Acute-on-chronic liver failure (ACLF) is a catastrophic syndrome with a significant burden in cirrhosis patients, characterized by multi-organ failures and high 90-day mortality (15-100%). Its course is dynamic, and improvement/worsening over the first seven days determines the patient’s outcomes. Mortality prediction is essential to prognosticate patients, allocate resources, and guide definite therapies e.g. liver transplantation. Existing predictive models can misclassify up to 20-30% of patients, indicating a need for precision in prediction. Integrating the immuno-biology of disease with clinical variables can improve such predictions.

Dysregulated systemic inflammation and cell death are central to the pathobiology of ACLF. Both pro- and anti-inflammatory responses exist and the balance between the two determines the outcomes in ACLF patients. The existing hypothesis of inflammatory cell damage and unbridled immunoparesis leading to death is primarily derived from the cross-sectional assessment of the immune system in ACLF. The knowledge of dynamicity of immune-balance is urgently required, which can predict the outcomes more precisely and guide the novel immune-modulatory therapies.

Advanced flow cytometry and ELISA techniques can precisely estimate immune cells, their functions, cell death, and various cytokines. "Omics" platform allows an unbiased understanding of the complex biology of a condition and proteomics exhibits a better opportunity to discover scalable biomarkers and develop novel therapies. Machine learning can be integrated to analyze large-scale, multi-dimensional, complex data.

Therefore, we first aim to analyze the trajectories in the immuno-proteomic, cell death, and clinical profile of ACLF patients to understand the dynamic pathobiology of disease and associate them with mortality. Second, we aim to establish a machine learning model integrating clinical, cell death, and immuno-proteomic variables to predict mortality in ACLF.

We will conduct a cohort study in three phases. Firstly; in the discovery phase, eligible ACLF patients will be enrolled and followed up till 90-days or transplantation or death, whichever early. Clinical details will be serially noted for 90-days. The immunological and cell death profile will be recorded at baseline and day-7 through measuring monocyte/neutrophil/T-/B-/NK-cells-numbers, subsets and functions, cell death markers, and pro-/anti-inflammatory cytokines. Plasma proteome (protein levels and pathways) will be assessed at baseline and day-7 of presentation.

Second; in the computational phase, the comparisons of dynamic changes in immunological, proteomic, cell death, and clinical profile over time will be made between/within survivors and non-survivors. We will employ machine learning on these variables to derive a mortality prediction model. The model’s performance will be compared with existing predictive models.

Third; in the validation phase, the model will be validated in a separate cohort of ACLF patients.