MSIDE Accelarmed: Adaptive patient-centered outcome-driven coverage and benefit design for patients with complex conditions

In this post we discuss the AccelarMed analytics platform and MSIDE Smart Decisions – products of MSIDE Solutions.

What others say about us

Market leaders have recognized our new AI-enabled market approach for value-based contracting in precision medicine and specialty drug market access. As an example, an article in Pharma Boardroom  outlining how AI can be leveraged to enable new drug marketing models for specialty drugs as well as to identify qualifying populations and measure cost savings and outcomes – has referenced our platform AccelarMed.

Outcome-driven coverage and pricing enabled by AI on combination of real world clinical and claims data and medical literature research.

“The FDA concedes that the health care community uses real-world data to support expanded coverage decisions and to develop guidelines and decision support tools for use in clinical practice.”
2021, Understanding real-world data in the real world | BioPharma Dive

To find cost, pricing, and prior authorization strategies for complex medical conditions, new approaches are needed. Static value-based models are insufficient and cannot accommodate the necessary decisions for ever-changing disease progression.

Enabled by new technologies – such as Machine Learning and generative AI companies now can find answers quickly and reliably and provide adaptive coverage throughout the patient journey, improve patient outcomes and satisfaction while preserving sustainable ROI.

Leveraging the power of AI – a combination of RWD financial analysis paired with outcome research from medical literature: 47% cost savings over 36 months for the most efficient treatment pathway discovered in real world data (RWD) accompanied by evidence for pathway effectiveness from medical literature.

As an example, MSIDE Smart Decisions AI mines real-world data from approximately 750,000 patients with rheumatoid arthritis to understand the effectiveness and efficiency of drug therapy pathways. It found that a treatment pathway involving a combination of methotrexate and sulfasalazine followed by methotrexate and etanercept had a 47% lower cost than the least cost-efficient pathway and a 34% lower cost than the most common pathway. Upon request the generative AI also found evidence from studies and articles supporting the superior effectiveness and patient outcomes of the discovered pathway, with links to supporting articles listed on PubMed.

MSIDE Smart Decisions: the ultimate entry point to value-driven patient-centered ROI – based on patient journeys derived from a robust national data set

In this post we discuss the AccelarMed analytics platform and MSIDE Smart Decisions – products of MSIDE Solutions.

What others say about us

Market leaders have recognized our new AI-enabled market approach for value-based contracting in precision medicine and specialty drug market access. As an example, an article in Pharma Boardroom  outlining how AI can be leveraged to enable new drug marketing models for specialty drugs as well as to identify qualifying populations and measure cost savings and outcomes – has referenced our platform AccelarMed.

How to start exploring outcome-driven opportunities

• In this post we are exploring how MSIDE Smart Decisions – the ultimate solution for ML enabled value pathways analytics – helps health plans and life science companies model value-driven patient-centered ROI.
• MSIDE Smart Decisions is built on the flexible Big Data, Analytics and AI platform AccelarMed and aims at simplifying the entry into value-based payment modeling through data driven insights based on robust national data set.
• Customers can harness the power of our comprehensive graph data models and machine learning algorithms to unlock valuable insights – by simply signing up and start exploring opportunities for savings and improvements in patient outcomes.

Key benefits at a glance

1. Allows key insights about potential cost savings and ROI derived from a robust national data set.
2. Allows customers to identify key areas of interest from patient journeys within national data set, before making the investment in building the comprehensive graph data models, ML and analytics necessary to perform the analysis on their own client data. This is especially important when it comes to relatively narrow patient cohorts which are the target group for some specialty drug regiments.
3. Provides an important benchmark which ultimately allows customers to assess how the pathways compare between their populations and the national data set.

How it works

There are myriads of different pathways in patient journeys. As an example – patients with Rheumatoid Arthritis can receive a therapy with conventional DMARD (cDMARD) such as methotrexate or a combination of conventional DMARDs such as sulfasalazine and methotrexate. They can take those medications with different dosages, escalate or de-escalate before switching to a biologic alternative (bDMARD). Some pathways will include TNFi, other will start with selected immunosuppressants – alone or in combination with a cDMARD. The dosages and duration between switch of line of therapy will be different. In addition – factors like comorbidities, events like hospitalizations or emergency visits will have impact on the outcome of those therapies.

Finding the qualifying sub-populations – often narrow patient cohorts, identifying desirable outcome and cost efficient pathways within those cohorts is a time-consuming undertaking. Time-to-value is a key.

MSIDE Smart Decisions offers:

• Pre-defined ML models that process millions of pathway combinations to detect those with lower and higher value. As an example of a high value pathway – certain combinations of conventional therapies followed by a switch to the more expensive biologics in combination with cDMARDs will result in lower cost PMPM over 36 months as well as longer duration before switch compared to other therapy line alternatives.
• Intuitive visualizations that illustrate the various pathways between therapy lines, frequency of utilization of a particular pathway as well as cost efficiency. It provides intuitive visualizations of the high value and low value pathways and emphasizes those pathways detected by the machine learning models.
• It allows for cost savings calculations from substitution of lower-value with higher-value pathways.