Years before he co-launched a stealthy business to fix the filthy world of health data, Gaurav Kaushik Slowly connecting the dots was how better visualization could affect health outcomes. In 2018, the budding entrepreneur was working with a Boston-based cancer research company and FlatIron Health to see how cancer patients, mutations in their cancers, and health outcomes were all related.
Eventually, her team conducted an analysis that suggested that patients with triple-negative breast cancer, a harsher form of cancer that particularly affects women of color, respond well to immunotherapy.
Understanding the implications of linking unstructured patient data with treatment plans, Kaushik encouraged SciIO, a new startup he co-founded with the CEO Will Moneydis, a former Thiel partner and managing partner of the Dorm Room Fund. The startup is using natural language processing and data analysis to create a massive database of patient data that can help stakeholders better understand and treat people as a whole.
“You cannot navigate without maps, and there is no map for healthcare. If we want to understand the basics – like whether patients have dire, unmet needs and need special attention or new solutions, or find novel treatments for rare diseases – that takes thousands of hours of labor and years to uncover. ,” Manidis said.
Now, ScienceIO isn’t the first startup to attempt to fix healthcare data. And it probably won’t be the last. The startup differs, however, in that it has spent years building a database it claims is the most representative data.
“We have spent the last two years building a first of its kind healthcare AI platform. We are adopting a data-first approach to artificial intelligence, building on the technology required to transform discrete healthcare data into high-quality, computable data,” said Kaushik. “There is tremendous opportunity to build data-driven solutions in healthcare, and we are excited to see an ecosystem of companies emerge and benefit from our platform and broadening. [natural language processing] Renaissance.”
Natural Language Processing (NLP) is an advanced technology that makes it easier for computers to understand human speech. The company explained how NLP can be used for sentiment analysis, in which the technology looks at social media posts and predicts how the humans behind it are feeling. ScienceIO’s application of NLP incorporates machine learning to discover variables that affect patient health, using more than 9 million medical conditions, drugs, devices, and genes as potential clues.
Comprehensiveness means that the product is applicable to many different potential customers. Broadly speaking, for example, Kaushik thinks that physicians will be able to build a complete picture of patients based on their backgrounds.
Kaushik said, “The patients you deal with have many health issues, and it is not enough to say that we understand your cancer really well, or that we understand the socio-economic conditions independently. ” “It’s about having incredible depth in every subject area, and without diminishing the totality of the patient.”
He continued: “The reason we spent three years not talking to the world and creating this data set was to make sure that we represent the patients a physician should see them rather than reducing their biorisk.”
Manidis gave an example involving insurance providers who receive thousands of medical plans – and data points such as bill codes, costs, terms – everyday.
“You’re trying to figure out how to prioritize” [claims], either to send it to adjudication or to look for things like fraud detection,” Manidis said. “You can use ScienceIO to structure the data and then understand the claims, and Can reimburse patients faster [and] more accurately.”
Specifically, ScienceIO does not track, it only makes data more searchable and produces analysis that can be turned into usable insights. ScienceIO said it is currently in pilot programs with several customers, but declined to name specifics. The results of these pilots, according to Kaushik, will help them set a realistic timeline for general availability.
Progress so far has helped the one-time secret business raise an $8 million seed round. Investors in the round include institutional investors such as Section 32 and C Lane Ventures, as well as entrepreneurs including Lachey Groom and Josh Buckley.