Circulating miR-133a-3p defines a low-risk subphenotype in patients with heart failure and central sleep apnea: a decision tree machine learning approach.

BACKGROUND: Patients with heart failure with reduced ejection fraction (HFrEF) and central sleep apnea (CSA) are at a very high risk of fatal outcomes. OBJECTIVE: To test whether the circulating miRNome provides additional information for risk stratification on top of clinical predictors in patients with HFrEF and CSA. METHODS: The study included patients with HFrEF and CSA from the SERVE-HF trial. A three-step protocol was applied: microRNA (miRNA) screening (n = 20), technical validation (n = 60), and biological validation (n = 587). The primary outcome was either death from any cause, lifesaving cardiovascular intervention, or unplanned hospitalization for worsening of heart failure, whatever occurred first. MiRNA quantification was performed in plasma samples using miRNA sequencing and RT-qPCR. RESULTS: Circulating miR-133a-3p levels were inversely associated with the primary study outcome. Nonetheless, miR-133a-3p did not improve a previously established clinical prognostic model in terms of discrimination or reclassification. A customized regression tree model constructed using the Classification and Regression Tree (CART) algorithm identified eight patient subphenotypes with specific risk patterns based on clinical and molecular characteristics. MiR-133a-3p entered the regression tree defining the group at the lowest risk; patients with log(NT-proBNP) ≤ 6 pg/mL (miR-133a-3p levels above 1.5 arbitrary units). The overall predictive capacity of suffering the event was highly stable over the follow-up (from 0.735 to 0.767). CONCLUSIONS: The combination of clinical information, circulating miRNAs, and decision tree learning allows the identification of specific risk subphenotypes in patients with HFrEF and CSA.

Hyperkalaemia prevalence, recurrence and management in chronic haemodialysis: a prospective multicentre French regional registry 2-year survey.

BACKGROUND: Observational studies have reported increased mortality rates in hyperkalaemic or hypokalaemic chronic haemodialysis patients. This study assessed the prevalence and recurrence of hyperkalaemia (HK) along with the concomitant prescription of low-potassium (K) dialysis baths and of K-binding agents in a registry within a French regional disease management programme. METHODS: This was a prospective multicentre (14 chronic haemodialysis centres, Lorraine Region) study encompassing 527 chronic haemodialysis patients followed from 2 January 2014 to 31 December 2015. Predialysis serum K (14 734) measurements, dialysis bath K concentrations and concomitant K binder prescriptions were collected with an electronic health record system. RESULTS: At baseline, 26.4%, 13.8% and 4.9% of patients were hyperkalaemic (i.e. K >5.1, 5.5 or 6 mmol/L, respectively) and 12.5%, 1.9% and 0.4% were hypokalaemic (i.e. K<4, 3.5 or 3 mmol/L, respectively). A total of 61% of patients were prescribed a K-binding resin [essentially sodium polystyrene sulfonate (SPS)], while 2 mmol/L and 3 mmol/L K concentration baths were used relatively equally. Over time, the proportion of patients being prescribed any K-binding agent increased up to 78%. The percentage of patients experiencing HK at any time was 73.8% (HK >5.1 mmol/L), 57.9% (HK >5.5 mmol/L) and 34.5% (HK >6 mmol/L). Only 6.3% of patients became normokalaemic within 3 months after an HK >5.5 mmol/L despite dynamic management of K baths and K binders (i.e. increased prescription of 2 mmol/L K baths and increased SPS doses). CONCLUSIONS: HK was found to be highly prevalent and recurrent in this regional registry despite the widespread and dynamic prescription of low-K dialysis baths and K binders. More effective potassium mitigating strategies are eagerly warranted.