Transdermal drug delivery systems (TDDS) offer an alternative to conventional oral and injectable drug administration by bypassing the gastrointestinal tract and liver metabolism, improving bioavailability, and minimizing systemic side effects. However, widespread adoption of TDDS is limited by challenges such as the skin’s permeability barrier, particularly the stratum corneum, and the need for optimized formulations. Factors like skin type, hydration levels, and age further complicate the development of universally effective solutions. Advances in artificial intelligence (AI) address these challenges through predictive modeling and personalized medicine approaches. Machine learning models trained on extensive molecular datasets predict skin permeability and accelerate the selection of suitable drug candidates. AI-driven algorithms optimize formulations, including penetration enhancers and advanced delivery technologies like microneedles and liposomes, while ensuring safety and efficacy. Personalized TDDS design tailors drug delivery to individual patient profiles, enhancing therapeutic precision. Innovative systems, such as sensor-integrated patches, dynamically adjust drug release based on real-time feedback, ensuring optimal outcomes. AI also streamlines the pharmaceutical process, from disease diagnosis to the prediction of drug distribution in skin layers, enabling efficient formulation development. This review highlights AI’s transformative role in TDDS, including applications of models such as Deep Neural Networks (DNN), Artificial Neural Networks (ANN), BioSIM, COMSOL, K-Nearest Neighbors (KNN), and Set Covering Machine (SVM). These technologies revolutionize TDDS for both skin and non-skin diseases, demonstrating AI’s potential to overcome existing barriers and improve patient care through innovative drug delivery solutions.

Background: Mango seed kernels, an agro-industrial waste byproduct, constitute approximately 40–50% of the fruit’s weight and serve as a substantial source of starch. There are only a few reported studies on the pharmaceutical applications of Mango Seed Kernel Starch (MSKS) and drug carriers produced from this source. This study aims to isolate starch from mango seed kernels (MSKS), prepare drug-loaded mango seed kernel starch nanoparticles (MSKSNPs), and study the in vitro transdermal permeation. Methods: The MSKS was prepared using the alkaline method and freeze-dried. The prepared starch was analyzed for physicochemical properties relative to corn starch. The mango seed kernel starch nanoparticles (MSKSNPs) were prepared using mild alkali hydrolysis and the ultrasonication method. The model drug selected for this study was diclofenac sodium (DS), a commonly prescribed non-steroidal anti-inflammatory drug. Results: The average particle size of the drug-loaded nanoparticles was 140.0 ± 3.6 nm, with a PDI of 0.42 ± 0.03. The Transmission Electron Microscopy images confirmed the globular structure of MSKSNPs. X-ray Diffraction revealed that the diclofenac crystal size decreased to 14 nm from 33 nm in the pure drug, confirming the amorphous nature of MSKSNPs. The drug-loaded MSKSNPs showed a % encapsulation efficiency of 92.4 ± 3.7 and % drug loading of 31.08 ± 0.96. The cumulative drug released from MSKSNPs after 6 h, 12 h, and 24 h was found to be 25.58 ± 1.30, 59.68 ± 2.98, and 127.5 ± 6.4 μg/cm^2, respectively, which was more than the ethanolic drug solution with statistical significance (p-value < 0.01) along with enhanced skin retention. Conclusions: MSKSNPs were efficiently synthesized using mild alkali hydrolysis and ultrasonication, showing enhanced transdermal delivery. Skin retention was significantly higher in MSKSNPs (p-value < 0.05). The cytotoxic studies revealed that both formulations exhibit similar dose-dependent cytotoxicity, with no significant difference (p > 0.05) in their potency under the tested conditions.

Transdermal drug delivery offers several advantages over conventional routes. However, its use is limited by the low permeability of the stratum corneum. This limitation is especially significant in the case of hydrophilic drugs such as caffeine. This study explored microemulsion systems to enhance the transdermal delivery of caffeine (CF) using chemical penetration enhancers as cosurfactants. Kolliphor^® PS80 (PS80), Kolliphor^® RH40 (RH40), Kolliphor^® PS20 (PS20), and Kollicream^® OD (OD) were evaluated as cosurfactants for the first time in microemulsion formulations consisting of water, oil, and a fixed surfactant-to-cosurfactant ratio of 4:1 (w/w), with 14% of each cosurfactant incorporated. CF skin permeation from microemulsions was assessed via in vitro permeation studies using Franz diffusion cells and human cadaver skin. The results showed that OD-based microemulsions achieved approximately 3-fold higher CF skin permeation compared with the control formulation and 1.4–1.6-fold higher permeation compared with formulations containing PS80, RH40, and PS20. Furthermore, CF solubility in the four cosurfactants followed the order: PS20 > RH40 > PS80 > OD. These findings indicate that PS20 provides the highest solubility for CF among the tested cosurfactants. The results also included visual evaluations. No significant changes in appearance or physical properties were observed during the 10-month study. All samples remained clear and stable throughout the testing period. This study uniquely highlights the critical role of cosurfactant selection in optimizing microemulsion-based transdermal delivery systems. This work addresses a previously unexplored aspect, namely, the effect of cosurfactants with different physicochemical properties on the skin permeation of caffeine. The findings provide valuable insight into developing more effective transdermal and topical drug delivery systems.

Transdermal drug delivery systems (TDDS) offer an alternative to conventional oral and injectable drug administration by bypassing the gastrointestinal tract and liver metabolism, improving bioavailability, and minimizing systemic side effects. However, widespread adoption of TDDS is limited by challenges such as the skin's permeability barrier, particularly the stratum corneum, and the need for optimized formulations. Factors like skin type, hydration levels, and age further complicate the development of universally effective solutions. Advances in artificial intelligence (AI) address these challenges through predictive modeling and personalized medicine approaches. Machine learning models trained on extensive molecular datasets predict skin permeability and accelerate the selection of suitable drug candidates. AI-driven algorithms optimize formulations, including penetration enhancers and advanced delivery technologies like microneedles and liposomes, while ensuring safety and efficacy. Personalized TDDS design tailors drug delivery to individual patient profiles, enhancing therapeutic precision. Innovative systems, such as sensor-integrated patches, dynamically adjust drug release based on real-time feedback, ensuring optimal outcomes. AI also streamlines the pharmaceutical process, from disease diagnosis to the prediction of drug distribution in skin layers, enabling efficient formulation development. This review highlights AI's transformative role in TDDS, including applications of models such as Deep Neural Networks (DNN), Artificial Neural Networks (ANN), BioSIM, COMSOL, K-Nearest Neighbors (KNN), and Set Covering Machine (SVM). These technologies revolutionize TDDS for both skin and non-skin diseases, demonstrating AI's potential to overcome existing barriers and improve patient care through innovative drug delivery solutions.