us.graph.md - technology

Graph MD has developed an innovative knowledge synthesis architecture applied to telemedicine using Graph Data Science with the Neo4j Enterprise Graph DB database. We were able to include all the world's classified diseases and the main symptoms from PubMed. The Graph DB has fifty thousand terms for Patients, Symptoms, and Diseases; and four hundred thousand relationships between nodes. According to the opinion of leading experts: It would not be possible to build the model with these characteristics in a relational database.

In this Complex System, it is possible to demonstrate the viability of the idea of proposing an intelligence storage solution based on the construction of personal patient databases. Soon, a person will have a system larger than that of a large company today.

Considering models as dependent data. The proposal was to create an architecture to significantly reduce the volume of relationships in the knowledge base. To solve the issue of isolation, the concept of knowledge synthesis bases was created, which gives the project its name.

Zero-knowledge bases receive patient data and diagnostic maps so that intelligent agents can validate the most likely hypotheses. At this point, all AI is already pre-stored in tags and relationships within the synthesis database, with their respective values pre-calculated by AI algorithms that have been validated by medical specialists. This is where the concept of Knowledge Place comes in to make the solution profitable. Patients do not pay for the application, but rather for the knowledge applied to their health needs.

Because, as we know, the analysis of a patient's diagnosis can have different levels of abstraction for different medical specialists! Using this innovative architecture, we created the super app graph.md in java spring data on a cloud high-performance platform. With different points of view, you can navigate between fifty thousand terms, with a maximum of fifty choices, or assignments, made through questions with guidelines or suggested answers.

Thus, allowing navigation in the graph md in an intelligent way. The interaction between patients and medical specialists to define a diagnostic hypothesis can be synchronous or asynchronous. The magic happens when we identify the initial context, that is, all patients who are approximately the same as the patient being analyzed and who already have a diagnosis assigned in the knowledge base.

By entering this group, we can check whether the patient under analysis has some of the complementary concepts of the other patients who have already been diagnosed. With assertive choices, we follow the shortest path within the graph to achieve the goal of verifying or excluding an initial diagnostic hypothesis. Smarter queries that find only the most relevant terms can be used at this point. At the end of the process, we show the terms, or classification symptoms, for the target diagnoses. This process occurs in iterative and interactive cycles. The graph.md system is always available to help the patient provide the relevant information at each moment and to help the doctor discover the diagnosis based on proven scientific medical methodologies. It is important to note that AI at this point is one level below the medical methodology. Only context identification actions are performed in the diagnostic process. The pre-diagnosis process creates the basis for medical studies, in these longitudinal studies on a timeline with isolated cross-sectional parameters, where doctors can measure the temporal evolution of the parameters and create guidelines that will be applied to the diagnosis of patients in the future on the graph.md platform. Many of these parameters are only in the physiological universe and are not related to symptoms and diseases. Here, an important contribution is made in acting in preventive health, not only with generic guidelines but with objective actions that remove the patient from an accentuated exposure to a specific and contextualized risk. Simple, practical, and personalized actions that move the patient from a risk state mapped in graph.md to a safe physiological state mapped in the same way in graph.md, considering both genetic and phenotypic aspects. It is worth noting that a genetic risk load does not attribute the disease to the patient, it only requires more assertive behavior to suppress it. [technology e1 audiobook]

As an example, the allegory follows: in the graph.md synthetic universe, data from companies' products arrive at the secure Graph DB. The person interacts in this ZK (Zero Knowledge) Graph DB and chooses the best products (sneakers) for their profile (usage) based on their logs, friends' records, and sports experts. Once the choice is made, the user will request an anonymous purchase, collect the data they want to keep from their analysis and discard it, or save the data in a database in their profile. The important thing is that the company does not store any data from our members; everything is recorded and defined so that interactions and syntheses occur in ZK Graphs owned by people. It is strange to think that the person has to enter the company's store website (Amazon, Best Buy, Nike, etc.) if now they can receive everything they need and make a ZK choice with an anonymous purchase. Once the transaction is made, people do not receive advertising about anything, as there is no information about the person outside their graph.md Universe. Except in specific and controlled conditions, to be used only for your benefit, as a support for medical diagnosis. The HIPAA (Health Insurance Portability and Accountability Act) protocol, long applied in the healthcare sector, is cited here as a reference for use.

The development of computational models to support Synthesis solutions is based on the perspective of integral mapping of knowledge in a graph md. With dynamic interaction, it is possible to create schemas in these graph dbs supported by the Object Process Methodology defined by Dov Dori of the Israel Institute of Technology, seeking a more meaningful experience for the user who becomes part of the process of building the knowledge base simply and intuitively. Multiple visualization perspectives are allowed, providing a real analysis of the data based on their relationships. A fact that would be impossible for great experts if they were processed by a relational database. This difference motivates the direction of the knowledge synthesis developed for the graph.md platform. [technology e2 audiobook]

In order not to go into too much detail on this subject, we will only mention the concept of “liquid relations” defined by Zygmunt Bauman when talking about postmodern society. Fortunately, the author brings a positive idea about the subject of humanity. We believe that everyone’s contribution in this aspect is fundamental to solving this existential dilemma. Inverting the role of technology from a great villain to a positive instrument of transformation is what motivates the Knowledge Synthesis project of the graph.md platform. We want to transform users into engineers of their knowledge!

We will work very hard to make the best possible technology available to people, which is currently only accessible to large companies. Here comes the key point: a person will have a system that is larger than that of a large company. Each individual will build their system throughout their life. In all basic and non-subjective aspects, the systems will be approximately the same, so it is no longer the system that will be developed. The entire basic and standardized system is already developed and ready for use. But not the base! So in this universe, the complete inversion of the process occurs. The person who must prepare and model their database to make their data available to a specific application.

This idea seems strange in today's computational world of continuous development of systems that never end, but if we stop and think about it, people have to prepare themselves to participate and perform everything in life. College entrance exams, civil service exams, changing habits when transitioning from single to married life, constant and ongoing learning to raise children, and even presenting evidence in court when subpoenaed by a judge.

All the processes of life in society are already defined, they are just getting better. We must think of a system that allows for complex interaction! Today we are in the era of super protocols, such as ChainLink, Ocean protocol, SDAO, and Agix, and we will be heading towards the era of super applications in a few years. Our goal is for super apps to be for people and not for companies. Furthermore, we must direct all our energies towards building a better world. Thus, we will always be developing technology by people for people within the graph.md platform. [technology e3 audiobook]

get in touch

contact@graph.md to get more information on graph md points of view.

Av. João Pessoa, 731 - Sala 802 - Cep: 90.040-000 - Porto Alegre, Brazil