Tasks that are not directly related to the treatment of patients
Modern artificial intelligence systems are already helping doctors treat patients. For example, the company HeartFlow, using CT images, computer modeling of blood flow and deep learning algorithms, is
able to build a 3D card of the heart. This gives doctors the opportunity to more accurately and quickly diagnose heart disease, reducing the number of necessary invasive procedures by 80%.
However, AI is used in areas not directly related to the treatment of the patient, but still affecting the quality of medical care. Today we want to talk about these, to some extent auxiliary, but still important tasks.
"An attentive doctor will come wherever you are comfortable "Hospital Routing
AI systems and machine learning can help not only in the diagnosis. For example, in late May, the University College London Clinic in Bloomsbury (UCLH) announced that it will
use AI systems to identify patients who really need emergency medical care.
When a patient complains of pain enters the emergency room, the medical staff will perform standard procedures - take blood for analysis, take anamnesis, and take an x-ray if necessary. As noted in the clinic, in 80% of cases, patients have nothing serious - they are prescribed medications and are allowed to go home.
The system of artificial intelligence will allow you to quickly identify the very 20% that really require emergency assistance. The UCLH CEO, in an interview with the Guardian,
said that the software would
give the patient priority, assessing the danger of the symptoms he voiced. For example, abdominal pain can mean appendicitis or kidney disease, so such a person will “move” towards the head of the line.
Machine learning algorithms can also help with patient and doctor routing. For example, a researcher and consultant neurologist at the National Hospital of Neurology and Neurosurgery in the UK Parashkev Nachev (Parashkev Nachev) developed a machine learning algorithm that analyzes information about appointments to the clinic and assesses the likelihood that a patient will miss an MRT session for one reason or another. scan. His system
takes into account such parameters as the person's age, his address and distance to the clinic, weather conditions. So far, the scientist has managed to achieve an accuracy of 85%. It helps to quickly reallocate the recording time.
And in the same UCLH artificial intelligence system, which is developed by scientists from the Institute. Alan Turing
will track how doctors and patients “move” around the hospital — what tasks they perform, what procedures they go to. This will help identify potential bottlenecks in the organization of the clinic's work - situations or places where queues or shortages of equipment are potentially possible.
Search for new knowledge
Treatment practitioners, which are followed by doctors, tend to become obsolete. New methodologies, new research and preparations are emerging. Back in 2004, researchers studied the contents of 341 medical journals and found that the total number of monthly publications
exceeded 7,000 .
Ideally, it is necessary for the doctor to constantly maintain the level of subject knowledge, to keep abreast of modern treatment practices - however, it is almost impossible to study the entire body of publications that regularly appear in subject journals - even if it is a specialist.
Artificial intelligence technology in combination with search engines
can help in this situation. A similar solution was developed by scientists from the American Research Center
RAND , which is engaged in methods of analyzing strategic problems. They taught the system to search in huge amounts of information keywords and terms related to the subject of the request.
During tests, this topic was data on gout, low bone density and osteoarthritis of the knee joint. The algorithm has managed to reduce the number of topical articles of interest to doctors by 67–83%. According to the developers, the system missed only two articles that would have been selected by people, but none of them contained critical information. The accuracy of the machine learning algorithm was 96%.
Drug development
The experience of pharmaceutical companies
shows that about 12 years have passed since the start of preclinical testing until approval of the drug and treatment of patients. At the same time, only 0.1% of “candidate drugs” fall for clinical tests. Approval is received by 20% of them.
To help resolve this situation and accelerate the release of new drugs are capable of artificial intelligence systems. Machine learning and AI systems are
used in the early stages of drug development.
An example is the AtomWise solution from San Francisco. Their system is called AtomNet. It uses deep learning methods to predict how molecules will behave and with what probability they will form the necessary bonds.
During the training, AtomNet developers “fed” the artificial intelligence system with data on the results of several millions of already known molecular interactions. Based on these interactions, the
system learned to predict interactions that have not yet occurred. The software has already helped
create drugs for treating Ebola.
Artificial intelligence systems and machine learning help doctors and scientists work more efficiently. Doctors are freed from routine tasks, it becomes easier for scientists to conduct research, and patients receive treatment more quickly.
Today, developments at the interface of AI and medicine are becoming increasingly popular. For example, Google began to select companies involved in creating “medical” artificial intelligence systems to participate in the startup accelerator program Launchpad Studio. At the end of last year, four companies
joined the project at once.
We at DOC + are also engaged in development in this area: we are developing our own
NLP-system , which is able to process texts on medical subjects. It is used in our
chat bot - it helps to collect anamnesis, is able to isolate the symptoms of diseases from the patient's complaints and in a structured form sends them to the doctor.
By the way, in addition to the blog on Habré, we are conducting the thematic magazine “ Only to Ask ” - in it we tell about modern medicine and health: