased in elevated CO2, whereas the biomass N pool was unchanged or even increased. The higher net root production in elevated CO2 might be a strategy for the plants to cope with increased nutrient demand leading to a long-term increase in N uptake on a whole-plant basis. Drought reduced grass root biomass and N uptake, especially when combined with warming, but CO2 was the most pronounced main factor effect. Several significant interactions of the treatments were found, which indicates that the responses were nonadditive and that changes to multiple environmental changes cannot be predicted from single-factor responses alone.