Oslo Cancer Cluster har engelsk som arbeidsspråk og vi har valgt å ikke oversette teksten
New development in cognitive computing, a platform based on artificial intelligence and signal processing where computers learn patterns and rules, will impact us in many areas. One is medical imaging in diagnostics, where machine learning will assist repetitive jobs and provide better and more precise diagnostics. Another is in-person and online consultations, where digitalisation will enable virtual assistants and potentially a disruption in hospital management with potential to give staff more time with patients. Health management, enabled by the internet of things (IoT) and mobile sensors, will lift lifestyle management and risk management to a new level. In drug discovery, the implementation of new tools for drug design and creation, again aided by statstics and machine learning, can inform how to optimize the vast space of potential drug combination when many drugs and many targets are available. These and similar developments, will change how clinical practice develops. Giving the right treatment to the right patient at the right time, also termed precision medicine, is indeed one of the great frontiers of medicine today. Cognitive technology may transform how treatment plans are designed and how we utilize genomics and new biomarkers to achieve precision medicine.
Data complexity in healthcare
The central dogma of the Information Technology requirement in medicine is software that can efficiently ‘read •• mine •• understand’ medical data; such as patient diagnostic information/health data, radiography images, clinical trial data, and drug combination therapy data etc. The health care system contains not only the simple text records, but also complex data ranging from graphs from the diagnosis labs to images from the radiology instruments. What if we could use image and text analytics to produce a computerised radiologist assistant which could quickly filter to clinicians/radiologists for decision support? What if computers can combine imaging data along with the rest of clinical patient data to summaries of the patients’ conditions, coincidental diagnosis, automatic triage and second opinion, as well as statistical comparisons to similar patients? IT companies see this need and collaborate with academia . One example is Intel, a technology company, with a Health and Life Sciences division to power the data set management and analytic tools for the optimisation of diagnostics, treatment and care delivery  . Another example is IBM’s Medical Sieve, a cognitive radiologist assistant with advanced multimodal analytics, clinical knowledge and reasoning capabilities , [5, 6].
Artificial intelligence will facilitate introduction of Personalised Medicine
Personalised Medicine is an emerging approach for disease treatment and prev- ention that takes into account individual variability in genes, environment, and lifestyle for each person . Computational systems can eventually offer patients with a fast and efficient healthcare sys- tem for both diagnosis and treatment.
One example where computational systems play a central part is the Cancer Moonshot initiative in the United States, called by President Obama in his 2016 State of the Union Address , aiming to eliminate cancer to achieve a decade’s worth of progress in 5 years. The collaboration between Lawrence Livermore National Laboratory and Norwegian Cancer Registry is a part of this strategy . The project, facilitated by Oslo Cancer Cluster, is aiming to optimize cancer screening by using machine learning and neural networks to look at historical data .
Computer-aided diagnosis methods have recently become a part of the routine clinical work with the help of emerging digital assistant technologies . Digital assistant technologies for efficient and faster diagnosis towards disease prevention – anticipating a world where diseases are minimized or avoided entirely. The penetration of IT into healthcare also helps to reduce medication errors and streamline infection-prevention protocols . One example is when sensors capture measurements when a tumor flares up again after treatment at an early stage. Another is to improve prevention by insights to minimize the risks based on learning from larger groups.Thanks to analytics, interoperability and latest technological innovations  – major tech players are getting involved in the digital health race and more companies are investing on how to integrate smart sensors, connected devices and digital assistants into diagnostic labs and clinics.
IBM Watson, a cognitive computing platform, is one example. It uses natural language processing and machine learning to reveal insights from large amounts of unstructured data . The system, analyses high volumes of data, understands complex questions posed in natural language, and proposes evidence-based answers.
Norway should take a clear position in digital health
A decade ago none of us could have imagined that the mobile technology can create a database with the wisdom of our own body. Just from a smart watch, data ranging from blood pressure to heartbeat can be recorded on a real-time basis and data of an individual can be monitored on a long term basis. This kind of patient generated data can be obtained easily and longitudinally, over the course of a lifetime, creating the concept of ‘long data’ . This comes on top the ‘big data’ concept that gained popularity with the advancement of genomic, proteomic and diagnostic technologies in clinical practice.
Apple recently announced that their ResearchKit apps can now import a user’s genetic data from the consumer testing service 23andMe. MyHeartCounts, a cardiovascular-disease app developed by Stanford University, will be the first to be able to easily incorporate users’ 23andMe data, if participants allow it . Microsoft’s Connected Health Platform is a complex platform of tools, accelerators, solutions, prescriptive architecture, designs and deployment guidance for the digital health partners .
With the advancements in both hardware and sectors, the list of such emerging technologies in the field of diagnosis and health care treatment is long. At Oslo Cancer Cluster (OCC), we understand the importance to create and encourage the latest trending technologies and establish an upper edge in digital health for faster accurate disease diagnosis and personalised medicine. Supporting governmental initiatives and infrastructure will be critical towards establishing a transparent digital health society and shaping sustainable healthcare. •