Saama Technologies, Inc., a data analytics company, unveiled three new machine learning-based capabilities that extend the existing functionality of its Life Science Analytics Cloud (LSAC).
Saama announced the addition of these programs infused with artificial intelligence (AI)—Virtual Assistant/AI, Operational and Financial Risk Mitigation, and Drug Efficacy and Patient Safety Analytics—during the 10th Annual Summit for Clinical Ops Executives (SCOPE) in Orlando.
“This trio of new LSAC proficiencies demonstrates Saama’s commitment to strategic, targeted and pragmatic deployment of AI to continually advance clinical operations,” said Malaikannan Sankarasubbu, Vice President of AI Research at Saama. “These exciting new features are the first in a series that will be launched throughout 2019 to exponentially enhance the value of our LSAC platform for Saama’s life science partners. These new features translate into clinical trial time and cost savings and, ultimately, safer and more effective drugs.”
Virtual Assistant/AI
Saama’s 2018 introduction of its Deep Learning Intelligent Assistant (DaLIA), a context and domain-aware conversational user interface for LSAC, shifted the human-computer interaction paradigm. Saama has expanded DaLIA’s capabilities even further, broadening its capacity for identifying the intent (what you would like to do or know) of the query and catapulting the Virtual Assistant to an enhanced level of conversational user engagement. When DaLIA replies to a researcher’s question about study conduct, whether from an operational or clinical perspective, it is now enabled to factor in key parameters, such as the names of persons, organizations, and locations, as well as expressions of times, quantities, monetary values and percentages. DaLIA remembers the context of previous inquiries and can seamlessly enfold new entities into the discussion to provide rapid clinical operations insights. Queries about various aspects of clinical development, including start-up, enrollment, data quality and financial risk, result in responses that factor in the intent and specificity of the questions. This allows DaLIA to mine the data resources from an enterprise’s LSAC deployment and provide answers.
Operational and Financial Risk Mitigation
Saama’s new Operational and Financial Risk Mitigation significantly advances the ability to track clinical trial key performance indicators (KPIs), managing and mitigating operational and financial risks. Saama is implementing an auto-ML model into LSAC that provides the ability to go beyond the current industry standard of tracking only planned and actual KPIs. This novel feature predicts when critical KPIs, such as first site activated, first and last patient enrolled, etc., will be achieved, empowering researchers to make subsequent, in-flight decisions about and modifications to a clinical trial. Saama’s Operational and Financial Risk Mitigation eliminates the need for clinical teams to run their own labor-intensive analyses to approximate these important milestones. LSAC will use historical data from various trial sites and automatically apply the appropriate machine learning algorithm so customers seamlessly see site-related predictions. Operational and Financial Risk Mitigation provides researchers with the power of information, enabling them to make decisions and course corrections before obstacles delay a trial.
Drug Efficacy and Patient Safety Analytics
Saama’s LSAC is now also informed by an ML-based Drug Efficacy and Patient Safety Analytics feature that significantly streamlines the time and effort traditionally required to correlate patient profiles with data variables. With effective clinical data management and standardization, upwards of 50 variables can now be analyzed simultaneously by LSAC for immediate identification of patient outliers, versus the current, time-intensive process of trial staff manually examining only a few variables at a time. The new feature fundamentally changes clinical trial medical monitoring, enabling researchers to identify previously undetectable patient deviations, as well as potential corresponding safety and efficacy issues, sooner than ever before. Saama estimates that the new Drug Efficacy and Patient Safety Analytics capability will result in an approximately 30 percent savings in clinical trial staff time and effort by rendering the need to rely on manual data analysis obsolete.
