The research team led by the Max Planck Institute has developed an artificial intelligence method to increase the percentage of success in diagnosing psychosis.
Psychosis, which affects more than 50 million people around the world and usually occurs in men and women between the ages of 12 and 29, can be expressed as a symptom of a range of mental illnesses rather than a medical condition in itself. Understanding the symptoms of psychosis, which we can define as a symptom rather than a disease in itself, is a very difficult process.
In the light of current medical methods, the complexity of the diagnostic methods applied for high-risk patients and the need for professional support for the process in question is actually a luxury for many people living in the world. The researches revealed show that 22% of those diagnosed with psychosis actually go through this process.
The research team led by the Max Planck Institute, which wants to increase the percentage of predictions for the onset of psychosis in high-risk patients, has developed a machine learning method that can be used in research conducted in this context. Investigating the methods used by expert personnel in this field to diagnose psychosis, the researchers blended the data they obtained with the machine learning method and enabled the system to make different inferences.
Stating that the machine learning method cannot replace professional medical experts, the research team stated that with the developed method, the decision-making process can be accelerated and experts can be advised for advanced examinations.
The performance of the developed machine learning method close to that of humans is a source of hope for many patients. Because one of the biggest advantages of the method lies in the fact that personnel working in health institutions that do not specialize in psychosis can make diagnoses with high accuracy with machine learning assisted analysis methods.