Artificial Intelligence in Medicine. Experience of Work of the Center with IT-Company
Bibliographic record
Abstract
Введение. IT-технологии сегодня все больше и больше внедряются в нашу жизнь, во все ее сферы. И конечно же, медицина не остается в стороне. Современная медицина на сегодняшний день не представляется без IT-технологий, которые уже используются при ведении медицинской документации, формировании баз данных, в диагностике, лечении и т. д. Стремлению к точности диагностики и безопасности хирургии помогает внедрение в медицинскую практику искусственного интеллекта (ИИ).Цель исследования. Показать эффективность и успехи совместной работы IT-компании и специалистов ГУ «Республиканский клинический медицинский центр» Управления делами Президента Республики Беларусь (ГУ «РКМЦ» УдПРБ) во внедрении ИИ в клиническую практику.Материалы и методы. IT-компания Aibolit Technologies разработала и создала хирургическую систему Aibolit для помощи хирургам до, во время и после операции.Главная цель Aibolit – помочь уменьшить возможные осложнения и облегчить работу хирургов, используя возможности ИИ и других инноваций. На этапах «обучения» различных направлений данной системы активное участие приняли специалисты ГУ «РКМЦ» УдПРБ. Результаты. На базе ГУ «РКМЦ» УдПРБ начато тестирование и клиническое использование хирургической системы Aibolit по различным направлениям. На сегодняшний день имеется продукт, позволяющий работать по заданным темам.Выводы. Развитие современных IT-технологий и внедрение их в хирургическую практику с активным применением ИИ является новым шагом в высокотехнологической хирургии. Необходимо продолжение и углубление совместной работы IТ-компаний с профессиональным медицинским миром с целью разработки и более значимого внедрения ИИ во всех отраслях медицины. Introduction. Today, IT technologies are being introduced more and more into our life and in all its spheres. In addition, of course, medicine does not remain on the sidelines. Modern medicine todayis not possible without IT technologies that are already used in the management of medical records, formation of databases, diagnostics, treatment, etc. The introduction of artificial intelligence (AI) into medical practice helps to strive for the accuracy of diagnostics and safety of surgery.Purpose. To show the effectiveness and success of the joint work of the IT company and specialists of the "Republican Clinical Medical Center" of the Presidential Administration of the Republic of Belarus ("RKMC") in the implementation of AI in clinical practice.Materials and methods. IT Company "Aibolit Technologies" has developed the surgical system "Aibolit" to help surgeons before, during and after surgery. The main goal of Aibolit is to help to reduce possible complications and facilitate the work of surgeons, using the capabilities of AI and other innovations. At the stages of "training" in various areas of this system, the specialists of the "RKMC" took an active part.Results. On the base of the "RKMC", the testing and clinical use of the Aibolit surgical system in various areas has begun. Today, the product allows you to work on specified topics.Conclusion. The development of modern IT technologies and their introduction into surgicalpractice with the active use of AI is a new step in high-tech surgery. It is necessary to continue and deepen the joint work of IT companies with the professional medical world in order to develop and more significantly implement AI in all branches of medicine.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.004 | 0.004 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.003 | 0.008 |
| Scholarly communication | 0.007 | 0.005 |
| Open science | 0.001 | 0.004 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.010 | 0.003 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".