RESUMEN
Real-world registries have been critical to building the scientific knowledge of rare diseases, including Pulmonary Arterial Hypertension (PAH). In the past 4 decades, a considerable number of registries on this condition have allowed to improve the pathology and its subgroups definition, to advance in the understanding of its pathophysiology, to elaborate prognostic scales and to check the transferability of the results from clinical trials to clinical practice. However, in a moment where a huge amount of data from multiple sources is available, they are not always taken into account by the registries. For that reason, Machine Learning (ML) offer a unique opportunity to manage all these data and, finally, to obtain tools that may help to get an earlier diagnose, to help to deduce the prognosis and, in the end, to advance in Personalized Medicine. Thus, we present a narrative revision with the aims of, in one hand, summing up the aspects in which data extraction is important in rare diseases -focusing on the knowledge gained from PAH real-world registries- and, on the other hand, describing some of the achievements and the potential use of the ML techniques on PAH.
Asunto(s)
Aprendizaje Automático , Hipertensión Arterial Pulmonar , Sistema de Registros , Humanos , Hipertensión Arterial Pulmonar/diagnóstico , Pronóstico , Hipertensión Pulmonar/diagnósticoRESUMEN
BACKGROUND: Long-term consequences of COVID-19 are still partly known. AIM OF THE STUDY: To derive a clinical score for risk prediction of long-term major cardiac adverse events (MACE) and all cause death in COVID-19 hospitalized patients. METHODS: 2573 consecutive patients were enrolled in a multicenter, international registry (HOPE-2) from January 2020 to April 2021 and identified as the derivation cohort. Five hundred and twenty-six patients from the Cardio-Covid-Italy registry were considered as external validation cohort. A long-term prognostic risk score for MACE and all cause death was derived from a multivariable regression model. RESULTS: Out of 2573 patients enrolled in the HOPE-2 registry, 1481 (58 %) were male, with mean age of 60±16 years. At long-term follow-up, the overall rate of patients affected by MACE and/or all cause death was 7.8 %. After multivariable regression analysis, independent predictors of MACE and all cause death were identified. The HOPE-2 prognostic score was therefore calculated by giving: 1-4 points for age class (<65 years, 65-74, 75-84, ≥85), 3 points for history of cardiovascular disease, 1 point for hypertension, 3 points for increased troponin serum levels at admission and 2 points for acute renal failure during hospitalization. Score accuracy at ROC curve analysis was 0.79 (0.74 at external validation). Stratification into 3 risk groups (<3, 3-6, >6 points) classified patients into low, intermediate and high risk. The observed MACE and all-cause death rates were 1.9 %, 9.4 % and 26.3 % for low- intermediate and high-risk patients, respectively (Log-rank test p < 0.01). CONCLUSIONS: The HOPE-2 prognostic score may be useful for long-term risk stratification in patients with previous COVID-19 hospitalization. High-risk patients may require a strict follow-up.
Asunto(s)
COVID-19 , Enfermedades Cardiovasculares , Hospitalización , Sistema de Registros , Humanos , COVID-19/mortalidad , COVID-19/epidemiología , Masculino , Femenino , Persona de Mediana Edad , Anciano , Hospitalización/estadística & datos numéricos , Medición de Riesgo/métodos , Enfermedades Cardiovasculares/mortalidad , Enfermedades Cardiovasculares/epidemiología , Pronóstico , Anciano de 80 o más Años , SARS-CoV-2 , Factores de Riesgo , Causas de Muerte , Italia/epidemiología , Estudios de SeguimientoRESUMEN
INTRODUCTION: Patients with pre-existing respiratory diseases in the setting of COVID-19 may have a greater risk of severe complications and even death. METHODS: A retrospective, multicenter, cohort study with 5847 COVID-19 patients admitted to hospitals. Patients were separated in two groups, with/without previous lung disease. Evaluation of factors associated with survival and secondary composite end-point such as ICU admission and respiratory support, were explored. RESULTS: 1,271 patients (22%) had a previous lung disease, mostly COPD. All-cause mortality occurred in 376 patients with lung disease (29.5%) and in 819 patients without (17.9%) (p < 0.001). Kaplan-Meier curves showed that patients with lung diseases had a worse 30-day survival (HR = 1.78; 95%C.I. 1.58-2.01; p < 0.001) and COPD had almost 40% mortality. Multivariable Cox regression showed that prior lung disease remained a risk factor for mortality (HR, 1.21; 95%C.I. 1.02-1.44; p = 0.02). Variables independently associated with all-cause mortality risk in patients with lung diseases were oxygen saturation less than 92% on admission (HR, 4.35; 95% CI 3.08-6.15) and elevated D-dimer (HR, 1.84; 95% CI 1.27-2.67). Age younger than 60 years (HR 0.37; 95% CI 0.21-0.65) was associated with decreased risk of death. CONCLUSIONS: Previous lung disease is a risk factor for mortality in patients with COVID-19. Older age, male gender, home oxygen therapy, and respiratory failure on admission were associated with an increased mortality. Efforts must be done to identify respiratory patients to set measures to improve their clinical outcomes
INTRODUCCIÓN: Los pacientes con enfermedades respiratorias preexistentes pueden tener en el contexto de la covid-19 un mayor riesgo de complicaciones graves e incluso de muerte. MÉTODOS: Estudio de cohortes multicéntrico y retrospectivo de 5.847 pacientes con covid-19 ingresados en hospitales. Los pacientes se separaron en 2 grupos, sin y con enfermedad pulmonar previa. Se evaluaron factores asociados con la supervivencia y criterios combinados de valoración secundarios, como el ingreso en la UCI y la necesidad de asistencia respiratoria. RESULTADOS: Mil doscientos setenta y un (1.271) pacientes (22%) tenían una enfermedad pulmonar previa, principalmente EPOC. La mortalidad por todas las causas ocurrió en 376 pacientes con enfermedad pulmonar (29,5%) y en 819 pacientes sin enfermedad pulmonar (17,9%; p < 0,001). Las curvas de Kaplan-Meier mostraron que los pacientes con enfermedades pulmonares tenían una peor supervivencia a los 30 días (HR: 1,78; IC del 95%: 1,58-2,01; p < 0,001) y la EPOC tenía una mortalidad de casi el 40%. La regresión de Cox multivariante mostró que la enfermedad pulmonar previa seguía siendo un factor de riesgo de mortalidad (HR: 1,21; IC del 95%: 1,02-1,44; p = 0,02). Las variables asociadas de forma independiente con el riesgo de muerte por todas las causas en pacientes con enfermedades pulmonares fueron la saturación de oxígeno inferior al 92% al ingreso (HR: 4,35; IC del 95%: 3,08-6,15) y el dímero D elevado (HR: 1,84; IC del 95%: 1,27-2,67). La edad menor de 60 años (HR: 0,37; IC del 95%: 0,21-0,65) se asoció con una disminución del riesgo de muerte. CONCLUSIONES: La enfermedad pulmonar previa es un factor de riesgo de muerte en pacientes con covid-19. La edad avanzada, el sexo masculino, la oxigenoterapia domiciliaria y la insuficiencia respiratoria al ingreso se asociaron con un aumento de la mortalidad. Se deben realizar esfuerzos para identificar a los pacientes respiratorios y establecer medidas para mejorar sus resultados clínicos
Asunto(s)
Humanos , Masculino , Femenino , Anciano , Mortalidad Hospitalaria , Enfermedades Pulmonares/mortalidad , Infecciones por Coronavirus/mortalidad , Neumonía Viral/mortalidad , Pandemias , Enfermedades Pulmonares/complicaciones , Infecciones por Coronavirus/complicaciones , Neumonía Viral/complicaciones , Estudios Retrospectivos , Prevalencia , Factores Sexuales , Enfermedad Pulmonar Obstructiva Crónica/complicaciones , Enfermedad Pulmonar Obstructiva Crónica/mortalidad , Estimación de Kaplan-Meier , Pronóstico , ComorbilidadRESUMEN
No disponible