Unsupervised machine learning identifies biomarkers of disease progression in post-kala-azar dermal leishmaniasis in Sudan

by Torres A, Younis BM, Tesema S, Solana JC, Moreno J, Martín-Galiano AJ,  Musa AM, Alves F, Carrillo E. PLOS Neglected Tropical Diseases 2025,19(3): e0012924. doi: 10.1371/journal.pntd.0012924

Summary: Post-kala-azar dermal leishmaniasis (PKDL) is a rash that may appear after recovery from visceral leishmaniasis caused by Leishmania donovani. The factors influencing progression to a severe form of the disease are not well understood. The authors of this study used machine learning to identify biomarkers of disease progression in PKDL using clinical, biochemical, haematological, and immunological data from a cohort of 110 Sudanese patients with either progressive (worsening) or stable conditions at diagnosis. This is the first study to identify a combination of patient factors that was able to detect a worsening PKDL state in Sudanese patients. This approach could be used to train supervised algorithms based on larger patient cohorts to improve diagnosis and gain further insight into PKDL.

The post Unsupervised machine learning identifies biomarkers of disease progression in post-kala-azar dermal leishmaniasis in Sudan first appeared on DNDi.