Specific loss power of magnetic nanoparticles: A machine learning approach

Coı̈sson, M.; Barrera, Gabriele; Celegato, Federica; Allia, Paolo; Tiberto, P.

doi:10.1063/5.0099498

Cited by 5 publications

(9 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ANN algorithms can be used to optimize nanopharmaceuticals formulations for enhanced transport and targeting of nanomedicines through the prediction of interactions between MHNs nanocarriers, drugs, biological mediators, or cell membranes, as well as the estimation of drug encapsulation efficiency [ 20 ]. In addition, ANN can improve clinical outcomes while reducing toxicity, by improving the efficiency of drug delivery and design of the MHNs [ 21 , 22 , 23 , 24 ]. The purpose of this section is to provide an overview of the development and implementation of MHNs for cancer diagnosis and treatment using ANN approaches.…”

Section: Introductionmentioning

confidence: 99%

A Review of Advanced Multifunctional Magnetic Nanostructures for Cancer Diagnosis and Therapy Integrated into an Artificial Intelligence Approach

et al. 2023

View full text Add to dashboard Cite

The new era of nanomedicine offers significant opportunities for cancer diagnostics and treatment. Magnetic nanoplatforms could be highly effective tools for cancer diagnosis and treatment in the future. Due to their tunable morphologies and superior properties, multifunctional magnetic nanomaterials and their hybrid nanostructures can be designed as specific carriers of drugs, imaging agents, and magnetic theranostics. Multifunctional magnetic nanostructures are promising theranostic agents due to their ability to diagnose and combine therapies. This review provides a comprehensive overview of the development of advanced multifunctional magnetic nanostructures combining magnetic and optical properties, providing photoresponsive magnetic platforms for promising medical applications. Moreover, this review discusses various innovative developments using multifunctional magnetic nanostructures, including drug delivery, cancer treatment, tumor-specific ligands that deliver chemotherapeutics or hormonal agents, magnetic resonance imaging, and tissue engineering. Additionally, artificial intelligence (AI) can be used to optimize material properties in cancer diagnosis and treatment, based on predicted interactions with drugs, cell membranes, vasculature, biological fluid, and the immune system to enhance the effectiveness of therapeutic agents. Furthermore, this review provides an overview of AI approaches used to assess the practical utility of multifunctional magnetic nanostructures for cancer diagnosis and treatment. Finally, the review presents the current knowledge and perspectives on hybrid magnetic systems as cancer treatment tools with AI models.

show abstract

Section: Introductionmentioning

confidence: 99%

A Review of Advanced Multifunctional Magnetic Nanostructures for Cancer Diagnosis and Therapy Integrated into an Artificial Intelligence Approach

et al. 2023

View full text Add to dashboard Cite

show abstract

“…[17,25,27,28] To do that, significant extension of theoretical models would have been necessary, which, in turn, would increase their complexity and the demand for compute. [29] Machine learning (ML) methods can overcome the aforementioned limitations by leveraging large amounts of data. ML algorithms use training data to learn complex dependencies between sample features and its properties of interest bypassing explicit mathematical formulation of their relationship.…”

Section: Introductionmentioning

confidence: 99%

“…[37] Nelson and Sanvito used chemical composition as the only feature for prediction of the Curie temperature of ferromagnets with an accuracy of ≈50 K. [38] Coïsson et al leveraged data of numerical simulations to predict power losses of magnetic nanoparticles for hyperthermia applications in good agreement with experimental data. [29] ML methods possess huge potential for designing magnetic nanoparticles for medical applications that have not yet been fully explored. [19] In this work, we propose an ML approach to predict the parameters determining efficacy of nanoparticles in MRI (r 1 and r 2 relaxivities) or hyperthermia treatment (SAR).…”

Section: Introductionmentioning

confidence: 99%

“…[ 17,25,27,28 ] To do that, significant extension of theoretical models would have been necessary, which, in turn, would increase their complexity and the demand for compute. [ 29 ]…”

Section: Introductionmentioning

confidence: 99%

“…leveraged data of numerical simulations to predict power losses of magnetic nanoparticles for hyperthermia applications in good agreement with experimental data. [ 29 ] ML methods possess huge potential for designing magnetic nanoparticles for medical applications that have not yet been fully explored. [ 19 ]…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Quantifying the Efficacy of Magnetic Nanoparticles for MRI and Hyperthermia Applications via Machine Learning Methods

Kim

Serov

Falchevskaya

et al. 2023

Small

View full text Add to dashboard Cite

Magnetic nanoparticles are a prospective class of materials for use in biomedicine as agents for magnetic resonance imagining (MRI) and hyperthermia treatment. However, synthesis of nanoparticles with high efficacy is resource‐intensive experimental work. In turn, the use of machine learning (ML) methods is becoming useful in materials design and serves as a great approach to designing nanomagnets for biomedicine. In this work, for the first time, an ML‐based approach is developed for the prediction of main parameters of material efficacy, i.e., specific absorption rate (SAR) for hyperthermia and r1/r2 relaxivities in MRI, with parameters of nanoparticles as well as experimental conditions as descriptors. For that, a unique database with more than 980 magnetic nanoparticles collected from scientific articles is assembled. Using this data, several tree‐based ensemble models are trained to predict SAR, r1 and r2 relaxivity. After hyperparameter optimization, models reach performances of R2 = 0.86, R2 = 0.78, and R2 = 0.75, respectively. Testing the models on samples unseen during the training shows no performance drops. Finally, DiMag, an open access resource created to guide synthesis of novel nanosized magnets for MRI and hyperthermia treatment with machine learning and boost development of new biomedical agents, is developed.

show abstract

Pharmaceutical Quality by Design Approach to Develop High-Performance Nanoparticles for Magnetic Hyperthermia

Ansari,

Suárez-López,

Thersleff

et al. 2024

ACS Nano

View full text Add to dashboard Cite

Magnetic hyperthermia holds significant therapeutic potential, yet its clinical adoption faces challenges. One obstacle is the large-scale synthesis of high-quality superparamagnetic iron oxide nanoparticles (SPIONs) required for inducing hyperthermia. Robust and scalable manufacturing would ensure control over the key quality attributes of SPIONs, and facilitate clinical translation and regulatory approval. Therefore, we implemented a risk-based pharmaceutical quality by design (QbD) approach for SPION production using flame spray pyrolysis (FSP), a scalable technique with excellent batch-to-batch consistency. A design of experiments method enabled precise size control during manufacturing. Subsequent modeling linked the SPION size (6−30 nm) and composition to intrinsic loss power (ILP), a measure of hyperthermia performance. FSP successfully fine-tuned the SPION composition with dopants (Zn, Mn, Mg), at various concentrations. Hyperthermia performance showed a strong nonlinear relationship with SPION size and composition. Moreover, the ILP demonstrated a stronger correlation to coercivity and remanence than to the saturation magnetization of SPIONs. The optimal operating space identified the midsized (15−18 nm) Mn 0.25 Fe 2.75 O 4 as the most promising nanoparticle for hyperthermia. The production of these nanoparticles on a pilot scale showed the feasibility of large-scale manufacturing, and cytotoxicity investigations in multiple cell lines confirmed their biocompatibility. In vitro hyperthermia studies with Caco-2 cells revealed that Mn 0.25 Fe 2.75 O 4 nanoparticles induced 80% greater cell death than undoped SPIONs. The systematic QbD approach developed here incorporates process robustness, scalability, and predictability, thus, supporting the clinical translation of high-performance SPIONs for magnetic hyperthermia.

show abstract

Specific loss power of magnetic nanoparticles: A machine learning approach

Cited by 5 publications

References 38 publications

A Review of Advanced Multifunctional Magnetic Nanostructures for Cancer Diagnosis and Therapy Integrated into an Artificial Intelligence Approach

A Review of Advanced Multifunctional Magnetic Nanostructures for Cancer Diagnosis and Therapy Integrated into an Artificial Intelligence Approach

Quantifying the Efficacy of Magnetic Nanoparticles for MRI and Hyperthermia Applications via Machine Learning Methods

Pharmaceutical Quality by Design Approach to Develop High-Performance Nanoparticles for Magnetic Hyperthermia

Contact Info

Product

Resources

About