Databricks launches lakehouse for healthcare, life sciences
Databricks has launched its first lakehouse platform for organisations across the healthcare and life sciences industries, increasing the scope for innovation.
Data and AI company Databricks says its Lakehouse for Healthcare and Life Sciences is an industry first and eliminates the need for legacy data architectures, which have been known to inhibit innovation in patient care and drug discovery by creating data silos and difficulties for advanced analytics.
Databricks says its new lakehouse provides a single platform for data management, analytics and advanced AI use cases such as disease prediction, medical image classification, and biomarker discovery.
The company adds that this means healthcare organisations will be able to deliver on the promise of precision medicine.
Early adopters of the new platform include GE Healthcare, Regeneron, ThermoFisher and Walgreens, and partners, Lovelytics, John Snow Labs and ZS Associates.
"One of the biggest challenges facing healthcare organisations today is building a comprehensive view of the patient," GE Healthcare, LCS Digital, chief technology officer Joji George says.
"The Databricks Lakehouse for Healthcare and Life Sciences is helping GE Healthcare with a modern, open and collaborative platform to build patient views across care pathways.
"By unifying our data in a single platform with a full suite of analytics and ML capabilities, we've diminished costly legacy data silos and equipped our teams with timely and accurate insights."
Databricks says it is already assisting data and AI innovators in healthcare, with the likes of pediatric behavioural health company Cognoa using AI to develop diagnostic and therapeutic products intended to enable earlier and more equitable access to care and improved outcomes of children and families living with behavioural conditions.
Furthermore, precision medicine company CareDX is utilising the power of data to further the discovery and development of differentiated genomics-based solutions for transplant patients.
This allows scientists to detect the presence of cancer tumour DNA in blood long before traditional detection methods and provide early cancer screening during annual physicals from a single blood draw.
"We recognise the important role that data plays in getting our products into the hands of those that need them the most, and the Databricks Lakehouse for Healthcare and Life Sciences solution helps us achieve that goal," Thermo Fisher Scientific senior IT director Feng Liang says.
"This modern platform for data and AI has enabled us to eliminate costly data silos, unlock new opportunities to innovate, and become a more data-driven organisation."
Databricks says its Lakehouse for Healthcare and Life Sciences affords customers tailored data and AI solutions to manage common industry challenges.
Through analytics accelerators and open source libraries such as Glow for genomics, along with a certified ecosystem of partners, organisations can jumpstart their analytics projects and save weeks to months of development time for data engineers and data scientists.
Databricks is headquartered in San Francisco and was founded by the original creators of Apache Spark, Delta Lake and MLflow.
The company has offices around the globe, and more than 5,000 organisations use the Databricks Lakehouse Platform worldwide to unify their data, analytics and AI.
Solutions in the company's Lakehouse for Healthcare and Life Sciences include:
- Disease Risk Prediction: use ML to assess a patient's risk for a given condition based on a patient's encounter history and demographic information.
- Digital Pathology Classification: rapidly analyse thousands of whole slide images with deep learning to automate the detection of metastasis.
- Real-World Evidence Suite: seamlessly ingest a wide variety of data types, map to analytic data models like OMOP, and build cohorts with tools like propensity score matching.
- Natural Language Processing with John Snow Labs: analyse unstructured medical text using NLP for use cases such as oncology research, drug safety monitoring and anonymising PHI.
- Interoperability with Lovelytics: automate the ingestion of streaming FHIR bundles into the lakehouse for downstream patient analytics at scale.
- Biomedical Research with ZS Associates: improve biomarker discovery for precision medicine with a highly scalable and extensible whole-genome processing solution.
"With the Lakehouse for Healthcare and Sciences, we can help accelerate the development of novel therapeutics and fundamentally change the way care is delivered by going from measuring disease to predicting it," Databricks global industry lead for Healthcare and Life Sciences, Michael Sanky, says.
"The opportunity for healthcare to be transformed with data and AI cannot be overstated," Databricks Regulated Industries senior vice president Michael Hartman says.
"As organisations fully transition to electronic medical records, new data types like genomics evolve, and Internet of Things and wearables take off, the industry is awash in massive amounts of data.
"But this data is siloed, and teams don't have the tools to properly use it. With Lakehouse for Healthcare and Life Sciences, we can drive transformation across the entire healthcare ecosystem and help empower our customers to solve specific industry challenges and, ultimately, drive better outcomes for the future of healthcare."