Messenger RNA (mRNA) vaccines are revolutionizing the therapy of cancer. It can be flexibly developed in a short period of time, allowing transient expression of multiple antigens for safe and efficient immunization. A diversity of mRNA vaccines is being explored in clinic to benefit patients with cancer. However, the translation of mRNA vaccines is still hampered by multistage delivery barriers before initiating strong immunity, including rapid clearance, poor targeting to lymphoid organs and dendritic cells, catalytic hydrolysis and weak capability to pass through phospholipid bilayers. Besides, vaccination with mRNA alone can barely induce strong immune responses in the absence of adjuvants. It remains challenging to improve cytosolic delivery of mRNA and promote its in vivo vaccination efficacy in combination with adjuvants.

In past decades, a huge number of nanocarriers have been reported to promote transfection efficacy of nucleic acid drugs or deliver drugs to lymph nodes. These studies provide valuable features including size, surface charge, modification, responsiveness, components and cytotoxicity to achieve the goal for lymph nodes drainage or cytosolic access. Machine learning techniques provide powerful tools for exploring the physicochemical characteristics and biological features of these nanoparticles, and facilitate the design of nanocarriers with high efficiency. Commonly, machine learning models were trained, selected and optimized with high quality and massive datasets from computations and high-throughput experimental data, and in turn guide the rational design, screening and optimization of nanocarriers. By leveraging existing nanocarriers’ databases, machine learning may provide insights into rational design of nanovaccines with high efficiency.

In a new research article published in the Beijing-based National Science Review, scientists from the Chinese Academy of Sciences and Shanghai Jiao Tong University used machine learning to guide the rationalized design of mRNA nanovaccines. This study identified the key parameters of nanovaccines for efficient delivery of mRNA and cGAMP based on a machine learning model from the Nanocarrier Database (2010-2021, web of science). The mRNA/cGAMP nanocomplexes based on phenylboronic acid grafted polyethyleneimine were prepared and further encapsulated with anionic lipids to obtain the nanovaccine. (1) The negative surface charge of the nanovaccine reduces the interaction with negatively charged glycosaminoglycans in matrix and improves accumulation in the lymph nodes. (2) The nanovaccine, after being internalized by the antigen-presenting cells (APCs) in the lymph nodes, promotes the release of mRNA and cGAMP from the endosomes to the cytoplasm, which activates the STING pathway and induces the presentation of tumor antigens. (3) The activation of STING pathway promotes the release of IFN-I, which activates T cell immune response to kill tumor cells and inhibit tumor growth and metastasis. Compared with the mRNA alone, the therapeutic strategy based on this nanovaccine demonstrated stronger anti-tumor effects in melanoma and colorectal cancer models.

###

See the article:

STING agonist-boosted mRNA immunization via intelligent design of nanovaccines for enhancing cancer immunotherapy

https://doi.org/10.1093/nsr/nwad214

A research group led by Tokyo Medical and Dental University (TMDU) finds that when common orthopedic symptoms are given, ChatGPT’s diagnosis and recommendations are inconsistent

Tokyo, Japan – ChatGPT, a sophisticated chatbot driven by artificial intelligence (AI) technology, has been increasingly used in health care contexts, one of which is assisting patients in self-diagnosing before seeking medical help. Although it seems very useful at first glance, AI may cause more harm than good to the patient if it is not accurate in its diagnosis and recommendations. A research team from Japan and the United States recently found that the precision of ChatGPT’s diagnoses and the degree to which it recommends medical consultation require further development.

In a study published in September, the multi-institutional research team led by Tokyo Medical and Dental University (TMDU) evaluated the accuracy (percentage of correct responses) and precision of ChatGPT’s response to five common orthopedic diseases (including carpal tunnel syndrome, cervical myelopathy, and hip osteoarthritis) because orthopedic complaints are very common in clinical practice and comprise up to 26% of the reasons why patients seek care. Over a 5-day course, each of the study researchers submitted the same questions to ChatGPT. The reproducibility between days and researchers was also calculated, and the strength of the recommendation that the patient seek medical attention was evaluated.

“We found that accuracy and reproducibility of ChatGPT’s diagnosis are not consistent over the five conditions. ChatGPT’s diagnosis was 100% accurate for carpal tunnel syndrome, but only 4% for cervical myelopathy,” says lead author Tomoyuki Kuroiwa. Additionally, reproducibility between days and researchers varied from “poor” to “almost perfect” among the five conditions even though researchers entered the same questions every time.

ChatGPT was also inconsistent in recommending medical consultation. Although almost 80% of ChatGPT’s answers recommended medical consultation, only 12.8% included a strong recommendation as set by the study standards. “Without direct language, it is possible that the patient is left confused after self-diagnosis, or worse, experience harm from a misdiagnosis,” says Kuroiwa.

This is the first study to evaluate the reproducibility and degree of the medical consultation recommendation of ChatGPT’s ability to self-diagnose. “In its current form, ChatGPT is inconsistent in both accuracy and precision to help patients diagnose their disease,” explains senior author Koji Fujita. “Given the risk of error and potential harm from misdiagnosis, it is important for any diagnostic tool to include clear language alerting patients to seek expert medical opinions for confirmation of a disease.”

The researchers also note some limitations of the study including the use of questions simulated by the research team and not patient-derived questions; focusing on only five orthopedic diseases; and using only ChatGPT. While it is still too early to use AI intelligence for self-diagnosis, the training of ChatGPT on diseases of interest could change this. Future studies can help shed light on the role of AI as a diagnostic tool.

###

The article, “The potential of ChatGPT as a self-diagnostic tool in common orthopedic diseases: exploratory study,” was published in Journal of Medical Internet Research at DOI: 10.2196/47621