Machine Learning-Based Integrated Analysis of PANoptosis Patterns in Acute Myeloid Leukemia Reveals a Signature Predicting Survival and Immunotherapy

Objective. We conducted a meticulous bioinformatics analysis leveraging expression data of 226 PANRGs obtained from previous studies, as well as clinical data from AML patients derived from the HOVON database. Methods. Through meticulous data analysis and manipulation, we were able to categorize AML cases into two distinct PANRG clusters and subsequently identify differentially expressed genes (PRDEGs) with prognostic significance. Furthermore, we organized the patient data into two corresponding gene clusters, allowing us to investigate the intricate relationship between the risk score, patient prognosis, and the immune landscape. Results. Our findings disclosed significant associations between the identified PANRGs, gene clusters, patient survival, immune system, and cancer-related biological processes and pathways. Importantly, we successfully constructed a prognostic signature comprising nineteen genes, enabling the stratification of patients into high-risk and low-risk groups based on individually calculated risk scores. Furthermore, we developed a robust and practical nomogram model, integrating the risk score and other pertinent clinical features, to facilitate accurate patient survival prediction. Our comprehensive analysis demonstrated that the high-risk group exhibited notably worse prognosis, with the risk score proving to be significantly correlated with infiltration of most immune cells. The qRT-PCR results revealed significant differential expression patterns of LGR5 and VSIG4 in normal and human leukemia cell lines (HL-60 and MV-4-11). Conclusions. Our findings underscore the potential utility of PANoptosis-based molecular clustering and prognostic signatures as predictive tools for assessing patient survival in AML.