Artificial intelligence (AI), machine learning, deep learning, semantic computing – these terms have been slowly permeating the medical industry for the past few years, bringing with them technology and solutions that are changing the shape of healthcare. Each of these technologies is connected, each one providing something different to the industry and changing how medical professionals manage their roles and patient care. While AI is perhaps the most well-known of the technology terms, deep learning in healthcare is a branch of AI that offers transformative potential and introduces an even richer layer to medical technology solutions.
Deep learning provides the healthcare industry with the ability to analyze data at exceptional speeds without compromising on accuracy. It’s not machine learning, nor is it AI, it’s an elegant blend of both that uses a layered algorithmic architecture to sift through data at an astonishing rate. The benefits of deep learning in healthcare are plentiful – fast, efficient, accurate – but they don’t stop there. Even more benefits lie within the neural networks formed by multiple layers of AI and ML and their ability to learn. Yes, the secret to deep learning’s success is in the name – learning.
Deep learning uses mathematical models that are designed to operate a lot like the human brain. The multiple layers of network and technology allow for computing capability that’s unprecedented, and the ability to sift through vast quantities of data that would previously have been lost, forgotten or missed. These deep learning networks can solve complex problems and tease out strands of insight from reams of data that abound within the healthcare profession. It’s a skillset that hasn’t gone unnoticed by the healthcare profession.
In 2018, IDC predicted that the worldwide market for cognitive and AI systems would reach US77.6 billion by 2022. Towards the end of 2019, IDC predicted it would reach $US97.9 billion by 2023 with a compound annual growth rate (CAGR) of 28.4%. The market is seeing steady growth thanks to the ubiquity of the technology and the potential it has in transforming multiple industries, not just healthcare.
Although, deep learning in healthcare remains a field bursting with possibility and remarkable innovation. Organizations have tapped into the power of the algorithm and the capability of AI and ML to create solutions that are ideally suited to the rigorous demands of the healthcare industry.
A History of Deep Learning in Healthcare
Deep learning in healthcare has already left its mark. Google has spent a significant amount of time examining how deep learning models can be used to make predictions around hospitalized patients, supporting clinicians in managing patient data and outcomes. The blog post, entitled ‘Deep learning for Electronic Health Records’ went on to highlight how deep learning could be used to reduce the admin load while increasing insights into patient care and requirements. This is an optimal use for deep learning within healthcare due to its ability to minimize the admin impact while allowing for medical professionals to focus on what they do best – health.
In the UK, the NHS has committed to becoming a leader in healthcare powered by deep learning, AI and ML. The healthcare provider has recognized the value that this technology brings to the table. Certainly for the NHS, beleaguered by cost cutting, Brexit and ongoing skill shortages, the ability to refine patient care through the use of intelligent analyses and deep learning toolkits is alluring. An investment into deep learning solutions could potentially help the organization bypass some of the legacy challenges that have impacted on efficiencies while streamlining patient care. It can also provide much needed support to the healthcare professionals themselves. In August 2019, Boris Johnson put money behind the deep learning in healthcare initiatives for the NHS to the tune of £250 million, cementing the reality that AI, ML and deep learning would become part of the government institution’s future.
While there are criticisms around the potential implementation of AI at the NHS, a recent report released by the Lancet Digital Health Journal did a lot for its credibility. The report found that the ‘performance of deep learning models to be the equivalent to that of health-care professionals’. A remarkable statement that did come with some caveats, but ultimately emphasized how deep learning in healthcare could benefit patients and health systems in clinical practice.
Deep learning applications in healthcare have already been seen in medical imaging solutions, chatbots that can identify patterns in patient symptoms, deep learning algorithms that can identify specific types of cancer, and imaging solutions that use deep learning to identify rare diseases or specific types of pathology. Deep learning has been playing a fundamental role in providing medical professionals with insights that allow them to identify issues early on, thereby delivering far more personalized and relevant patient care.
Is Deep Learning the Future of Healthcare?
The future of healthcare has never been more exciting. Not only do AI and ML present an opportunity to develop solutions that cater for very specific needs within the industry, but deep learning in healthcare can become incredibly powerful for supporting clinicians and transforming patient care.
In a recent book published by Dr Eric Topol entitled ‘Deep Medicine’, the cardiologist and geneticist emphasizes how deep learning in healthcare could ‘restore the care in healthcare’. In his interview with The Guardian, he eloquently describes precisely why deep learning is of immense value to the healthcare profession.
This is the precise premise of solutions such as Aidoc. It’s designed not as a tool to supplant the doctor, but as one that supports them. Ultimately, deep learning is not at the point where it can replace people, but is does provide clinicians with the support they need to really thrive within their chosen careers. Aidoc, for example, has developed algorithms that expedite patient diagnosis and treatment within the radiology profession. The company has received several accreditations and approvals from the Food and Drug Administration, the European Union CE and the Therapeutic Goods of Australia (TGA) for its specialized algorithms. These algorithms include intracranial hemorrhage, pulmonary embolism and cervical-spine fracture and allow for the system to prioritize those patients that are in most need of medical care. This targeted form of AI and deep learning helps the overburdened radiologist by flagging items that are of concern and thereby allows the healthcare professional to direct patients with greater control and efficiency. It also reduces admin by integrating into workflows and improving access to relevant patient information.
Does all this mean that deep learning is the future of healthcare? The answer is yes. Ultimately, the technology that supports the medical profession is becoming increasingly capable of integrating AI-based algorithms that can streamline and simplify complex data analysis and improve diagnosis. It can be trained and it can learn. It can reduce reporting delays and improve workflows. And it can be used to shift the benchmarks of patient care in a time and budget strapped economy.
Deep learning in healthcare will continue to make inroads into the industry, especially now that more and more medical professionals are recognizing the value it brings. This technology can only benefit from intense collaboration with industry and specialist organizations. It needs to remain agile and able to adapt to ensure that it always remains relevant to the profession.
Aidoc has already seen several successful implementations of its deep learning radiology technology, providing increased clinician support and workflow optimization. Abnormalities are quickly identified and prioritized and radiologist workloads balanced more effectively. The profession is one of the most pressured and often radiologists work 10-12-hour days just to keep up with punishing workloads and industry requirements. With Aidoc, they can spend more time working with patients and other professionals while still getting rich analysis of medical imagery and data.
While deep learning in healthcare is still in the early stages of its potential, it has already seen significant results. The benefits it brings have been recognized by leading institutions and medical bodies, and the popularity of the solutions has reached a fever pitch. From only one or two stands at the RSNA conference in 2017, AI and deep learning in healthcare solutions have their own floor, display area and presentations. The future still lies in the hands of the medical professionals, but they are now being supported by technology that understands their unique needs and environments and reduces the stresses that they experience on a daily basis.