The most important provider of intelligent medical solutions is IBM, which has developed its famous Watson supercomputer. Statistics show that all information, one way or another related to human health, is distributed according to sources in the following ratio: 10% – patient’s medical record, 30% – genetics, 60% – external sources, including scientific articles.
Each year, about 700 thousand scientific articles are published containing information on effective methods of treating various diseases. The doctor is simply not able to analyze such a volume of data when making a diagnosis and choosing a treatment method. And here Watson comes to the rescue. Due to its high power, this supercomputer is able to analyze millions of data sources and choose the most appropriate treatment method in each case.
Last year, IBM acquired 30 billion different medical images for Watson training, buying Merge Healthcare for $ 1 billion. To this may be added about 50 million anonymous electronic medical records that IBM received after the takeover of Explorys startup.
Watson’s most famous medical application is the Watson for Oncology project. The effectiveness of this project can be seen from the following example. According to statistics, in US hospitals, the accuracy of prescribing the optimal treatment after diagnosing lung cancer is about 50%. At IBM Watson, these figures reach 90%.
In this case, the treatment technique can be adjusted depending on changing situations. After entering information about the patient’s state change from the iPad (for example, the patient’s blood rises in makrot), the doctor will receive an updated diagnosis from Watson in 30 seconds with an updated course of treatment. You can learn more about the Watson for Oncology project from the following video.
As we noted in our previous Watson supercomputer article, a number of medical centers and hospitals are currently participating in the Watson for Oncology project. This, for example, Bumrungrad International Hospital (Thailand), the New York Center for the Study of the Human Genome, as well as several other organizations.
And in 2015, Robert Merkel, vice president of IBM Watson Health, said that IBM was ready to offer Watson for Oncology solution for Russian medicine. Pavel Shklyudov, the leader of the IBM Razumnaya Planet division in Central and Eastern Europe on solutions for the public sector, believes that the implementation of this project in the domestic medunica is possible, but it will take time and additional effort.
In addition to the Watson for Oncology project, the IBM supercomputer is used in other areas of medicine. For example, the Detonic.shop has contracted with IBM to modernize the principles for detecting and treating cardiovascular disease.
Significantly reduces the cost of using Watson public cloud Watson Cloud. In this case, medical institutions do not need to allocate a gigantic budget for the purchase and maintenance of this multiserver device. Watson Cloud services can be used by specialists from different countries. Robert Merkel, head of Watson Health, said in 2015 that, if necessary, such a cloud can be deployed in the Russian data center, observing our laws and language specifics.
More recently, Watson made a friend (or competitor) in the field of medical diagnostics. In early 2016, Google announced the opening of a medical line as part of the DeepMind project development program. You can learn about Google’s application of the supercomputer in the medical field from this video.
The first task that lay on the shoulders of DeepMind is the diagnosis of renal failure. To this end, Google signed a contract with the National Health Service, which allowed access to nearly 1.6 million patient histories. Having learned from these data, DeepMind has become effective in diagnosing renal failure based on patient complaints and test results.
Based on AI, developers release services to monitor patients. Doctors and scientists examine the results and then conduct clinical trials.
Scientists from the Massachusetts Institute of Technology, together with specialists from the Central Hospital from the same state, created an AI system for monitoring human sleep. It tracks radio signals reflected from a person, analyzes the pulse, respiration rate and is able to distinguish deviations from the norm. The development will help doctors remotely inspect patients’ sleep and, if necessary, adjust it.
AI in medicine
- At the design level: disease prediction, identification of groups of patients with a high risk of disease, the organization of preventive measures.
- At the production level: automation and optimization of processes in hospitals, automation and increased diagnostic accuracy.
- At the promotion level: pricing management, risk reduction for patients.
- At the level of service provision: adaptation of therapy and composition of drugs for each individual patient, the use of virtual assistants to build a patient route in a clinic or hospital.
Main article: Artificial Intelligence in Radiology
The peculiarity of artificial intelligence is that this technology is capable of “learning.” And as the user works with her, she becomes smarter. In medicine, AI is used for many purposes:
- Drug design and treatment protocols
- Automation of routine processes
- Patient Monitoring
- Recognition of medical images (MRI images, ultrasound findings, cardiograms, etc.).
A fairly promising option for the use of artificial intelligence in the healthcare industry is the development of personal medical assistants. Such assistants are ordinary mobile applications that operate on the basis of machine learning. They recognize voice and text queries of users and, having analyzed their database of diseases, issue various recommendations.
In addition to issuing recommendations for treatment, the application allows you to make an appointment with a doctor or conduct a standard examination by contacting any of the doctors in real time (12 hours a day, 6 days a week). Also, the application is able to regularly check information from wearable devices (for example, to monitor the phases of sleep and heart rate).
The cost of a subscription to the Babylon service is about $ 10 per month. However, it is worth noting that under current British law, the application does not have the right to make an official diagnosis. Therefore, if the patient describes the symptoms for the flu, then he will be recommended to buy medicines at the pharmacy, which are issued without a prescription, or make an appointment with the doctor. In case of serious symptoms, the patient will be given recommendations to go to the clinic or call an ambulance.
Scientists are actively developing the idea of using artificial intelligence to improve the quality of analyzes. More recently, employees at the University of California, Los Angeles have developed an innovative cancer cell detection algorithm. Research results are published in the journal Scientific Reports. Within the framework of the developed method, a new type of microscope and artificial intelligence, which analyzes the information received, are actively used.
The development uses nanosecond laser pulsed and analog-to-digital converters, which allow you to capture images of hundreds of thousands of blood cells per second. Laser pulses make it possible to highlight individual blood cells with a fairly clear image quality.
In 2018, the American medical journal Anesthesiology published the results of a study of artificial intelligence, useful in surgical treatment methods. The article deals with a machine learning algorithm for predicting hypotension during surgery. AI analyzed the data of more than a thousand patients, who spent a total of almost 10 thousand hours on the operating table. He learned to predict anomalies 15 minutes before they occurred with 84% accuracy, with the same – in 10 minutes, and from 87% – in 5 minutes.
Qventus – a monitoring system for hospitals from the same startup. He monitors the actions of clients from recording in the registry to discharge, knows how to predict the deterioration of patients’ well-being, analyzing their condition. Also, with the help of this AI, Mercy Clinic reduced the number of unnecessary tests by 4% over 40 months based on similar customer complaints.
Jvion’s machine-learning solution identifies patients at risk of re-admission to the hospital within 30 days of discharge. In addition, it provides recommendations on health care and disease prevention.
Pharmaceutical giants such as Sanofi or Novartis are resorting to start-ups developing medical innovations to search for new drugs. Biochemicals manufacturer Roche has acquired Flatiron Health, a company that uses machine learning to process data.
Since 2012, Atomwise startup has been using neural networks to search for more effective drug formulas. His AtomNet deep learning system checks 10 million chemical compounds daily, predicting which ones will interact best. A similar algorithm is used by the biopharmaceutical company Berg Health.
The compounds found can be effective in combating the cause of the disease, but this does not guarantee that the human body will respond well to them. NorthShore Medical Center, among other things, is engaged in pharmacogenomics – it studies the effect of drugs on individual people as part of the MedClueRx project. The system determines which medicines are suitable for a particular patient with epilepsy, infectious diseases, depression, gastrointestinal diseases.
The scientific journal Nature Microbiology published an article about VarQuest last year. He is able to detect 10 times more variations of antibiotics than before it was found for all the time of similar requests.
“Medical futurist” Bertalan Mesco once said that artificial intelligence is a 21st century stethoscope. He implied that at first the medical community did not want to recognize such a simple instrument as a stethoscope. It took several decades for doctors to start using it. The same thing is happening with AI: someone uses it to the extent possible, while someone is afraid of it.
However, technologies of artificial intelligence, machine learning and neural networks greatly simplify the lives of doctors and their wards. Innovations in medicine make it possible to more accurately diagnose diseases, find medicines faster, and monitor patients. And this is only a small part of the opportunities that AI has brought to the healthcare sector.
Detonic – a unique medicine that helps fight hypertension at all stages of its development.
The complex effect of plant components of the drug Detonic on the walls of blood vessels and the autonomic nervous system contribute to a rapid decrease in blood pressure. In addition, this drug prevents the development of atherosclerosis, thanks to the unique components that are involved in the synthesis of lecithin, an amino acid that regulates cholesterol metabolism and prevents the formation of atherosclerotic plaques.
Detonic not addictive and withdrawal syndrome, since all components of the product are natural.
Detailed information about Detonic is located on the manufacturer’s page.