Premkumar, Madhumita

SummaryBackground and AimsMachine learning (ML) can identify the hidden patterns without hypothesis in heterogeneous diseases like acute‐on‐chronic live failure (ACLF). We employed ML to describe and predict yet unknown clusters in ACLF.MethodsClinical data of 1568 patients with ACLF from a tertiary care centre (2015–2023) were subjected to distance‐, density‐ and model‐based clustering algorithms. Final model was selected on best cluster separation, viz. Silhouette width and Dunn's index (for distance‐ or density‐based algorithms) and minimum BIC (for model‐based algorithms). Cluster assignments, patient trajectories and survival were analysed through inferential statistics. Supervised ML models were trained in 70% data that predicted clusters in remaining 30% data followed by an temporal validation.ResultsThe cohort was male‐predominant (87%), aged 44.3 years, with alcohol‐associated hepatitis (62.9%) and survival of 50.5%. Due to poor performance of distance‐ and density‐based algorithms and better explainability, the latent class model (LCM) was selected for exploration. LCM revealed four clusters with distinct trajectories, reversibility and survival (independent of MELD, CLIF‐C ACLF and AARC scores). Cluster1 had patients with none/one organ failure and highest reversibility. Cluster2 had females with viral hepatitis and two organ failures. More‐than‐one acute precipitant, severity, infections, organ failures and irreversibility escalated from clusters 1 to 4. Circulatory and renal failures critically influenced cluster assignments. Incorporating clusters to CLIF‐C ACLF, infection and ACLF definition improved the discriminative accuracy of CLIF‐C‐ACLF by 11%. Extreme gradient boost and decision trees could predict clusters with AUCs of 0.989 (0.979–0.995) and 0.875 (0.865–0.890). MELD, CLIF‐C‐OF, haemoglobin, lactate, CLIF‐C‐ACLF and ALT were critical variables for cluster prediction. Clusters with distinct survival were documented in a temporal validation cohort.ConclusionsML for the first time could identify clusters with distinct phenotypes, trajectories and outcomes in ACLF. Stratification into clusters can address heterogeneity, guide prognosis, recruitment in trials, resource allocation and liver transplant discussions in ACLF.

AbstractVasoactive drugs form the mainstay of therapy for two of the most important complications of liver disease: hepatorenal syndrome (HRS) and acute variceal bleed (AVB). With cumulative evidence supporting the use in cirrhosis, terlipressin has been recommended for the management of HRS and AVB. However, owing to the safety concerns, terlipressin was not approved by food and drug administration (FDA) until now. In this review, we discuss the pharmacology and the major practice‐changing studies on the safety and efficacy of terlipressin in patients with cirrhosis particularly focusing on existing indications like AVB and HRS and reviewing new data on the expanding indications in liver disease. The references for this review were identified from PUBMED with MeSH terms such as “terlipressin,” “hepatorenal syndrome,” “varices, esophagal and gastric,” “ascites” and “cirrhosis.” Terlipressin, a synthetic analogue of vasopressin, was introduced in 1975 to overcome the adverse effects of vasopressin. Terlipressin is an effective drug for HRS reversal in patients with liver cirrhosis and acute‐on‐chronic liver failure. There is documented mortality benefit with terlipressin therapy in HRS and AVB. Adverse effects are common with terlipressin and need to be monitored strictly. There is some evidence to support the use of this drug in refractory ascites, hepatic hydrothorax, paracentesis‐induced circulatory dysfunction and perioperatively during liver transplantation. However, terlipressin is not yet recommended for such indications. In conclusion, terlipressin has stood the test of time with expanding indications and clear prerequisites for clinical use. Our review warrants a fresh perspective on the efficacy and safety of terlipressin.