https://www.selleckchem.com/products/pp1.html ns. The machine learning model provides more personalized and reliable prognostic information of tongue cancer than the nomogram. However, the level of transparency offered by the nomogram in estimating patients' outcomes seems more confident and strengthened the principle of shared decision making between the patient and clinician. Therefore, a combination of a nomogram - machine learning (NomoML) predictive model may help to improve care, provides information to patients, and facilitates the clinicians in making tongue cancer management-related decisions.Low-environmental-impact emulsion systems for transdermal drug delivery in topical treatment have gained increasing interest. However, low stability and adverse systemic side effects severely decrease their efficiency. This study proposed a stable oil-in-water (O/W) emulsion loaded with bifonazole (BFZ) as a lipophilic drug stabilized by poly(2-isopropoxy-2-oxo-1,3,2-dioxaphospholane)-modified cellulose nanocrystals (CNC-g-PIPP) as vehicles for topical delivery of lipophilic drugs. We fully characterized stability, BFZ-loaded particle-stabilized emulsions (PEs) for morphology, droplet size, and its distribution. In addition, we evaluated the in vitro drug-releasing capacity and in vitro skin permeation of BFZ in a porcine skin animal model using a side-bi-side® diffusion cell. An O/W BFZ-loaded emulsion stabilized with CNC-g-PIPP particles (BFZ-loaded CP-PE) with a small mean droplet size of 2.54 ± 1.39 μm was developed and was stable for > = 15 days without a significant change in droplet size. The BFZ-loading efficiency in PEs was 83.1 %. BFZ was slowly released over an extended period, and the releasing ratio from BFZ-loaded CP-PE was only 17 % after 48 h. The BFZ-loaded CP-PE showed a ∼4.4-fold increase in BFZ permeation and penetration compared to a conventional surfactant-stabilized emulsion and BFZ control solution. Fluorescence-labeling studies showed that BFZ-