Equipped with a strong team of machine learning engineers and medical experts from prestigious hospitals, BioMind™ envisions to scale healthcare specialist expertise globally using AI so that patients around the world can benefit from accurate diagnosis, personalised treatments, fast access and affordable healthcare solutions. BioMind™ is an Artificial Intelligence (AI) company that specialises in creating predictive applications to assist doctors in their daily work. These include building state-of-the-art AI technologies to help hospitals diagnose and treat medical conditions.
On 22 December 2017, they launched the world’s first AI research center for neurological disorders called “CHAIN”. CHAIN is the world’s largest and the most comprehensive AI research center of its kind and is featured in over 60 global media including Channel News Asia, The Straits Times and CCTV. CHAIN covers a wide spectrum of AI research areas including diagnosis, treatment, patient rehabilitation and many others in the neurological space.
One of the products at the forefront of BioMind™’s offering is the world’s first CE-certified AI application for brain diagnosis. It is a state-of-the-art diagnostic support system that uses deep learning technology to analyse MRI and CT images. It automatically recommends a diagnosis and report for doctors to review – within seconds. BioMind™ is jointly developed, comprised of medical specialists and deep learning experts. Its capabilities include image segmentation, prediction, analysis and 3D reconstruction of abnormalities. The application can analyse neurological disorders such as brain tumours, vascular diseases and stroke-related conditions.
Inevitable human weaknesses can be compensated by the strengths of technology. Doctors having to deal with voluminous work; both clinical and administrative tasks can result in long diagnosis times and fatigue. This causes delayed service delivery, affects consistent judgement and blind spots are not uncommon to experience. For example, according to the British Medical Journal, in the USA alone 12 million people suffer from misdiagnoses, costing the country billions of dollars; AI can help to change this.
In the radiology sector, BioMind™ uses deep learning (an advanced AI technique) to learn how to detect and analyse conditions by training on a large plethora of past medical scans corroborated by biopsy results. It further combines the experience of medical experts. The outcome: it is not only able to screen brain abnormalities in medical scans but also propose plausible conditions that the patient is suffering from. Clinically, this has proven to achieve much higher accuracy than the average radiologist. The entire process from analysing to generating reports can be completed within seconds, as opposed to the usual time needed by a human doctor, thus improving doctors’ efficiency, accuracy and consistency in diagnosis.
“I am convinced that radiologists will embrace AI to help us manage ‘routine’ tasks quickly and efficiently, thus giving us more time to focus on things that really matter. As shown in CHAIN, AI systems (BioMind) offer a unique opportunity to make a new beginning, to re-invent what we do, to boost productivity and accuracy. I am convinced that AI can take over time-consuming routine tasks, freeing up time and resources to focus our attention on individual patients, and, thereby, moving from volume-based radiology towards value-based radiology. Take charge of your own future, and embrace it with confidence, courage and determination.”
– Dr Paul Parizel, former President of the European Society of Radiology
Medical images make up more than 80% of all medical data. The number of radiologists is increasing at a yearly rate of 3-5%, whereas the number of medical images is increasing at a much faster yearly rate of 40%. All patients would love to be attended to by experienced doctors. How can we expand this pool to meet the urgent need?
BioMind™ harnesses decades of knowledge and rapidly makes intelligent predictions to achieve similar results to those of senior doctors. Thus, their technology can be deployed in hospitals and used as a tool to assist radiologists in their diagnosis, significantly levelling up both productivity gains and accuracy in judgement. It can also be used as an effective training tool to quickly level up junior doctors. Such tools can be scaled up for deployment not just around us, but also in faraway regions, extending the reach and reliability of high-quality diagnosis to a large segment of the population.
As Dr. Gauden Galea from the World Health Organisation puts it, “AI tech like BioMind could aid doctors in rural areas, enabling their residents to access quality healthcare. Take this technology and deliver it to a rural health district and you’ve suddenly got a magical health enhancement that gives doctors there the ability to diagnose” (Source: The Straits Times, 2018).
BioMind™ also has the ability to continuously self-learn and improve through cycles of predictions and doctors’ revisions. This means that their products can take on a large spectrum of conditions and can be upgraded to analyse other body systems, creating a multi-specialist assistive role to help doctors across a variety of disciplines.
The future economy would be an environment where humans and AI co-exist. Rather than a disruption, the combined strengths can significantly improve the quality of life for both patients and service providers. AI closes the gap of a severe shortage of medical professionals and provides insights to empower doctors’ judgement. For example, BioMind™ highlights areas on image scans where the suspected condition resides, thus reducing blind spots which otherwise would have gone unnoticed. It further generates an editable report automatically and allows doctors to review and confirm. As the entire application is integrated into the existing workflow within a hospital’s environment, the user experience is seamless and secure. The future belongs to those who prepare for it.
BioMind™ will be part of the ECR 2019 Artificial Intelligence Exhibition (AIX) in hall X1, booth AI-21.
* Contents provided by BioMind and adapted by the ESR office