Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 2
Encontrada(s) 1 página(s)

RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Random Forest-Based Prediction of Stroke Outcome

  • Fernández-Lozano, Carlos
  • Hervella, Pablo
  • Mato-Abad, Virginia
  • Rodríguez-Yáñez, Manuel
  • Suárez-Garaboa, Sonia
  • López-Dequidt, Iria
  • Estany-Gestal, Ana
  • Sobrino, Tomás
  • Campos, Francisco
  • Castillo, José
  • Rodríguez-Yáñez, S.
  • Iglesias Rey, Ramón
[Abstract] We research into the clinical, biochemical and neuroimaging factors associated with the outcome of stroke patients to generate a predictive model using machine learning techniques for prediction of mortality and morbidity 3-months after admission. The dataset consisted of patients with ischemic stroke (IS) and non-traumatic intracerebral hemorrhage (ICH) admitted to Stroke Unit of a European Tertiary Hospital prospectively registered. We identified the main variables for machine learning Random Forest (RF), generating a predictive model that can estimate patient mortality/morbidity according to the following groups: (1) IS + ICH, (2) IS, and (3) ICH. A total of 6022 patients were included: 4922 (mean age 71.9 ± 13.8 years) with IS and 1100 (mean age 73.3 ± 13.1 years) with ICH. NIHSS at 24, 48 h and axillary temperature at admission were the most important variables to consider for evolution of patients at 3-months. IS + ICH group was the most stable for mortality prediction [0.904 ± 0.025 of area under the receiver operating characteristics curve (AUC)]. IS group presented similar results, although variability between experiments was slightly higher (0.909 ± 0.032 of AUC). ICH group was the one in which RF had more problems to make adequate predictions (0.9837 vs. 0.7104 of AUC). There were no major differences between IS and IS + ICH groups according to morbidity prediction (0.738 and 0.755 of AUC) but, after checking normality with a Shapiro Wilk test with the null hypothesis that the data follow a normal distribution, it was rejected with W = 0.93546 (p-value < 2.2e−16). Conditions required for a parametric test do not hold, and we performed a paired Wilcoxon Test assuming the null hypothesis that all the groups have the same performance. The null hypothesis was rejected with a value < 2.2e−16, so there are statistical differences between IS and ICH groups. In conclusion, machine learning algorithms RF can be effectively used in stroke patients for long-term outcome prediction of mortality and morbidity., This study was partially supported by grants from the Spanish Ministry of Science and Innovation (SAF2017-84267-R), Xunta de Galicia (Axencia Galega de Innovación (GAIN): IN607A2018/3), Instituto de Salud Carlos III (ISCIII) (PI17/00540, PI17/01103), Spanish Research Network on Cerebrovascular Diseases RETICS-INVICTUS PLUS (RD16/0019) and by the European Union FEDER program. T. Sobrino (CPII17/00027), F. Campos (CPII19/00020) are recipients of research contracts from the Miguel Servet Program (Instituto de Salud Carlos III). General Directorate of Culture, Education and University Management of Xunta de Galicia (ED431G/01,252 ED431D 2017/16), “Galician Network for Colorectal Cancer Research" (Ref. ED431D 2017/23), Competitive Reference Groups (ED431C 2018/49), Spanish Ministry of Economy and Competitiveness via funding of the unique installation BIOCAI (UNLC08-1E-002, UNLC13-13–3503), European Regional Development Funds (FEDER)., Xunta de Galicia; IN607A2018/3, Xunta de Galicia; ED431G/01,252, Xunta de Galicia; ED431D 2017/16
Dipòsit Digital de Documents de la UAB
Publicación Artículo científico (JournalArticle)

Association of High Serum Levels of Growth Factors with Good Outcome in Ischemic Stroke, a Multicenter Study

  • Sobrino, Tomás|||0000-0002-9760-8690
  • Rodríguez-Yáñez, Manuel
  • Campos, Francisco|||0000-0001-8665-1039
  • Iglesias-Rey, Ramón|||0000-0002-9985-9135
  • Millán Torné, Mònica|||0000-0002-4692-5936
  • Pérez de la Ossa, Natalia|||0000-0002-6063-211X
  • Dávalos, Antoni|||0000-0003-2949-5679
  • Delgado Mederos, Raquel|||0000-0003-3737-7226
  • Martínez-Domeño, Alejandro|||0000-0002-9933-3192
  • Martí-Fàbregas, Joan|||0000-0001-9229-8649
  • Castellanos, María del Mar|||0000-0003-3116-1352
  • Serena, Joaquín|||0000-0002-4478-7744
  • Lago, Aida
  • Díez-Tejedor, Exuperio
  • Castillo, José
The main objective of this research work was to study the association of serum levels of growth factors (GF) and SDF-1α with the functional outcome and reduction of lesion volume in ischemic stroke patients. In this multicenter study, 552 patients with non-lacunar stroke (male, 62.1%; mean age, 68.2 ± 11.4) were included within 24 h from symptom onset. The main outcome variable was good functional outcome (modified Rankin Scale [mRS] ≤ 2) at 12 months. Secondary outcome variable was infarct volume (in mL) after 6 ± 3 months. Serum levels of VEGF, Ang-1, G-CSF, BDNF, and SDF-1α were measured by ELISA at admission, 7 ± 1 days, at 3 ± 1 months, and 12 ± 3 months. Except for BDNF, all GF and SDF-1α serum levels showed a peak value at day 7 and remained elevated during the first 3 months (all p < 0.01). High serum levels at day 7 of VEGF (OR, 19.3), Ang-1 (OR, 14.7), G-CSF (OR, 9.6), and SDF-1α (OR, 28.5) were independently associated with good outcome at 12 months (all p < 0.0001). On the other hand, serum levels of VEGF (B, - 21.4), G-CSF (B, - 14.0), Ang-1 (B, - 13.3), and SDF-1α (B, - 44.6) measured at day 7 were independently associated with lesion volume at 6 months (p < 0.01). In summary, high serum levels of VEGF, Ang-1, G-CSF, and SDF-1α at day 7 and 3 months after ischemic stroke are associated with good functional outcome and smaller residual lesion at 1 year of follow-up.