Learn more about our AI
Our AI, developed by our team of research scientists, engineers and healthcare professions, is a suite of AI tools designed around a nurse's brain to provide accessible healthcare for millions. A number of these tools are modular, so they can be standalone and used in isolation, or combined to suit different requirements. We're working with partners, from governments and foundations, to businesses and pharmaceuticals, to tech companies and telcos, tailoring our platform to meet their specific needs.
What it does
We've designed our AI to empower people with knowledge of their health, with the aim of relieving pressure on care giver. It mimics the way a nurse operates, performing some of the cognitive tasks they carry out.
Central to our AI is a form of digital knowledge base of care (our knowledge graph) that contains the definitions, characteristics and relationships of the different diseases, symptoms and treatments. It contextualizes this information with a graphical representation that shows the relationships between the medical components.
Machine learning uses past data to predict what will happen in the future with minimal programming. Our machine learning model can reason in order to decide on and provide information about the likely causes for people's symptoms. It then recommends next steps, including treatment information. It can also assess your disease risk based on your current health and behaviour.
Computer vision is technique to teach computers to learn, process, analyze, and make sense of visual data (images or videos) in the same way that humans do. Computer vision technology tends to mimic the way the human brain works. Researchers at Jubo train the our system to recognize pattern with massive amount of visual data—computers process images, label objects on them, and find patterns in those objects.
Natural Language Processing
Natural language processing is technique that gives computers the ability to read, understand and interpret human language. It helps computers measure sentiment and determine which parts of human language are important. For computers, this is an extremely difficult thing to do because of the large amount of unstructured data, the lack of formal rules and the absence of real-world context or intent.
Jubo Care Graph
At Jubo.ai, our knowledge graph solutions help healthcare leading companies and individuals achieve greater outcomes. Two knowledge graphs were created with an aim to help you live differently. For care service, in order to empower our users to do better, the Jubo Knowledge Graph (JKG) was created and connects care services, based on knowledge mining and expert-in-the-loop algorithms.
Jubo Digital Twins
The Jubo Digital Twin (JDT) is a knowledge graph built for patients. It monitors, simulates, and predicts health condition for long-term care patients. Two machine learning algorithms, “Vital Signs Anomaly Detection” and “Bedsore Image Diagnosis”, have been developed and show significant improvement in practice. Five more AI applications are planned and developing for the next stage.
With the power of computer vision, machines are able to autonomously interpret images of wounds, x-ray images, even paper documents including prescriptions and medical exam reports. Then, important information scattered randomly throughout the images can be organized for further usage. This allows caregivers to spend less effort on time-consuming works such as understanding and recording medical images, typing paper-based data into computers, etc.
Here we demonstrate the Bedsore Image Analyzer, an AI-based computer vision feature. The visual algorithm locates the bedsore and evaluates its severity, shape, color, etc. Below are some sample images for quick try-out. You may also upload and try your own images.
Natural Language Processing
At Jubo, we use NLP to understand textual care data (i.g., medical notes, literature, and social media), and transform them into structured system. Once NLP converts the text to structured data, machine learning system can use it to classify patients, extract insights, and summarize information.
For example, the below is a demo of AI algorithms understanding a string of nursing note, and transferring the note into nursing focus. The AI uses a modification of Bidirectional Encoder Representations from Transformers (BERT) model, which was trained with pairwise labeled dataset, for classification of textual nursing notes. At Jubo.ai, we develop different NLP techniques to power our AI services, and build the next generation of healthcare system.
possible focuses of your note...