Settings
  • Light
  • Dark
  • Auto
Select Page

Artificial Intelligence (AI) and healthcare are converging in ways never imagined and the benefits to the healthcare system are only now being realized in full. When we think of AI in societal terms, the broad spectrum of artificial superintelligence is usually what comes to mind. Let’s get a better idea of the trajectory so we can understand the potential impacts and requirements that AI in its iterations will have.

Right now, we are working at the scale of the Artificial Narrow Intelligence (ANI), and even though it is pushing us forward into artificial superintelligence (find more details on the right side of the graphic), ANI is still a strong force in its own right. With automation and quantification being the foundation of AI, ANI’s handling the complexity of information and data processing is quintessential to the medical industry. Another interesting facet will be advanced analytics and prediction software, which will become ever more important in the growing field of precision medicine and preventive care.

Artificial Narrow Intelligence

With all the progress that artificial superintelligence might give, we are simply not there yet; though we are in the age of ANI, which is characterized by AI solutions that perform single tasks based on specific datasets within a predefined range. Many ANI solutions can perform menial tasks much faster and far more accurately than a human being ever could, and a machine will never tire no matter how dull and repetitive a task may be. One of the common misconceptions regarding ANI is that the technology is not as “narrow” as one might think. If we look to the AI Continuum (see figure), we can see the trajectory laid out and the extent of ANI. ANI is seeing even more complex connections and more data being integrated and aggregated from an ever-increasing number of data sources.

Automation and Quantification

With the AI Continuum in mind, there is an important aspect right at the beginning: Improved and standardized data quality will likely make it easier to use more complex algorithms further up the curve. Thus, the initial point of data generation sets the baseline for quality. Data processing and interpretation, as well as data mapping and fusion, are rather time-consuming tasks for medical staff but are easy for machines to perform. In imaging, we talk about digital segmentation and characterization tools, and about algorithms that automatically visualize, measure and classify. Beyond imaging, think of medical data mining in plain text documents, such as reports, or interpreting other medical data of almost any kind. This kind of automation and quantification can help relieve doctors from the stresses of tedium.

Advanced Analytics and Prediction

Advanced data analytics allow for higher goals to be set for patient-centric predictions and cohort analysis, with the target of early-stage treatment. Patient-centric predictive simulations, colloquially called “digital twins”, make use of all kinds of available patient data, including imaging, clinical records and lab data that includes omics; and they may also draw on behavioral data and on social determinants of health. This level of interpretation requires complex data integration and smart algorithms. When set up properly, this will help physicians focus on what matters most: the patient. Thinking one step further, cohort-centric predictions are also on the horizon, helping to bring preventive medicine to the front lines.

Exciting times ahead: now

ASI will theoretically surpass human intelligence. As such, it is a theoretical construct which is still out of reach in the near future. But there are already exciting times ahead – we still have much to develop in terms of ANI. At its current capabilities, ANI still struggles with the most important factors of human social skills, such as the doctor-patient-relationship or bedside manner. But, as of right now, ANI already has the ability to support radiologists as a companion.

Find out more about AI in clinical routine by clicking here: www.siemens-healthineers.com/ai

Access the full article by clicking here: https://www.siemens-healthineers.com/insights/news/ai-continuum-in-healthcare.html?stc=wwhc206378

Latest posts

Welcome to the blog on Artificial Intelligence of the European Society of Radiology

This blog aims at bringing educational and critical perspectives on AI to readers. It should help imaging professionals to learn and keep up to date with the technologies being developed in this rapidly evolving field.