Malignancy prediction among tissues from Oral SCC patients including neck invasions: a 1H HRMAS NMR based metabolomic study

Assessing the Reporting Quality of Machine Learning Algorithms in Head and Neck Oncology

OBJECTIVE

This study aimed to assess reporting quality of machine learning (ML) algorithms in the head and neck oncology literature using the TRIPOD-AI criteria.

DATA SOURCES

A comprehensive search was conducted using PubMed, Scopus, Embase, and Cochrane Database of Systematic Reviews, incorporating search terms related to "artificial intelligence," "machine learning," "deep learning," "neural network," and various head and neck neoplasms.

REVIEW METHODS

Two independent reviewers analyzed each published study for adherence to the 65-point TRIPOD-AI criteria. Items were classified as "Yes," "No," or "NA" for each publication. The proportion of studies satisfying each TRIPOD-AI criterion was calculated. Additionally, the evidence level for each study was evaluated independently by two reviewers using the Oxford Centre for Evidence-Based Medicine (OCEBM) Levels of Evidence. Discrepancies were reconciled through discussion until consensus was reached.

RESULTS

The study highlights the need for improvements in ML algorithm reporting in head and neck oncology. This includes more comprehensive descriptions of datasets, standardization of model performance reporting, and increased sharing of ML models, data, and code with the research community. Adoption of TRIPOD-AI is necessary for achieving standardized ML research reporting in head and neck oncology.

CONCLUSION

Current reporting of ML algorithms hinders clinical application, reproducibility, and understanding of the data used for model training. To overcome these limitations and improve patient and clinician trust, ML developers should provide open access to models, code, and source data, fostering iterative progress through community critique, thus enhancing model accuracy and mitigating biases.

LEVEL OF EVIDENCE

NA Laryngoscope, 2024.

Application of metabolomics in oral squamous cell carcinoma

BACKGROUND

Oral squamous cell carcinoma (OSCC) is a prevalent malignancy affecting the head and neck region. The prognosis for OSCC patients remains unfavorable due to the absence of precise and efficient early diagnostic techniques. Metabolomics offers a promising approach for identifying distinct metabolites, thereby facilitating early detection and treatment of OSCC.

OBJECTIVE

This review aims to provide a comprehensive overview of recent advancements in metabolic marker identification for early OSCC diagnosis. Additionally, the clinical significance and potential applications of metabolic markers for the management of OSCC are discussed.

RESULTS

This review summarizes metabolic changes during the occurrence and development of oral squamous cell carcinoma and reviews prospects for the clinical application of characteristic, differential metabolites in saliva, serum, and OSCC tissue. In this review, the application of metabolomic technology in OSCC research was summarized, and future research directions were proposed.

CONCLUSION

Metabolomics, detection technology that is the closest to phenotype, can efficiently identify differential metabolites. Combined with statistical data analyses and artificial intelligence technology, it can rapidly screen characteristic biomarkers for early diagnosis, treatment, and prognosis evaluations.

Metabolic landscape of head and neck squamous cell carcinoma informs a novel kynurenine/Siglec-15 axis in immune escape

BACKGROUND

Metabolic reprograming and immune escape are two hallmarks of cancer. However, how metabolic disorders drive immune escape in head and neck squamous cell carcinoma (HNSCC) remains unclear. Therefore, the aim of the present study was to investigate the metabolic landscape of HNSCC and its mechanism of driving immune escape.

METHODS

Analysis of paired tumor tissues and adjacent normal tissues from 69 HNSCC patients was performed using liquid/gas chromatography-mass spectrometry and RNA-sequencing. The tumor-promoting function of kynurenine (Kyn) was explored in vitro and in vivo. The downstream target of Kyn was investigated in CD8+ T cells. The regulation of CD8+ T cells was investigated after Siglec-15 overexpression in vivo. An engineering nanoparticle was established to deliver Siglec-15 small interfering RNA (siS15), and its association with immunotherapy response were investigated. The association between Siglec-15 and CD8+ programmed cell death 1 (PD-1)+ T cells was analyzed in a HNSCC patient cohort.

RESULTS

A total of 178 metabolites showed significant dysregulation in HNSCC, including carbohydrates, lipids and lipid-like molecules, and amino acids. Among these, amino acid metabolism was the most significantly altered, especially Kyn, which promoted tumor proliferation and metastasis. In addition, most immune checkpoint molecules were upregulated in Kyn-high patients based on RNA-sequencing. Furthermore, tumor-derived Kyn was transferred into CD8+ T cells and induced T cell functional exhaustion, and blocking Kyn transporters restored its killing activity. Accroding to the results, mechanistically, Kyn transcriptionally regulated the expression of Siglec-15 via aryl hydrocarbon receptor (AhR), and overexpression of Siglec-15 promoted immune escape by suppressing T cell infiltration and activation. Targeting AhR in vivo reduced Kyn-mediated Siglec-15 expression and promoted intratumoral CD8+ T cell infiltration and killing capacity. Finally, a NH2-modified mesoporous silica nanoparticle was designed to deliver siS15, which restored CD8+ T cell function status and enhanced anti-PD-1 efficacy in tumor-bearing immunocompetent mice. Clinically, Siglec-15 was positively correlated with AhR expression and CD8+PD-1+ T cell infiltration in HNSCC tissues.

CONCLUSIONS

The findings describe the metabolic landscape of HNSCC comprehensively and reveal that the Kyn/Siglec-15 axis may be a novel potential immunometabolism mechanism, providing a promising therapeutic strategy for cancers.

Biological biomarkers of oral cancer

The oral squamous cell carcinoma (OSCC) 5 year survival rate of 41% has marginally improved in the last few years, with less than a 1% improvement per year from 2005 to 2017, with higher survival rates when detected at early stages. Based on histopathological grading of oral dysplasia, it is estimated that severe dysplasia has a malignant transformation rate of 7%-50%. Despite these numbers, oral dysplasia grading does not reliably predict its clinical behavior. Thus, more accurate markers predicting oral dysplasia progression to cancer would enable better targeting of these lesions for closer follow-up, especially in the early stages of the disease. In this context, molecular biomarkers derived from genetics, proteins, and metabolites play key roles in clinical oncology. These molecular signatures can help predict the likelihood of OSCC development and/or progression and have the potential to detect the disease at an early stage and, support treatment decision-making and predict treatment responsiveness. Also, identifying reliable biomarkers for OSCC detection that can be obtained non-invasively would enhance management of OSCC. This review will discuss biomarkers for OSCC that have emerged from different biological areas, including genomics, transcriptomics, proteomics, metabolomics, immunomics, and microbiomics.

High-resolution magic angle spinning NMR for intact biological specimen analysis: Initial discovery, recent developments, and future directions

High-resolution magic angle spinning (HRMAS) NMR, an approach for intact biological material analysis discovered more than 25 years ago, has been advanced by many technical developments and applied to many biomedical uses. This article provides a history of its discovery, first by explaining the key scientific advances that paved the way for HRMAS NMR's invention, and then by turning to recent developments that have profited from applying and advancing the technique during the last 5 years. Developments aimed at directly impacting healthcare include HRMAS NMR metabolomics applications within studies of human disease states such as cancers, brain diseases, metabolic diseases, transplantation medicine, and adiposity. Here, the discussion describes recent HRMAS NMR metabolomics studies of breast cancer and prostate cancer, as well as of matching tissues with biofluids, multimodality studies, and mechanistic investigations, all conducted to better understand disease metabolic characteristics for diagnosis, opportune windows for treatment, and prognostication. In addition, HRMAS NMR metabolomics studies of plants, foods, and cell structures, along with longitudinal cell studies, are reviewed and discussed. Finally, inspired by the technique's history of discoveries and recent successes, future biomedical arenas that stand to benefit from HRMAS NMR-initiated scientific investigations are presented.

Construction of machine learning-based models for cancer outcomes in low and lower-middle income countries: A scoping review

Background

The impact and utility of machine learning (ML)-based prediction tools for cancer outcomes including assistive diagnosis, risk stratification, and adjunctive decision-making have been largely described and realized in the high income and upper-middle-income countries. However, statistical projections have estimated higher cancer incidence and mortality risks in low and lower-middle-income countries (LLMICs). Therefore, this review aimed to evaluate the utilization, model construction methods, and degree of implementation of ML-based models for cancer outcomes in LLMICs.

Methods

PubMed/Medline, Scopus, and Web of Science databases were searched and articles describing the use of ML-based models for cancer among local populations in LLMICs between 2002 and 2022 were included. A total of 140 articles from 22,516 citations that met the eligibility criteria were included in this study.

Results

ML-based models from LLMICs were often based on traditional ML algorithms than deep or deep hybrid learning. We found that the construction of ML-based models was skewed to particular LLMICs such as India, Iran, Pakistan, and Egypt with a paucity of applications in sub-Saharan Africa. Moreover, models for breast, head and neck, and brain cancer outcomes were frequently explored. Many models were deemed suboptimal according to the Prediction model Risk of Bias Assessment tool (PROBAST) due to sample size constraints and technical flaws in ML modeling even though their performance accuracy ranged from 0.65 to 1.00. While the development and internal validation were described for all models included (n=137), only 4.4% (6/137) have been validated in independent cohorts and 0.7% (1/137) have been assessed for clinical impact and efficacy.

Conclusion

Overall, the application of ML for modeling cancer outcomes in LLMICs is increasing. However, model development is largely unsatisfactory. We recommend model retraining using larger sample sizes, intensified external validation practices, and increased impact assessment studies using randomized controlled trial designs

Systematic review registration

https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=308345, identifier CRD42022308345.

Machine-Learning Applications in Oral Cancer: A Systematic Review

Over the years, several machine-learning applications have been suggested to assist in various clinical scenarios relevant to oral cancer. We offer a systematic review to identify, assess, and summarize the evidence for reported uses in the areas of oral cancer detection and prevention, prognosis, pre-cancer, treatment, and quality of life. The main algorithms applied in the context of oral cancer applications corresponded to SVM, ANN, and LR, comprising 87.71% of the total published articles in the field. Genomic, histopathological, image, medical/clinical, spectral, and speech data were used most often to predict the four areas of application found in this review. In conclusion, our study has shown that machine-learning applications are useful for prognosis, diagnosis, and prevention of potentially malignant oral lesions (pre-cancer) and therapy. Nevertheless, we strongly recommended the application of these methods in daily clinical practice.

Artificial Intelligence in Chemistry: Current Trends and Future Directions

The application of artificial intelligence (AI) to chemistry has grown tremendously in recent years. In this Review, we studied the growth and distribution of AI-related chemistry publications in the last two decades using the CAS Content Collection. The volume of both journal and patent publications have increased dramatically, especially since 2015. Study of the distribution of publications over various chemistry research areas revealed that analytical chemistry and biochemistry are integrating AI to the greatest extent and with the highest growth rates. We also investigated trends in interdisciplinary research and identified frequently occurring combinations of research areas in publications. Furthermore, topic analyses were conducted for journal and patent publications to illustrate emerging associations of AI with certain chemistry research topics. Notable publications in various chemistry disciplines were then evaluated and presented to highlight emerging use cases. Finally, the occurrence of different classes of substances and their roles in AI-related chemistry research were quantified, further detailing the popularity of AI adoption in the life sciences and analytical chemistry. In summary, this Review offers a broad overview of how AI has progressed in various fields of chemistry and aims to provide an understanding of its future directions.

Study of the metabolic alterations in patulin-induced neoplastic transformation in normal intestinal cells

Several surveillance studies have reported significantly high level of patulin (PAT), mycotoxin in fruit juices suggesting the possible exposure to human. In vitro studies have showed that PAT can alter the permeability, ion transport and modulates tight junction of intestine. In real scenario, human can be exposed with low levels of PAT for longer duration through different fruits and their products. Hence, keeping this possibility in view, we conducted a study where normal intestinal cells were exposed with non-toxic levels of PAT for longer duration and found that PAT exposure causes cancer-like properties in normal intestinal cells. It is a well-known fact that cancer cells rewired their metabolism for cell growth and survival and metabolites closely depict the phenotypic properties of cells. Here, metabolomic study was performed in the PAT transformed and passage matched non-transformed cells using ¹H HRMAS NMR. We have identified 12 significantly up-regulated metabolites, which, interestingly, were majorly amino acids, suggesting that PAT-induced pre-cancerous cells are involved in acquirement of nutrients for high protein turn-over. Furthermore, pathway analysis of metabolomics data indicated that aminoacyl tRNA biosynthesis, D-glutamate metabolism, glyoxylate and dicarboxylate metabolism and nitrogen metabolism were majorly hampered in PAT-induced pre-cancerous properties in normal intestinal cells.

Metabolic landscape of oral squamous cell carcinoma

BACKGROUND

Head and neck cancers are the seventh most common type of cancer worldwide, with almost half of the cases affecting the oral cavity. Oral squamous cell carcinoma (OSCC) is the most common form of oral cancer, showing poor prognosis and high mortality. OSCC molecular pathogenesis is complex, resulting from a wide range of events that involve the interplay between genetic mutations and altered levels of transcripts, proteins, and metabolites. Metabolomics is a recently developed sub-area of omics sciences focused on the comprehensive analysis of small molecules involved in several biological pathways by high throughput technologies.

AIM OF REVIEW

This review summarizes and evaluates studies focused on the metabolomics analysis of OSCC and oral premalignant disorders to better interpret the complex process of oral carcinogenesis. Additionally, the metabolic biomarkers signatures identified so far are also included. Moreover, we discuss the limitations of these studies and make suggestions for future investigations.

KEY SCIENTIFIC CONCEPTS

Although many questions about the metabolic features of OSCC have already been answered in metabolomic studies, further validation and optimization are still required to translate these findings into clinical applications.