PIONEER WITH PURPOSE™
Cubismi is pioneering a Decision Flow™-3D digital health platform to transform the explosion of health big data into targeted and visually-rich decision information for optimal expert decision-making. With Decision Flow-3D™, clinical teams will be able to connect intelligence and analytics insights into a synthesized decision-making framework — ushering in an era of continually improved precision era outcomes at significantly lower costs.
The US healthcare system is facing a diagnostic error crisis and legacy information technology systems are a major culprit. Legacy silos and interfaces impede physicians’ cognitive processes and communication. Further, these systems place healthcare professionals under increasing stress with the explosion of big data. According to published research, the amount of healthcare big data has exploded at a rate of roughly 10-fold over the last 20 years, while the number of doctors has increased only 2-fold. Diagnostic errors negatively impact the health and safety of patients, but also cost the US economy billions of dollars annually.
In fast-paced clinical environments, as the number of health data points for each decision explodes, decision complexity across each patient’s journey increases and patient care outcomes decline. 5
Legacy technology vendors treat humans like machines and falsely assume good clinical decision-making can be reduced to a set of simple, quantifiable tasks. They assume “workflow” task elimination and increases in data points with AI analytics held in legacy data silos will support better outcomes, but it does not.
As the velocity, veracity, volumes, and variety of big data increases, the complexity for each decision also increases for physicians and other healthcare professionals in fast-paced clinical environments.
Cognitive effort and physical toil for increasing tasks increases and users are forced to harvest more data from legacy silos, each with its own legacy interface.
"Workflow" "AI point solutions" attempt to decrease the number of tasks and increase user efficiency, but fail because the rate of increase as the number of tasks increases at a faster rate than limited "AI point solution" pain relief.
In recent years, many groups have attempted to use "artificial intelligence" algorithms (aka, neural networks) on single medical images to automate "black box" diagnostic decisions made by Radiologists today, coined “AI Automation.” Although it has proven powerful in closed-system training, these brittle algorithms perform poorly in the open and less predictable environments of clinical medicine. Further, trained algorithms show poor transferability from one healthcare system to another, and are not interpretable by medical experts. In a recent ACR survey, 93% of radiologists say these tools are unreliable in open-system clinical medicine. Top experts believe it will take >10 years to safely implement AI Automation into healthcare.
Yet, "Radiomics" research also supports evidence that patterns of big data from medical images, sometimes combined with other data such as genetics, can provide biometric predictions of patient outcomes, such as the likelihood of response to a certain drug treatment. However, these methods use outdated standard segmentations that have been shown repeatedly to lack even the most basic measure reproducibility. Radiomics and Radiogenomics have thus seen limited successful translation into clinical medicine.
We know that powerful new big data technology provides a great opportunity to solve massive problems. Failure is simply not an option.
We need powerful new ways for healthcare professionals and other users to ergonomically use exploding big data for personalized and precision healthcare.
RE-IMAGINE BIG DATA TO IMAGINE A BETTER FUTURE, DIGITALLY TRANSFORMED.
Cubismi's transformational core technology is designed to allow physician users and other healthcare professionals to ergonomically pull insights from oceans of big data to make better patient care decisions, quickly, in fast paced clinical environments.
Cubismi’s core innovation stems from proprietary cloud-based precision biomap ‘digital twin’ technology that structures health data into a holistic 3D-time virtual map for each patient. All of a patient’s digital data is mapped to anatomy and across time, driving more powerful and reliable predictive analytics. Once mapped, the stitched data can be compared to similar population stitched data to deliver predictions using machine learning and explainable AI, such as - one day - far earlier detection of cancer. This holistic structured 3D-time virtual map in the cloud will someday allow universal credentialed access and will power the development of novel human-information interaction capabilities over time.
LEARN MORE ABOUT OUR TECHNOLOGY
Each Decision Flow-3D™ synthesized component will use Cubismi's foundational cloud-accessible 3D-time virtual map for each patient, updated across time and clinical care pathways by each user. The HUMAN-CENTRIC system is designed for a leap forward in ergonomic human-information interaction and will accelerate information flows to reduce cognitive effort and help physicians make better decisions, quickly and seamlessly. The modernized cloud-based system will also enable a leap forward in efficient and accurate communication among physician teams and with patients. In the future, Decision Intelligence dashboards will display optimized clinical care pathway outcomes.
Based on how medical imaging is interacted with, the system will know what information physicians need to see. This provides the right information, in the right context, at the right time.
In the future, this fully implemented technology is poised to significantly reduce expert time harvesting data and information for each decision. Well-designed and automated structured datasets will provide richer information for each clinical decision.
Once fully implemented, our unified cloud platform will provide 3D "smartview" visual models for better communication about patient care decisions across all stages of each patient’s journey. From history and intake, to imaging and analysis, to treatment plan - all doctors, radiologists, and patients will communicate at a higher level.
Organizational-level dashboard with novel insights.
Decision Intelligence (DI) is a proven machine learning (ML) and “AI” analytics methodology to manage today’s new reality of ever-increasing decision complexity. When multiple individual decisions and/or algorithmic outputs are synthesized for improvement of a given outcome, it can be used to power continually improved outcomes through additional analysis, monitoring, feedback, and improvement of decision-making frameworks. It leverages various methods for improving, supporting, automating, and augmenting individual decisions within each larger decision-making framework. DI has been validated in domains such as mortgage approvals, Formula 1 racing, and Google Maps route optimization. Only by using DI analytics will we be able to assure AI tools are actually improving patient care outcomes. The first known clinical medicine DI use cases were used by the NHS in the UK for a COVID application.
In medicine, clinical decision-making does not only impact patient care outcomes, it also impacts the business of healthcare. Healthcare leaders need to move beyond thinking about task workflows and take a broader view about fundamentally enabling a new age of healthcare Decision Intelligence.
“The physician clinical decision is the most important business
decision in all of healthcare.”
— Stephen Pollak, PhD, leading healthcare IT strategist
“We need patient care pathways and imaging pathways that are dynamic and continually learning what is better and what is worse, and combined use to inform what to do for an individual life.”
— Alexander Norbash, MD, Chair, UCSD Department of Radiology, University of California at San Diego, USA
OUR BRAND PROMISE: PUTTING THE POWER OF DECISION INTELLIGENCE INTO THE HANDS OF PATIENTS AND HEALTHCARE PROFESSIONALS
