The Google Brain team uses artificial intelligence to predict the death risk among hospital patients. The neural network collects information for predictions, as well as links back the predictions to the records from which it draws conclusions.

United States: The Google Brain team has been using artificial intelligence to predict the death risk among hospital patients and the results have surprised the medical community by showing that a high degree of accuracy than a hospital’s in-house warning system. The Medical Brain team could possibly help different companies in the healthcare business.

The technology Giant’s health-care potential of neural networks is a form of artificial intelligence software which utilizes the available data to automatically learn and improve. The tool that can forecast multiple patient outcomes like the duration of patient’s stay in hospitals, chances of re-admission and the probabilities of death.

Google's team published its findings in a paper on Nature Titled Scalable and Accurate Deep Learning with Electronic Health Records. In case study of a woman with metastatic breast cancer, Google used its algorithm and 24 hours after she was admitted, Google predicted a 19.9 percent likelihood of her dying within the hospital, which is completely different from the 9.3 percent estimate that the hospital’s augmented Early Warning Rating (aEWR) predicted. The patient died within 10 days of admission.

The medical experts seem impressed with Google's systems as they can go through the data that was previously out of reach for example notes in PDFs or scribbled on old charts. Manual reach takes a huge amount of time, and the hospital's internal systems cannot sift through and comprehend the information.

The neural network not only collects all the information for predictions, but also links back the predictions to the records from which it drew its conclusions from, thus making it more credible. It has proven to be way faster and more accurate than existing techniques.

In the healthcare sector, most of the information is still being entered manually. Google’s approach however can surpass everything, as machines will learn to parse data on their own. Using AI in healthcare however remains a major challenge as it might create a fear of machine learning predicting or could having an incredible amount of say over who will get what care and will die when.

According to TechSci Research, Google’s move is anticipated to revolutionize the healthcare sector in predicting patient death and likeliness of discharging with the use of Artificial Intelligence. The move is anticipated to act as a huge driver for the Artificial Intelligence Market as healthcare turns into one of the major application area for AI. Moreover, factors such as increasing venture capital investments, growing technological advancements and booming healthcare industry is expected to drive the global artificial intelligence market in the coming years. Artificial Intelligence finds it uses in multiple industries like automobile, healthcare and pharmaceuticals, finance, consumer electronics, etc. Moreover, rising acquisitions of start-ups by leading players such as Google, Samsung, Microsoft and others is driving the global artificial intelligence market. Furthermore, increasing research & development activities are also expected to aid the penetration of artificial intelligence into newer applications in next five years.

According to the recently published report by TechSci Research, “Global Artificial Intelligence Market By Application (Image Recognition, Natural Language Processing, Speech Recognition, etc.), By End User (Consumer Electronics, BFSI, etc.), By Region, Competition Forecast & Opportunities, 2012 – 2022”, the global market of artificial intelligence is anticipated to grow at a CAGR of over 60% during 2017 – 2022. On the basis of application, global artificial intelligence market has been broadly segmented into image recognition, natural language processing, speech recognition, gesture control & others. Among these categories, image recognition dominated global artificial intelligence market in 2016, and the segment is expected to maintain its dominance over the next five years as well.

Please follow our LinkedIn and Twitter pages to get live updates on market research insights and analysis.