RobO2: Data Distributed Ventilator

RobO2 is committed to solving the world problem for medical ventilation of lungs. We propose a solution which can be manufactured, scaled and used sustainably in all countries around the world. This requires a focus on not being relying upon medical supply chain infrastructure nor on hospitals with significant human and physical infrastructure. If this simple concept were to exist people would not die in Low to middle income countries from preventable disease.

RobO2 aims to address the following problems for manufacturing and learning from past ventilators and projects: 

Scalability: During COVID-19, the demand for ventilators increased significantly world-wide. The total worldwide requirement was assessed to be approximately 880,000 machines. Major ventilator manufacturers increased production by approximately 50%, however, supply chain issues strongly affected the production as existing high-cost ventilators have specially-manufactured components and they could not be made quickly.

Affordability: Current medical ventilators are high-cost devices (between $25,000 and $50,000).  This leads to the major problem of unavailability of ventilators in low- and middle- income countries (LMICs), where they face limitations in local infrastructure, personnel expertise, and budget constraints.

Reliability: During the COVID-19 pandemic, many low-cost ventilators were developed. However, these ventilators were designed quickly and did not meet the medical requirements to enable their use in ICUs.

Respiratory failure: Studies shows that ventilator-associated complications were common and that there are high numbers of patients at risk of ventilator-induced lung injury. Particular barriers identified include complex equipment, lack of training and environmental issues such as oxygen supply or electricity surges. This ventilator project will allow these barriers to be addressed.

The RobO2 ventilator has been specifically designed based on these novelties: (a) a high-performance low-cost ventilator for LMICs, (b) be safely used by non-expert personnel, (c) be able to scale up when demand increases, and (d) be developed, tested and manufactured with the highest level of diligence required for a medical product.

All electro mechanical components and systems have been designed from the ground up to ensure ability to manufacture without existing supply chain. RobO2 has also been designed in a unique way that allows untrained personnel to service and use it. This has two primary aspects: the physical use and servicing secondly the automated control decisions to avoid knowledge of ventilation. This requires machine learning and intelligence within the ventilator driven by extensive sensing and logging of all data.

Right from the beginning, (add real date – March 2019) our team has been working closely with the clinical team from Oxford University Clinical Research Unit (OUCRU) and Mahidol Oxford Tropical Medicine Research Unit (MORU) to understand the current problems as well as the real needs for ventilators in LMICs. Our design is therefore based on the intensive studies and feedback from front-line workers when they use the ventilators in LMICs. We believe our solution is going to have positive impact on the following target population:  

Patients: Understanding that respiratory failure is one of the commonest reasons for ICU admission throughout the world, the ultimate goal of RoBO2 is to protect patients’ lungs from any damage when being ventilated. The ventilator design includes a platform to collect and upload sensor measurement, which allows autonomous operation. The ventilator will automatically decide what to do for the patient breath by breath. Controlling breath by breath will ensure the ventilation is adapted every single breath to improve the outcomes. Additionally, our distributed learning mechanism will allow the data to be used effectively and privately, hence providing meaningful suggestions about the patient conditions based on enormous library of healthcare data.

Doctors and nurses: The ventilator can be used easily with intelligent mode. This will save time for doctors and nurses overloaded hospitals during a pandemic as well as in LMICs, where there are a lack of well-trained doctors and even facilities to support ICU ventilators. The machine’s mechanism also allows nurses to service and maintain it without the help of technicians or special tools. Moreover, Ventilators will scale their ability to make decisions over time as the algorithms are developed and improved.

Scientists and policy makers: Although we did not collect any data from the ventilator, scientists and policy makers will still benefit from our distributed learning approach, as we can utilize a large amount of medical data in a decentralized manner. These data can be used in census studies and longitudinal epidemiological studies. Our learning approach will allow the science community to make better decisions without worrying about the privacy concerns when sharing the medical data.

RobO2 is a technology-based solution that protects people’s health from such emerging pandemic like Covid-19. To resolve the cost, the supply chain problems and to save as many lives as possible, RobO2 is designed so it can be easy to scale up the manufacture by using commoditised manufacturing and components in worst supply chain scenario. Furthermore, the machine can be installed, serviced and maintained by an untrained doctors or nurses without infrastructure for such technology.  Since there is a shortage of medical staff during a pandemic, RobO2 provides the solution by controlling the parameters autonomously based on patient’s condition.

The core philosophy of our human-centric design thinking process lies in end-user engagement and disciplinary risk assessment. At the beginning, we collaborated with clinicians to produce a User Requirements Specification for a Ventilator. Furthermore, regular online and offline meetings/workshops have been organised for information exchange and feedback between end-users and engineers. Continuous interaction with doctors helps us to evaluate our progress in a most objective way.

The concept phase was already pass as the feasibility of RobO2 ventilator was proved with the proof-of-concept prototype built and tested within the first 3 months since the idea was invented.  

RobO2 currently is at the concept phase. We have working prototypes which can perform pressure control, volume control and produce different sets of data. The data generated shows that RobO2 can run ventilation in all the required modes, collect the data required and process the data.

Our innovative approach is as follows:

Design from the ground up: the goal is to design a minimal-viable-product, not only for the sake of manufacturing scalability (commoditized manufacturing) but also allow engineers to have a LEAN approach. LEAN means that wefirst design just what is needed and then focus on improving critical areas which determine how well the patient is ventilated and protect the patient’s lung. Moreover, a simple, straight-forward mechanism allows doctors and nurses to service and maintain the machine themselves, without intense specialized training and special tools.

Intensive testing and feasibility study: RobO2 is currently under intensive testing to check the reliability and feasibility of the ventilator.

Robust learning approach without violating the patient’s privacy: We employ federated learning approach that enables us to build a distributed learning system. Therefore, we do not need to collect any patient’s data, and while still be able to build a large-scale learning model from various medical data.

At present the solution is not available for use, and in one year will still not be complete. Our goal for the next 2 year is complete the intensive testing and feasibility study (by both expert and non-expert users) to prove the reliability and feasibility of the ventilator. Following that, we aim to be in the clinic with user study over 1000 people. Once this has been achieved, expected in the next 5 years if successfully scaled it will support hundreds of thousands if not millions of patients around the world who currently have no access to ventilation. The existing solutions are not fit for purpose as they are too expensive, cannot be maintained and cannot be operated in low to middle income settings.

Useability data of the project are qualitative and quantitative. Focus groups and interview data will be transcribed and translated and analysed qualitatively. Detailed field notes will be kept for observation periods.

Usability feedback summaries will be passed to the Blacksheep team through multidisciplinary meetings. Additionally, we aim to use all data obtained to explore formal and informal clinical decision-making roles, responsibilities and processes encompassed in ICU ventilation care. We will use frameworks such as the Non-adoption, Abandonment, Scale-Up, Spread, and Sustainability (NASSS) Framework to understand behaviour and requirements specifically around ventilator use. Details of the outcome measurements for the non-human participant parts of this project are contained in the main proposal.

As we are at the proof-of-concept stage, the focus now is on the hardware and firmware development of the machine. Many tests have been run and the collected data has been processed through R data analysis tools to understand the machine’s performance, the shape of the data, as well as areas for improvement.

Engineer and manegeent staff (full-time at Blacksheep)

·       Mark Gilligan, CEO

·       Ngoc Ta, Project Manager

·       Vu Tran, Lead Electronic Engineer

·       Hang Ha, Lead Software Engineer

• Lap Nguyen, Manufacturing Engineer

7 part-time clinicians

The project team consists of clinicians, engineers and data scientists.

The clinical team includes Vietnamese and international ICU clinicians at OUCRU and MORU already working on Flagship projects. In addition there is an expert advisory group of clinicians with particular expertise in ventilation from leading ICUs within Vietnam and Europe as well as users in ICUs in Vietnam, Laos and Bangladesh.

Blacksheep has the strength of an established and world-class manufacturer of scientific equipment, with expertise in producing medical grade equipment to international standards, and also has connection to Viettel (Vietnam’s largest telecoms company) and VNG group (Vietnam’s most successful app and cloud computing company) who have the capability and resource to develop the electronic control and cloud computing respectively. Blacksheep is responsible for creating the software framework to enable machine control, data collection and cloud storage.

Data scientists from Imperial College will focus on analysis of the data and making decisions around how to treat a patient breath by breath. This team will analyse and build models around distributed data and build the intelligence required for autonomous running. This work will be done in collaboration with the clinicians who have the required expertise of ventilators and ventilation.

Blacksheep, as a company, has equal employment opportunity policy. We encourage woman to apply to our engineering jobs. In fact, three out of 5 people in the company management team are woman. Half of engineering positions are hold by women. 

The objective of ROBO2 project aims at providing more access to health care facility for disadvantage communities from poor-, low- and middle-income countries. These are reflected in all of our project phases from product design to development stage. Such features as affordability, scalability and reliability, adjustability from child to adult are significant to ensure the vulnerable communities can enjoy good quality health care services. However, the design of the product is the collective contribution from all stakeholders from different countries (Laos, Vietnam, Bangladesh, UK) different sectors i.e. researchers, medical practitioners, manufacturers, patients.

We sought support from MIT Solve because we share the mission of the fund to protect people worldwide, which is to fight against the devastating pandemic using the best of our ability. The support of MIT solve could help us  to tap on initial support than to reach to wider network of impact minded leaders from across industries and sectors.

Secondly, the wider network and collaboration from different sectors and various stakeholders will enable teams to access a bigger pool of knowledge. As a result, we can create the bigger global impact on health care system using advanced technology. Go together we can go further

Currently as we are focusing on product research and development, our team only includes technicians and engineers. We believe we have a strong team that can complete and deliver all the promises. Nonetheless, once RobO2 ventilators are validated (by the end of the Beta prototype phase), we will need to expand our operations and some critical fields like legality and marketing will needs people with expertise to take charge of. Hence we are seeking advice and mentorship to support the selected above areas which we are not good at.