Proteomics-based plasma test

Early detection of cancer is crucial for reducing the global burden of cancer, but effective screening tests for many cancers do not exist. A new study, published in BMJ Oncology, aimed to develop a novel proteome-based multi-cancer screening test that could detect early-stage cancers with high accuracy. Plasma samples were collected from 440 individuals, healthy and diagnosed with 18 early-stage solid tumours. Using a proximity extension assay, more than 3,000 high-abundance and low-abundance proteins were measured in each sample. A multi-step statistical approach then identified a limited set of sex-specific proteins that could detect early-stage cancers and their tissue of origin with high accuracy.

The sex-specific cancer detection panels consisting of 10 proteins showed high accuracy for both males and females and were able to identify 93% of cancers among males and 84% of cancers among females, with 99% specificity. In addition, the sex-specific localisation panels consisted of 150 proteins and were able to identify the tissue of origin of most cancers in more than 80% of cases. The analysis of the plasma concentrations of proteins selected showed that almost all the proteins were in the low-concentration part of the human plasma proteome.

The authors concluded that the proteome-based screening test showed promising performance compared with other technologies and could be a starting point for developing a new generation of screening tests for the early detection of cancer. While further validation in larger population cohorts is necessary to establish the reliability and generalisability of the findings, they say the results provide a foundation for future research and emphasise the potential of proteomic analysis in revolutionising cancer diagnosis at the population level. 

AI to aid treatment of aggressive skin cancers 

Artificial intelligence is now being used to determine the course and severity of aggressive skin cancers, such as Merkel cell carcinoma (MCC), and has the potential to enhance clinical decision making by generating personalised predictions of treatment specific outcomes for patients and their doctors.

An international team, led by researchers at Newcastle University, UK, has combined machine learning with clinical expertise to develop a web-based system called ‘DeepMerkel’ which offers the power to predict MCC treatment specific outcomes based on personal and tumour specific features. They propose that this system could be applied to other aggressive skin cancers for precision prognostication, the enhancement of informed clinical decision making and improved patient choice.

Dr Tom Andrew, a plastic surgeon and PhD student at Newcastle University said; “DeepMerkel is allowing us to predict the course and severity of a Merkel cell carcinoma enabling us to personalise treatment so that patients are getting the optimal management.

Using AI allowed us to understand subtle new patterns and trends in the data which meant on an individual level, we are able to provide more accurate predictions for each patient.” The research was published in two complementary publications in Nature Digital Medicine and the Journal of the American Academy of Dermatology.

Advanced imaging finds prostate metastases

Conventional imaging may not be able to correctly assess prostate cancer patients whose cancer has metastasised and spread to other areas of the body. 

Researchers at the University of California, Los Angeles, looked at a group of people with prostate cancer who were previously classed as non-metastatic using conventional cancer imaging. When they used prostate-specific membrane antigen–positron emission tomographic/computed tomographic (PSMA-PET/CT) imaging instead of conventional imaging almost half of the people screened showed evidence of metastases. PSMA-PET is a relatively new imaging technology that uses small amounts of radio tracers to bind to prostate cancer cells in the patient’s body. This imaging agent then allows these cells to be seen using PET imaging.

This study, published in JAMA Network Open, found that by using PSMA-PET/CT, 46% of patients had at least one metastasis and 24% had five or more metastases. “Our study demonstrates the critical role of PSMA-PET in accurately staging prostate cancer, which can significantly impact treatment decisions and outcomes,” said senior author of the study Jeremie Calais, associate professor at the department of molecular and medical pharmacology at the David Geffen School of Medicine at UCLA. These results support others showing its superiority over more conventional imaging for giving accurate diagnostic and prognostic information for patients but the authors say more high-quality prospective data will be needed to claim superiority of PSMA-PET for treatment-guidance in terms of patient outcome.

AI determines who benefits in clinical trials

An artificial intelligence (AI) platform has been developed that identified which patients will benefit most from participating in a clinical trial. US researchers developed TrialTranslator, a machine learning framework to ‘translate’ clinical trial results to real-world populations. By emulating a number of landmark cancer clinical trials using real-world data, they were able to recapitulate actual clinical trial findings, helping them to identify which distinct groups of patients may respond well to treatments in a clinical trial, and those that may not.

The 11 trials selected investigated anticancer regimens considered standard of care for the four most prevalent advanced solid malignancies in the US: advanced non-small cell lung cancer, metastatic breast cancer, metastatic prostate cancer and metastatic colorectal cancer. Their analysis revealed that patients with low- and medium-risk phenotypes, which are machine learning-based traits used to assess the underlying prognosis of a patient, had survival times and treatment-associated survival benefits similar to those who were observed in the randomised controlled trials.

In contrast, those with high-risk phenotypes showed significantly lower survival times and treatment-associated survival benefits compared to the randomised controlled trials.