Pasar al contenido principal

CONSTRUCCION Y VALIDACION DE UN SCORE PREDICTIVO DE RIESGO DE INSTITUCIONALIZACION, INGRESOS HOSPITALARIOS Y MORTALIDAD, EN MAYORES DE 65 AÑOS CON MULTIMORBILIDAD Y FRAGILIDAD

PI19/00535

•
Nombre agencia financiadora Instituto de Salud Carlos III
Acrónimo agencia financiadora ISCIII
Programa Programa Estatal de Generación de Conocimiento y Fortalecimiento del Sistema Español de I+D+I
Subprograma Subprograma Estatal de Generación de Conocimiento
Convocatoria Proyectos de Investigación en Salud
Año convocatoria 2019
Plan Estatal 2017-2020 Plan Estatal de Investigación Científica y Técnica y de Innovación
Centro beneficiario IDIAP JORDI GOL
Centro realización IDIAP JORDI GOL

Resultados relacionados

Resultados totales (Incluyendo duplicados): 4
Encontrada(s) 1 página(s)

Dipòsit Digital de Documents de la UAB
Publicación Artículo científico (JournalArticle)

Use of Attention Maps to Enrich Discriminability in Deep Learning Prediction Models Using Longitudinal Data from Electronic Health Records

  • Carrasco-Ribelles, Lucía Amalia|||0000-0001-9263-1747
  • Cabrera-Bean, Margarita|||0000-0001-9058-3825
  • Llanes-Jurado, Jose|||0000-0001-6778-5912
  • Violán, Concepció|||0000-0003-3309-5360
Featured Application: A better discrimination in a prediction model does not imply a better interpretability. In healthcare, where transparency is crucial, both discriminability and interpretability should be checked before stating that a new model is better. Background: In predictive modelling, particularly in fields such as healthcare, the importance of understanding the model's behaviour rivals, if not surpasses, that of discriminability. To this end, attention mechanisms have been included in deep learning models for years. However, when comparing different models, the one with the best discriminability is usually chosen without considering the clinical plausibility of their predictions. Objective: In this work several attention-based deep learning architectures with increasing degrees of complexity were designed and compared aiming to study the balance between discriminability and plausibility with architecture complexity when working with longitudinal data from Electronic Health Records (EHRs). Methods: We developed four deep learning-based architectures with attention mechanisms that were progressively more complex to handle longitudinal data from EHRs. We evaluated their discriminability and resulting attention maps and compared them amongst architectures and different input processing approaches. We trained them on 10 years of data from EHRs from Catalonia (Spain) and evaluated them using a 5-fold cross-validation to predict 1-year all-cause mortality in a subsample of 500,000 people over 65 years of age. Results: Generally, the simplest architectures led to the best overall discriminability, slightly decreasing with complexity by up to 8.7%. However, the attention maps resulting from the simpler architectures were less informative and less clinically plausible compared to those from more complex architectures. Moreover, the latter could give attention weights both in the time and feature domains. Conclusions: Our results suggest that discriminability and more informative and clinically plausible attention maps do not always go together. Given the preferences within the healthcare field for enhanced explainability, establishing a balance with discriminability is imperative.
Dipòsit Digital de Documents de la UAB
Publicación Artículo científico (JournalArticle)

Development of Attention-based Prediction Models for All-cause Mortality, Home Care Need, and Nursing Home Admission in Ageing Adults in Spain Using Longitudinal Electronic Health Record Data

  • Carrasco-Ribelles, Lucía A
  • Cabrera-Bean, Margarita|||0000-0001-9058-3825
  • Khalid, Sara|||0000-0002-2845-5731
  • Roso-Llorach, Albert|||0000-0002-9264-0405
  • Violán, Concepció|||0000-0003-3309-5360
The online version contains supplementary material available at 10.1007/s10916-024-02138-z.
Dipòsit Digital de Documents de la UAB
Publicación Artículo científico (JournalArticle)

12-year evolution of multimorbidity patterns among older adults based on Hidden Markov Models

  • Roso-Llorach, Albert|||0000-0002-9264-0405
  • Vetrano, Davide L.|||0000-0002-3099-4830
  • Trevisan, Caterina
  • Fernández, Sergio
  • Guisado-Clavero, Marina|||0000-0002-8448-2929
  • Carrasco-Ribelles, Lucía Amalia|||0000-0001-9263-1747
  • Fratiglioni, Laura
  • Violán, Concepció|||0000-0003-3309-5360
  • Calderón-Larrañaga, Amaia|||0000-0001-9064-9222
Background: The evolution of multimorbidity patterns during aging is still an under-researched area. We lack evidence concerning the time spent by older adults within one same multimorbidity pattern, and their transitional probability across different patterns when further chronic diseases arise. The aim of this study is to fill this gap by exploring multimorbidity patterns across decades of age in older adults, and longitudinal dynamics among these patterns. Methods: Longitudinal study based on the Swedish National study on Aging and Care in Kungsholmen (SNAC-K) on adults ≥60 years (N=3,363). Hidden Markov Models were applied to model the temporal evolution of both multimorbidity patterns and individuals' transitions over a 12-year follow-up. Findings: Within the study population (mean age 76.1 years, 66.6% female), 87.2% had ≥2 chronic conditions at baseline. Four longitudinal multimorbidity patterns were identified for each decade. Individuals in all decades showed the shortest permanence time in an Unspecific pattern lacking any overrepresented diseases (range: 4.6-10.9 years), but the pattern with the longest permanence time varied by age. Sexagenarians remained longest in the Psychiatric-endocrine and sensorial pattern (15.4 years); septuagenarians in the Neuro-vascular and skin-sensorial pattern (11.0 years); and octogenarians and beyond in the Neuro-sensorial pattern (8.9 years). Transition probabilities varied across decades, sexagenarians showing the highest levels of stability. Interpretation: Our findings highlight the dynamism and heterogeneity underlying multimorbidity by quantifying the varying permanence times and transition probabilities across patterns in different decades. With increasing age, older adults experience decreasing stability and progressively shorter permanence time within one same multimorbidity pattern.
Dipòsit Digital de Documents de la UAB
Publicación Artículo científico (JournalArticle)

Validation of an electronic frailty index with electronic health records, eFRAGICAP index

  • Orfila, Francesc|||0000-0002-2409-1731
  • Carrasco-Ribelles, Lucía Amalia|||0000-0001-9263-1747
  • Abellana, Rosa|||0000-0003-4487-4431
  • Roso-Llorach, Albert|||0000-0002-9264-0405
  • Cegri, Francisco
  • Reyes, Carlen|||0000-0001-8486-3265
  • Violán, Concepció|||0000-0003-3309-5360
To create an electronic frailty index (eFRAGICAP) using electronic health records (EHR) in Catalunya (Spain) and assess its predictive validity with a two-year follow-up of the outcomes: homecare need, institutionalization and mortality in the elderly. Additionally, to assess its concurrent validity compared to other standardized measures: the Clinical Frailty Scale (CFS) and the Risk Instrument for Screening in the Community (RISC). The eFRAGICAP was based on the electronic frailty index (eFI) developed in United Kingdom, and includes 36 deficits identified through clinical diagnoses, prescriptions, physical examinations, and questionnaires registered in the EHR of primary health care centres (PHC). All subjects 65 assigned to a PHC in Barcelona on 1st January, 2016 were included. Subjects were classified according to their eFRAGICAP index as: fit, mild, moderate or severe frailty. Predictive validity was assessed comparing results with the following outcomes: institutionalization, homecare need, and mortality at 24 months. Concurrent validation of the eFRAGICAP was performed with a sample of subjects (n = 333) drawn from the global cohort and the CFS and RISC. Discrimination and calibration measures for the outcomes of institutionalization, homecare need, and mortality and frailty scales were calculated. 253,684 subjects had their eFRAGICAP index calculated. Mean age was 76.3 years (59.5% women). Of these, 41.1% were classified as fit, and 32.2% as presenting mild, 18.7% moderate, and 7.9% severe frailty. The mean age of the subjects included in the validation subsample (n = 333) was 79.9 years (57.7% women). Of these, 12.6% were classified as fit, and 31.5% presented mild, 39.6% moderate, and 16.2% severe frailty. Regarding the outcome analyses, the eFRAGICAP was good in the detection of subjects who were institutionalized, required homecare assistance, or died at 24 months (c-statistic of 0.841, 0.853, and 0.803, respectively). eFRAGICAP was also good in the detection of frail subjects compared to the CFS (AUC 0.821) and the RISC (AUC 0.848). The eFRAGICAP has a good discriminative capacity to identify frail subjects compared to other frailty scales and predictive outcomes. The online version contains supplementary material available at 10.1186/s12877-022-03090-8.