Healthcare Analytics, Population Health Management, Healthcare Big Data

Tools & Strategies News

Artificial Intelligence, Big Data Basics Lead Top 10 Stories of 2018

Industry professionals are looking to absorb the basics of artificial intelligence and big data analytics as they move into a complex and challenging 2019.

Artificial intelligence and big data analytics in healthcare

Source: Thinkstock

By Jennifer Bresnick

- Healthcare professionals gearing up for a data-driven 2019 have spent the past year equipping themselves with the knowledge they need to succeed in a heavily digital environment.

Readers of HealthITAnalytics.com couldn’t get enough of artificial intelligence and big data analytics, both of which have advanced by leaps and bounds in recent months.

Our “how to” articles featured most often on the reading lists of industry professionals, indicating that many executive and clinical leaders are still cultivating an understanding of these complex and promising technologies.

From clinical decision support and imaging analytics to risk scoring, natural language processing, and breaking down data siloes, readers appear extremely eager to develop the skills and strategies required to turn their data assets into actionable insights.

Counting down to the most popular article, here are our top ten stories from 2018.

10. Top 10 Disruptive Companies to Watch in the Healthcare Space

Amazon, Apple, and Google – oh my!  The tech giants are gathering to fight for a piece of the healthcare pie, and they are bringing their considerable data-savvy to bear on the problems of consumerism, price transparency, and data analytics. 

Amazon’s intriguing moves into population health and its partnership with JP Morgan Chase and Berkshire Hathaway may have grabbed the most headlines in 2018, but plenty of other new players are making moves to watch.

Google, Apple, Microsoft, and even Facebook are exploring how best to use their enormous data analytics experience and serious financial clout to make a dent in spending and outcomes, leaving traditional enterprises to get better at what they do – or get out of the way.

9. Arguing the Pros and Cons of Artificial Intelligence in Healthcare

Artificial intelligence is becoming more and more ingrained into everyday life, and the trepidation around smarter-than-human algorithms hasn’t gone away.  Clinicians remain wary of AI for a number of reasons, and many have not yet relinquished the idea that AI is out for their jobs.

Questions of ethics, liability, accuracy, and privacy remain unanswered as we head into 2019, leaving many stakeholders debating whether or not AI is really the answer to some of healthcare’s most pressing questions.

In this article, we break down the arguments for and against artificial intelligence and examine some of the issues likely to be facing the industry for many years to come.

8. What Are the Social Determinants of Population Health?

The circumstances in which people live, work, and play are becoming increasingly important for healthcare providers who are financially responsible for long-term outcomes. 

The social determinants of health (SDOH) can influence between 60 and 80 percent of a person’s outcomes, significantly outweighing the impact of direct clinical care.

But what exactly are these factors, how can providers identify socioeconomic issues, and what can they do to address these key challenges that affect the majority of people in one way or another?

This resource breaks down some of the most common social determinants and offers data and resources to help providers jumpstart their population health management initiatives.

7. Five Blockchain Use Cases for Healthcare Payers, Providers

Artificial intelligence isn’t the only emerging technology capturing the interest of healthcare stakeholders.  Blockchain, the distributed ledger methodology best known for supporting Bitcoin, is also finding a place in the health IT landscape.

It isn’t always easy to understand – and even with a firm grasp on how the technology works, it’s not always clear how it will be applied to healthcare’s big problems.

Payers and providers considering adding blockchain to their toolkits may wish to check out this list of potential use cases for the decentralized data management strategy.

6. Understanding the Basics of Clinical Decision Support

Connecting providers to the right information at the right time is an ongoing challenge for healthcare organizations, especially those that feel like they are drowning in data but lacking meaningful information.

Clinical decision support (CDS) tools that sift through huge volumes of data to recommend treatments, tests, or diagnoses can help to ease the cognitive burdens created by digital data overload.

But what exactly does “clinical decision support” mean, and how can providers choose and implement these tools effectively?

In this article, HealthITAnalytics.com breaks down the basics of clinical decision support and shares expert opinions on how to integrate CDS into the clinical workflow.

5. 10 High-Value Use Cases for Predictive Analytics in Healthcare

Figuring out how to apply emerging technologies to real-world use cases can be a challenge, especially when facing a category of tools as broad as “predictive analytics.”

Predictive analytics tools can leverage machine learning to offer proactive warnings or suggestions for care, but they can also rely on more traditional statistical modeling as well.

What are the top clinical and administrative use cases for predictive analytics, and how are healthcare organizations taking advantage of algorithms that purport to offer a glimpse into the future?

4. Using Risk Scores, Stratification for Population Health Management

Risk scoring is a fundamental competency for population health management, especially in organizations that have limited resources to address a wide range of clinical and socioeconomic needs – in other words, just about every organization.

Identifying patients headed for an expensive, traumatic exacerbation of a chronic disease before they experience a crisis can reduce spending for providers while maintaining a higher quality of life for patients. 

Big data analytics skills are required to develop risk scores and present information to providers in a meaningful, workflow-friendly manner.  Organizations must gather as much relevant data as possible to create comprehensive and accurate scores, giving providers another tool to engage patients and decide on a plan of care.

In this very popular piece, experts explain how they are applying risk scoring strategies to their population health management problems and why it is important for providers and payers to develop stratification tools to identify and manage high-risk individuals.

3. What is the Role of Natural Language Processing in Healthcare?

Natural language processing (NLP) is a branch of machine learning that focuses on interpreting unstructured data – such as free text notes or voice inputs – into a structured, machine-readable format.

With the rise of chatbots, the growing need for EHR documentation assistance, and the exponential explosion of clinical notes that contain valuable fodder for analytics, NLP has become a major focus for the industry.

But unstructured data, by its very nature, is messy and variable.  NLP tools sometimes find it difficult to identify semantic meaning from a language as rich in idioms as English, and matching the myriad ways to express common clinical terms with their underlying meaning can be problematic.

How is NLP finding a place in healthcare, and what are the challenges that developers will need to overcome in order to create useful, accurate tools to improve the workflow?

2. Top 10 Challenges of Big Data Analytics in Healthcare

Our second most popular story of the year breaks down the top big data analytics challenges facing the healthcare industry.

Big data is complicated by nature, and organizations struggling with legacy infrastructure – and legacy ideas about governance and data management – are likely to face some significant problems as they attempt to generate actionable insights.

From capturing and querying data to visualizing and reporting on the results, analytics is full of potential pitfalls.  This top 10 list follows data throughout its lifecycle, addressing the potential issues facing healthcare stakeholders every step of the way.

1. Top 12 Ways Artificial Intelligence Will Impact Healthcare

2018 was a huge year for artificial intelligence, building upon the lessons learned throughout the beginning of the decade. 

The sophistication of AI tools increased extremely rapidly in a shockingly short period of time, inspiring Partners Healthcare to devote an entire three-day event to discussing the challenges and opportunities of AI in healthcare.

The World Medical Innovation Forum was packed with luminaries from Partners, Harvard University, and the broader technology development sector.

At the end of the conference, experts from across the sector presented the “Disruptive Dozen” – a list of twelve areas that are expected to see an AI overhaul in the near future.

These top 12 use cases for artificial intelligence captivated our readers during 2018, becoming – by far – our most-read story of the year.  

The interest in artificial intelligence doesn’t seem like it will be slackening any time soon. 

AI is finding its way into any number of innovative tools and technologies to address common pain points in the industry, and the intense focus on research and development is producing startling new breakthroughs on an almost-daily basis.

As the calendar year comes to a close, it seems safe to predict that many of 2019’s top stories will also revolve around artificial intelligence and how cutting-edge analytics are revolutionizing the care continuum.

Stay tuned to HealthITAnalytics.com over the next twelve months to find out!

X

Join 25,000 of your peers

Register for free to get access to all our articles, webcasts, white papers and exclusive interviews.

Our privacy policy


no, thanks

Continue to site...