Contributed: Nine revolutionary ways AI is advancing healthcare
Researchers at SEAS and MGH’s Radiology Laboratory of Medical Imaging and Computation are at work on the two problems. The AI-based diagnostic system to detect intracranial hemorrhages unveiled in December 2019 was designed to be trained on hundreds, rather than thousands, of CT scans. Though excitement has been building about the latest wave of AI, the technology has been in medicine for decades in some form, Parkes said. As early as the 1970s, “expert systems” were developed that encoded knowledge in a variety of fields in order to make recommendations on appropriate actions in particular circumstances. Among them was Mycin, developed by Stanford University researchers to help doctors better diagnose and treat bacterial infections. Though Mycin was as good as human experts at this narrow chore, rule-based systems proved brittle, hard to maintain, and too costly, Parkes said.
Institutions will have to develop teams with expertise in partnering with, procuring, and implementing AI products that have been developed or pioneered by other institutions. Orchestrating the introduction of new specializations coming from data science and engineering within healthcare delivery will become a critical skill in itself. There will be an urgent need for health systems to attract and retain such scarce and valuable talent, for example, by developing flexible and exciting career paths and clear routes to leadership roles. Ultimately respondents would expect to see AI as an integral part of the healthcare value chain, from how we learn, to how we investigate and deliver care, to how we improve the health of populations. We believe that AI has an important role to play in the healthcare offerings of the future.
Tackling healthcare’s biggest burdens with generative AI
Kontos and her team are testing ways AI can be used to identify women who are at high risk for developing breast cancer. They’re using AI to analyze different features in mammograms—X-ray pictures of the breast—such as breast density. Women who have a higher risk of breast cancer can take preventative steps, like more frequent screenings. Medical science has improved rapidly, raising life expectancy around the world, but as longevity increases, healthcare systems face growing demand for their services, rising costs and a workforce that is struggling to meet the needs of its patients. The unique selling point for these recent innovations is that they allow remote video conversations between the patient and the physician.
We describe a non-exhaustive suite of AI applications in healthcare in the near term, medium term and longer term, for the potential capabilities of AI to augment, automate and transform medicine. Many AI systems are initially designed to solve a problem at one healthcare system patient population specific to that location and context. Scale up of AI systems requires special attention to deployment modalities, model updates, the regulatory system, variation between systems and reimbursement environment.
Predictive analytics and risk assessment
Given that lung cancer is the biggest cause of cancer mortality worldwide, scientists and doctors have designed an AI tool that can accurately detect early-stage lung cancer to speed up diagnosis and set patients enroute for treatment. The same algorithms can examine in detail the available scientific literature and support the identification of genetic biomarkers that assess disease, enabling more effective clinical trials and shorter periods to put treatments on the market. For example, Theator’s Surgical Intelligence Platform analyzes thousands of hours of surgical videos, structures data from hundreds of procedures and helps surgeons understand what went right and what did not during operations. This work is used by surgeons to improve their skills and techniques, help save lives and achieve better health outcomes for the patients. One striking example is Google’s DeepMind, which developed an AI system capable of detecting eye diseases, including diabetic retinopathy, with an accuracy rate comparable to expert human ophthalmologists. This innovation not only saves valuable time but can also prevent blindness by catching diseases in their early stages.
This will require AI to be embedded more extensively in clinical workflows, through the intensive engagement of professional bodies and providers. It will also require well designed and integrated solutions to use existing technologies effectively in new contexts. This scaling up of AI deployment would be fuelled by a combination of technological advancements (e.g., in deep learning, NLP, connectivity etc.) and cultural change and capability building within organizations. Therefore, they can make predictions for efficient and personalized treatment strategies. Personalized medicine, as an extension of medical sciences, uses practice and medical decisions to deliver customized healthcare services to patients . The healthcare ecosystem is realizing the importance of AI-powered tools in the next-generation healthcare technology.
Connecting People With Care
Intelligent robots are also used as transporting units and recovery and consulting assistance. However, these machines show great potential in changing the way medical procedures are performed. Back-office work and administrative functions, such as finance and staffing, provide the foundations on which a hospital system runs.
ICD is managed and published by the WHO and contains codes for diseases and symptoms as well as various findings, circumstances, and causes of disease. Here is an illustrative example of how an NLP algorithm can be used to extract and identify the ICD code from a clinical guidelines description. Unstructured text is organized into structured data by parsing for relevant clauses followed by classification of ICD-10 codes based on frequency of occurrence. The NLP algorithm is run at various thresholds to improve classification accuracy and the data is aggregated for the final output (Fig. 2.6
). Gamification refers to utilization of game design elements for nongame-related applications.
Caption Health is improving patient care by making ultrasound technologies more accessible, with a focus on early disease detection. It has taken time — some say far too long — but medicine stands on the brink of an AI revolution. In a recent article in the New England Journal of Medicine, Isaac Kohane, head of Harvard Medical School’s Department of Biomedical Informatics, and his co-authors say that AI will indeed make it possible to bring all medical knowledge to bear in service of any case. Those unwelcome words sink in for a few minutes, and then your doctor begins describing recent advances in artificial intelligence, advances that let her compare your case to the cases of every other patient who’s ever had the same kind of cancer. She says she’s found the most effective treatment, one best suited for the specific genetic subtype of the disease in someone with your genetic background — truly personalized medicine. Extracting the greatest value from the gen-AI opportunity will require broad, high-quality data sets.
However, in order to promote self-management and improve the outcomes for patients, a patient-centric personal health record should be implemented. The goal is to allow ample freedom for patients to manage their conditions, while freeing up time for the clinicians to perform more crucial and urgent tasks. For others, these immersive technologies could help cope with the pain and the discomfort of their cancer or mental health condition.
AI and Clinical Practice—the Learning Health System and AI
Hospitals and other health care facilities collect a lot of information from their patients. AI medication systems can browse through these archives to assist doctors in formulating precision medication for individual patients. Effective treatment of cancer heavily depends on early detection and preemptive measures. Certain types of cancer, such as different types of melanoma, are notoriously difficult to detect during the early stages.
Et al. (2020), automated AI diagnosis of skin lesions is ready to be tested in clinical environments and has the potential to provide diagnostic support and expanded access to care . A meta-analysis of 70 studies found the accuracy of computer-aided diagnosis of melanoma to be comparable to that of human experts . Interaction with the surroundings allowed us to gain further understanding of the world and provided us with the much-needed experience.
AI can analyze medical images, such as X-rays or MRIs, and assist radiologists in detecting abnormalities. This can improve the accuracy of diagnoses and reduce the likelihood of missed diagnoses. AI can also help medical professionals make more informed decisions regarding treatment plans and provide personalized care by taking into account a patient’s medical history and genetic makeup. Remote patient care uses AI-powered technology to provide healthcare services and monitor patients remotely. Telemedicine is a form of remote patient care that enables patients to receive real-time medical treatment and consultations wherever they are located as opposed to seeing a doctor in-person. This ensures patients in even the most remote locations receive access to healthcare services and decreases healthcare expenditures by reducing hospital visits.
- Introducing a reliable symptom assessment tool can rule out other causes of illness to reduce the number of unnecessary visits to the ED.
- In summary, predictive analytics plays an increasingly important role in population health.
- In particular, the development of deep learning (DL) has had an impact on the way we look at AI tools today and is the reason for much of the recent excitement surrounding AI applications.
- Machine learning has also been implemented to assess the toxicity of molecules, for instance, using DeepTox, a DL-based model for evaluating the toxic effects of compounds based on a dataset containing many drug molecules .
- Faster clinical data interpretation is crucial in ED to classify the seriousness of the situation and the need for immediate intervention.
- Nevertheless, there are some challenges that need to be considered as AI usage increases in healthcare, such as ethical, social and technical challenges.
Affective computing refers to a discipline that allows the machine to process, interpret, simulate, and analyze human behavior and emotions. Here, patients will be able to interact with the device in a remote manner and access their biometric data, all the while feeling that they are interacting with a caring and empathetic system that truly wants the best outcome for them. This setting can be applied both at home and in a hospital setting to relieve work pressure from healthcare workers and improve service. The MARIO project (Managing active and healthy Aging with use of caring Service robots) is another assistive robot which has attracted a lot of attention. The project aims to address the problems of loneliness, isolation, and dementia, which are commonly observed with elderly people.
In particular, the development of deep learning (DL) has had an impact on the way we look at AI tools today and is the reason for much of the recent excitement surrounding AI applications. DL allows finding correlations that were too complex to render using previous machine learning algorithms. This is largely based on artificial neural networks and compared with earlier neural networks, which only had 3–5 layers of connections, DL networks have more than 10 layers.
A human-centred AI approach combines an ethnographic understanding of health systems, with AI. After defining key problems, the next step is to identify which problems are appropriate for AI to solve, whether there is availability of applicable datasets to build and later evaluate AI. By contextualising algorithms in an existing workflow, AI systems would operate within existing norms and practices to ensure adoption, providing appropriate solutions to existing problems for the end user. Collaboration among stakeholders is vital for robust AI systems, ethical guidelines, and patient and provider trust.
- The tactile sensory system can detect mass calcifications inside the breast tissue based on palpation of different points of the tissue and comparing with different reference data, and subsequently determine whether there are any significant abnormalities in the breast tissue.
- This is combined with other efforts to employ DL to find molecules that can interact with the main proteases (Mpro or 3CLpro) of the virus, resulting in the disruption of the replication machinery of the virus inside the host , .
- For these patients, this immersive experience could act as a personal rehabilitation physiotherapist who engages their upper limb movement multiple times a day, allowing for possible neuroplasticity and a gradual return of normal motor function to these regions.
- In medical imaging, a field where experts say AI holds the most promise soonest, the process begins with a review of thousands of images — of potential lung cancer, for example — that have been viewed and coded by experts.
- Like clinician documentation, several cases for gen AI in healthcare are emerging, to a mix of excitement and apprehension by technologists and healthcare professionals alike.
Read more about AI for Way to Revolutionize Medicine here.