iFLYHealth puts forward the "One Body With Two Wings" technical framework. With medical knowledge self-learning as foundation, clinical reasoning and health interaction as two wings, the framework pursues to push forward continuous technology evolution, leading our two main product directions: clinical assistant and health assistant.
The mission of iFLYHealth is to become “AI assistant for every doctor and health partner for everyone”. Being faced with the diverse need of product design and capability in the clinical assistant and health assistant scenarios, we contribute ourselves to solve the core complex technical tasks such as AI perception, AI cognition, and multimodal fusion in the medical situation.
From the perspectives of AI technology, there are many difficulties to solve, such as in the area of medical knowledge learning, knowledge constructing, knowledge mastering and applying to specific tasks, in the area of clinical reasoning to face with complex, multi-source, heterogeneous and dynamic clinical information, in the area of clinical human-computer interaction to deal with perceptual recognition, multimodal information understanding, and dialogue management.
iFLYHealth's clinical reasoning technology is expected to reach every doctor, to cover the whole process of diagnosis and treatment, to comprehensively improve the quality of medical service and to optimize medical resources.
Machine-assisted clinical decision support technology is by using clinical records and medical knowledge, to predict patient's disease, to assist doctor in illness diagnoses, and to provide clinical decision support.
Auxiliary risk assessment technology is through the whole-course progressive contextual time-aware analysis of patients' pathography at different stages, to realize real-time prognosis for the progression of the disease, significantly enhance the efficiency of the physician evaluation, and improve medical quality and safety.
During the diagnosis and treatment, the doctor will adopt different therapeutic regimens for different patient's conditions. As for the varied skill levels of doctors, it is a hard nut to crack in medicine and AI technology to assist them in obtaining updated and more effective therapeutic regimens in the course of diagnosis and treatment.
iFLYHealth's perceptual interaction technology optimizes pre-diagnosis, during-diagnosis, and post-diagnosis processes in the core medical scenarios. It jointly builds a smart medical service model with hospitals to improve the efficiency of diagnosis and treatment for patients so as to enjoy high-quality whole-course and personalized medical service.
It addresses the issues of information loss caused by separate modeling in the traditional framework, complicated manual annotation for the training process, and the inability to mix types of information for modeling.
Based on the multimodal information of patients, such as text, voice, and image, it obtains the multidimensional medical representation of patients in the process of human-computer interaction through in-depth multimodal understanding, and simulates the real process of doctor-patient interaction.
In the scenario of medical human-computer interaction, the event knowledge graph and dynamic information of diagnosis and treatment are combined together to better describe the rich logical relations (such as continuation, causality, conditional relation, hyponymy relation, etc.) among medical events and entities in spatial-temporal domain. The Question Answering Model correlates the events perceived during the conversation to the ones in the Event-Evolutionary Graph, then evolves and reasons, and finally, gives reasonable suggestions to the patient.
Based on AI, Personalized Active Intervention technology aims to achieve diagnosis and treatment actively and health interaction and management for patients, such as medication guidance, diet recommendation, exercise intervention, etc, whilst in traditional intervention technology there exists many shortcomings such as high dependence on human resource, limited manual personalized services, and so on.
In the foreseeable future, knowledge self-learning will play a crucial role in semantic search, knowledge question answering, and clinical decision-making in the medical field.
With the advent of the age of intelligence, the comprehensive knowledge and data of clinical data, clinical guidelines, omics data, and medical ecosystem can be aggregated to build a comprehensive medical brain and provide help to clinicians, science researchers, and public managers, which has become the development direction of the medical industry in the future.
Traditional knowledge construction has the problems such as strong dependence on domain experts, long construction cycles, and high demand of professions, so in industry human-machine coupling is usually adopted to improve the efficiency of knowledge construction, but still dependent largely on domain experts. To solve this, iFLYHealth has proposed an automated knowledge building and evolving technology based on deep learning. It provides the machine with the abilities to learn domain knowledge actively, to extract candidate knowledge from massive medical texts automatically, and to integrate them into medical knowledge graph, so achieves a double cycle of knowledge extracting and knowledge updating, realizes autonomous construction of a comprehensive, authoritative, professional medical knowledge base, and forms a new efficient and accurate mode of medical knowledge construction.
Complex Medical Intelligence System refers to an autonomous system of many medical tasks, which are formed through a series of continuous development, deployment, update, and adjustment processes in the continuous integration and coupling association. It is a highly reusable, portable, and propagable large-scale application system characterized by a hardware and software integration, man-machine collaboration, data integration, and an autonomous evolution.
Protect life and health with AI
Thank you for your attention and trust! Learn about our solutions, products, and services，please leave your information.
Consult Now
Protect life and health with AI
iFLYHealth Official Account
iFLYHealth Video Channel
Smart Healthcare 
Smart Hospital
Intelligent Hardware 
Smart Medical Insurance
Smart Imaging Union