Acute myeloid leukemia (AML), the most prevalent acute leukemia in adults, is characterized by its heterogeneity, which contributes to a poor prognosis and high recurrence rate. Recently, a unique form of cell death, called disulfidptosis, has been identified, which could transforming our understanding of and strategy for cancer treatment. Consequently, further inquiry is necessary to explore the possible link between disulfidptosis and AML. To facilitate this analysis, the researchers obtained single-cell RNA sequencing (scRNA-seq) data from AML patients using the Gene Expression Omnibus (GEO) database. By applying the Cox proportional hazards model and least absolute shrinkage and selection operator (LASSO) regression analysis, we created a signature of disulfidptosis-related long non-coding RNAs (DRLs). This predictive model was established based on six specific DRLs (AC005076.1, AP002807.1, HDAC4-AS1, L3MBTL4-AS1, LINC01694, and THAP9-AS1). The utility of this model in forecasting the prognosis of AML patients was corroborated by the receiver operating characteristic (ROC) curve. Moreover, significant variations in the biological functions and signaling pathways were discovered by gene ontology (GO) and Gene Set Enrichment Analysis (GSEA). To further investigate the relationship between immune infiltration, the study assessed variations in immune checkpoint expression and immune cell subset infiltration. Additionally, we used real-time quantitative PCR (RT-qPCR) to detect lncRNA expression in AML and healthy control to substantiate our analysis results. In conclusion, the results of this study may help discover novel therapeutic targets and prognostic biomarkers for AML, paving the way for customized precision chemotherapy.