Search

Made available in DSpace on 2022-04-28T19:49:04Z (GMT). No. of bitstreams: 0 Previous issue date: 2022-02-01 Papaya trees (Carica papaya L.) can bear female, hermaphrodite, and male flowers. However, only the hermaphrodite type produces elongate fruit required and appreciated by the consumer market. Sex type determination is carried out based on the plant phenotype after planting the seedlings, increasing the production costs. In this regard, the objective of this study was to verify the feasibility of using near infrared spectroscopy (NIR) as a non-destructive method for sexing papaya trees. The NIR spectra were collected using seeds and leaves of the respective seedlings of the cultivars ‘T2′, ‘Formosa’, and ‘Calimosa’ (Formosa group), and ‘THB’ and ‘Ouro’ (Solo group). By using the seeds, it was possible to obtain a F-score value of 0.81 for the external validation set applying the principal component analysis and quadratic discriminant analysis (PCA-QDA). By using the leaves, the F-score values was slightly lower (0.79) applying PCA and linear discriminant analysis (PCA-LDA). It was possible to use NIR spectroscopy associated with multivariate techniques as a non-destructive method to determine the sex types in papaya trees using both seeds and leaves of the seedlings. Universidade Estadual Paulista (UNESP) Faculdade de Ciências Agrárias e Veterinárias (FCAV) Campus de Jaboticabal Departamento de Ciências da Produção Agrícola Via de Acesso Prof. Paulo Donato Castellane s/n Universidade Federal do Rio Grande do Norte Instituto de Química Química Biológica e Quimiometria Departamento de Química, Lagoa Nova Universidade Federal de Goiás (UFG) Escola de Agronomia Campus Samambaia. Departamento de horticultura. Av. Esperança s/n Universidade Estadual Paulista (UNESP) Faculdade de Ciências Agrárias e Veterinárias (FCAV) Campus de Jaboticabal Departamento de Ciências da Produção Agrícola Via de Acesso Prof. Paulo Donato Castellane s/n

Achieving complete surgical cytoreduction in advanced stage high grade serous ovarian cancer (HGSOC) patients warrants an availability of Critical Care Unit (CCU) beds. Machine Learning (ML) could be helpful in monitoring CCU admissions to improve standards of care. We aimed to improve the accuracy of predicting CCU admission in HGSOC patients by ML algorithms and developed an ML-based predictive score. A cohort of 291 advanced stage HGSOC patients with fully curated data was selected. Several linear and non-linear distances, and quadratic discriminant ML methods, were employed to derive prediction information for CCU admission. When all the variables were included in the model, the prediction accuracies were higher for linear discriminant (0.90) and quadratic discriminant (0.93) methods compared with conventional logistic regression (0.84). Feature selection identified pre-treatment albumin, surgical complexity score, estimated blood loss, operative time, and bowel resection with stoma as the most significant prediction features. The real-time prediction accuracy of the Graphical User Interface CCU calculator reached 95%. Limited, potentially modifiable, mostly intra-operative factors contributing to CCU admission were identified and suggest areas for targeted interventions. The accurate quantification of CCU admission patterns is critical information when counseling patients about peri-operative risks related to their cytoreductive surgery.