NeuroBlu Analytics v4.2.0 marks the advancement of our mission to provide the most comprehensive tools for mental health analytics, paired with the largest and most robust source of NLP-enriched, real-world data. This release introduces unprecedented density enhancements to our data offerings, additional NLP labels, and enhanced capabilities for cohort analysis to unlock deeper insights from NeuroBlu Data.
Comprehensive depression and anxiety analysis
NeuroBlu Analytics v4.2.0 features a landmark increase in patient coverage for key psychiatric scales such as PHQ-2 and PHQ-9 (Patient Health Questionnaire), GAD-7 (Generalized Anxiety Disorder 7-item), and C-SSRS (Columbia Suicide Severity Rating Scale). 4.3 million patients additional now have PHQ-2 scores (a 380% increase from the prior release), 3.2 million additional patients now have PHQ-9 scores (a 237% increase), 1.3 million additional patients now have GAD-7 scores (a 1000% increase) and 71,000 additional patients now have C-SSRS scores (a 20% increase). In addition, this release includes improved data quality and consistency across data partners for PHQ-2 and PHQ-9 scales. The substantial increase in these scales enables more robust and representative studies on depression and anxiety, with millions of additional patients now available for analysis.
Enhanced NLP capabilities including new labels and temporality
Holmusk has developed a novel natural language processing (NLP) approach called NeuroBlu NLP that extracts key information from clinical notes and transforms it into structured, analyzable, and actionable data. Four new NLP-derived labels have been added to the depressive disorders model, including poor self-image, lack of energy, poor concentration, and depressed mood, in addition to the existing labels of anhedonia, suicidal thoughts, suicidal attempt, and suicidal behavior. Temporality has also been added to the new labels as well as the anhedonia label, distinguishing between current and historical symptom references. These additions allow researchers to conduct more granular analyses of depressive symptoms, leading to an improved understanding of symptom patterns and treatment responses.
Streamlined cohort characterization
The new Output option for Descriptive Statistics enables users to automatically generate comprehensive statistical reports for cohorts they create. This includes demographic information, clinical characteristics, healthcare utilization, and more and is available in both CSV and PDF formats. This new feature significantly reduces the time and effort required to understand cohort characteristics, enabling researchers to quickly generate and share comprehensive reports for study design and analysis. In addition, the updated Cohort Summary tab in Cohort Explorer exhibits improved categorization of psychiatric vs. non-psychiatric drugs and brands to quickly assess pharmacotherapy prescriptions.
Looking ahead
We continue to incorporate customer feedback, insights and needs to shape the future of mental health research and analytics. In upcoming releases, we are excited to introduce an SQL editor for direct querying of NeuroBlu Data, including collaborative features for saving and sharing SQL queries. We will continue to incorporate expanded outcome measures and data quality improvements. Looking further ahead, we are developing predictive modeling features for identifying risk factors and personalizing treatment approaches.
We invite our user community to explore these powerful new capabilities in NeuroBlu Analytics v4.2.0. By leveraging these new features and our expanded real-world dataset, researchers can drive more impactful discoveries and contribute to advancing mental health care and treatment strategies.
Interested in seeing NeuroBlu Analytics for yourself? Contact us to schedule a demo.
Already a customer? Log in here.
