Artificial Intelligence Improving How We Diagnose Cancer – Technology Networks

The Journal Metabolism Clinical and Experimental mentions in a recent review that the use of artificial intelligence (AI) in medicine has come to cover such broad topics from informatics to the application of nanorobots for the delivery of drugs. AI has come a long way from its humble beginnings. With the advanced development of AI systems and machine learning, more significant medical applications for the technology are emerging. According to Cloudwedge, FocalNet, an AI system recently developed by researchers at UCLA, can aid radiologists and oncology specialists in diagnosing prostate cancer.

According to UK Cancer Research Magazine, over 17 million cancer cases were diagnosed across the globe throughout 2018. The same research suggests there will be 27.5 million new cancer cases diagnosed each year by 2040.

Although these recent statistics seem discouraging, if we compare diagnosis and treatment data, patient outcomes have improved significantly compared to a few decades ago in the 1970s, less than a quarter of people suffering from cancer survived. Today, thanks to progress in the field, survival rates have significantly improved. AI is a part of that progress.

As early as 1988, The Annals of Internal Medicine mentioned that conventional computer-aided diagnoses were limited, and to overcome the shortfalls, researchers turned to artificial intelligence. However, because of the limited technology available at the time, the system had to be manually trained by medical personnel, and it's likely that this training only incorporated the personal experience of a handful of doctors. Despite these limitations, this set the stage for the use of neural networks in today's medical field.

These neural networks are the most basic form of artificial intelligence. Machine learning is the branch of AI that is focused on teaching machines to be better at tasks iteratively. By developing algorithms that can help systems determine where they were right and where they were wrong automatically, the system could theoretically learn generations worth of data in a short space of time. Despite the theoretical soundness of the technique, and the use of complex algorithms that can recognize behaviors and patterns, AI technology has only recently been able to offer the human-like insight and determinations required for it to excel in the medical field.

Nature reports that the New York Genome Center relies on a unique piece of software for screening its patients for glioblastoma - an artificial intelligence system developed by IBM called Watson. Watson gained fame in 2011 thanks to its excellent performance in a televised game show, but the AI is now being to put to work aiding the diagnostic field. However, the system still needs more data to be trained to function appropriately, and as yet, AI isn't able to teach itself what is correct and what isn't. The goal for IBM's Watson is to be able to read patient files and then access the relevant information needed to give the most accurate diagnosis and treatment plan.

While it has the ability to understand the meaning of language and can develop on its own via machine learning, Watson still has a way to go before it can be introduced into the real world as an effective assistant. But even today, AI has shown in potential in some specialized medical tasks, with human help. According to a recent Northwestern University study, AI can outperform radiologists at cancer screening, especially in patients with lung cancer. The results show that using AI cut false positives by 11%. The medical field might not be so far away from having its own well-trained AI delivering proper diagnoses. It all depends on how fast AI technology advances and how quickly it can learn to diagnose like a human physician.

Go here to read the rest:

Artificial Intelligence Improving How We Diagnose Cancer - Technology Networks