[The ethics of IA in medicine must be based on the practical ethics of the healthcare relationship]. / L'éthique de l'IA en médecine doit reposer sur l'éthique pratique de la relation de soin.

THE ETHICS OF IA IN MEDICINE MUST BE BASED ON THE PRACTICAL ETHICS OF THE HEALTHCARE RELATIONSHIP. Artificial intelligence (AI) offers more and more applications on the Internet, smartphones, computers, telemedicine. AI is growing rapidly in health. Transdisciplinary, AI must respect software engineering (reliability, robustness, security), knowledge obsolescence, law, ethics because a wide variety of algorithms, more or less opaque, process personal data help clinical decision. Hospital or city doctors and caregivers question the benefits/risks/costs of AI for the patient, the care relationship, deontology and medical ethics. Drawing on 30 years of experience in AI and medical ethics, the author proposes a first indicator of the ethical risks of AI (axis 1) evaluated by the surface of a radar diagram defined on the other 6 axes: Semantics, Opacity and acceptability, Complexity and autonomy, Target population, Actors (roles and motivations). Highly autonomous strong AI carries the most ethic risks.

L'ÉTHIQUE DE L'IA EN MÉDECINE DOIT REPOSER SUR L'ÉTHIQUE PRATIQUE DE LA RELATION DE SOIN. L'intelligence artificielle (IA) offre de plus en plus d'applications de santé sur smartphones, ordinateurs, télémédecine, internet des objets. Transdisciplinaire, l'IA doit respecter l'ingénierie logicielle (fiabilité, robustesse, sécurité), l'obsolescence des connaissances, le droit, l'éthique, car une grande variété d'algorithmes, plus ou moins opaques, traitent des données personnelles dans l'aide à la décision clinique. Médecins et soignants hospitaliers ou libéraux s'interrogent sur les bénéfices, risques, coûts de l'IA pour le patient, la relation de soin, la déontologie et l'éthique médicale. S'appuyant sur trente ans d'expérience en IA et en éthique médicale, cet article propose un premier indicateur des risques éthiques de l'IA (premier axe) défini par la surface du diagramme radar des autres axes (sémantique ; opacité et acceptabilité ; complexité et autonomie ; population cible ; acteurs [rôles et motivations]). L'IA forte autonome est celle qui comporte le plus de risques éthiques.

An ontology-driven clinical decision support system (IDDAP) for infectious disease diagnosis and antibiotic prescription.

BACKGROUND: The available antibiotic decision-making systems were developed from a physician's perspective. However, because infectious diseases are common, many patients desire access to knowledge via a search engine. Although the use of antibiotics should, in principle, be subject to a doctor's advice, many patients take them without authorization, and some people cannot easily or rapidly consult a doctor. In such cases, a reliable antibiotic prescription support system is needed. METHODS AND RESULTS: This study describes the construction and optimization of the sensitivity and specificity of a decision support system named IDDAP, which is based on ontologies for infectious disease diagnosis and antibiotic therapy. The ontology for this system was constructed by collecting existing ontologies associated with infectious diseases, syndromes, bacteria and drugs into the ontology's hierarchical conceptual schema. First, IDDAP identifies a potential infectious disease based on a patient's self-described disease state. Then, the system searches for and proposes an appropriate antibiotic therapy specifically adapted to the patient based on factors such as the patient's body temperature, infection sites, symptoms/signs, complications, antibacterial spectrum, contraindications, drug-drug interactions between the proposed therapy and previously prescribed medication, and the route of therapy administration. The constructed domain ontology contains 1,267,004 classes, 7,608,725 axioms, and 1,266,993 members of "SubClassOf" that pertain to infectious diseases, bacteria, syndromes, anti-bacterial drugs and other relevant components. The system includes 507 infectious diseases and their therapy methods in combination with 332 different infection sites, 936 relevant symptoms of the digestive, reproductive, neurological and other systems, 371 types of complications, 838,407 types of bacteria, 341 types of antibiotics, 1504 pairs of reaction rates (antibacterial spectrum) between antibiotics and bacteria, 431 pairs of drug interaction relationships and 86 pairs of antibiotic-specific population contraindicated relationships. Compared with the existing infectious disease-relevant ontologies in the field of knowledge comprehension, this ontology is more complete. Analysis of IDDAP's performance in terms of classifiers based on receiver operating characteristic (ROC) curve results (89.91%) revealed IDDAP's advantages when combined with our ontology. CONCLUSIONS AND SIGNIFICANCE: This study attempted to bridge the patient/caregiver gap by building a sophisticated application that uses artificial intelligence and machine learning computational techniques to perform data-driven decision-making at the point of primary care. The first level of decision-making is conducted by the IDDAP and provides the patient with a first-line therapy. Patients can then make a subjective judgment, and if any questions arise, should consult a physician for subsequent decisions, particularly in complicated cases or in cases in which the necessary information is not yet available in the knowledge base.

Emerging medical informatics with case-based reasoning for aiding clinical decision in multi-agent system.

This research aims to depict the methodological steps and tools about the combined operation of case-based reasoning (CBR) and multi-agent system (MAS) to expose the ontological application in the field of clinical decision support. The multi-agent architecture works for the consideration of the whole cycle of clinical decision-making adaptable to many medical aspects such as the diagnosis, prognosis, treatment, therapeutic monitoring of gastric cancer. In the multi-agent architecture, the ontological agent type employs the domain knowledge to ease the extraction of similar clinical cases and provide treatment suggestions to patients and physicians. Ontological agent is used for the extension of domain hierarchy and the interpretation of input requests. Case-based reasoning memorizes and restores experience data for solving similar problems, with the help of matching approach and defined interfaces of ontologies. A typical case is developed to illustrate the implementation of the knowledge acquisition and restitution of medical experts.