Full Program »
A Decision Tree–based Classifier To Provide Nutritional Plans Recommendations
The use of machine learning algorithms in the field of nutritional health is a topic that has been developed in recent years for the early diagnosis of diseases or for the recommendation of better nutritional habits. Previous studies mention that, if dietary habits are not changed, in the long term, there is a risk of further medical complications that can lead to death. People with poor diets are more prone to chronic diseases. This study proposes a model, to be used by nutritionists and patients, for the recommendation of nutritional plans using the decision tree technique. The model receives the exact percentage of macronutrients and patient data such as age, height, weight and the disease they suffer from. BMI (Body Mass Index) and BMR (Basal Metabolic Rate) are calculated to complete the parameters needed for the algorithm. The decision tree algorithm evaluates these parameters and recommends the best nutritional plan for the patient. The algorithm used in the model was trained with a dataset of meal plan data assigned by specialists to patients. These data have the nutritional information of the foods, which were obtained from the Peruvian food composition table. It also has the clinical data of the patients to whom these diets were assigned. These data were collected from the nutrition area of the Hospital Marino Molina Sccipa in Lima, Peru. The algorithm is implemented in the Python environment and the Scikit-learn library was used for the correct training of the model. Preliminary results of the experiment with the proposed algorithm show an accuracy of 78.95% allowing to provide accurate recommendations from a considerable amount of historical data, in a matter of seconds. The recommendations generated by the model allow the nutrition specialist to obtain real information on the progress of the nutritional plan assigned to a patient to monitor its evolution. Finally, the accuracy of the algorithm has been proven, generating the necessary knowledge so that it can be used in different case studies.