AI in Healthcare Institutions: Where are we?

AI in healthcare establishments: it’s already a reality!

Help with diagnosis and the choice of treatments, forecasting patient flows or even automating tasks: in all areas, artificial intelligence is improving the performance of healthcare establishments.

Healthcare professionals are using these technologies to build solutions that concretely improve patient care and experience and optimize the internal organization of structures.

To support its deployment, Anap is launching a national platform for sharing AI solutions. It makes it possible to reference projects carried out in healthcare establishments and to share key information on their design and deployment, in order to inspire all healthcare players.

This platform is a sharing space open to all professionals. Our objective: to give visibility to the artificial intelligence solutions deployed and to capitalize on these experiences! Artificial intelligence is a major performance lever for healthcare establishments: to provide better care, to streamline care and to save valuable time by automating certain administrative tasks. I call on professionals to take advantage of our platform, to share their solutions or to come and find useful information for their projects. says the director general of Anap, Stéphane Pardoux.

AI in healthcare: a performance lever for healthcare establishments

Thanks to the digitization of the healthcare system, more and more data is available. They make it possible to feed the artificial intelligences at the service of all the activities of the hospital.

  • Artificial Intelligence makes it possible to improve the reliability of diagnostic capabilities interpretation of images in radiology or anatomopathology, exploitation of biological and genetic results, aggregation of medical histories, etc.;
  • It helps not only in diagnosis, but also in choice of the most appropriate therapies to the patient, or even guide the surgical procedure (see SurgAR project, CHU Clermont Ferrand and TransCUPtomics project, GHICL);
  • She permits to anticipate the use of hospital capacities : we saw it during the Covid crisis, especially for critical care sectors;
  • Artificial intelligence technologies are also at the heart of “Digital Twins”, these virtual doubles that allow simulate different scenarios and inform decision-making and its impacts;
  • AI also contributes to streamline the patient experience in establishments, through chatbots, sensor data processing, and using clustering technologies (study of similarities between individuals to group them together) and process mining (use of data to analyze processes in real time) .

Like other sectors, such as banking or insurance, artificial intelligence technologies make it possible toautomate tasks daunting such as the verification of an identity document before admission, the codification of medical acts before invoicing to Health Insurance, the processing of supplier invoices… So many tasks that are time-consuming but essential to the proper daily functioning of a hospital. Their automation makes it possible to free up time to remobilize it at the heart of their mission: care.

A national platform to promote and facilitate access to good practices in AI

The ia.anap.fr site lists projects by category: organization, data management, predictive medicine, diagnosis, patient follow-up, decision-making and task automation. At a glance, professionals will be able to visualize for each project, its history, its level of maturity, the number of users who benefit from it and the key success factors identified.

This panorama will be regularly supplemented and updated. The objective is to build a shared base of successful and inspiring artificial intelligence initiatives in healthcare establishments.

Any professional can contact Anap to submit a project and be referenced. After making contact and studying the project by a selection committee, Anap will be able to distribute the solution in question on its platform.

Anap invites each establishment that uses artificial intelligence to make its achievements visible on this platform.

Focus on 4 solutions referenced on the Anap platform

SurgAR, Prof. Nicolas Bourdel University Hospital of Clermont-Ferrand

The objective of the project SurgAR is to make it possible to display in augmented reality the internal structure of the organs during the surgical gesture carried out by a minimally invasive way (use of a camera and small incisions). The organs thus become semi-transparent, the surgeon is truly guided in real time.

This solution combining computer vision and artificial intelligence is intended to be deployed in operating theaters regardless of the laparoscopic surgery equipment they have. An online version is also available for surgeons to practice using the tool. The entire project team is currently working on obtaining CE marking.

“Beyond the development of initiatives combining fundamental and clinical research that can help health professionals, it is interesting to see to what extent these projects in the field of Artificial Intelligence must really also be exported as entities to in their own right (startup / spin-off) outside the hospital and university environment in which they were born. There is therefore also an economic issue, and more generally, an issue in terms of how AI can create collaboration between hospitals, public research laboratories and private structures such as start-ups. »

Professor Nicolas Bourdel

SUOG: Dr. Ferdinand Dhombres, AP-HP

This project was born from the observation of a strong need for assistance in pregnancy ultrasound, linked in particular to the difficulties of access to experts and the complexity of the possible diagnoses. The solution proposed by SUOG is based on mixed artificial intelligence, a combination of machine learning (for ultrasound image recognition) and symbolic reasoning algorithms based on ontologies. The source data come from 10 expert centers in Europe for the most exhaustive coverage possible of the developmental anomalies listed by Orphanet, the portal for rare diseases. The project’s prospects are now numerous. Large-scale clinical trials are planned from 2022, and the marketing of the project should see the light of day at the end of 2023.

“With 130,000 cases of birth defects and approximately 50,000 cases of ectopic pregnancy per year in Europe, the need for effective assistance with ultrasound screening has become critical. The SUOG assistant responds to the problem of access to sonographer experts and allows an improvement of ultrasounds for a better organization of perinatal care. »

Dr Ferdinand Dhombres

Know Your PatientGHICL

The project is hosted by the Group of Hospitals of the Catholic Institute of Lille (GHICL) and responds to a need to streamline the admission of patients and improve their journey within the establishments. The solution is based in particular on the recovery of models of algorithms specific to the banking sector which automate the processing of identity documents, while providing a portal for admission officers.

The perspectives specific to the project are based on the ongoing development of the third-party pathway (admission for a relative), the automatic recognition of the mutual card and the development of integration of the solution with other publishers of hospital information systems.

TransCUPtomics, Institut Curie

Faced with the difficulties of identifying the tissue origin of certain multi-metastatic cancers and when knowledge of the origin of a cancer generally serves as the basis for the implementation of an appropriate treatment, the Institut Curie has developed an artificial intelligence solution.

Launched in 2019, this solution, now accessible to pathologists and oncologists, makes it possible to identify the tissue origin of cancers of unknown primary in order to be able to offer a targeted treatment to the patient. During the evaluation and validation phases TransCUPtomics will have allowed the identification of 80% of cancerous tumours.

Discover all the projects referenced on ia.anap.fr


We would love to say thanks to the author of this short article for this outstanding content

AI in Healthcare Institutions: Where are we?


Check out our social media profiles as well as other pages related to themhttps://www.ai-magazine.com/related-pages/