Blood samples from patients infected with a parasitic worm that causes schistosomiasis contain hidden information that marks different stages of the disease.
In recently published research, the team used machine learning to uncover this hidden information and improve early detection and diagnosis of infection.
The parasite that causes schistosomiasis completes its life cycle in two hosts – first in snails and then in mammals such as humans, dogs and mice. The eggs of freshwater worms enter human hosts through the skin and travel through the body, affecting multiple organs, including the liver, intestine, bladder, and urethra.
When these larvae reach the blood vessels that connect the intestines to the liver, they turn into adult worms. They then release eggs that are excreted when the infected person defecates, continuing the cycle of transmission.
Because diagnosis is currently based on detecting eggs in feces, doctors usually miss the early stages of infection. By the time the eggs are detected, patients have already reached an advanced stage of the disease.
Because diagnosis rates are poor, public health officials are mass-administering the drug praziquantel to populations in affected regions. However, praziquantel cannot eliminate juvenile worms in the early stages of infection, nor can it prevent reinfection.
The parasite completes its life cycle in two hosts
The study provides a clear path to improving early detection and diagnosis by identifying hidden information in the blood that signals early, active infection.
The body reacts to a schistosomiasis infection by mounting an immune response involving several types of immune cells as well as antibodies that specifically target molecules secreted by or present on the worms and eggs.
The study introduces two ways to detect certain antibody characteristics that signal early infection. The first is a test that captures a quantitative and qualitative profile of the immune response, including various classes of antibodies and characteristics that dictate how they communicate with other immune cells. This allowed us to identify specific facets of the immune response that distinguish uninfected patients from patients with early- and late-stage disease.
Second, a new machine learning approach was developed that analyzes antibodies to identify latent characteristics of the immune response related to disease stage and severity.
The model was trained on immune profile data from infected and uninfected patients, and the model was tested on data not used for training and on data from another geographic location. Not only biomarkers for the disease have been identified, but also the potential mechanism underlying the infection.
Information hidden in blood
Schistosomiasis is a neglected tropical disease that affects more than 200 million people worldwide, causing 280,000 deaths annually. Early diagnosis can improve the effectiveness of treatment and prevent serious illness, he writes ScienceAlert.
Furthermore, unlike many machine learning methods that are black boxes, the approach is also interpretable. This means it can provide insights into why and how the disease develops, beyond simply identifying disease markers, guiding future strategies for early diagnosis and treatment.
The signatures of schistosomiasis infection we identified remain stable in two geographic regions on two continents. Future research could explore how well these biomarkers apply to other populations.
Furthermore, the paper identifies a potential mechanism underlying disease progression. A certain immune response against a specific protein on the surface of the worms was found to signal an intermediate stage of infection.
Understanding how the immune system responds to this little-studied antigen could improve diagnosis and treatment.
We recommend you also read:
They ate bear meat, and then were diagnosed with roundworms
Man Woke Up With Worms In His Brain After Consuming A Lifetime Of ‘Unfried’ Bacon
Chernobyl worms are not affected by radiation at all
Scientists have created eco-friendly materials inspired by worms
Source: www.descopera.ro
