Three Keys to Improving Hospital Patient Flow with Machine Learning

Health systems alike struggle to effectively manage hospital patient flow. With machine learning and predictive models, health systems can improve patient flow for different departments throughout the system like the emergency department. Health systems should focus on three key areas to foster successful data science that will lead to improved hospital patient flow: Key 1. Build a data science team. Key 2. Create a ML pipeline to aggregate all data sources. Key 3. Form a comprehensive leadership team to govern data. Improving hospital patient flow through predictive models results in reduced patient wait times, reduced staff overtime, improved patient outcomes, and improved patient and clinician satisfaction.

A Roadmap for Optimizing Clinical Decision Support

Compared to industries such as aerospace and automotive, healthcare lags behind in decision support innovation. Following the aerospace and automotive arenas, healthcare can learn critical lessons about improving its clinical decision support capabilities to help clinicians make more efficient, data-informed decisions:

1. Achieve widespread digitization: Healthcare must digitize its assets and operations (patient registration, scheduling, encounters, diagnosis, orders, billings, and claims) for effective CDS similarly to how aerospace digitized the aircraft, air traffic control, baggage handling, ticketing, maintenance, and manufacturing.
2. Build data volume and scope: Healthcare must collect socioeconomic, genomic, patient-reported outcomes, claims data, and more to truly understand the patient at the center of the human health data ecosystem.

AI in Healthcare: Finding the Right Answers Faster

Health systems rely on data to make informed decisions—but only if that data leads to the right conclusion. Health systems often use common analytic methods to draw the wrong conclusions that lead to wasted resources and worse outcomes for patients. It is crucial for data leaders to lay the right data foundation before applying AI, select the best data visualization tool, and prepare to overcome five common roadblocks with AI in healthcare:

1. Predictive Analysis Before Diagnostic Analysis Leads to Correlation but Not Causation.
2. Change Management Isn’t Considered Part of the Process.
3. The Wrong Terms to Describe the Work.
4. Trying to Compensate for Low Data Literacy Resulting in Unclear Conclusions.
5. Lack of Agreement on Definitions Causes Confusion.

As AI provides more efficiency and power in healthcare, organizations still need a collaborative approach, deep understanding of data processes, and strong leadership to effect real change.

AI-Assisted Decision Making: Healthcare’s Next Frontier

While many healthcare organizations have implemented Artificial Intelligence (AI) and Machine Learning (ML) tools at the point of care, few have successfully applied them to high-level decision making. A new frontier is expanding AI from artificial intelligence to augmented intelligence; traditional AI focuses on improving analytics efficiency while augmented intelligence is about improving the decision-making ability of healthcare leaders. This article addresses the capabilities health systems should embrace and provides two examples of how AI can assist with leaders with their most important decisions. Healthcare leaders’ biggest needs of from AI are the ability to separate signal from noise and make decisions that impact the future.

Artificial Intelligence in Healthcare: A Change Management Problem

The key to successfully leveraging artificial intelligence (AI) in healthcare rests not wholly in the technical aspects of predictive and prescriptive machines but also in change management within healthcare organizations. Better adoption and results with AI rely on a commitment to the challenge of change, the right tools, and a human-centered perspective. To succeed in change management and get optimal value from predictive and prescriptive models, clinical and operational leaders must use three perspectives:

1. Functional: Does the model make sense?
2. Contextual: Does the model fit into the workflow?
3. Operational: What benefits and risks are traded?

Machine Learning Tools Unlock the Most Critical Insights from Unstructured Health Data

Patient comments such as “I feel dizzy” or “my stomach hurts” can tell clinicians a lot about an individual’s health, as can additional background, including zip code, employment status, access to transportation, and more. This critical information, however, is captured as free text, or unstructured data, making it impossible for traditional analytics to leverage. Machine learning tools (e.g., NLP and text mining) help health systems better understand the patient and their circumstances by unlocking valuable insights residing unstructured data:

1. NLP analyzes large amounts of natural language data for human users.
2. Text mining derives value through the analysis of mass amounts of text (e.g., word frequency, length of words, etc.).

A New Era of Personalized Medicine: The Power of Analytics and AI

Healthcare is looking towards an era of personalized medicine in which providers customize treatments for the individual patient. Realizing this tailored level of care s a new level of data volume and analytics and AI capabilities that, while novel to healthcare, other industries are thriving in. Choosing the right role models as healthcare works towards the analytics- and AI-driven territory of personalized medicine will guide informed strategies and establish best practices. With experience and expertise in these key areas, the military, aerospace, and automotive industries can serve as healthcare’s best examples:

1. The human cognitive processes of complex decision making.
2. The digitization of their industries, with the “health” of their assets as key drivers.
3. Operating in a “big data” ecosystem.

How Artificial Intelligence Can Overcome Healthcare Data Security Challenges and Improve Patient Trust

As healthcare organizations today face more security threats than ever, artificial intelligence (AI) combined with human judgment is emerging as the perfect pair to improve healthcare data security. Together, they power a highly accurate privacy analytics model that allows organizations to review access points to patient data and detect when a system’s EHR is potentially exposed to a privacy violation, attack, or breach. With specific techniques, including supervised and unsupervised machine learning and transparent AI methods, health systems can advance toward more predictive, analytics-based, collaborative privacy analytics infrastructures that safeguard patient privacy.

Healthcare Data Management: Three Principles of Using Data to Its Full Potential

Author Douglas Laney is now tackling the topic of Infonomics: the practice of information economics. In his 2017 book, Infonomics: How to Monetize, Manage, and Measure Information as an asset for competitive advantage, Laney provides detailed rationale as well as a thoughtful framework for treating information as a modern-day organization’s most valuable asset. This article walks through how healthcare organizations can leverage data to its full potential using this framework and the three principles of infonomics:

• Measure - How much data does the organization have? What is it worth?
• Manage - What data does the organization have? Where is it stored?
• Monetize - How does the organization use data?

Healthcare NLP: The Secret to Unstructured Data’s Full Potential

While healthcare data is an ever-growing resource, thanks to broader EHR adoption and new sources (e.g., patient-generated data), many health systems aren’t currently leveraging this information cache to its full potential. Analysts can’t extract and analyze a significant portion of healthcare data (e.g., follow-up appointments, vitals, charges, orders, encounters, and symptoms) because it’s in an unstructured, or text, form, which is bigger and more complex than structured data. Natural language processing (NLP) taps into the potential of unstructured data by using artificial intelligence (AI) to extract and analyze meaningful insights from the estimated 80 percent of health data that exists in text form. Though still an evolving capability, NLP is showing promise in helping organizations get more from their data.

Customer Journey Analytics: Cracking the Patient Engagement Challenge for Payers

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.

Reducing Hospital Readmissions: A Case for Integrated 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.

Healthcare NLP: Four Essentials to Make the Most of Unstructured Data

Many health systems are eager to embrace the capability of natural language processing (NLP) to access the vast patient insights recorded as unstructured text in clinical notes and records. Many healthcare data and analytics teams, however, aren’t experienced in or prepared for the unique challenges of working with text and, specifically, don’t have the knowledge to transform unstructured text into a usable format for NLP. Data engineers can follow four need-to-know principles to meet and overcome the challenges of making unstructured text available for advanced NLP analysis:

1. Text is bigger and more complex.
2. Text comes from different data sources.
3. Text is stored in multiple areas.
4. Text user documentation patterns matter.

Meaningful Machine Learning Visualizations for Clinical Users: A Framework

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:

1. People: who are the targeted users?
2. Context: in what context or environment do they work?
3. Activities: what activities do they perform?

Three Ways Evidence-Based Medicine Improves Machine Learning

As health systems continue to adopt machine learning to impact significant outcomes (e.g., reducing readmissions, preventing hospital-acquired infections, and reducing length of stay), they must also leverage evidence-based medicine. Evidence adds critical insight to machine learning models, ensuring that models incorporate all necessary variables in their risk prediction, and builds credibility among clinicians. Evidence-based medicine brings three essential elements to healthcare machine learning:

1. Boosts machine learning model credibility.
2. Engages data experts around healthcare projects.
3. Saves time and money and increases ROI.

Cloud-Based Open-Platform Data Solutions: The Best Way to Meet Today’s Growing Health Data Demands

Smartphone applications, home monitoring equipment, genomic sequencing, and social determinants of health are adding significantly to the scope of healthcare data, creating new challenges for health systems in data management and storage. Traditional on-premises data warehouses, however, don’t have the capacity or capabilities to support this new era of bigger healthcare data. Organizations must add more secure, scalable, elastic, and analytically agile cloud-based, open-platform data solutions that leverage analytics as a service (AaaS). Moving toward cloud hosting will help health systems avoid the five common challenges of on-premises data warehouses:

1. Predicting future demand is difficult.
2. Infrastructure scaling is lumpy and inelastic.
3. Security risk mitigation is a major investment.
4. Data architectures limit flexibility and are resource intensive.
5. Analytics expertise is misallocated.