eprintid: 4914 rev_number: 9 eprint_status: archive userid: 2 dir: disk0/00/00/49/14 datestamp: 2022-12-05 23:30:16 lastmod: 2022-12-05 23:30:17 status_changed: 2022-12-05 23:30:16 type: article metadata_visibility: show creators_name: Salvador, Raymond creators_name: García-León, María Ángeles creators_name: Feria-Raposo, Isabel creators_name: Botillo-Martín, Carlota creators_name: Martín-Lorenzo, Carlos creators_name: Corte-Souto, Carmen creators_name: Aguilar-Valero, Tania creators_name: Gil Sanz, David creators_name: Porta-Pelayo, David creators_name: Martín-Carrasco, Manuel creators_name: del Olmo-Romero, Francisco creators_name: Maria Santiago-Bautista, Jose creators_name: Herrero-Muñecas, Pilar creators_name: Castillo-Oramas, Eglee creators_name: Larrubia-Romero, Jesús creators_name: Rios-Alvarado, Zoila creators_name: Antonio Larraz-Romeo, José creators_name: Guardiola-Ripoll, Maria creators_name: Almodóvar-Payá, Carmen creators_name: Fatjó-Vilas Mestre, Mar creators_name: Sarró, Salvador creators_name: McKenna, Peter J creators_name: González-Pablos, Emilio creators_name: Negro-González, Emilio creators_name: María Castells Bescos, Eva creators_name: Felipe Martínez, Elena creators_name: Muñoz Hermoso, Paula creators_name: Camaño Serna, Cora creators_name: Rebolleda Gil, Carlos creators_name: Feliz Muñoz, Carmen creators_name: Sevillano De La Fuente, Paula creators_name: Sánchez Perez, Manuel creators_name: Arrece Iriondo, Izascun creators_name: Vicente Jauregui Berecibar, José creators_name: Domínguez Panchón, Ana creators_name: Felices de la Fuente, Alfredo creators_name: Bosque Gabarre, Clara creators_name: Pomarol-Clotet, Edith creators_id: creators_id: creators_id: creators_id: creators_id: creators_id: creators_id: creators_id: david.gil@uneatlantico.es creators_id: creators_id: creators_id: creators_id: creators_id: creators_id: creators_id: creators_id: creators_id: creators_id: creators_id: creators_id: creators_id: creators_id: creators_id: creators_id: creators_id: creators_id: creators_id: creators_id: creators_id: creators_id: creators_id: creators_id: creators_id: creators_id: creators_id: creators_id: creators_id: creators_id: title: Fingerprints as Predictors of Schizophrenia: A Deep Learning Study ispublished: pub subjects: uneat_eng subjects: uneat_ps divisions: uneatlantico_produccion_cientifica full_text_status: public keywords: schizophrenia, machine learning, dermatoglyphics, diagnosis, artificial intelligence abstract: Background and Hypothesis The existing developmental bond between fingerprint generation and growth of the central nervous system points to a potential use of fingerprints as risk markers in schizophrenia. However, the high complexity of fingerprints geometrical patterns may require flexible algorithms capable of characterizing such complexity. Study Design Based on an initial sample of scanned fingerprints from 612 patients with a diagnosis of non-affective psychosis and 844 healthy subjects, we have built deep learning classification algorithms based on convolutional neural networks. Previously, the general architecture of the network was chosen from exploratory fittings carried out with an independent fingerprint dataset from the National Institute of Standards and Technology. The network architecture was then applied for building classification algorithms (patients vs controls) based on single fingers and multi-input models. Unbiased estimates of classification accuracy were obtained by applying a 5-fold cross-validation scheme. Study Results The highest level of accuracy from networks based on single fingers was achieved by the right thumb network (weighted validation accuracy = 68%), while the highest accuracy from the multi-input models was attained by the model that simultaneously used images from the left thumb, index and middle fingers (weighted validation accuracy = 70%). Conclusion Although fitted models were based on data from patients with a well established diagnosis, since fingerprints remain lifelong stable after birth, our results imply that fingerprints may be applied as early predictors of psychosis. Specially, if they are used in high prevalence subpopulations such as those of individuals at high risk for psychosis. date: 2022 publication: Schizophrenia Bulletin id_number: doi:10.1093/schbul/sbac173 refereed: TRUE issn: 0586-7614 official_url: http://doi.org/10.1093/schbul/sbac173 access: open language: en citation: Artículo Materias > Ingeniería Materias > Psicología Universidad Europea del Atlántico > Investigación > Producción Científica Abierto Inglés Background and Hypothesis The existing developmental bond between fingerprint generation and growth of the central nervous system points to a potential use of fingerprints as risk markers in schizophrenia. However, the high complexity of fingerprints geometrical patterns may require flexible algorithms capable of characterizing such complexity. Study Design Based on an initial sample of scanned fingerprints from 612 patients with a diagnosis of non-affective psychosis and 844 healthy subjects, we have built deep learning classification algorithms based on convolutional neural networks. Previously, the general architecture of the network was chosen from exploratory fittings carried out with an independent fingerprint dataset from the National Institute of Standards and Technology. The network architecture was then applied for building classification algorithms (patients vs controls) based on single fingers and multi-input models. Unbiased estimates of classification accuracy were obtained by applying a 5-fold cross-validation scheme. Study Results The highest level of accuracy from networks based on single fingers was achieved by the right thumb network (weighted validation accuracy = 68%), while the highest accuracy from the multi-input models was attained by the model that simultaneously used images from the left thumb, index and middle fingers (weighted validation accuracy = 70%). Conclusion Although fitted models were based on data from patients with a well established diagnosis, since fingerprints remain lifelong stable after birth, our results imply that fingerprints may be applied as early predictors of psychosis. Specially, if they are used in high prevalence subpopulations such as those of individuals at high risk for psychosis. metadata Salvador, Raymond; García-León, María Ángeles; Feria-Raposo, Isabel; Botillo-Martín, Carlota; Martín-Lorenzo, Carlos; Corte-Souto, Carmen; Aguilar-Valero, Tania; Gil Sanz, David; Porta-Pelayo, David; Martín-Carrasco, Manuel; del Olmo-Romero, Francisco; Maria Santiago-Bautista, Jose; Herrero-Muñecas, Pilar; Castillo-Oramas, Eglee; Larrubia-Romero, Jesús; Rios-Alvarado, Zoila; Antonio Larraz-Romeo, José; Guardiola-Ripoll, Maria; Almodóvar-Payá, Carmen; Fatjó-Vilas Mestre, Mar; Sarró, Salvador; McKenna, Peter J; González-Pablos, Emilio; Negro-González, Emilio; María Castells Bescos, Eva; Felipe Martínez, Elena; Muñoz Hermoso, Paula; Camaño Serna, Cora; Rebolleda Gil, Carlos; Feliz Muñoz, Carmen; Sevillano De La Fuente, Paula; Sánchez Perez, Manuel; Arrece Iriondo, Izascun; Vicente Jauregui Berecibar, José; Domínguez Panchón, Ana; Felices de la Fuente, Alfredo; Bosque Gabarre, Clara y Pomarol-Clotet, Edith mail SIN ESPECIFICAR, SIN ESPECIFICAR, SIN ESPECIFICAR, SIN ESPECIFICAR, SIN ESPECIFICAR, SIN ESPECIFICAR, SIN ESPECIFICAR, david.gil@uneatlantico.es, SIN ESPECIFICAR, SIN ESPECIFICAR, SIN ESPECIFICAR, SIN ESPECIFICAR, SIN ESPECIFICAR, SIN ESPECIFICAR, SIN ESPECIFICAR, SIN ESPECIFICAR, SIN ESPECIFICAR, SIN ESPECIFICAR, SIN ESPECIFICAR, SIN ESPECIFICAR, SIN ESPECIFICAR, SIN ESPECIFICAR, SIN ESPECIFICAR, SIN ESPECIFICAR, SIN ESPECIFICAR, SIN ESPECIFICAR, SIN ESPECIFICAR, SIN ESPECIFICAR, SIN ESPECIFICAR, SIN ESPECIFICAR, SIN ESPECIFICAR, SIN ESPECIFICAR, SIN ESPECIFICAR, SIN ESPECIFICAR, SIN ESPECIFICAR, SIN ESPECIFICAR, SIN ESPECIFICAR, SIN ESPECIFICAR (2022) Fingerprints as Predictors of Schizophrenia: A Deep Learning Study. Schizophrenia Bulletin. ISSN 0586-7614 document_url: http://repositorio.uneatlantico.es/id/eprint/4914/1/sbac173.pdf