OBJECTIVE: The main goal of this paper is to obtain a classification model based on feed-forward multilayer perceptrons in order to improve postpartum depression prediction during the 32 weeks after childbirth with a high sensitivity and specificity and to develop a tool to be integrated in a decision support system for clinicians. MATERIALS AND METHODS: Multilayer perceptrons were trained on data from 1397 women who had just given birth, from seven Spanish general hospitals, including clinical, environmental and genetic variables. A prospective cohort study was made just after delivery, at 8 weeks and at 32 weeks after delivery. The models were evaluated with the geometric mean of accuracies using a hold-out strategy. RESULTS: Multilayer perceptrons showed good performance (high sensitivity and specificity) as predictive models for postpartum depression. CONCLUSIONS: The use of these models in a decision support system can be clinically evaluated in future work. The analysis of the models by pruning leads to a qualitative interpretation of the influence of each variable in the interest of clinical protocols.
OBJECTIVE: The main goal of this paper is to obtain a classification model based on feed-forward multilayer perceptrons in order to improve postpartum depression prediction during the 32 weeks after childbirth with a high sensitivity and specificity and to develop a tool to be integrated in a decision support system for clinicians. MATERIALS AND METHODS: Multilayer perceptrons were trained on data from 1397 women who had just given birth, from seven Spanish general hospitals, including clinical, environmental and genetic variables. A prospective cohort study was made just after delivery, at 8 weeks and at 32 weeks after delivery. The models were evaluated with the geometric mean of accuracies using a hold-out strategy. RESULTS: Multilayer perceptrons showed good performance (high sensitivity and specificity) as predictive models for postpartum depression. CONCLUSIONS: The use of these models in a decision support system can be clinically evaluated in future work. The analysis of the models by pruning leads to a qualitative interpretation of the influence of each variable in the interest of clinical protocols.
Authors: Juergen Dukart; Natalia Chechko; Lisa Hahn; Simon B Eickhoff; Ute Habel; Elmar Stickeler; Patricia Schnakenberg; Tamme W Goecke; Susanne Stickel; Matthias Franz Journal: Transl Psychiatry Date: 2021-02-11 Impact factor: 6.222
Authors: Emma Motrico; Rena Bina; Sara Domínguez-Salas; Vera Mateus; Yolanda Contreras-García; Mercedes Carrasco-Portiño; Erilda Ajaz; Gisele Apter; Andri Christoforou; Pelin Dikmen-Yildiz; Ethel Felice; Camellia Hancheva; Eleni Vousoura; Claire A Wilson; Rachel Buhagiar; Carmen Cadarso-Suárez; Raquel Costa; Emmanuel Devouche; Ana Ganho-Ávila; Diego Gómez-Baya; Francisco Gude; Eleni Hadjigeorgiou; Drorit Levy; Ana Osorio; María Fe Rodriguez; Sandra Saldivia; María Fernanda González; Marina Mattioli; Ana Mesquita Journal: BMC Public Health Date: 2021-02-17 Impact factor: 3.295