Custom AI solutions using deep learning and in-memory,
high-throughput technologies that will automate processes, recognize hidden patterns and capture key insights.
Jiva.ai empowers healthcare organizations with the power of Machine Learning to recognize key patterns in their data.
& improve efficiencies and human health outcomes.
Patients are living longer with increasing levels of chronic illnesses and disease. These are putting a lot of financial and operational pressures on healthcare systems globally. Simultaneously, healthcare data is increasing exponentially. This has pushed the present day tools, that require a lot of human interaction to understand and analyse this data, to their limits.
Jiva.ai, is a deep learning engine that can spot patterns in complex data sets. These can then be targeted to deliver human health improvements, cost savings and a stronger more efficient operations framework.
Jiva.ai can provide quantifiable value to the healthcare sector
We currently work with the following core healthcare and life sciences segments
Health Services Providers
Pharma Life Sciences
Jiva.ai’s power lies within its simplicity. It sifts through multiple layers of operational data in a relatively shorter time scale leading to an unparalleled level of smart insights and cost savings.
The AI engine has been developed with business professionals with 45 years of collective experience in healthcare, genetics, technology, data and machine learning.
information in real-time for
our AI to analyse
- USE CASE 1
- USE CASE 2
- USE CASE 3
- USE CASE 4
- USE CASE 5
The challenge to early diagnostics often exists due to resource constraints. Jiva.ai resolves this problem through the deployment of an automated process which analyses existing data for MRI patients with a view to identify high risk patients which require further clinical assessment.
This will reduce the costs associated with biopsies, delayed or incorrect diagnoses, increased hospital occupancy, and litigation.
Jiva.ai can be implemented in a hospital environment to consume live patient data to produce real-time analytics. This will speed up diagnosis and detect early deterioration, which will free up time for staff to spend on higher-value tasks and provide cost as well as human health savings.
Healthcare systems are overwhelmed providing care for people in their last year of life. Jiva.ai will be deployed on patient datasets to identify patients in their final years and honouring their care preferences. Removing avoidable admissions and thus preventing hospital-acquired infections, repeated veno-puncture and investigations. This will deliver patient comfort and well-being, and will eliminate costs to the acute care system.
Jiva.ai can be applied to the results from investigatory tests (urine, bloods, pathology), hospital codes and HESS data (admission, diagnosis, discharge) to identify the risk of readmission and disease, for preventative purposes.
Falls and fractures, in people aged 65 and over, account for over 4 million bed days each year in England. The healthcare cost associated with fragility fractures is estimated at a £2 billion a year. Injurious falls, including over 70,000 hip fractures annually, are the leading cause of accident-related mortality in older people.
Jiva will be employed on Health and Social Care data to predict those that are at risk of falling so they can be targeted with prevention strategies.
Under the Hood
1) Jiva is build from the ground up with the view that models of the data will change over time, and the stakeholder will want to join models together to obtain better predictions about the system. This targets one of the main issues with using these techniques, which is that models are often not extensible and therefore there is a time cost to keeping it updated.
2) Jiva.ai relies on expert knowledge in the form of a semantic network, which both supports the former notion of model integration and also dictates the learning phase. As an example, one may want to integrate kernels (predictors) between:
(a) Genetic markers for diabetes
(b) Blood markers for heart disease
(c) Socio-demographic factors
(age, income, house prices, environmental factors, etc).
These models can be learned independently, and integrated later. Individually the models are useful for micro-study, however together one can start to make inferences based on real data across scales and concepts that would not ordinarily put together. The idea is to improve your machine learning capability over time. As disparate kernels get added to Jiva.ai we hope it will evolve into general artificial intelligence.
Our team with Big Ideas
Manish has a doctorate in mathematical modelling with an emphasis on dealing with large, complex datasets. He is the technical architect of Jiva.ai, a new machine learning algorithm that will form the basis of a new breed of AIs.
New Business Lead
Chetan has a doctorate in dentistry and a BSc in Immunology & Oncology with his thesis in developing an anti-cancer protein. He is currently on the NHS Clinical Entrepreneurship Scheme, to implement Jiva.ai into healthcare systems.
Strategy & Innovation Lead
Binit holds an MBA from Brunel University and has a background in innovation and growth. With a career in digital and consulting, he oversees the Jiva.ai product roadmap and is responsible for innovation, strategy and operations.