Nanomedicine Ex Machina: Between Model-Informed Development and Artificial Intelligence.

Today, a growing number of computational aids and simulations are shaping model-informed drug development. Artificial intelligence, a family of self-learning algorithms, is only the latest emerging trend applied by academic researchers and the pharmaceutical industry. Nanomedicine successfully conquered several niche markets and offers a wide variety of innovative drug delivery strategies. Still, only a small number of patients benefit from these advanced treatments, and the number of data sources is very limited. As a consequence, "big data" approaches are not always feasible and smart combinations of human and artificial intelligence define the research landscape. These methodologies will potentially transform the future of nanomedicine and define new challenges and limitations of machine learning in their development. In our review, we present an overview of modeling and artificial intelligence applications in the development and manufacture of nanomedicines. Also, we elucidate the role of each method as a facilitator of breakthroughs and highlight important limitations.

A physiologically-based nanocarrier biopharmaceutics model to reverse-engineer the in vivo drug release.

Over the years, a wide variety of nanomedicines has entered global markets, providing a blueprint for the emerging generics industry. They are characterized by a unique pharmacokinetic behavior difficult to explain with conventional methods. In the present approach a physiologically-based nanocarrier biopharmaceutics model has been developed. Providing a compartmental framework of the distribution and elimination of nanocarrier delivery systems, this model was applied to human clinical data of the drug products Doxil®, Myocet®, and AmBisome® as well as to the formulation prototypes Foslip® and NanoBB-1-Dox. A parameter optimization by differential evolution led to an accurate representation of the human data (AAFE < 2). For each formulation, separate half-lives for the carrier and the free drug as well as the drug release were calculated from the total drug concentration-time profile. In this context, a static in vitro set-up and the dynamic in vivo situation with a continuous infusion and accumulation of the carrier were simulated. For Doxil®, a total drug release ranging from 0.01 to 22.1% was determined. With the time of release exceeding the elimination time of the carrier, the major fraction was available for drug targeting. NanoBB-1-Dox released 76.2-77.8% of the drug into the plasma, leading to an accumulated fraction of approximately 20%. The mean residence time of encapsulated doxorubicin was 128 h for Doxil® and 0.784 h for NanoBB-1-Dox, giving the stealth liposomes more time to accumulate at the intended target site. For all other formulations, Myocet®, AmBisome®, and Foslip®, the major fraction of the dose was released into the blood plasma without being available for targeted delivery.

System dynamics modeling for tooth decay treatment in Brazilian children.

Prevention and health promotion are considered important strategies to control oral diseases. Dental caries is preventable disease and remains the most common chronic disease that affects mainly low income children and still considered the main cause of tooth loss in adulthood in Brazil. The aim of this study is to present a System Dynamics model (SDM) specifically developed with the Stella Architect software to estimate the cost and clinical hours required to control the evolution of dental caries in preschool children in Maringá, Brazil. Two main strategies to control caries were considered in the model: the application of fluoride varnish on teeth presenting white spots, and the use of Atraumatic Restorative Treatment (ART) in cavitated carious lesions without pulp involvement. The parameters used in the model were: number of people covered by a local oral health team = 4,000; number of children up to 5 years = 7% of the population; children's decayed, missing, filled teeth (dmft) index = 2.4; time/cost of 4 applications of fluoride varnish = 5 minutes/US$ 0.716; and time/cost of each ART restoration = 15 minutes/US$ 1.475. The SDM generated an estimated total cost of US$698.00, and a total of 112 clinical hours to treat the population in question. The use of the SDM presented here has the potential to assist decision making by measuring the material and human resources required to prevent and control dental caries at an early age.

System dynamics modeling for tooth decay treatment in Brazilian children

Abstract Prevention and health promotion are considered important strategies to control oral diseases. Dental caries is preventable disease and remains the most common chronic disease that affects mainly low income children and still considered the main cause of tooth loss in adulthood in Brazil. The aim of this study is to present a System Dynamics model (SDM) specifically developed with the Stella Architect software to estimate the cost and clinical hours required to control the evolution of dental caries in preschool children in Maringá, Brazil. Two main strategies to control caries were considered in the model: the application of fluoride varnish on teeth presenting white spots, and the use of Atraumatic Restorative Treatment (ART) in cavitated carious lesions without pulp involvement. The parameters used in the model were: number of people covered by a local oral health team = 4,000; number of children up to 5 years = 7% of the population; children's decayed, missing, filled teeth (dmft) index = 2.4; time/cost of 4 applications of fluoride varnish = 5 minutes/US$ 0.716; and time/cost of each ART restoration = 15 minutes/US$ 1.475. The SDM generated an estimated total cost of US$698.00, and a total of 112 clinical hours to treat the population in question. The use of the SDM presented here has the potential to assist decision making by measuring the material and human resources required to prevent and control dental caries at an early age.