As the population ages, long-term and post-acute care settings are becoming increasingly central to how many therapies are prescribed, administered, and evaluated, but these patient populations remain underrepresented in clinical research. PointClickCare Life Sciences’ longitudinal real-world data from skilled nursing and senior living facilities offer a deeper insight into treatment patterns, outcomes, and disease progression in this medically complex population than more traditional sources, such as claims data. Study Buddy, a new AI-assisted analytical interface, enables researchers to interrogate this rich data set directly, accelerating evidence generation from months to minutes.
An Underserved Population, Trapped in Complex Data
As the global population ages, a growing proportion of patients spend meaningful periods of time in post-acute skilled nursing and long-term care (LTC) facilities. These individuals often manage multiple chronic conditions, take complex medication regimens, and experience care trajectories that differ markedly from those seen in acute or ambulatory settings. Despite this, LTC populations remain underserved by the biopharmaceutical industry and are frequently excluded from traditional clinical trials. For drug developers, the challenge is not a lack of relevance but a lack of accessible, interpretable data capable of supporting discovery, development, and post-market research in this population. Regulatory agencies, such as the U.S. Food and Drug Administration (FDA), have placed growing emphasis on the use of real-world evidence to evaluate safety, effectiveness, and patterns of use in broader and more medically complex patient populations, creating both a scientific and regulatory incentive to better understand care delivered in long-term and post-acute settings.
PointClickCare is working to address that gap. The company collects continuous, real-time, longitudinal data from the majority of LTC facilities in the United States, spanning skilled nursing and senior living environments. These data are then structured to support pharmaceutical and biotechnology companies seeking to better understand treatment effects, care patterns, and outcomes in an aging and medically complex population. In parallel, PointClickCare supports public policy and population health research through collaborations with organizations like the Centers for Disease Control and Prevention and researchers in health economics, outcomes research, and the social sciences.
The resulting real-world data set provides deep visibility into outcomes and biomarkers, diagnoses and comorbidities, treatment and therapy patterns, healthcare provider encounters, and claims. Drug developers can “follow the drug” across the care continuum, examining prescribing behavior, administration, uptake, adherence, patient demographics, geographic variation, and comorbidity burden. These insights can inform product life cycle planning and post-approval strategy, demonstrating real-world effectiveness and evaluation of expanded or adjacent use cases. At scale, the data also supports drug repositioning efforts by combining longitudinal records from more than 10 million long-term and skilled nursing care residents with advanced statistical modeling. PointClickCare Life Sciences further supports customers in designing real-world, data-driven clinical studies and in analyzing and interpreting the resulting evidence.
Importantly, while the data set is highly standardized to enable aggregation, comparison, and querying, it retains a level of detail and granularity that reflects how care is actually delivered in LTC settings. This richness makes it possible to address a wide range of clinical research questions relevant to drug development, phase IV studies, market access, and health economics and outcomes research. At the same time, that same depth creates a practical barrier: effectively analyzing gigabytes of interconnected data requires a working understanding of how LTC operates, why specific data elements are collected, and how disparate data streams relate to one another. For many users, extracting value from the data has historically required significant time, specialized expertise, and prolonged immersion.
Turning Complex Questions into Real-World Evidence
To address the practical challenges of working with complex LTC data, PointClickCare initially built a project-focused analytics function within its Life Sciences group. This team supports customers by translating research questions into structured analyses, an approach that delivers value but requires time-intensive collaboration and deep familiarity with the data. As demand has grown for faster, more direct access to insights, PointClickCare Life Sciences introduced Study Buddy: a large language model (LLM)–based interface designed to allow users to query the data set directly and receive results in minutes rather than days, weeks, or months. The system leverages the model’s underlying understanding of diseases, drugs, and clinical relationships to place user questions within a meaningful biomedical context rather than treating them as isolated data requests.
Study Buddy enables researchers to unlock real-world evidence from LTC data by converting natural-language questions into structured analytical outputs. Tasks that once required weeks of manual effort, such as cohort definition, variable selection, and preliminary analysis, can now be completed far more efficiently. Users can explore the data without specialized technical training, deep LTC operational expertise, or prior mastery of the regulatory nuances that shape how these data are collected. Sample queries and curated definition libraries, validated by the PointClickCare Life Sciences team, help ensure analytical rigor while reducing ambiguity. To support confidence in the results, Study Buddy makes the reasoning process and underlying queries used to generate each output available for user review and validation directly within the data set. Results are returned in formats, such as table shells, that are immediately usable in studies, posters, and publications.
Study Buddy is designed for anyone engaged in LTC real-world data analysis, including researchers in the biopharmaceutical industry, academia, and government, as well as professionals in health economics and outcomes research, biostatistics, and epidemiology. By lowering the barrier between question and insight, the platform allows these users to focus less on data wrangling and more on data interpretation, study design, and decision-making, all while leveraging the depth, quality, and scale of the PointClickCare Life Sciences data set. Collaboration with the Life Sciences team is, as always, available; but Study Buddy puts the power of our data in the hands of the user.
Designing the Interface Around the Question, Not the Model
The design of Study Buddy is therefore guided not by the technology itself, but by the need to interpret complex long-term and post-acute care data in a clinically meaningful and analytically rigorous way. A central design priority was maintaining analytical focus without introducing bias. Rather than relying on traditional model training approaches, Study Buddy uses a protocol that does not require retraining the underlying model. Instead, the design ensures that questions are interpreted within the real-world clinical and operational context of long-term and post-acute care, reducing the risk of misinterpretation and preserving analytical integrity. This focus allows researchers to generate insights that are both flexible and aligned with how care is delivered.
One of the persistent challenges in real-world data analysis is the way questions are posed. Users often begin with broad or loosely defined inquiries, reflecting how research questions naturally evolve, but this ambiguity can leave room for misinterpretation by automated systems. Ongoing development efforts therefore focus on improving how Study Buddy responds to imprecise inputs. To address this challenge, Study Buddy incorporates foundational rules and shared definitions for common concepts, enabling the interface to guide users from an initial, high-level question toward a more clearly specified analytical request. This structured approach helps users refine their queries while preserving analytical rigor and minimizing the risk of misinterpretation.
Enabling Analyses That Extend Beyond Traditional Trial Frameworks
A fundamental challenge in working with real-world data is that it is generated through routine care rather than through a predefined research protocol. While traditional clinical trials rely on prospectively specified variables captured at fixed time points, long-term and post-acute care data reflect clinical workflows, regulatory requirements, and reimbursement practices. The structure and utility of these data therefore depend heavily on study design and on how research questions are defined and operationalized.
Study Buddy supports researchers in navigating this complexity by enabling structured, clinically grounded analyses within a real-world data environment. The platform allows users to evaluate both straightforward and complex analytical questions efficiently, reducing the time required to define cohorts, specify variables, and generate preliminary results. This enables researchers to test hypotheses, refine study parameters, and assess feasibility more rapidly while maintaining alignment with established research and regulatory standards.
In this way, real-world data from long-term and senior care populations can be applied to questions that are difficult to address through traditional trials alone, including treatment patterns, outcomes in medically complex or underrepresented populations, and longitudinal changes in routine care settings. These analyses can support post-market evidence generation, health economics and outcomes research, and broader understanding of how therapies perform in everyday clinical practice.
Study Buddy delivers results in clear, structured formats aligned with common research workflows, including analytical summaries and tables that can be incorporated into study documentation, posters, and publications. By streamlining access to complex data while preserving analytical rigor, the platform helps translate real-world evidence into insights that can inform both scientific investigation and clinical decision-making.
Delivering Value First, Then Expanding
Study Buddy is currently completing final stages of development, with an initial release targeted for early 2026. This initial version is designed to deliver immediate benefits by simplifying and accelerating analysis of the company’s real-time, longitudinal skilled nursing and senior living data, while laying the foundation for expanded capabilities.
As customers begin working with Study Buddy, the expectation is that confidence in the platform will grow through hands-on use. Ongoing development will continue to enhance analytical functionality, visualization, and reporting workflows, informed by real-world usage and feedback. Additional features are planned as the platform evolves, all with the aim of further reducing friction between complex data and actionable insight.
Built on Structure, Rigor, and Trust
The value of Study Buddy does not stem from the use of an LLM alone. As with any advanced analytical approach, the reliability of the outputs ultimately depends on the quality of the underlying data. In this case, the strength of the platform reflects the depth, consistency, and structure of the real-world data set established by PointClickCare.
This foundation — the PointClickCare Advantage — is built on the scale of the data, its longitudinal continuity, and the rigor applied to its preparation. Electronic health record data are widely recognized as heterogeneous and difficult to harmonize. To address this, all data used within Study Buddy undergo a data harmonization process, ensuring that it is cleaned, standardized, and organized in a way that supports robust analysis. This structured approach improves consistency across data sources and enables more reliable interpretation. In parallel, extensive mock designs and user testing were conducted to identify and close potential capability gaps before launch.
Equally important is data privacy and security. All data made available through Study Buddy are de-identified via an expert determination process to ensure that re-identification is not statistically feasible. This safeguards patient privacy while allowing the data to be used responsibly to support research and evidence generation. As a result, PointClickCare’s real-world data can be applied with confidence to the development and evaluation of new therapeutics for a population that has historically been underrepresented in clinical research.
Applying Real-World Data Across the Product Life Cycle
The continuous, real-time, longitudinal skilled nursing and senior living data collected by PointClickCare support a wide range of applications across drug development, post-market research, and commercial strategy. The richness and granularity of the data set make it possible to address diverse clinical research questions, from early development through phase IV studies, while also informing market access and health economics analyses. Longitudinal visibility into patient journeys, disease progression, comorbidities, symptom onset and resolution, and treatment effects over time can guide development decisions and help clarify how therapies perform in real-world care settings. At the same time, data on drug utilization, adverse events, burden of care, and quality of life across a medically complex population can support robust post-approval evidence generation.
For branded drug product owners, these insights extend beyond clinical research into life cycle and commercial planning. PointClickCare Life Sciences data can be used to map product adoption over time, identify underdiagnosed or underserved patient populations, and examine prescribing patterns, treatment switching, and label expansion opportunities. These findings can inform launch strategy, refine positioning, and support more targeted sales and marketing efforts. In certain contexts, real-world evidence from LTC settings may complement — and in limited cases substitute for — traditional clinical trial data, particularly when demonstrating treatment value, earlier diagnosis, or improved outcomes in routine care. Such evidence can also support value-based care and pricing discussions.
Study Buddy lowers the barrier to applying the PointClickCare Life Sciences data set across all of these use cases by making exploration and analysis faster and more accessible. In addition to supporting pharmaceutical industry applications, the platform can facilitate academic research by enabling rapid, preliminary analyses that help investigators assess feasibility and strengthen funding proposals before committing to larger studies.
