More than 21 million people in Africa are infected with the threadworm Onchocerca volvulus, the causative agent of river blindness, also known as onchocerciasis. Approximately one in ten of those affected goes blind. Parasitologists at the University Hospital Bonn, Germany, are looking for new, more effective tools against the insidious parasite.
Scientists want to develop a method through which artificial intelligence (AI) evaluates tissue samples from patients under the microscope. The aim is to reduce the time required for diagnosis and establish a more objective standard for analysis.
The black fly bite mainly infects people in sub-Saharan Africa with the larvae of the threadworm Onchocerca volvulus - the trigger of river blindness, or onchocerciasis. First, the larvae grow into sexually mature worms, which prefer to live in knots under the skin. A female, which can grow up to 60 centimeters, produces up to 1,000 microfilariae per day. These microfilariae spread via the lymph channels from the skin to the eye. There, the cornea becomes inflamed and its demise leads to blindness. The "baby worms" are also picked up by a new blackfly during a bite to the infected person and spread further.
The WHO recommends treatment of all persons in affected areas with ivermectin, which kills the worms descendants, but is not able to damage the adult worm. Thus, despite this therapy, new generations of microfilaria can emerge relatively quickly, which are responsible for further transmission by mosquitoes and for the symptoms of impaired vision and skin inflammation. Therefore, treatment must be carried out over many years in order to eradicate the disease sustainably. "It is important to find substances that kill adult worms directly," says Prof. Dr. Achim Hörauf, head of the Institute of Medical Microbiology, Immunology and Parasitology (IMMIP) at the University Hospital Bonn.
A key in the search for better treatments could lie in a symbiosis discovered by Prof. Hörauf. The threadworm Onchocerca volvulus has been harboring bacteria that it needs to survive for millions of years. If these bacteria die, the parasite dies sooner or later. "Antibiotics with spectrum effects specifically directed towards these bacteria open a chance to permanently prevent the transmission of river blindness," said Prof. Hörauf.
Although the antibiotic doxycycline, the prototype of an active substance discovered by Hörauf's group, is used worldwide for the treatment of filaria in hospitals, it is not well suited for mass treatment in remote areas with poor infrastructure. The antibiotic needs to be taken daily for four to six weeks to be effective. The Bonn-based parasitologists are therefore continuing their worldwide research alliance to find faster-acting alternatives with shorter therapy times that will finally kill the threadworm Onchocerca volvulus.
In order to evaluate the success of new treatments, the parasitic nodes must be removed from the patient's skin and analyzed. Experts use microscopes to assess the sex, vitality, embryonic development of the nematodes, and the presence of symbiotic bacteria on the basis of thin incisions. "This process is very time-consuming and depends directly on the experience of the persons making the judgment", explained Dr. Ute Klarmann-Schulz. There is a high motivation behind the task of her interdisciplinary working group at IMMIP to optimize this analysis process. For this, they are turning into artificial intelligence (AI).
Dr. Daniel Kühlwein, a member of the AI Centers of Excellence at the global consulting company Capgemini, is an expert in the field of artificial intelligence. With his support, the working group led by Dr. Klarmann-Schulz at the University Hospital Bonn plans to develop an AI system that will automate the evaluation of histological sections. They are using existing deep learning models for object recognition. "The pre-trained AI systems can basically already, for example, recognize lines," explains Dr. Kühlwein.
The AI system learns to recognize and evaluate worms from previous microscope images of histological sections, already carried out by the Bonn-based parasitologists and their African partners in numerous clinical studies. The scientists want to reduce the time required for the evaluation and establish an objective standard for the analysis.