No matter how much information we put out into the public airwaves, some questions will always remain. And that's why we've put together responses to the most common questions we receive from our prospects, clients and partners.
IPM.ai is an Insights as a Service (IaaS) company that empowers the world’s leading life sciences companies to better understand and improve the lives of patients through the research, development and commercialization of new therapies and modalities of care for specialty and rare disease. Our system of insight discovers, engages and activates the ideal patient by utilizing granular-level longitudinal analytics, artificial intelligence and machine learning in conjunction with a real world evidence, social determinants of health and outcomes research pool of over 300 million de-identified patients.
IPM.ai was founded by Ron Ellwell and Simon Simoeonov. Ron was previously an Operating Partner at Bessemer Ventures and served on the Boards of several companies including including MFORMA, now owned by Electronic Arts, Enforta, now owned by ER Telecom, and ReefEdge, now owned by Symantec; Chief Executive Officer of Goal.com, the world’s second largest online sports media company only behind ESPN that was acquired by Perform Media Group; and Chief Executive Officer of Octave Communications, a former leader in the design and manufacturing of voice and data infrastructure now owned by Plantronics. Simon was previously founding CTO of Evidon, now owned by CrownPeak), Thing Labs, now owned by AOL and a founding investor in Veracode, now Broadcom. In his VC days, Sim was an Entrepreneur in Residence at General Catalyst Partners and Technology Partner at Polaris Partners. Before his days as an investor, Sim was Vice President of Emerging Technologies and Chief Architect at Macromedia, now owned by Adobe and Founder and Chief Architect at Allaire, one of the first Internet platform companies whose flagship product, ColdFusion, ran thousands of sites such as Priceline and MySpace.
IPM.ai serves the pharmaceutical, biopharmaceutical, and biotechnology industries.
IPM.ai helps clinical operations, commercial operations, analytics, insights and marketing professionals make better decisions quicker with less risk during the pre-clinical, clinical and commercialization stages of a specialty or rare disease therapy.
IPM.ai helps life sciences companies identify, engage, and activate rare disease patients who could benefit from new therapies and modalities of care.
While there is no universal definition, a disease is defined as rare in the United States if it affects less than 200,000 people (620 patients per million). Today, there are nearly 7,000 known rare diseases affecting 30 million people in the U.S. While each disease affects a small patient population, as a category, rare diseases have a significant impact on patients, their families, and the healthcare system. Rare diseases are devastating to children and families. 95% of rare diseases have no pharmacological treatment options, exacerbating misdiagnosis and resulting in significant healthcare spend that does not improve patient outcomes. Many of these diseases are chronic, debilitating, or fatal. In the small number of cases where treatments exist, they are often complex, costly, and patients may wait years for a correct diagnosis. Rare diseases are challenging to diagnose because patients, families, and physicians have little awareness of the disease and its often complex symptomatology.
Most rare diseases lack the codes needed for diagnosis, treatment, billing, reimbursement, and research. Of the 7,000 rare diseases known to exist, only about 500 have a diagnostic code in the International Classification of Diseases (ICD). ICD codes are used by healthcare providers to classify diagnoses, symptoms, findings and procedures as well as guide treatment decisions. Without an ICD code, a physician is left describing the signs and symptoms of a rare disease rather than establishing a diagnosis for the disease itself. As a result, the rare disease cannot be easily recognized within a healthcare system, further fragmenting care. Overcoming these barriers requires persistence from patients and their families, and demands innovation from the healthcare ecosystem.
Largely caused by lifestyle factors, specialty diseases are typically of polygenic origin, meaning that the disease mechanism involves the combined action of multiple genes. With specialty diseases, a standard of care is generally well-established. Patients usually have access to multiple treatment options that are approved and available. And, while there are exceptions, rare cancers are generally much better studied and characterized than non-oncological rare diseases. The very significant biopharmaceutical focus on oncology clearly has beneficial spill-over effects for rare oncological conditions.
IPM.ai’s capabilities include market assessment, patient finding and profiling, treatment journey mapping, HCP identification, patient and HCP segmentation, referral network mapping, specialty inference, KOL discovery and HCP activation.
IPM.ai insights can be applied to the preclinical, clinical and commercialization phases of a typical product lifecycle.
Conventional drug commercial efforts are anchored in top-down, projected Rx data at the physician level. The shift to low prevalence, rare conditions with individuals who are undiagnosed or misdiagnosed, healthcare providers who are unaware of disease states and their manifestations, as well as treatment journeys that are not well-understood requires the use of machine learning and artificial intelligence in conjunction with real world data (RWD) to create models that reveal the ideal patient and their healthcare ecosystems.
An Ideal Patient is any patient that can benefit from a specialty or rare disease therapy such as diagnosed and/or treated patients, undiagnosed or misdiagnosed patients, patients ready to switch therapies or patients about to progress or relapse.
Ideal patient identification begins by defining patients for machine learning models to “learn”. These ML models are then trained on the selected population, confirming existing hypotheses and revealing latent insights. Using this ideal patient profile, AI then derives lookalike models and scores the broader patient universe based on similarity to the ideal patient. Transparent model diagnostics allow us to evaluate the strength of the model in a “supervised” ML environment. Outputs are then compared against a list of predictive variables and triangulation metrics which facilitate the decision on scoring cut-off. ML models then score the patient universe and create final classifications.
A system of insight (SOI) refers to the people, processes and technologies that turn unstructured and unconnected big data noise into augmented intelligence in the form of smart insights that lead to improved decision making and optimal outcomes.
Augmented intelligence is an alternative conceptualization of artificial intelligence that focuses on its assistive role, emphasizing the fact that cognitive technology is designed to enhance human intelligence rather than replace it.
Real world data (RWD) is data derived from a number of sources that are associated with outcomes in a heterogeneous patient population in real-world settings, such as patient surveys, clinical trials, and observational cohort studies. RWD refers to observational data as opposed to data gathered in an experimental setting such as a randomized controlled trial (RCT). It is instead derived from electronic health records (EHRs), claims and billing activities, product and disease registries, etc.
Real-world insights (RWI) gives an intimate understanding of patients and their healthcare ecosystems, including primary care physicians, specialists, key opinion leaders and influencers.
IPM.ai utilizes granular longitudinal data streams surrounding 300 million unique de-identified patients over a ten-year span, covering 99% of all healthcare providers, 98% of all healthcare systems, 96% of all outpatient facilities, and 89% of all hospitals.
Our data sources are refreshed weekly.
IPM.ai’s platform architecture easily allows us to curate, transform, integrate, and unify any disparate, unconnected and unstructured data source such as genetic, lab, clinical trial and patient portal data.
Data tokenization is the process of turning a meaningful piece of data, such as an account number, into a random string of characters called a token that has no meaningful value if breached. Tokens serve as reference to the original data, but cannot be used to guess those values.
Our partner Datavant creates irreversible, site-specific tokens for each record in a two-step approach that allows common tokens to match records at the de-identified level without personal identifiable information or protected health information ever entering the IPM.ai system.
IPM.ai’s patented architecture and data processing methodology is HIPAA certified, uniquely positioning us to combine disparate data sets – including clients’ first-party data – without the need for a lengthy and expensive recertification process.
IPM.ai’s competitors generally have little demonstrated specialty and rare disease expertise and as such, limited capabilities to address the needs of this specialized market. In addition, many of the methodologies utilized by these firms to create the ideal patient are actually “black box” in nature and do not fully disclose to the client how each actionable insight was derived. Finally, many competitors utilize mathematics over industry experience, in that they have benches of data scientists but lack industry know-how.
IPM.ai has an integrated approach to serving our clients. First is our People. Our data scientists, analytics and delivery professionals are industry experts traditionally found in top tier-life sciences consulting firms. Second is our Processes. Our proprietary data curation, analytical model building, scoring and indexing methods are grounded in the nuances of the specialty, rare disease and precision medicine markets. Third is our technology. We deploy deep learning, artificial intelligence and evolutionary computation to transform noise and unconnected real world evidence into real world insights. Finally, is our data. We always begin with the precise business problem we are trying to solve prior to curating and unifying the right real world data streams for inclusion in our data universe. It's the very reason why we can optimize the design of our algorithms to uncover high-definition insights as well as achieve better performance results.
Let's discuss your specific questions, challenges and needs.