Artificial Intelligence and Infectious Disease Imaging.

The mass production of the graphics processing unit and the coronavirus disease 2019 (COVID-19) pandemic have provided the means and the motivation, respectively, for rapid developments in artificial intelligence (AI) and medical imaging techniques. This has led to new opportunities to improve patient care but also new challenges that must be overcome before these techniques are put into practice. In particular, early AI models reported high performances but failed to perform as well on new data. However, these mistakes motivated further innovation focused on developing models that were not only accurate but also stable and generalizable to new data. The recent developments in AI in response to the COVID-19 pandemic will reap future dividends by facilitating, expediting, and informing other medical AI applications and educating the broad academic audience on the topic. Furthermore, AI research on imaging animal models of infectious diseases offers a unique problem space that can fill in evidence gaps that exist in clinical infectious disease research. Here, we aim to provide a focused assessment of the AI techniques leveraged in the infectious disease imaging research space, highlight the unique challenges, and discuss burgeoning solutions.

HAL-X: Scalable hierarchical clustering for rapid and tunable single-cell analysis.

Data clustering plays a significant role in biomedical sciences, particularly in single-cell data analysis. Researchers use clustering algorithms to group individual cells into populations that can be evaluated across different levels of disease progression, drug response, and other clinical statuses. In many cases, multiple sets of clusters must be generated to assess varying levels of cluster specificity. For example, there are many subtypes of leukocytes (e.g. T cells), whose individual preponderance and phenotype must be assessed for statistical/functional significance. In this report, we introduce a novel hierarchical density clustering algorithm (HAL-x) that uses supervised linkage methods to build a cluster hierarchy on raw single-cell data. With this new approach, HAL-x can quickly predict multiple sets of labels for immense datasets, achieving a considerable improvement in computational efficiency on large datasets compared to existing methods. We also show that cell clusters generated by HAL-x yield near-perfect F1-scores when classifying different clinical statuses based on single-cell profiles. Our hierarchical density clustering algorithm achieves high accuracy in single cell classification in a scalable, tunable and rapid manner.

Harnessing PubMed User Query Logs for Post Hoc Explanations of Recommended Similar Articles.

Searching for a related article based on a reference article is an integral part of scientific research. PubMed, like many academic search engines, has a "similar articles" feature that recommends articles relevant to the current article viewed by a user. Explaining recommended items can be of great utility to users, particularly in the literature search process. With more than a million biomedical papers being published each year, explaining the recommended similar articles would facilitate researchers and clinicians in searching for related articles. Nonetheless, the majority of current literature recommendation systems lack explanations for their suggestions. We employ a post hoc approach to explaining recommendations by identifying relevant tokens in the titles of similar articles. Our major contribution is building PubCLogs by repurposing 5.6 million pairs of coclicked articles from PubMed's user query logs. Using our PubCLogs dataset, we train the Highlight Similar Article Title (HSAT), a transformer-based model designed to select the most relevant parts of the title of a similar article, based on the title and abstract of a seed article. HSAT demonstrates strong performance in our empirical evaluations, achieving an F1 score of 91.72 percent on the PubCLogs test set, considerably outperforming several baselines including BM25 (70.62), MPNet (67.11), MedCPT (62.22), GPT-3.5 (46.00), and GPT-4 (64.89). Additional evaluations on a separate, manually annotated test set further verifies HSAT's performance. Moreover, participants of our user study indicate a preference for HSAT, due to its superior balance between conciseness and comprehensiveness. Our study suggests that repurposing user query logs of academic search engines can be a promising way to train state-of-the-art models for explaining literature recommendation.

Simulated Misuse of Large Language Models and Clinical Credit Systems.

Large language models (LLMs) have been proposed to support many healthcare tasks, including disease diagnostics and treatment personalization. While AI may be applied to assist or enhance the delivery of healthcare, there is also a risk of misuse. LLMs could be used to allocate resources based on unfair, inaccurate, or unjust criteria. For example, a social credit system uses big data to assess "trustworthiness" in society, punishing those who score poorly based on evaluation metrics defined only by a power structure (corporate entity, governing body). Such a system may be amplified by powerful LLMs which can rate individuals based on multimodal data - financial transactions, internet activity, and other behavioural inputs. Healthcare data is perhaps the most sensitive information which can be collected and could potentially be used to violate civil liberty via a "clinical credit system", which may include limiting or rationing access to standard care. This report simulates how clinical datasets might be exploited and proposes strategies to mitigate the risks inherent to the development of AI models for healthcare.

A Review of Ultrasound-Mediated Checkpoint Inhibitor Immunotherapy.

Over the past decade, immunotherapy has emerged as a major modality in cancer medicine. However, despite its unprecedented success, immunotherapy currently benefits only a subgroup of patients, may induce responses of limited duration and is associated with potentially treatment-limiting side effects. In addition, responses to immunotherapeutics are sometimes diminished by the emergence of a complex array of resistance mechanisms. The efficacy of immunotherapy depends on dynamic interactions between tumour cells and the immune landscape in the tumour microenvironment. Ultrasound, especially in conjunction with cavitation-promoting agents such as microbubbles, can assist in the uptake and/or local release of immunotherapeutic agents at specific target sites, thereby increasing treatment efficacy and reducing systemic toxicity. There is also increasing evidence that ultrasound and/or cavitation may themselves directly stimulate a beneficial immune response. In this review, we summarize the latest developments in the use of ultrasound and cavitation agents to promote checkpoint inhibitor immunotherapy.

Digital Omicron detection using unscripted voice samples from social media.

The success of artificial intelligence in clinical environments relies upon the diversity and availability of training data. In some cases, social media data may be used to counterbalance the limited amount of accessible, well-curated clinical data, but this possibility remains largely unexplored. In this study, we mined YouTube to collect voice data from individuals with self-declared positive COVID-19 tests during time periods in which Omicron was the predominant variant1,2,3, while also sampling non-Omicron COVID-19 variants, other upper respiratory infections (URI), and healthy subjects. The resulting dataset was used to train a DenseNet model to detect the Omicron variant from voice changes. Our model achieved 0.85/0.80 specificity/sensitivity in separating Omicron samples from healthy samples and 0.76/0.70 specificity/sensitivity in separating Omicron samples from symptomatic non-COVID samples. In comparison with past studies, which used scripted voice samples, we showed that leveraging the intra-sample variance inherent to unscripted speech enhanced generalization. Our work introduced novel design paradigms for audio-based diagnostic tools and established the potential of social media data to train digital diagnostic models suitable for real-world deployment.

Stem-like CD8 T cells mediate response of adoptive cell immunotherapy against human cancer.

Adoptive T cell therapy (ACT) using ex vivo-expanded autologous tumor-infiltrating lymphocytes (TILs) can mediate complete regression of certain human cancers. The impact of TIL phenotypes on clinical success of TIL-ACT is currently unclear. Using high-dimensional analysis of human ACT products, we identified a memory-progenitor CD39-negative stem-like phenotype (CD39-CD69-) associated with complete cancer regression and TIL persistence and a terminally differentiated CD39-positive state (CD39+CD69+) associated with poor TIL persistence. Most antitumor neoantigen-reactive TILs were found in the differentiated CD39+ state. However, ACT responders retained a pool of CD39- stem-like neoantigen-specific TILs that was lacking in ACT nonresponders. Tumor-reactive stem-like TILs were capable of self-renewal, expansion, persistence, and superior antitumor response in vivo. These data suggest that TIL subsets mediating ACT response are distinct from TIL subsets enriched for antitumor reactivity.

Defective glycosylation and multisystem abnormalities characterize the primary immunodeficiency XMEN disease.

X-linked immunodeficiency with magnesium defect, EBV infection, and neoplasia (XMEN) disease are caused by deficiency of the magnesium transporter 1 (MAGT1) gene. We studied 23 patients with XMEN, 8 of whom were EBV naive. We observed lymphadenopathy (LAD), cytopenias, liver disease, cavum septum pellucidum (CSP), and increased CD4-CD8-B220-TCRαß+ T cells (αßDNTs), in addition to the previously described features of an inverted CD4/CD8 ratio, CD4+ T lymphocytopenia, increased B cells, dysgammaglobulinemia, and decreased expression of the natural killer group 2, member D (NKG2D) receptor. EBV-associated B cell malignancies occurred frequently in EBV-infected patients. We studied patients with XMEN and patients with autoimmune lymphoproliferative syndrome (ALPS) by deep immunophenotyping (32 immune markers) using time-of-flight mass cytometry (CyTOF). Our analysis revealed that the abundance of 2 populations of naive B cells (CD20+CD27-CD22+IgM+HLA-DR+CXCR5+CXCR4++CD10+CD38+ and CD20+CD27-CD22+IgM+HLA-DR+CXCR5+CXCR4+CD10-CD38-) could differentially classify XMEN, ALPS, and healthy individuals. We also performed glycoproteomics analysis on T lymphocytes and show that XMEN disease is a congenital disorder of glycosylation that affects a restricted subset of glycoproteins. Transfection of MAGT1 mRNA enabled us to rescue proteins with defective glycosylation. Together, these data provide new clinical and pathophysiological foundations with important ramifications for the diagnosis and treatment of XMEN disease.