Search

Summary: Background and Aims: Machine 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. Methods: Clinical 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. Results: The 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. Conclusions: ML 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. [ABSTRACT FROM AUTHOR]

Summary: Background and Aims: Myokines are the muscle‐derived hormones orchestrating muscle and systemic health. Their role in the progression of alcohol‐associated liver disease (ALD) remains elusive. Methods: Three‐hundred‐one patients across the spectrum of ALD including fatty liver (FL, N = 13), compensated cirrhosis (CC, N = 17), non‐acute decompensation (NAD, N = 95), acute decompensation (AD, N = 51) and acute‐on‐chronic liver failure (ACLF, N = 125) were recruited between 2021 and 2023. Plasma myostatin, decorin levels, nutritional status, handgrip strength (HGS), systemic inflammation, infection, ammonia, disease course and 30‐day mortality were recorded. Results: Patients aged 48 years (IQR: 38–52) and 97.7% of males were enrolled. Myostatin was elevated while decorin was reduced in cirrhosis compared to without cirrhosis, and further in DC compared to CC (p < 0.001). A step‐wise increase in myostatin and reduction in decorin was observed transitioning from NAD to AD to ACLF (p < 0.001). Myostatin was further increased and decorin was reduced along with the grades and organ failures in AD and ACLF (p < 0.001, each). Baseline decorin (AUC: 0.797) and its combination with MELD (AUC: 0.814) predicted disease resolution in AD and ACLF. Although, both myostatin (aOR: 18.96) and decorin (aOR: 0.02) could predict mortality, decorin was independent (aOR: 0.04) and additive to MELD (AUC of MELD+logDecorin + logTLC + HE‐grade:0.815); p < 0.05 each. Myostatin increased and decorin reduced with inflammation, hyperammonaemia, malnutrition and HGS in AD and ACLF (p < 0.05, each). Conclusion: Myokines are linked with malnutrition, fibrosis, systemic inflammation, organ failures, disease course and mortality in ALD. Decorin enhances the risk estimation of mortality of MELD in AD and ACLF. Therapeutic modulation of myokines is a potentially disease‐modifying target in ALD. [ABSTRACT FROM AUTHOR]

The famous Ascoli-Arzelà theorem served as a springboard for research into compactness in function spaces, particularly spaces of continuous functions. This paper investigates compact subsets of spaces of continuous functions endowed with topologies between the topology of pointwise convergence and the topology of uniform convergence. More precisely, this paper studies necessary and sufficient conditions for a subset to be compact in Cλ,u(X) for a locally-λ space X when λ ⊇ 퓕(X), for a hemi- λ λf-space X when λ ⊆ 퓟 퓢(X), and for a k-space X when λ ⊇ 퓚(X). This paper also studies that every bounded subset of Cλ,u(X) has compact closure for some classes of topological spaces X. [ABSTRACT FROM AUTHOR]

HR Analytics has gained immense popularity among the consultants and practitioners in the field of HR management. HR Analytics applies various statistical tools on the collected data to create interventions, propose strategies and assess their effectiveness in the organizational performance of various departments such as marketing, finance, etc. Though the HR Analytics is not less known but has been remained relatively less explored. However, it has not been subjected to scrutiny by academic researchers. The present study, therefore, investigates the impact of HR Analytics on organizational performance and how this relationship is mediated by employee motivation. A descriptive design was adopted and data was collected from HR employees from Bangalore, who adopt analytics for various HR processes. The results showed that motivation partially mediated the effects of HR Analytic on organizational performance. The analytical skills of employees which involves understanding, analyzing and interpreting data has a significant impact on the organizational performance of the organization in terms of improved decision-making and return on investment achieved. Further, motivating employees at work to generate and experiment with new ideas; to customize new ways to deliver products and services by analyzing data; to adopt and use creative analytics in any process; and to find satisfaction at work can further enhance the effectiveness of analytical skills on organizational performance. Based on these results, the study emphasizes the need for developing analytical skills among HR employees and motivating them to increase organizational performance. [ABSTRACT FROM AUTHOR]