The fast-growing field of nanotheranostics is revolutionizing cancer treatment by allowing for precise diagnosis and targeted therapy at the cellular and molecular levels. These nanoscale platforms provide considerable benefits in oncology, including improved disease and therapy specificity, lower systemic toxicity, and real-time monitoring of therapeutic outcomes. However, nanoparticles' complicated interactions with biological systems, notably the immune system, present significant obstacles for clinical translation. While certain nanoparticles can elicit favorable anti-tumor immune responses, others cause immunotoxicity, including complement activation-related pseudoallergy (CARPA), cytokine storms, chronic inflammation, and organ damage. Traditional toxicity evaluation approaches are frequently time-consuming, expensive, and insufficient to capture these intricate nanoparticle-biological interactions. Artificial intelligence (AI) and machine learning (ML) have emerged as transformational solutions to these problems. This paper summarizes current achievements in nanotheranostics for cancer, delves into the causes of nanoparticle-induced immunotoxicity, and demonstrates how AI/ML may help anticipate and create safer nanoparticles. Integrating AI/ML with modern computational approaches allows for the detection of potentially dangerous nanoparticle qualities, guides the optimization of physicochemical features, and speeds up the development of immune-compatible nanotheranostics suited to individual patients. The combination of nanotechnology with AI/ML has the potential to completely realize the therapeutic promise of nanotheranostics while assuring patient safety in the age of precision medicine.

The MDA-MB-231 cell line is derived from triple-negative breast cancer (TNBC), representing one of the most aggressive forms of breast cancer. Innovative therapeutic strategies, including s targeted therapies using nanocarriers, hold significant promise, particularly for difficult-to-treat cancers such as TNBC. Nanoparticles have transformed the medical field by serving as advanced drug delivery systems for cancer treatment. They play a critical role in overcoming the drug resistance often associated with cancer therapies. When utilized as drug delivery vehicles, nanoparticles can specifically target cancer cells and effectively reduce or eliminate multidrug resistance. Among them, chitosan-coated magnetic nanoparticles (MNPs) have been widely explored for the loading and controlled release of various anticancer agents. In this study, we evaluated the effects of dexamethasone-loaded chitosan-coated MNPs on MDA-MB-231 cell lines. Fourier transform infrared spectroscopy and scanning electron microscopy were employed to verify the successful loading of dexamethasone onto the nanoparticles. To assess cytotoxicity, empty nanoparticles, free drug, and drug-loaded nanoparticles were tested on the cells. The results indicated that empty nanoparticles exhibited no toxic effects. The IC50 value of the free drug was 123 µg/mL, while the IC50 value of the drug-loaded nanoparticles was significantly lower, at 63 µg/mL. These findings confirmed the successful conjugation of dexamethasone to the chitosan-coated MNPs, demonstrating substantial cytotoxic effects on breast cancer cells. Although dexamethasone has been reported to exhibit both tumor-suppressive and pro-metastatic effects, its specific impact on TNBC warrants further investigation in future studies.

Instant and accurate evaluation of drug resistance in tumors before and during chemotherapy is important for patients with advanced colon cancer and is beneficial for prolonging their progression-free survival time. Here, the possible biomarkers that reflect the drug resistance of colon cancer were investigated using proton magnetic resonance spectroscopy (1H-MRS) in vivo. SW480[5-fluorouracil(5-FU)-responsive] and SW480/5-FU (5-FU-resistant) xenograft models were generated and subjected to in vivo 1H-MRS examinations when the maximum tumor diameter reached 1–1.5 cm. The areas under the peaks for metabolites, including choline (Cho), lactate (Lac), glutamine/glutamate (Glx), and myo-inositol (Ins)/creatine (Cr) in the tumors, were analyzed between two groups. The resistance-related protein expression, cell morphology, necrosis, apoptosis, and cell survival of these tumor specimens were assessed. The content for tCho, Lac, Glx, and Ins/Cr in the tumors of the SW480 group was significantly lower than that of the SW480/5-FU group (P < 0.05). While there was no significant difference in the degree of necrosis and apoptosis rate of tumor cells between the two groups (P > 0.05), the tumor cells of the SW480/5-FU showed a higher cell density and larger nuclei. The expression levels of resistance-related proteins (P-gp, MPR1, PKC) in the SW480 group were lower than those in the SW480/5-FU group (P < 0.01). The survival rate of 5-FU-resistant colon cancer cells was significantly higher than that of 5-FU-responsive ones at 5-FU concentrations greater than 2.5 μg/mL (P < 0.05). These results suggest that alterations in tCho, Lac, Glx1, Glx2, and Ins/Cr detected by 1H-MRS may be used for monitoring tumor resistance to 5-FU in vivo.

Breast cancer was a prevalent form of cancer worldwide. Thermography, a method for diagnosing breast cancer, involves recording the thermal patterns of the breast. This article explores the use of a convolutional neural network (CNN) algorithm to extract features from a dataset of thermographic images. Initially, the CNN network was used to extract a feature vector from the images. Subsequently, machine learning techniques can be used for image classification. This study utilizes four classification methods, namely Fully connected neural network (FCnet), support vector machine (SVM), classification linear model (CLINEAR), and KNN, to classify breast cancer from thermographic images. The accuracy rates achieved by the FCnet, SVM, CLINEAR, and k-nearest neighbors (KNN) algorithms were 94.2%, 95.0%, 95.0%, and 94.1%, respectively. Furthermore, the reliability parameters for these classifiers were computed as 92.1%, 97.5%, 96.5%, and 91.2%, while their respective sensitivities were calculated as 95.5%, 94.1%, 90.4%, and 93.2%. These findings can assist experts in developing an expert system for breast cancer diagnosis.

There are numerous studies reported on the usage of the sapindus emarginatus (SE) fruit in cancer and other treatments in the past few years. In this study, crude SE fruit extract was prepared and it was further used to synthesis gold nanoparticles (Au Nps). The synthesized Au Nps were left embedded in the SE fruit extract. The Au Nps embedded in the SE fruit extract (SE-Au Nps) were characterized using UV-Visiable Spectroscopy, Centrifugal Particle Size analyzer (CPS), Scanning Electron Microscope (SEM) and Fourier Transform Infrared Spectroscopy (FTIR). MTT assay was carried out for both SE fruit extract and SE-Au Nps on MCF7 breast cancer cell line and thus compared. The UV-Visible Absorbance for the SE-Au Nps was obtained at 543 nm. The centrifugal particle size analysis of the Au Nps embedded in SE fruit extract showed the size of the nanoparticles to be widely varying with higher fraction of particles between the size ranges of 15 to 20 nm. The morphology of the Au Nps embedded in SE fruit extract was observed using SEM. The presence of Au Nps in SE fruit extract was confirmed using FTIR. The results of the MTT assay on MCF7 breast cancer cell line proved that the % cell viability was less for SE-Au Nps than that of the SE fruit extract alone. Thus, the antiproliferative activity of the SE fruit extract was significantly enhanced by embedding it with Au Nps and it can be effectively used in therapeutic applications after further studies.