Peces-Barba, G. (German)
- Publications
- item.page.relationships.isContributorAdvisorOfPublication
- item.page.relationships.isContributorOfPublication
6 results
Search Results
Now showing 1 - 6 of 6
- New GOLD classification: longitudinal data on group assignment(BioMed Central, 2014) Ramos, P. (Pilar); Galdiz, J.B. (Juan Bautista); Cosio, B.G. (Borja G.); Martinez-Gonzalez, C. (Cristina); Casanova, C. (Ciro); Soler-Cataluña, J.J. (Juan José); Agüero, R. (Ramón); Marin, J.M. (José M.); Calle-Rubio, M. (Miryam); Marin, M. (Margarita); Torres, J.P. (Juan P.) de; Irigaray, R. (Rosa); Soriano, J.B. (Joan B.); Diego-Damia, A. (Alfredo) de; Solanes-García, I. (Ingrid); Feu-Collado, N. (Nuria); Balcells, E. (Eva); Llunell, A. (Antonia); Lopez-Campos, J.L. (José Luis); Alfageme, I. (Inmaculada); Mir-Viladrich, I. (Isabel); Peces-Barba, G. (German)In the new GOLD grading classification, the type of tool used to determine the level of symptoms can substantially alter the group assignment. A change in category after one year was associated with longitudinal changes in the CAT and BODE index.
- Deep learning-based lesion subtyping and prediction of clinical outcomes in COVID-19 pneumonia using chest CT(2022) Seijo, L. (Luis); Sellarés, J. (Jacobo); Bermejo-Peláez, D. (David); Sánchez, M. (Marcelo); Bastarrika, G. (Gorka); Ledesma-Carbayo, M.J. (María J.); Gotera-Rivera, C. (Carolina); Benegas, M. (Mariana); Palacios-Miras, C. (Carmelo); Cuerpo, S. (Sara); Luengo-Oroz, M. (Miguel); San-José-Estépar, R. (Raúl); Gallardo-Madueño, G. (Guillermo); Fernández-Velilla, M. (María); Peces-Barba, G. (German)The main objective of this work is to develop and evaluate an artificial intelligence system based on deep learning capable of automatically identifying, quantifying, and characterizing COVID-19 pneumonia patterns in order to assess disease severity and predict clinical outcomes, and to compare the prediction performance with respect to human reader severity assessment and whole lung radiomics. We propose a deep learning based scheme to automatically segment the different lesion subtypes in nonenhanced CT scans. The automatic lesion quantification was used to predict clinical outcomes. The proposed technique has been independently tested in a multicentric cohort of 103 patients, retrospectively collected between March and July of 2020. Segmentation of lesion subtypes was evaluated using both overlapping (Dice) and distance-based (Hausdorff and average surface) metrics, while the proposed system to predict clinically relevant outcomes was assessed using the area under the curve (AUC). Additionally, other metrics including sensitivity, specificity, positive predictive value and negative predictive value were estimated. 95% confidence intervals were properly calculated. The agreement between the automatic estimate of parenchymal damage (%) and the radiologists' severity scoring was strong, with a Spearman correlation coefficient (R) of 0.83. The automatic quantification of lesion subtypes was able to predict patient mortality, admission to the Intensive Care Units (ICU) and need for mechanical ventilation with an AUC of 0.87, 0.73 and 0.68 respectively. The proposed artificial intelligence system enabled a better prediction of those clinically relevant outcomes when compared to the radiologists' interpretation and to whole lung radiomics. In conclusion, deep learning lesion subtyping in COVID-19 pneumonia from noncontrast chest CT enables quantitative assessment of disease severity and better prediction of clinical outcomes with respect to whole lung radiomics or radiologists' severity score.
- Impact of applying the global lung initiative criteria for airway obstruction in GOLD defined COPD cohorts: the BODE and CHAIN experience(2024) Cabrera, C. (Carlos); Cosio, B.G. (Borja G.); Bastarrika, G. (Gorka); Celli, B.R. (Bartolomé R.); Gotera-Rivera, C. (Carolina); Casanova, C. (Ciro); Sangro, M. (Matilde); Marin, J.M. (José M.); Torres, J.P. (Juan P.) de; Fuster, A. (Antonia); Alcaide, A.B. (Ana Belén); Ezponda, A. (Ana); Solanes-García, I. (Ingrid); Feu-Collado, N. (Nuria); Marin-Marin, M. (Marta); Martínez, C. (Cristina); Calle, M. (Myriam); Marin, A. (Alicia); Peces-Barba, G. (German)Introduction: The Global Lung Function Initiative (GLI) has proposed new criteria for airflow limitation (AL) and recommends using these to interpret spirometry. The objective of this study was to explore the impact of the application of the AL GLI criteria in two well characterized GOLD-defined COPD cohorts. Methods: COPD patients from the BODE (n=360) and the COPD History Assessment In SpaiN (CHAIN) cohorts (n=722) were enrolled and followed. Age, gender, pack-years history, BMI, dyspnea, lung function measurements, exercise capacity, BODE index, history of exacerbations and survival were recorded. CT-detected comorbidities were registered in the BODE cohort. The proportion of subjects without AL by GLI criteria was determined in each cohort. The clinical, CT-detected comorbidity, and overall survival of these patients were evaluated. Results: In total, 18% of the BODE and 15% of the CHAIN cohort did not meet GLI AL criteria. In the BODE and CHAIN cohorts respectively, these patients had a high clinical burden (BODE≥3: 9% and 20%; mMRC≥2: 16% and 45%; exacerbations in the previous year: 31% and 9%; 6MWD<350m: 15% and 19%, respectively), and a similar prevalence of CT-diagnosed comorbidities compared with those with GLI AL. They also had a higher rate of long-term mortality - 33% and 22% respectively. Conclusions: An important proportion of patients from 2 GOLD-defined COPD cohorts did not meet GLI AL criteria at enrolment, although they had a significant burden of disease. Caution must be taken when applying the GLI AL criteria in clinical practice.
- Integration of longitudinal deep-radiomics and clinical data improves the prediction of durable benefits to anti-PD-1/PD-L1 immunotherapy in advanced NSCLC patients(2023) Seijo, L. (Luis); Bermejo-Peláez, D. (David); Gil-Bazo, I. (Ignacio); Farina, B. (Benito); Domine, M. (Manuel); Ledesma-Carbayo, M.J. (María J.); Ramos-Guerra, A.D. (Ana Delia); Corral-Jaime, J. (Jesús); Palacios-Miras, C. (Carmelo); Gallardo-Madueño, G. (Guillermo); Rubio-Pérez, J. (Jaime); Vilalta, A. (Anna); Muñoz-Barrutia, A. (Arrate); Alcázar, A. (Andrés); Peces-Barba, G. (German)Background Identifying predictive non-invasive biomarkers of immunotherapy response is crucial to avoid premature treatment interruptions or ineffective prolongation. Our aim was to develop a non-invasive biomarker for predicting immunotherapy clinical durable benefit, based on the integration of radiomics and clinical data monitored through early anti-PD-1/PD-L1 monoclonal antibodies treatment in patients with advanced non-small cell lung cancer (NSCLC).MethodsIn this study, 264 patients with pathologically confirmed stage IV NSCLC treated with immunotherapy were retrospectively collected from two institutions. The cohort was randomly divided into a training (n = 221) and an independent test set (n = 43), ensuring the balanced availability of baseline and follow-up data for each patient. Clinical data corresponding to the start of treatment was retrieved from electronic patient records, and blood test variables after the first and third cycles of immunotherapy were also collected. Additionally, traditional radiomics and deep-radiomics features were extracted from the primary tumors of the computed tomography (CT) scans before treatment and during patient follow-up. Random Forest was used to implementing baseline and longitudinal models using clinical and radiomics data separately, and then an ensemble model was built integrating both sources of information.ResultsThe integration of longitudinal clinical and deep-radiomics data significantly improved clinical durable benefit prediction at 6 and 9 months after treatment in the independent test set, achieving an area under the receiver operating characteristic curve of 0.824 (95% CI: [0.658,0.953]) and 0.753 (95% CI: [0.549,0.931]). The Kaplan-Meier survival analysis showed that, for both endpoints, the signatures significantly stratified high- and low-risk patients (p-value< 0.05) and were significantly correlated with progression-free survival (PFS6 model: C-index 0.723, p-value = 0.004; PFS9 model: C-index 0.685, p-value = 0.030) and overall survival (PFS6 models: C-index 0.768, p-value = 0.002; PFS9 model: C-index 0.736, p-value = 0.023).ConclusionsIntegrating multidimensional and longitudinal data improved clinical durable benefit prediction to immunotherapy treatment of advanced non-small cell lung cancer patients. The selection of effective treatment and the appropriate evaluation of clinical benefit are important for better managing cancer patients with prolonged survival and preserving quality of life.
- Untargeted Metabolomic Study of Lung Cancer Patients after Surgery with Curative Intent(2023) Seijo, L. (Luis); García-Barrera, T. (Tamara); Santana, R. (Rafael); Padrón-Fraysse, L. A. (Luis Alejandro); Gotera-Rivera, C. (Carolina); Herrera-Chilla, A. (Ángeles); Pereira-Vega, A. (Antonio); Sánchez-Espirilla, S. (Saida); Blanco-Orozco, A. I. (Ana Isabel); Díaz-Olivares, I. (Isabel); Callejón-Leblic, B. (Belén); Rodríguez-Pérez, M.C. (María C.); Gómez-Ariza, J. L. (José Luis); Lopez-Campos, J.L. (José Luis); Peces-Barba, G. (German)Lung cancer (LC) is a leading cause of mortality, claiming more than 1.8 million deaths per year worldwide. Surgery is one of the most effective treatments when the disease is in its early stages. The study of metabolic alterations after surgical intervention with curative intent could be used to assess the response to treatment or the detection of cancer recurrence. In this study, we have evaluated the metabolomic profile of serum samples (n = 110) from preoperative (PRE) and postoperative (POST) LC patients collected at two different time points (1 month, A; 3–6 months, B) with respect to healthy people. An untargeted metabolomic platform based on reversed phase (RP) and hydrophilic interaction chromatography (HILIC), using ultra-high performance liquid chromatography (UHPLC) and mass spectrometry (MS), was applied (MassIVE ID MSV000092213). Twenty-two altered metabolites were annotated by comparing all the different studied groups. DG(14,0/22:1), stearamide, proline, and E,e-carotene-3,3′-dione were found altered in PRE, and their levels returned to those of a baseline control group 3–6 months after surgery. Furthermore, 3-galactosyllactose levels remained altered after intervention in some patients. This study provides unique insights into the metabolic profiles of LC patients after surgery at two different time points by combining complementary analytical methods.
- Natural course of the diffusing capacity of the lungs for carbon monoxide in COPD: importance of sex(2021) Cabrera, C. (Carlos); Cosio, B.G. (Borja G.); Martinez-Gonzalez, C. (Cristina); Celli, B.R. (Bartolomé R.); Casanova, C. (Ciro); Divo, M. (Miguel); Marín-Oto, M. (Marta); Marin, J.M. (José M.); Ojeda, E. (Elena); Torres, J.P. (Juan P.) de; Fuster, A. (Antonia); Solanes-García, I. (Ingrid); Feu-Collado, N. (Nuria); Balcells, E. (Eva); González-Dávila, E. (Enrique); Pinto-Plata, V. (Víctor); Golpe, R. (Rafael); Amado, C. (Carlos); Calle, M. (Myriam); Lopez-Campos, J.L. (José Luis); Peces-Barba, G. (German)Background: The value of the single-breath diffusing capacity of the lungs for carbon monoxide (Dlco) relates to outcomes for patients with COPD. However, little is known about the natural course of Dlco over time, intersubject variability, and factors that may influence Dlco progression. Research question: What is the natural course of Dlco in patients with COPD over time, and which other factors, including sex differences, could influence this progression? Study design and methods: We phenotyped 602 smokers (women, 33%), of whom 506 (84%) had COPD and 96 (16%) had no airflow limitation. Lung function, including Dlco, was monitored annually over 5 years. A random coefficients model was used to evaluate Dlco changes over time. Results: The mean (± SE) yearly decline in Dlco % in patients with COPD was 1.34% ± 0.015%/y. This was steeper compared with non-COPD control subjects (0.04% ± 0.032%/y; P = .004). Sixteen percent of the patients with COPD, vs 4.3% of the control subjects, had a statistically significant Dlco % slope annual decline (4.14%/y). At baseline, women with COPD had lower Dlco values (11.37% ± 2.27%; P < .001) in spite of a higher FEV1 % than men. Compared with men, women with COPD had a steeper Dlco annual decline of 0.89% ± 0.42%/y (P = .039). Interpretation: Patients with COPD have an accelerated decline in Dlco compared with smokers without the disease. However, the decline is slow, and a testing interval of 3 to 4 years may be clinically informative. The lower and more rapid decline in Dlco values in women, compared with men, suggests a differential impact of sex in gas exchange function. Trial registry: ClinicalTrials.gov; No.: NCT01122758; URL: www.clinicaltrials.gov.