Customer journey analytics uses machine learning and big data to track and analyze when and through what channels customers interact with an organization, with an aim to influence behavior (e.g., buying behaviors among retail customers). Similarly, healthcare organizations want to influence health-related behaviors, such a taking medication as prescribed and not smoking, to improve outcomes and lower the cost of care. In a partnership with an analytics services provider, a payer organization is leveraging customer journey analytics among healthcare consumers to identify the best opportunities and channels for patient outreach. With this analytics-driven engagement strategy, the payer has found an opportunity to significantly improve patient engagement—a predicted overall increase from 18 percent to 31 percent.
Machine Learning / Predictive Analytics
Health systems continue to prioritize reducing hospital readmissions as part of their value-based payment and population health strategies. But organizations that aren’t fully integrating analytics into their readmission reduction workflows struggle to meet improvement goals. By embedding predictive models across the continuum of care, versus isolated them in episodes of care, health systems can leverage analytics for meaningful improvement.
Organizations that integrate predictive models into readmissions reduction workflows have achieved as much as a 40 percent reduction in risk-adjusted readmissions indexes. Effective analytics integration strategies use a multidisciplinary development approach to meet the needs of a patient’s entire care team and deliver common tools for all involved in the patient’s healthcare journey.
Health systems can leverage the predictive potential of machine learning to improve outcomes, lower costs, and save lives. Machine learning, however, doesn’t inherently produce insights that are actionable in the clinical setting, and frontline clinicians need information that’s accessible and meaningful at the point of care. Thoughtfully designed visualizations of machine learning insights are a powerful way to give clinical users the information they need, when and how they need it, to support informed decision making.
A design framework for machine learning visualizations addresses three key questions about who will use the decision-support insights and how:
People: who are the targeted users?
Context: in what context or environment do they work?
Activities: what activities do they perform?
Machine Learning in Healthcare: What C-Suite Executives Must Know to Use it Effectively in Their Organizations
Machine learning (ML) is gaining in popularity throughout healthcare. ML’s far-reaching benefits, from automating routine clinical tasks to providing visibility into which appointments are likely to no-show, make it a must-have in an industry that’s hyper focused on improving patient and operational outcomes.
This executive report—co-written by Microsoft Worldwide Health and Health Catalyst—is a basic guide to training machine learning algorithms and applying machine learning models to clinical and operational use case. This report shares practical, proven techniques healthcare organizations can use to improve their performance on a range of issues.
Health Catalyst President of Technology, Dale Sanders, gives straightforward answers to tough questions about the future of AI in healthcare. He starts by debunking a common belief: We are awash in valuable data in healthcare as a consequence of EHR adoption. The truth involves a need for deeper data about a patient.
In today’s improvement-driven healthcare environment, organizations must ensure that improvement measures help them reach desired outcomes and focus on the opportunities with optimal ROI. With data science-based analysis, health systems leverage machine learning to determine if improvement measures align with specific outcomes and avoid the risk and cost of carrying out interventions that are unlikely to support their goals.
There are four essential reasons that insights from data science help health systems implement and sustain improvement:
Measures aligned with desired outcomes drive improvement.
Improvement teams focus on processes they can impact.
Outcome-specific interventions might impact other outcomes.
Identifies opportunities with optimal ROI.
The Dangers of Commoditized Machine Learning in Healthcare: 5 Key Differentiators that Lead to Success
Many vendors deliver machine learning models with different applications in healthcare. But they don’t all deliver accurate models that are easy to implement, targeted to a specific use case, connected to actionable interventions, and surrounded by a machine learning community and support team with extensive, exclusive healthcare experience.
These machine learning qualities are possible only through a machine learning model delivered by a vendor with a unique set of capabilities. There are five differentiators behind effective machine learning models and vendors:
Vendor’s expertise and exclusive focus on healthcare.
Machine learning model’s access to extensive data sources.
Machine learning model’s ease of implementation.
Machine learning model’s interpretability and buy-in.
Machine learning model’s conformance with privacy standards.
These five factors separate the high-value vendors and models from the crowd, so healthcare systems can quickly implement machine learning and start seeing improvement results.
Introducing Touchstone: The Next-Generation Healthcare Benchmarking and Opportunity Prioritization Tool
To do healthcare benchmarking effectively and efficiently, healthcare organizations need to know where they’re underperforming, where they’re performing well, and how to focus and prioritize their improvement efforts. They also need a new approach to benchmarking that isn’t limited to the inpatient setting.
The Health Catalyst® Touchstone™ product is the next-generation healthcare benchmarking and prioritization tool that delivers what antiquated benchmarking technologies cannot:
Risk-adjusted benchmarking across the full continuum of care.
Artificial intelligence-powered recommendations.
Ranked lists of improvement opportunities.
Detailed analytics and an intuitive user interface that enable the easy exploration of factors driving performance issues.
Democratized benchmarking that’s available to as many people as the organization wants.
Touchstone was designed with many users and use cases in mind, from population health analysts looking to improve ACO performance to C-suite leaders who need a data-driven approach to prioritizing improvement opportunities.
Healthcare leaders who understand data science can embrace the significant improvement potential of the industry’s vast data stores, including an estimated $300 billion in annual costs savings. Executives must know the value of data science to understand the urgency in investing and supporting the technology and data scientists to fully leverage data’s capabilities. Today’s data science-savvy executives will lead the healthcare transformation by enabling faster, more accurate diagnoses and more effective, lower-risk treatments.
The FDA recently released guidance documents on the use of clinical decision support (CDS) and medical software that may be of concern to forward-thinking healthcare innovators who rely on these technologies to deliver exceptional care and improve outcomes. What will be the impact of this guidance on machine learning and predictive analytics efforts? How will the guidance affect timelines, costs, and effectiveness of ongoing machine learning implementation?
As healthcare delivery increasingly relies on digital innovation and support, more questions emerge about the governance of the accompanying tools and technology.
This article provides a summary of the FDA guidance on CDS, how CDS is defined, whether or not CDS is exempt from regulation, and how the FDA intends to enforce compliance. It also summarizes the FDA guidance on medical software, what software is exempt from regulation, and helps to answer some of the questions surrounding the digital health space.
One large healthcare system in the Pacific Northwest is moving machine learning technology from theory to practice. MultiCare Health System is using machine learning to develop a predictive model for reducing heart failure readmissions. Starting with 88 predictive variables applied to data from 69,000 heart failure patient encounters, the machine learning team has been able to quickly develop and refine a predictive model.
The output from the model has guided resource allocation efforts and pre-discharge decision making to significantly improve patient care management activities. And the data has engendered trust among clinicians who rely on it the most for clinical decision making.
This inside look at the application of advanced technology offers lessons for any healthcare system planning to ramp up its machine learning and predictive analytics efforts.
Care management is a tool for population health that focuses scarce healthcare resources on the sickest patients. Care management leaders need to know who those sickest patients are (or may be). The static risk models typically used for stratifying patients into risk categories only paint a partial picture of health and are ineffective for modern care management programs. Custom algorithms are now capable of predicting risk based on multiple risk models and multiple data sources. They help care management teams confidently stratify patient populations to paint a complete picture of care needs and efficiently deliver care to those who need it most.
This article explains how custom algorithms work on static risk models to normalize risk scores and improve patient stratification, care management, and, ultimately, population health management.
With over 400,000 patient-harm related deaths annually and costs of more the $1 billion, health systems urgently need ways to improve patient safety. One promising safety solution is patient harm risk assessment tools that leverage machine learning.
An effective patient safety surveillance tool has five core capabilities:
Identifies risk: provides concurrent daily surveillance for all-cause harm events in a health system population.
Stratifies patients at risk: places at-risk patients into risk categories (e.g., high, medium, and low risk).
Shows modifiable risk factors: by understanding patient risk factors that can be modified, clinicians know where to intervene to prevent harm.
Shows impactability: helps clinicians identify high-risk patients and prioritize treatment by patients who are most likely to benefit from preventive care.
Makes risk prediction accessible: integrates risk prediction into workflow tools for immediate access.
Uncompensated care can cost large health systems billions of dollars annually, making outstanding balances one of their biggest costs. Propensity-to-pay tools help organizations target unpaid accounts by using artificial intelligence (AI) to leverage external and internal financial and socioeconomic data and identify the likelihood that patients in a population will pay their balances (propensity to pay). With propensity-to-pay insight, financial teams can focus their efforts on patients most likely to pay, and connect patients who are unable to pay with charity care or government assistance. Both health systems and patients benefit, as patients can avoid bad debt and organizations receive compensation for care they’ve delivered.
Those in Big Data and Healthcare Analytics circles will seldom hear the phrase “less is more.” In a clinical setting however, there is an important lesson to learn in regards to the effective execution of predictive analytics. We should not confuse more data with more insight. More data is simply more—as in more tables, more lists, more replicates, more clinics, more controls, more rows, tables of tables and lists of lists, etc. You get the idea. In short, for predictive analytics to be effective in a clinical venue, a specific focus will always trump global utility.
The opioid-related death rate in the U.S. has quadrupled since 1999, making more effective ways to predict opioid misuse a healthcare priority. A new generation of machine learning-enabled risk assessment tools promises to deliver broader and more relevant insight into a patient’s risk.
With more comprehensive insight (including comorbidities, other substance abuse, the amount of medication prescribed, and the duration of opioid use), clinicians can make informed decisions when prescribing opioids and reduce the risk that patients will misuse, abuse, or overuse the pain killers. Clinicians will also be able to identify which patients might benefit from alternatives to opioid pain management (non-pharmacologic, multi-modal therapies, or care management programs).
Under value-based healthcare and the 2012 Hospital Readmission Reduction Program, healthcare organizations are more motivated than ever to reduce their incidence of preventable readmissions.
Health systems can reduce risk of hospital readmissions by developing readmission risk scores tailored specifically to their populations. A risk model that meets the following five requirements will have significant predictive value and is most likely to achieve systemwide adoption:
Identifies at-risk patients early.
Separates patients relevant to the disease-specific identification method and intervention strategy from all other in-hospital patients.
Uses organization-specific data to train a disease-specific model.
Exceeds performance of existing models.
Is developed in collaboration with domain experts.
Predictive analytics in healthcare must be timely, role-specific, and actionable to be successful. There are also three common types of healthcare predictive analytics: Risk scores (risk stratification using CMS-HCC or other models), What-if scenarios (simulations of specific outcomes given a certain combination of events, and Geo-spatial analytics (mapping a geographical location’s patient disease burden). The common thread in all of these is the element of action, or specifically, the intervention that really matters in healthcare predictive analytics.
Machine Learning in Healthcare: How it Supports Clinician Decisions—and Why Clinicians are Still in Charge
Machine learning in healthcare is transforming healthcare with its ability to tackle data variability and complexity. Everyone in healthcare should embrace this new technology and its ability to deliver more precise, faster, data-driven insight to clinical teams.
But just as machine learning has benefits, it also has limitations; for example, it loses its impact when implemented without realistic expectations or without thorough integration with existing clinical processes.
As the FDA works to publish guidance on digital health services, including governance regarding the use of algorithms to support clinical decisions, it’s important for everyone in the industry to hold themselves accountable for the quality of the data and the processes that put this data in front of clinicians.
Machine learning is transforming the way health systems deliver care to patients by surfacing insights to clinicians at the point of care; but, ultimately, the clinician considers the entire clinical picture to determine the most appropriate plan for patients.
Machine learning, used in the context of healthcare, is not about computers replacing doctors or rolling robots dispensing bedside care to patients. Perhaps a better term would be data-driven healthcare because it is the process of using historical patient data in a predictive model to determine the likelihood of a healthcare-related outcome. The black box that is the machine is no more than an algorithm trained by data. Most importantly, the predictions can be used by doctors to optimize decision making in real time, thus reducing readmissions, infection rates, and other complications that drive up costs and lower the quality of care.
This article explains some machine learning basics, dispels some misconceptions, and outlines five steps to its implementation:
Define the use case.
Prepare the data.
Train the model.
Make predictions on new data.
Deliver the risk score for use in clinical decision support.
Machine learning is destined to be a digital partner for physicians, executives, and health systems focused on improving clinical, financial, and operational performance. To get there, it must first be understood.
The Adverse Childhood Experience (ACE) study conducted by the CDC and Kaiser Permanent showed a strong correlation between ACEs and negative health outcomes later in life (e.g., risky health behaviors, chronic health conditions, and early death). ACE scores help paint a more complete picture of a person’s health history—a more comprehensive data snapshot of the entire patient.
Given that ACE scores build better data sets and machine learning relies on high-quality data, health systems should incorporate these nutrient-rich data sources into their machine learning models to better predict negative health outcomes, allow for earlier interventions, and improve outcomes.
Healthcare machine learning is evolving to use ACE scores and lifestyle data (e.g., eating habits) to improve population health management.
Machine learning is a term that crops up often in healthcare lately, but it’s important to understand what really constitutes learning in this context. What some call machine learning is actually unintentional programming, but true learning is derived during the process of building a predictive model. This article delves into the nuts and bolts of a healthcare machine learning model and describes the training process a model undergoes to impact outcomes for patients.
The key ingredient is data and the key deliverable is to complete the feedback loop so those responsible for managing care have actionable information at their disposal.
Machine learning is beyond conceptual; it’s incorporated into a growing list of predictive models for various disease classifications.
There are limitless opportunities for machine learning in healthcare. Defined as, “a field of computer science that uses pattern recognition to identify historical relationships in large data sets using an algorithm to create a generalized model of behavior,” machine learning is one of the most important life-saving technologies ever introduced to healthcare for several reasons:
Prevents hospital acquired infections (HAIs).
Reduces hospital length of stay (LOS).
Predicts chronic disease.
Reduces one-year mortality.
Improves sepsis outcomes.
It’s no wonder health systems are eager to start leveraging machine learning to save lives, improve outcomes, and make systemwide enhancements.
They can do so by understanding machine learning basics, the importance of customized machine learning (not one-size-fits-all models) and historical data (a requirement for answering basic machine learning questions), and how machine learning helps their patients, clinical teams, and bottom lines.
As data availability and open source tools make predictive analytics increasingly accessible for health systems, more organizations are adopting this advanced capability. Organizations won’t, however, use predictive analytics to its full potential—making it routine, pervasive, and actionable—without a deployment strategy that scales the technology.
Three recommendations can help health systems successfully deploy predictive analytics and leverage data experience to improve data-driven interventions and outcomes:
Fully leverage your analytics environment.
Standardize tools and methods using production quality code.
Deploy with a strategy for intervention.
Machine learning in healthcare is already proving its worth in clinical applications. From identifying tumors in mammograms, to diagnosing skin cancer and diabetic retinopathy from images, algorithms can perform certain duties more quickly and reliably than humans. While only used for specialized medicine now, the time will come where every practitioner and patient will benefit from cyber-assisted bedside care. This won’t develop without ethical implications, but the advantages that machine learning will bring to healthcare in terms of lower costs, improved quality of care, and greater provider and patient satisfaction, will easily outweigh those concerns.
In this article, Dr. Ed Corbett explores the intricacies of machine learning from two perspectives: as a physician and as a family caregiver with a personal story about how this data science could benefit patient lives today.