Numerous studies have engineered nanoparticles with different physicochemical properties to enhance the delivery efficiency to solid tumors, yet the mean and median delivery efficiencies are only 1.48% and 0.70% of the injected dose (%ID), respectively, according to a study using a non-physiologically based modeling approach based on published data from 2005 to 2015. In this study, we used physiologically based pharmacokinetic (PBPK) models to analyze 376 datasets covering a wide range of nanomedicines published from 2005 to 2018, and found mean and median delivery efficiencies at the last sampling time point of 2.23% and 0.76%ID, respectively. Also, the mean and median delivery efficiencies were 2.24% and 0.76%ID at 24 h, and were decreased to 1.23% and 0.35%ID at 168 h, respectively, after intravenous administration. While these delivery efficiencies appear to be higher than previous findings, they are still quite low and represent a critical barrier in the clinical translation of nanomedicines. We explored the potential causes of this poor delivery efficiency using the more mechanistic PBPK perspective applied to a subset of gold nanoparticles and found that low delivery efficiency was associated with low distribution and permeability coefficients at the tumor site (P<0.01). We also demonstrate how PBPK modeling and simulation can be used as an effective tool to investigate tumor delivery efficiency of nanomedicines.

The critical barrier for clinical translation of cancer nanomedicine stems from the inefficient delivery of nanoparticles (NPs) to target solid tumors. Rapid growth of computational power, new machine learning and artificial intelligence (AI) approaches provide new tools to address this challenge. In this study, we established an AI-assisted physiologically based pharmacokinetic (PBPK) model by integrating an AI-based quantitative structure-activity relationship (QSAR) model with a PBPK model to simulate tumor-targeted delivery efficiency (DE) and biodistribution of various NPs. The AI-based QSAR model was developed using machine learning and deep neural network algorithms that were trained with datasets from a published "Nano-Tumor Database" to predict critical input parameters of the PBPK model. The PBPK model with optimized NP cellular uptake kinetic parameters was used to predict the maximum delivery efficiency (DEmax) and DE at 24 (DE24) and 168 h (DE168) of different NPs in the tumor after intravenous injection and achieved a determination coefficient of R² = 0.83 [root mean squared error (RMSE) = 3.01] for DE24, R² = 0.56 (RMSE = 2.27) for DE168, and R² = 0.82 (RMSE = 3.51) for DEmax. The AI-PBPK model predictions correlated well with available experimentally-measured pharmacokinetic profiles of different NPs in tumors after intravenous injection (R² ≥ 0.70 for 133 out of 288 datasets). This AI-based PBPK model provides an efficient screening tool to rapidly predict delivery efficiency of a NP based on its physicochemical properties without relying on an animal training dataset.

Vitamin D deficiency (VDD) is common in women with and without polycystic ovary syndrome (PCOS) and may be associated with metabolic and endocrine disorders in PCOS. The aim of this meta-analysis is to assess the associations of serum vitamin D levels with metabolic and endocrine dysregulations in women with PCOS, and to determine effects of vitamin D supplementation on metabolic and hormonal functions in PCOS patients. The literature search was undertaken through five databases until 16 January 2015 for both observational and experimental studies concerning relationships between vitamin D and PCOS. A total of 366 citations were identified, of which 30 were selected (n = 3182). We found that lower serum vitamin D levels were related to metabolic and hormonal disorders in women with PCOS. Specifically, PCOS patients with VDD were more likely to have dysglycemia (e.g., increased levels of fasting glucose and homeostatic model assessment-insulin resistance index (HOMA-IR)) compared to those without VDD. This meta-analysis found no evidence that vitamin D supplementation reduced or mitigated metabolic and hormonal dysregulations in PCOS. VDD may be a comorbid manifestation of PCOS or a minor pathway in PCOS associated metabolic and hormonal dysregulation. Future prospective observational studies and randomized controlled trials with repeated VDD assessment and better characterization of PCOS disease severity at enrollment are needed to clarify whether VDD is a co-determinant of hormonal and metabolic dysregulations in PCOS, represents a consequence of hormonal and metabolic dysregulations in PCOS or both.

Background: Low delivery efficiency of nanoparticles (NPs) to the tumor is a critical barrier in the field of cancer nanomedicine. Strategies on how to improve NP tumor delivery efficiency remain to be determined. Methods: This study analyzed the roles of NP physicochemical properties, tumor models, and cancer types in NP tumor delivery efficiency using multiple machine learning and artificial intelligence methods, using data from a recently published Nano-Tumor Database that contains 376 datasets generated from a physiologically based pharmacokinetic (PBPK) model. Results: The deep neural network model adequately predicted the delivery efficiency of different NPs to different tumors and it outperformed all other machine learning methods; including random forest, support vector machine, linear regression, and bagged model methods. The adjusted determination coefficients (R²) in the full training dataset were 0.92, 0.77, 0.77 and 0.76 for the maximum delivery efficiency (DE_max), delivery efficiency at 24 h (DE₂₄), at 168 h (DE₁₆₈), and at the last sampling time (DE_Tlast). The corresponding R² values in the test dataset were 0.70, 0.46, 0.33 and 0.63, respectively. Also, this study showed that cancer type was an important determinant for the deep neural network model in predicting the tumor delivery efficiency across all endpoints (19– 29%). Among all physicochemical properties, the Zeta potential and core material played a greater role than other properties, such as the type, shape, and targeting strategy. Conclusion: This study provides a quantitative model to improve the design of cancer nanomedicine with greater tumor delivery efficiency. These results help to improve our understanding of the causes of low NP tumor delivery efficiency. This study demonstrates the feasibility of integrating artificial intelligence with PBPK modeling approaches to study cancer nanomedicine. Graphical Abstract:

Physiologically based pharmacokinetic (PBPK) models are useful tools in drug development and risk assessment of environmental chemicals. PBPK model development requires the collection of species-specific physiological, and chemical-specific absorption, distribution, metabolism, and excretion (ADME) parameters, which can be a time-consuming and expensive process. This raises a need to create computational models capable of predicting input parameter values for PBPK models, especially for new compounds. In this review, we summarize an emerging paradigm for integrating PBPK modeling with machine learning (ML) or artificial intelligence (AI)-based computational methods. This paradigm includes 3 steps (1) obtain time-concentration PK data and/or ADME parameters from publicly available databases, (2) develop ML/AI-based approaches to predict ADME parameters, and (3) incorporate the ML/AI models into PBPK models to predict PK summary statistics (eg, area under the curve and maximum plasma concentration). We also discuss a neural network architecture “neural ordinary differential equation (Neural-ODE)” that is capable of providing better predictive capabilities than other ML methods when used to directly predict time-series PK profiles. In order to support applications of ML/AI methods for PBPK model development, several challenges should be addressed (1) as more data become available, it is important to expand the training set by including the structural diversity of compounds to improve the prediction accuracy of ML/AI models; (2) due to the black box nature of many ML models, lack of sufficient interpretability is a limitation; (3) Neural-ODE has great potential to be used to generate time-series PK profiles for new compounds with limited ADME information, but its application remains to be explored. Despite existing challenges, ML/AI approaches will continue to facilitate the efficient development of robust PBPK models for a large number of chemicals.