- Researchers have designed a simple and inexpensive experimental test to diagnose cancer.
- All this test requires is a small, dried blood spot.
- The researchers found that the sensitivity was 82% to 100% and it took only a few minutes.
- This approach may be particularly useful for people in low-income countries.
Chinese scientists have developed a dried blood spot test to diagnose cancer. The new study focused on pancreatic, stomach, and colorectal cancers.
The system uses a type of artificial intelligence (AI) called machine learning, which makes it significantly faster and more cost-effective than current whole blood tests and other diagnostic techniques.
According to their recent paper,
Today, virtually everything, for better or worse, is powered by AI. But while AI may be taking away people's jobs and creating terrible “art,” its power can also be used for good.
Medical researchers are busy leveraging cutting-edge AI to help understand and manage diseases.
Part of this journey of discovery is identifying innovative ways to diagnose medical conditions. This is important work. In general, early detection of the disease leads to better outcomes.
Because some cancers are difficult to diagnose and reliable blood markers don't exist, some experts are studying whether AI can help.
Currently, accurate diagnosis often requires expensive facilities, equipment, and transportation. For example, whole blood requires temperature-controlled storage during transportation, which comes at a cost.
“Cost-effectiveness is key in disease screening,” the authors of the new paper write.
These costs place an additional burden on developing countries and poor regions, where many cancer cases are missed due to lack of access to health care. For this reason, some experts believe that by 2030,
Some diseases may have already occurred
However, the most common diagnostic markers of cancer, such as microRNAs and proteins, are more easily destroyed during drying. Also, the small amount of blood drawn for a blood spot test is generally not enough to diagnose cancer.
Today's medical news We spoke to Dr Joel Newman, consultant haematologist and clinical lead of pathology at Eastbourne District General Hospital, who was not involved in the study.
He spoke about the difficulty of detecting cancer using blood spots:
“We have to find something that can be detected in trace amounts of blood and that is reproducibly associated with cancer. This may lead to further investigation and concern.”
Recent studies have adopted innovative approaches. The company's technology detects metabolic changes associated with cancer, rather than focusing on existing cancer markers. The authors explain that this is because “most metabolites remain stable on dry patches.”
They believe that a cost-effective, AI-powered rapid dry blood spot test for cancer may be a viable option. Their experimental tests rely on a technique called nanoparticle-enhanced laser desorption ionization mass spectrometry (NPELDI MS).
Using an experimental test, researchers showed that dried blood spots can be used to diagnose cancer with a sensitivity of 82-100%. This is better than current whole blood tests, which are said to have a sensitivity of 50-80%.
As part of their study, they exposed bloodstain tests to various temperatures and environmental conditions. They discovered that the sample was still viable. By comparison, many standard whole blood tests require very low temperatures to prevent spoilage.
Additionally, whereas standard tests rely on expensive and time-consuming sample preparation, blood spot tests can be analyzed directly, saving time and money. Similarly, blood spot tests require less physical space, making them easier and cheaper to transport.
This approach may also be more secure. The process of drying bloodstains inactivates some harmful pathogens that remain active in whole blood.
As part of their analysis, the authors assessed how many more cancers could be detected using the dried bloodspot system if it were widely implemented.
Currently, colorectal cancer screening relies primarily on colonoscopy, pancreatic cancer requires computed tomography (CT scan), and gastric cancer is diagnosed using gastroscopy. will be done. These are all expensive techniques that require skilled medical staff.
In contrast, the authors explain that their approach “can achieve high levels of diagnostic accuracy even when performed by local healthcare workers in resource-limited clinical settings.”
They estimate that undiagnosed cancer cases in underserved populations range from 34.56% to 84.30%.
However, the authors estimate that if this new approach to population-based cancer screening were implemented in rural China, the proportion of undiagnosed cases would drop by:
- 84.30% to 29.20% for colorectal cancer
- 34.56% to 9.30% for pancreatic cancer
- 77.57% to 57.22% for gastric cancer
MNT We spoke with Anton Bilchik, MD, a surgical oncologist, medical director, and director of the gastrointestinal-hepatobiliary program at Providence St. John's Cancer Institute in Santa Monica, California, who was not involved in the study.
We asked whether these results were surprising.
“We were very surprised by these findings: a reduction in the estimated proportion of undiagnosed cancer cases. […] This is especially surprising in less developed regions. ”
To avoid missed diagnoses, blood spot testing must be rolled out to the entire population, meaning cost is a key factor.
The authors provide one example of how their technology can save money. He can send an envelope containing 100 dried filter paper bloodstain tests from Gansu, one of China's least developed provinces, to Shanghai in just 1.5 days. Shipping is only $0.32.
In comparison, a box of 100 liquid serum specimens, which is seven times larger, takes four to five days, requires cold chain transportation, and costs $3.42.
Finding cost-effective and accurate ways to diagnose cancer is of great interest, but there is much work to be done before this technology can be introduced into the clinic.
The study tested the AI model only on hundreds of samples taken from people known to have cancer.
Before this technology becomes mainstream, scientists need to test it on thousands of people in the real world. However, Bilchik remains optimistic about the future.
“The results need to be validated and prospectively studied, as this could change clinical practice and have a major impact on diagnosing overlooked cancers.”