March 19th, 2020
It is a privilege to serve the world in its hour of need – H2O.ai response to the COVID-19 pandemicRSS Share Category: AI4Good, Community, Data Science, Healthcare, Machine Learning
By: Sri Ambati, CEO & Founder
During the COVID-19 pandemic, our world, our nations, states, counties, cities and communities face an unprecedented challenge with an urgent need to help our citizens and ultimately our national and global economy. At highest risk are senior citizens, at-risk populations (individuals with immunodeficiency, hypertension, diabetes) and our critical frontline healthcare workforce. The need of the hour is for all of us – policy-makers, care sites and their staff, individuals and technologists – to come together to bring the finest in world’s technology in our fight against the virus. Our goal is to use the latest technological developments in data, artificial intelligence and machine learning to help reduce and ultimately eliminate the risk. In order to do that, we must act immediately at the federal, state and local levels and within the healthcare system itself. Our aim is to aid in managing our healthcare resources to accommodate testing as well as communication across our country, our hospitals and allied health facilities (skilled nursing and aged care). Informed organization and action will be essential to contain COVID-19 as well as continue to aggressively pursue all action to prevent the spread, and ultimately eradicate the virus and return to normalcy.
H2O.ai, a visionary and open leader in AI and machine learning, has pioneered and developed multiple AI/ML platforms, and is ready and eager to partner with Congress and our local communities to benefit the citizens of the nation and the world. H2O.ai’s mission is to democratize AI for all, with a unique view that AI can be used for good and, in healthcare, AI can be used to save people’s lives. H2O.ai is incredibly fortunate to be building the ecosystem in combating the COVID-19 pandemic with organizations like, health-innovation.org and working with our user community like Kaiser Permanente, Aetna, HCA, Allergan, Roche, Genentech, Merck, UnitedHealth Group and more. H2O.ai is currently working with one of the largest healthcare systems. It is a privilege for me and my team to be of service to the world at this time of need.
Government, Community Health, and Hospital Resourcing for Screening, Testing and Staffing: Given the increase in positive cases for healthcare workers, optimizing hospital facility capacity management and keeping healthcare workers as safe as possible is most critical. H2O.ai is currently working with a large healthcare system on AI and machine learning models that can be used to predict where and when resources are most urgently needed — which hospital in which county, city or community, to help people more efficiently.
Supply Chain: Managing medical supplies including antibiotics, ventilators and basic supplies such as masks and gloves, has become even more critical to our healthcare professionals in this pandemic. Using predictive modeling and analytics dashboards for supply chain distribution and optimization that are prevalent in retail and the manufacturing sector, H2O.ai will apply these techniques alongside the expertise of local healthcare officials, to predict equipment needs and all hospital care supplies, in order to better serve the public.
Screening and Testing: Working with testing and screening providers, the resultant data can be used to help make the AI and predictive models even more accurate. More data from every source, while confidential and private to the patient, the anonymous data gleaned can help the next patient, the next case, and the overall health of the community and ultimately defeat this disease.
Telehealth: By implementing telehealth technology solutions to target remote populations we will be able to examine and determine in real-time regions of contagion, containment or mandatory self-quarantine. The resulting data sets will be used to pinpoint more accurately the extent of the spread (and decline) and will be used to provide a fuller picture to the overall predictive data and statistical modeling. Analytics will improve efficiency and roll-out of telehealth solutions, in-house testing, and treatments.
ICU Transfers: If a patient is in critical condition, it is imperative that they are transferred to the ICU. Once in the ICU, overworked medical professionals can miss important factors to transfer them within the hospital or discharge. When discharge is done prematurely, this action can lead to death. In other words, unplanned or incorrect ICU transfers can lead to high morbidity and mortality in hospitals — this is even more a challenge when hospitals are busy. For the past several years, H2O.ai has been working with a leading healthcare provider on models that supply better predictions of patients that are likely to be transferred to ICUs and prevents mortality and readmissions. See here: ICU Transfers and Triage.
Data for Understanding Patient and Cluster Outbreak Trends: While maintaining privacy and rights of patient data, we can help with personalizing outcomes for patients based on age, comorbidities like diabetes, high blood pressure, and immune-compromised. Identifying and preventing the likelihood of sepsis for at-risk patients who are coming in for COVID-19.
Contact Tracing: Social distancing. Data is emerging from states that have implemented more aggressive shutdowns demonstrate that shutdowns of businesses have resulted in a 75x difference in spread. This is precisely what Singapore did to control the contagion. (E.g., Nashville vs. Chattanooga — bars didn’t close in Nashville until Sunday).
Drug discovery/Repurposing Existing Drugs: Drug delivery companies are aggressively exploring solutions with a vaccine clinical trial comprising 50 participants in Seattle. Repurposing existing drugs will also be necessary. Matching patients to Clinical Trials will help with both Drug discovery and save lives. For example, China is testing HIV drugs as a treatment protocol. To optimize these efforts, data screening will be critical for patient matching and cohort identification. India is using antibiotics from the 1950s as the primary protocol because the virus has not been exposed to those drug protocols. Combination of HIV and they are using antibiotics from the 50s because most people are resistant. For more severe cases, Viagra is also being considered given its efficacy in the reduction of pulmonary hypertension, which is one of the key causes of death of Covid-19.
H2O.ai is democratizing AI for the public good and is leading a movement of open source data science and machine learning communities, including 20,000 organizations with more than 250,000 data scientists world-wide. H2O.ai are the makers of industry-leading and proven enterprise-grade AI platforms, such as H2O Driverless AI and H2O Q, which provide effective dashboards for healthcare systems to solve their most critical problems.
About H2O.ai’s Mission for Public Good in time of Covid-19
H2O.ai’s team of world-class data science experts (aka Kaggle Grandmasters and Masters) have begun to mine open health data sets across multiple populations to generate accurate modeling to be deployed in a downloadable application that enables governments and healthcare providers, hospitals, particularly those who lack a data scientist on staff, to immediately begin predictive modeling on its patient caseload, medical staffing, and supply challenges.