RESUMEN
INTRODUCTION AND OBJECTIVES: Despite the huge clinical burden of MASLD, validated tools for early risk stratification are lacking, and heterogeneous disease expression and a highly variable rate of progression to clinical outcomes result in prognostic uncertainty. We aimed to investigate longitudinal electronic health record-based outcome prediction in MASLD using a state-of-the-art machine learning model. PATIENTS AND METHODS: n = 940 patients with histologically-defined MASLD were used to develop a deep-learning model for all-cause mortality prediction. Patient timelines, spanning 12 years, were fully-annotated with demographic/clinical characteristics, ICD-9 and -10 codes, blood test results, prescribing data, and secondary care activity. A Transformer neural network (TNN) was trained to output concomitant probabilities of 12-, 24-, and 36-month all-cause mortality. In-sample performance was assessed using 5-fold cross-validation. Out-of-sample performance was assessed in an independent set of n = 528 MASLD patients. RESULTS: In-sample model performance achieved AUROC curve 0.74-0.90 (95 % CI: 0.72-0.94), sensitivity 64 %-82 %, specificity 75 %-92 % and Positive Predictive Value (PPV) 94 %-98 %. Out-of-sample model validation had AUROC 0.70-0.86 (95 % CI: 0.67-0.90), sensitivity 69 %-70 %, specificity 96 %-97 % and PPV 75 %-77 %. Key predictive factors, identified using coefficients of determination, were age, presence of type 2 diabetes, and history of hospital admissions with length of stay >14 days. CONCLUSIONS: A TNN, applied to routinely-collected longitudinal electronic health records, achieved good performance in prediction of 12-, 24-, and 36-month all-cause mortality in patients with MASLD. Extrapolation of our technique to population-level data will enable scalable and accurate risk stratification to identify people most likely to benefit from anticipatory health care and personalized interventions.
Asunto(s)
Registros Electrónicos de Salud , Humanos , Masculino , Femenino , Persona de Mediana Edad , Medición de Riesgo , Anciano , Pronóstico , Causas de Muerte , Aprendizaje Profundo , Factores de Riesgo , Valor Predictivo de las Pruebas , Enfermedad del Hígado Graso no Alcohólico/mortalidad , Enfermedad del Hígado Graso no Alcohólico/diagnóstico , Adulto , Redes Neurales de la Computación , Estudios RetrospectivosRESUMEN
INTRODUCTION AND OBJECTIVES: Non-alcoholic fatty liver disease (NAFLD) is the most common liver disease worldwide and can progress to non-alcoholic steatohepatitis (NASH) and, ultimately, cirrhosis. Clostridioides difficile is the most common nosocomial cause of diarrhea and is associated with worse clinical outcomes in other liver diseases, including cirrhosis, but has not been extensively evaluated in concomitant NAFLD/NASH. MATERIALS AND METHODS: We conducted a retrospective cohort study using the National Inpatient Sample database from 2015 to 2017. Patients with a diagnosis of CDI, NAFLD, and NASH were identified using International Classification of Diseases (Tenth Revision) codes. The outcomes of our study include length of stay, hospitalization cost, mortality, and predictors of mortality. RESULTS: The CDI and NASH cohort had a higher degree of comorbidity burden and prevalence of peptic ulcer disease, congestive heart failure, diabetes mellitus, and cirrhosis. Patients with NASH and CDI had a significantly higher mortality rate compared to the CDI only cohort (mortality, 7.11 % vs. 6.36 %; P = 0.042). Patients with CDI and NASH were at increased risk for liver-related complications, acute kidney injury, and septic shock (P < 0.001) compared to patients with CDI only. Older age, intestinal complications, pneumonia, sepsis and septic shock, and liver failure conferred an increased risk of mortality among the CDI and NASH cohort. CONCLUSIONS: Patients with NASH had a higher rate of liver-related complications, progression to septic shock, and mortality rate following CDI infection compared to the CDI only cohort.
Asunto(s)
Infecciones por Clostridium , Enfermedad del Hígado Graso no Alcohólico , Humanos , Enfermedad del Hígado Graso no Alcohólico/mortalidad , Enfermedad del Hígado Graso no Alcohólico/epidemiología , Enfermedad del Hígado Graso no Alcohólico/complicaciones , Masculino , Femenino , Estudios Retrospectivos , Factores de Riesgo , Persona de Mediana Edad , Infecciones por Clostridium/mortalidad , Infecciones por Clostridium/epidemiología , Infecciones por Clostridium/diagnóstico , Anciano , Clostridioides difficile , Estados Unidos/epidemiología , Bases de Datos Factuales , Tiempo de Internación/estadística & datos numéricos , Adulto , Comorbilidad , Costos de Hospital , Medición de RiesgoRESUMEN
INTRODUCTION AND OBJECTIVES: Studies on the societal burden of patients with biopsy-confirmed non-alcoholic fatty liver disease (NAFLD) are sparse. This study examined this question, comparing NAFLD with matched reference groups. MATERIALS AND METHODS: Nationwide Danish healthcare registers were used to include all patients (≥18 years) diagnosed with biopsy-verified NAFLD (1997-2021). Patients were classified as having simple steatosis or non-alcoholic steatohepatitis (NASH) with or without cirrhosis, and all matched with liver-disease free reference groups. Healthcare costs and labour market outcomes were compared from 5 years before to 11 years after diagnosis. Patients were followed for 25 years to analyse risk of disability insurance and death. RESULTS: 3,712 patients with biopsy-verified NASH (n = 1,030), simple steatosis (n = 1,540) or cirrhosis (n = 1,142) were identified. The average total costs in the year leading up to diagnosis was 4.1-fold higher for NASH patients than the reference group (EUR 6,318), 6.2-fold higher for cirrhosis patients and 3.1-fold higher for simple steatosis patients. In NASH, outpatient hospital contacts were responsible for 49 % of the excess costs (EUR 3,121). NASH patients had statistically significantly lower income than their reference group as early as five years before diagnosis until nine years after diagnosis, and markedly higher risk of becoming disability insurance recipients (HR: 4.37; 95 % CI: 3.17-6.02) and of death (HR: 2.42; 95 % CI: 1.80-3.25). CONCLUSIONS: NASH, simple steatosis and cirrhosis are all associated with substantial costs for the individual and the society with excess healthcare costs and poorer labour market outcomes.
Asunto(s)
Costo de Enfermedad , Costos de la Atención en Salud , Enfermedad del Hígado Graso no Alcohólico , Sistema de Registros , Humanos , Enfermedad del Hígado Graso no Alcohólico/economía , Enfermedad del Hígado Graso no Alcohólico/mortalidad , Enfermedad del Hígado Graso no Alcohólico/epidemiología , Dinamarca/epidemiología , Femenino , Masculino , Persona de Mediana Edad , Adulto , Biopsia/economía , Cirrosis Hepática/economía , Cirrosis Hepática/mortalidad , Cirrosis Hepática/epidemiología , Anciano , Seguro por Discapacidad/economía , Seguro por Discapacidad/estadística & datos numéricosRESUMEN
INTRODUCTION AND OBJECTIVES: Cohort studies reported controversial results regarding the long-term prognosis of patients with lean non-alcoholic fatty liver disease (NAFLD) compared to non-lean NAFLD patients. This updated meta-analysis aimed to estimate the magnitude of the association between lean body mass index and all-cause mortality risk in NAFLD patients. MATERIALS AND METHODS: We systematically searched the EMBASE and MEDLINE databases from inception to March 2023 to identify observational studies that reported hazard ratio (HR) for all-cause mortality of patients with lean NAFLD versus those with non-lean, overweight, or obese NAFLD. Multivariable-adjusted hazard ratios (HRs) for all-cause mortality were pooled using a random effects model. RESULTS: Fourteen studies with 94,181 NAFLD patients (11.3 % with lean NAFLD) and 7,443 fatal events over a median follow-up of 8.4 years (IQR, 6.6-17.4 years) were included. Patients with lean NAFLD had a higher risk of all-cause mortality than those with non-lean NAFLD (random-effects HR 1.61, 95 % CI 1.37-1.89; I2=77 %). The magnitude of this risk remained unchanged even after stratified analysis by measures of NAFLD diagnosis, study country, cohort setting, length of follow-up, adjustment with fibrosis stage/cirrhosis, and the Newcastle-Ottawa Scale. The risk was independent of age, sex, and cardiometabolic risk factors. Sensitivity analyses did not alter these findings. The funnel plot and Egger's test revealed no significant publication bias. CONCLUSIONS: This meta-analysis revealed that lean NAFLD is associated with an approximately 1.6-fold increased mortality risk. Further studies are needed to unravel the existing but complex link between lean NAFLD and an increased risk of death.
Asunto(s)
Índice de Masa Corporal , Causas de Muerte , Enfermedad del Hígado Graso no Alcohólico , Enfermedad del Hígado Graso no Alcohólico/mortalidad , Enfermedad del Hígado Graso no Alcohólico/complicaciones , Humanos , Factores de Riesgo , Delgadez/mortalidad , Delgadez/complicaciones , Medición de Riesgo , PronósticoRESUMEN
BACKGROUND: Liver stiffness measurement (LSM, which reflects fibrosis) and controlled attenuation parameter (CAP, which reflects steatosis), two parameters derived from hepatic transient elastography (TE), have scarcely been evaluated as predictors of cardiovascular complications and mortality in individuals with type 2 diabetes and nonalcoholic fatty liver disease (NAFLD). METHODS: Four hundred type 2 diabetic patients with NAFLD had TE examination (by Fibroscan®) performed at baseline. Multivariate Cox analyses evaluated the associations between TE parameters and the occurrence of cardiovascular events (CVEs) and mortality. TE parameters were assessed as continuous variables and dichotomized at low/high values reflecting advanced liver fibrosis (LSM > 9.6 kPa) and severe steatosis (CAP > 296 or > 330 dB/m). Improvements in risk discrimination were assessed by C-statistic and by the relative Integrated Discrimination Improvement (IDI) index. RESULTS: During a median follow-up of 5.5 years, 85 patients died (40 from cardiovascular causes), and 69 had a CVE. As continuous variables, an increasing LSM was a risk marker for total CVEs (hazard ratio [HR]: 1.05; 95% CI: 1.01-1.08) and all-cause mortality (HR: 1.04; 95% CI: 1.01-1.07); whereas an increasing CAP was a protective factor for both outcomes (HR: 0.93; 95% CI: 0.89-0.98; and HR: 0.92; 95% CI: 0.88-0.97; respectively). As dichotomized variables, a high LSM remained a risk marker of adverse outcomes (with HRs ranging from 2.5 to 3.0) and a high CAP was protective (with HRs from 0.3 to 0.5). The subgroup of individuals with low-LSM/high-CAP had the lowest risks while the opposite subgroup with high-LSM/low-CAP had the highest risks. Both LSM and CAP improved risk discrimination, with increases in C-statistics up to 0.037 and IDIs up to 52%. CONCLUSIONS: Measured by hepatic TE, advanced liver fibrosis is a risk marker and severe steatosis is a protective factor for cardiovascular complications and mortality in individuals with type 2 diabetes and NAFLD.
Asunto(s)
Enfermedades Cardiovasculares/epidemiología , Diabetes Mellitus Tipo 2/epidemiología , Diagnóstico por Imagen de Elasticidad , Cirrosis Hepática/diagnóstico por imagen , Enfermedad del Hígado Graso no Alcohólico/diagnóstico por imagen , Anciano , Brasil/epidemiología , Enfermedades Cardiovasculares/diagnóstico , Enfermedades Cardiovasculares/mortalidad , Diabetes Mellitus Tipo 2/diagnóstico , Diabetes Mellitus Tipo 2/mortalidad , Femenino , Humanos , Incidencia , Cirrosis Hepática/mortalidad , Estudios Longitudinales , Masculino , Persona de Mediana Edad , Enfermedad del Hígado Graso no Alcohólico/mortalidad , Valor Predictivo de las Pruebas , Pronóstico , Estudios Prospectivos , Medición de Riesgo , Factores de Riesgo , Factores de TiempoRESUMEN
AIMS: To evaluate the non-alcoholic fatty liver disease (NAFLD) fibrosis score (NFS) and Fibrosis-4 score (FIB4) as predictors of complications development and mortality in a cohort of type 2 diabetes. METHODS: 554 type 2 diabetic subjects had NFS and FIB4 calculated at baseline. Multivariate Cox and Poisson analyses evaluated the associations between fibrosis scores and the occurrence of microvascular and cardiovascular complications, and all-cause mortality. RESULTS: According to recommended cut-offs of NFS, 12.8% had advanced fibrosis and 45.9% had absence of advanced fibrosis and of FIB4, 3.8% and 86.1%, respectively. During a median follow-up of 11â¯years, 217subjects died, 172 had cardiovascular events (CVEs), 184 had renal events, and 139 had retinopathy and 185 neuropathy events. As continuous variables, both scores predicted all-cause mortality: NFS, HR: 1.30 (pâ¯=â¯0.032) and FIB4, HR: 1.24 (pâ¯=â¯0.021); an increased NFS implied in a significant 90% excess risk of mortality, whereas a higher FIB4 in a borderline 69% higher risk. The scores were mainly predictors of mortality in women and for non-cardiovascular deaths. The NFS was a predictor of renal events, mainly for renal function deterioration. CONCLUSIONS: The NFS and FIB4 predicted all-cause mortality, particularly in women and for non-cardiovascular causes. The NFS predicted adverse renal outcomes. These liver fibrosis scores may improve stratification risk in individuals with diabetes and NAFLD.
Asunto(s)
Diabetes Mellitus Tipo 2 , Cirrosis Hepática/diagnóstico , Enfermedad del Hígado Graso no Alcohólico , Anciano , Estudios de Cohortes , Diabetes Mellitus Tipo 2/complicaciones , Diabetes Mellitus Tipo 2/mortalidad , Femenino , Humanos , Cirrosis Hepática/complicaciones , Masculino , Persona de Mediana Edad , Enfermedad del Hígado Graso no Alcohólico/complicaciones , Enfermedad del Hígado Graso no Alcohólico/mortalidadRESUMEN
INTRODUCTION: Nonalcoholic steatohepatitis (NASH) associated or not with cirrhosis is the third leading indication for liver transplantation (LT) around the world. After transplants, NASH has a high prevalence and occurs as both recurrent and de novo manifestations. De novo NASH can also occur in allografts of patients transplanted for non-NASH liver disease. OBJECTIVE: To evaluate recurrent or de novo NASH in post-LT patients. METHOD: A literature review was performed using search engines of indexed scientific material, including Medline (by PubMed), Scielo and Lilacs, to identify articles published in Portuguese and English until August 2016. Eligible studies included: place and year of publication, prevalence, clinical characteristics, risk factors and survival. RESULTS: A total of 110 articles were identified and 63 were selected. Most of the studies evaluated recurrence and survival after LT. Survival reached 90-100% in 1 year and 52-100% in 5 years. Recurrence of NAFLD (steatosis) was described in 15-100% and NASH, in 4-71%. NAFLD and de novo NASH were observed in 18-67% and 3-17%, respectively. Metabolic syndrome, diabetes mellitus, dyslipidemia and hypertension were seen in 45-58%, 18-59%, 25-66% and 52-82%, respectively. CONCLUSION: After liver transplants, patients present a high prevalence of recurrent and de novo NASH. They also show a high frequence of metabolic disorders. Nevertheless, these alterations seem not to influence patient survival.
Asunto(s)
Trasplante de Hígado/efectos adversos , Enfermedad del Hígado Graso no Alcohólico/etiología , Complicaciones Posoperatorias , Humanos , Trasplante de Hígado/mortalidad , Síndrome Metabólico/complicaciones , Enfermedad del Hígado Graso no Alcohólico/complicaciones , Enfermedad del Hígado Graso no Alcohólico/mortalidad , Enfermedad del Hígado Graso no Alcohólico/patología , Complicaciones Posoperatorias/mortalidad , Complicaciones Posoperatorias/patología , Recurrencia , Tasa de SupervivenciaRESUMEN
Summary Introduction: Nonalcoholic steatohepatitis (NASH) associated or not with cirrhosis is the third leading indication for liver transplantation (LT) around the world. After transplants, NASH has a high prevalence and occurs as both recurrent and de novo manifestations. De novo NASH can also occur in allografts of patients transplanted for non-NASH liver disease. Objective: To evaluate recurrent or de novo NASH in post-LT patients. Method: A literature review was performed using search engines of indexed scientific material, including Medline (by PubMed), Scielo and Lilacs, to identify articles published in Portuguese and English until August 2016. Eligible studies included: place and year of publication, prevalence, clinical characteristics, risk factors and survival. Results: A total of 110 articles were identified and 63 were selected. Most of the studies evaluated recurrence and survival after LT. Survival reached 90-100% in 1 year and 52-100% in 5 years. Recurrence of NAFLD (steatosis) was described in 15-100% and NASH, in 4-71%. NAFLD and de novo NASH were observed in 18-67% and 3-17%, respectively. Metabolic syndrome, diabetes mellitus, dyslipidemia and hypertension were seen in 45-58%, 18-59%, 25-66% and 52-82%, respectively. Conclusion: After liver transplants, patients present a high prevalence of recurrent and de novo NASH. They also show a high frequence of metabolic disorders. Nevertheless, these alterations seem not to influence patient survival.
Resumo Introdução: A doença hepática gordurosa não alcoólica (DHGNA) é a terceira causa de transplante hepático no mundo. Tem elevada prevalência após transplante hepático (TH) e é representada pela recorrência da esteato-hepatite (NASH), ou por NASH de novo, que ocorre em pacientes transplantados por outra etiologia. Objetivo: Realizar uma revisão da literatura para avaliar a relevância da recorrência ou do NASH de novo em pacientes transplantados de fígado. Método: Realizada revisão da literatura através de artigos indexados no Medline, Scielo e Lilacs até 2016 publicados em inglês e português. Foram considerados elegíveis estudos que incluíram local e ano de publicação, prevalência e características clínicas dos pacientes. Resultados: Foram identificados 110 artigos e selecionados 63, que avaliaram a recorrência de NASH, NASH de novo e sobrevida após o TH. A sobrevida foi de 90% a 100% em um ano e de 52-100% em 5 anos. A recorrência de esteatose variou de 15-100% e a de NASH de 4-71%, enquanto esteatose e NASH de novo variaram de 18-67% e 3-17%, respectivamente. A frequência de síndrome metabólica, diabetes, dislipidemia e hipertensão variaram de 45-58%, 18-59%, 25-66% e 52-82%, respectivamente. Conclusão: No pós-transplante de fígado, os pacientes apresentam elevada prevalência de recorrência, de NASH de novo e de distúrbios metabólicos. Entretanto, essas alterações parecem não influenciar a sobrevida dos pacientes.
Asunto(s)
Humanos , Complicaciones Posoperatorias/mortalidad , Complicaciones Posoperatorias/patología , Trasplante de Hígado/efectos adversos , Enfermedad del Hígado Graso no Alcohólico/etiología , Recurrencia , Tasa de Supervivencia , Trasplante de Hígado/mortalidad , Síndrome Metabólico/complicaciones , Enfermedad del Hígado Graso no Alcohólico/complicaciones , Enfermedad del Hígado Graso no Alcohólico/mortalidad , Enfermedad del Hígado Graso no Alcohólico/patologíaRESUMEN
Hispanic children of Mexican origin have a high incidence of NAFLD. Susceptibility has been linked to a combination of factors including an increasing epidemic of obesity in children and adolescents, an allele substitution in the PNPLA3 gene that reduces hepatic lipid catabolism, and an altered microbiome that may increase hepatic endotoxins. The combination of NAFLD and portal vein toxins secondary to an indigenous gut microbiome appear to lead to the early occurrence of NASH, which progresses to cirrhosis and early hepatocellular carcinoma. Early detection and treatment of hepatic changes are needed. Given the success of gastric bypass in reducing body weight, modifying the gut microbiome, and improving NAFLD/NASH in adults, a trial of gastric bypass in predisposed pediatric candidates should be undertaken.