Artificial intelligence (AI) is already showing diagnostic abilities at similar levels of accuracy to experienced healthcare professionals. With further improvements in AI technology in the future, could AI surpass doctors in terms of accuracy?
Such an eventuality could potentially — if the required financial commitment was made — go a long way towards easing the considerable burden placed on India’s healthcare system by the lack of healthcare professionals.
An AI system developed at the University of California, Los Angeles (UCLA) demonstrated comparable results with experienced doctors in reading magnetic resonance imaging (MRI) scans. The AI system — called FocalNet — is a convolutional neural network that is designed to detect prostate cancer lesions. Furthermore, the AI programme uses the data from the MRI scans to predict the aggressiveness of the tumour using the Gleason score, a grading system used to determine how aggressive the cancer is and what the best course of treatment will be.
Prostate cancer consistently ranks as one of the ten most common cancers in India, with it being the second most common cancer in men worldwide. In India incidence rates vary between roughly three and nine percent depending on region, with urban metropolises typically seeing far higher rates than rural areas.
AI in this instance could remove the human aspect of the diagnosis procedure, freeing hands to fulfill other roles such as treatment or surgeries. Such a tool could allow other staff, without the need of years of training to fill these roles.
Indian researchers also share success stories in the use of AI to diagnose medical conditions. Researchers at the National Institute of Mental Health and Neurosciences (NIMHANS) have developed a means by which to determine schizophrenia in a patient with a high degree of accuracy, by using AI to analyse trends in brain activity.
Lack of doctors and other qualified medical staff is one of the foremost issues reducing the efficiency and efficacy of the Indian medical system. Many areas lack the necessary staff levels and resources to perform many services, from specialised care across a range of disciplines to performing surgeries because of a lack of trainees.
While AI itself is not at a stage where it can perform a surgery, or provide a counselling service, the aforementioned studies and trials — along with many other examples in recent years — are showing that it may well be able to replace the need for trained medical staff in the role of diagnosis. This is not to say that India should forego the training of additional staff to fill the void, but, at the very least, AI could help to shoulder the burden.