Artificial intelligence applied to 'omics data in liver disease: towards a personalised approach for diagnosis, prognosis and treatment

Advancements in omics technologies and artificial intelligence (AI) methodologies are fuelling our progress towards personalised diagnosis, prognosis and treatment strategies in hepatology. This review provides a comprehensive overview of the current landscape of AI methods used for analysis of omics data in liver diseases. We present an overview of the prevalence of different omics levels across various liver diseases, as well as categorise the AI methodology used across the studies. Specifically, we highlight the predominance of transcriptomic and genomic profiling and the relatively sparse exploration of other levels such as the proteome and methylome, which represent untapped potential for novel insights. Publicly available database initiatives such as The Cancer Genome Atlas and The International Cancer Genome Consortium have paved the way for advancements in the diagnosis and treatment of hepatocellular carcinoma. However, the same availability of large omics datasets remains limited for other liver diseases. Furthermore, the application of sophisticated AI methods to handle the complexities of multiomics datasets requires substantial data to train and validate the models and faces challenges in achieving bias-free results with clinical utility. Strategies to address the paucity of data and capitalise on opportunities are discussed. Given the substantial global burden of chronic liver diseases, it is imperative that multicentre collaborations be established to generate large-scale omics data for early disease recognition and intervention. Exploring advanced AI methods is also necessary to maximise the potential of these datasets and improve early detection and personalised treatment strategies.

Read More

The Q for immune evasion in HCC: ER stress in myeloid cells

Hepatocellular carcinoma (HCC) is a leading cause of cancer-related mortality worldwide. In most cases, HCC develops in an already perturbed liver microenvironment with pre-existing liver cirrhosis and tissue remodelling. Once a tumour nodule evolves, a complex ecosystem comprising tumour, immune, structural cells and extracellular matrix develops and forms the so-called tumour microenvironment (TME).1 This TME is shaped by distinct metabolic networks particularly driven by metabolic reprogramming of tumour cells, which supports their function, as one of the hallmarks of cancer.2 For example, in many cancer types, tumour cells mostly depend on glucose consumption for their energy supply, leading to lactate production and acidic conditions in the TME even with enough oxygen (Warburg effect).3 In addition, tumour cells also heavily rely on the amino acid glutamine (single letter code: Q) for their nucleotide biosynthesis and thus proliferation as well as for lipid biosynthesis and…

Read More

Cross-sectional study protocol to assess ultraviolet radiation exposure among military outdoor workers in Lohatla, Northern Cape Province of South Africa

Introduction
The sun is one of the primary natural sources of ultraviolet radiation (UVR) and a known human carcinogen. It has been related to melanoma and several skin cancers, such as squamous cell carcinoma and basal cell carcinoma. Non-melanoma skin cancers are prevalent in South Africa, with high reported incidence rates in both genders. Due to its diversified population, South Africa experiences extreme ultraviolet index (UVI) levels, reaching 13 in the summer (a UVI of 11+ is considered extreme). Most summer workdays expose outdoor workers to repeated UVR exposure, which can lead to health risks like sunburn, premature ageing, cataracts, and an increased risk of skin cancer. This study aims to evaluate UV radiation exposure among outdoor military workers.

Methods and analysis
A cross-sectional quantitative study will occur at the Lohatla military base in Kathu, Northern Cape province of South Africa, using personal electronic dosimeters for solar UVR assessment. Additionally, a self-administered questionnaire will assist in assessing health effects and perceived exposure behaviours. The study addresses a critical public health concern, exploring significant risks associated with UVR exposure among outdoor military workers across different demographics.

Ethics and dissemination
The ethical approval for this study was obtained from the Health Sciences Research Committees of the University of Free State (UFS-HSD2023/1227/2811). The confidential data will be accessed by the named researchers and stored in secure password-protected platforms. In addition, the findings will be disseminated through high-impact publications in various formats to government departments and the broader scientific community.

Read More

Prediction of relative survival trends in patients with cutaneous squamous cell carcinoma using a model-based period analysis: a retrospective analysis of the surveillance, epidemiology, and end results database

Objectives
Cutaneous squamous cell carcinoma (CSCC) represents a malignancy characterised by the aberrant proliferation of skin epithelial cells, and certain instances of squamous cell carcinoma (SCC) exhibit features indicative of a heightened proclivity for recurrence, metastasis, and mortality. Tracking the latest survival rates for CSCC is crucial for patient care and public health strategies.

Design
This was a retrospective study.

Setting
The Surveillance, Epidemiology, and End Results (SEER) Programme database was established by the National Cancer Institute in 1973. It is one of the commonly used cancer databases in the United States, covering a variety of tumour types including lung cancer, breast cancer, gastric cancer, colorectal cancer, prostate cancer, etc. It collects cancer diagnosis, treatment and survival data for approximately 50% of the US population, providing systematic evidence support and valuable first-hand information for clinicians’ evidence-based practice and clinical medical research. The data used in this study covers 20 years of information on patients with cutaneous squamous cell carcinoma from 2000 to 2019.

Participants
In this study, we identified a cohort of 2 04 055 patients, comprising 95 287 women and 1 08 768 men, who were diagnosed with CSCC between 2000 and 2019 in the SEER database. The inclusion criteria for this research encompassed individuals aged 15 years and older, availability of data spanning from 2000 to 2019, confirmation through microscopic examination, and the presence of a primary tumour classified as CSCC. Exclusion criteria involved cases solely validated through autopsy or a death certificate, those alive or with indeterminable survival times, and instances with incomplete data.

Outcome measures
The SEER database’s patient trends and relative survival rate for patients with CSCC were evaluated using period analysis method from 2000 to 2019. The anticipated 5 year relative survival rate among CSCC patients for the years 2020 to 2024 was projected using a generalised linear model.

Results
A total of 204,055 CSCC patients were identified, 95 287 women and 1 08 768 men. Most patients were male, white, lived in urban areas, presenting with localised metastases, aged 55–64 years, and had untyped CSCC. During the observation period, the 5 year relative survival rate of CSCC patients showed a slight improvement overall, while the 5 year relative survival rate of some subtypes showed obvious fluctuations. Particularly noteworthy was the substantial amelioration observed in the small cell nonkeratinizing SCC subtype, escalating from 60.4% in 2000 to 72.8% in 2019. The 5 year overall relative survival rates for CSCC patients during the intervals 2000–2004, 2005–2009, 2010–2014, and 2015–2019 documented rates of 62.4%, 63.4%, 64.3%, and 66.3%, respectively. Males had slightly lower survival rates than females, older patients had lower rates than younger patients, and white patients had better outcomes than non-white patients. Urban patients had higher survival rates than rural patients. Patients with distant metastases had significantly lower survival rates.

Conclusion
The temporal span from 2000 to 2019 witnessed a gradual yet delimited increase in survival rates among CSCC patients. This incremental trajectory persists, with a prognosticated survival rate of 67.1 anticipated between 2020 and 2024.

Read More

Camrelizumab plus rivoceranib compared sorafenib as first-line therapeutic options for advanced hepatocellular carcinoma in China: a cost-effectiveness analysis

Aim
The objective of this research is to assess the cost-effectiveness of combining camrelizumab with rivoceranib in comparison to sorafenib as first-line therapeutic options for advanced hepatocellular carcinoma from the Chinese medical system perspective.

Methods
A partitioned survival model was employed to perform a comprehensive cost-effectiveness analysis. This analysis incorporated multiple factors, such as treatment effectiveness, adverse events and costs, all of which were derived from data obtained from the CARES-310 trial. Furthermore, sensitivity analyses were conducted to evaluate the robustness and reliability of the model.

Results
The comparison between the two groups demonstrated that the cohort receiving camrelizumab combined with rivoceranib exhibited a significant increase of 0.803 quality-adjusted life year (QALY), alongside an additional expenditure of US$7345.051. This computation resulted in an incremental cost-effectiveness ratio of US$9147.012 per QALY, which was lower than the willingness-to-pay threshold of US$39 855.785 per QALY in China. Sensitivity analyses conducted in this study further demonstrated the robustness of the results across various assumptions.

Conclusion
The adoption of camrelizumab plus rivoceranib as a treatment option is not only associated with improved health outcomes but also represents a cost-effective choice in China.

Read More

Global epidemiological profile in nasopharyngeal carcinoma: a prediction study

Objectives
This study delineates the global nasopharyngeal carcinoma’s (NPC) incidence and mortality across 185 countries in 2020 and projects the disease’s burden by 2040.

Design
A prediction study.

Setting
Countries within the 20 world regions.

Participants
Global NPC population.

Primary and secondary outcome measures
The estimated counts of NPC cases and deaths were retrieved from the GLOBOCAN 2020 database. Age-standardised incidence rates (ASIR) and age-standardised death rates (ASDR) were computed. Projections for NPC by 2040 were derived from global population forecasts.

Results
In the year 2020, East Asia emerged as the epicentre of both NPC incidences and mortalities, encompassing 49.39% (65 866 of the total 133 354 cases) and 45.56% (36 453 of the total 80 008 deaths), respectively, with China’s contribution being the most substantial (46.82% of cases and 43.50% of deaths). The disparity between genders was notable, as the ASIR and ASDR for males were approximately triple those observed in females. The incidence exhibited regional diversity, with South-Eastern Asia and East Asia recording the highest ASIR for males and females (7.7 and 2.5, and 3.9 and 1.5 per 100 000 person-years, respectively). Similarly, South-Eastern Asia also reported the highest ASDR for both genders (5.4 and 1.5 per 100 000 person-years, respectively). Projections for 2040 anticipate a rise in annual cases and deaths to 179 476 (indicating a 34.58% increase from 2020) and 113 851 (reflecting a 42.29% increase), respectively. Further analysis revealed a correlation between the Human Development Index and disease burden.

Conclusions
NPC, primarily impacting East Asia and predominantly affecting men, is poised for a significant increase in incidence and mortality by 2040, especially in Asia.

Read More