natural language processing Archives - Binary Fountain

Value-Based Care, Payers, and Patient Experience Data

value-based-care-payerAs value-based care flourishes, payers are starting to pay special attention to key steps on the patient’s care journey. In order to understand that journey and efficiently lower the costs of care, payers need to address questions about the member experience:

How do members navigate the systems payers have in place? How do they feel about the network of providers? Can members easily access important tools like telemedicine? How do members rate the overall quality of their health plan?

An increasing number of Natural Language Processing (NLP) powered tools are allowing organizations to swiftly collect and analyze bulk patient feedback. This technology allows users to quickly quantify and analyze open-text patient feedback. For payers, it’s a tool to understand and measure the entire patient journey and all aspects of member experience.

This post will explore how payers can use patient feedback data to improve patient experience, provider experience, and administrative workflows. Then, you’ll see how these improvements lead to lower healthcare costs and better outcomes.

How Can Payers Improve Patient Experience?

Payers can expand their access to customer feedback by increasing the types of surveys they analyze beyond CAHPS and HOS. Surveying can detect member sentiments on health plans, feedback on providers, and other trends in open-text feedback.

Organizations can build a comprehensive data hub by collecting patient feedback from surveys, call centers, social media reviews, and other member sources. Then, NLP analysis can turn that data into patient experience insights across multiple categories at the provider level.

Here are some ways payers are improving the patient experience with feedback data:

  • Capturing ratings and reviews in member portals so patients can see feedback and make decisions on their care journey
  • Providing scores for individual providers so members can utilize quantitative data from other patient’s experiences to compare options Proactively surveying members quickly after each episode of care to get real-time feedback
  • Using feedback to benchmark provider performance and help them improve. Physician and provider liaisons can follow up with providers on cost, quality, and patient feedback data
  • Leveraging scoring and feedback data in care coordination and referral management

NLP data helps payers understand what drives positive patient experience both inside and outside of the provider’s office. This includes members’ choices of their network providers on their patient portals and continues through each step of the care journey.

Quantify Patient Experience for Each Provider

Payers can also analyze patient feedback to measure provider performance. According to research, patients care most about the following provider experience quality measures:

  1. Thoroughness of examination
  2. Patient inclusion in decisions
  3. Ability to answer questions
  4. Provider’s attitude
  5. Patient perceived outcomes
  6. Amount of time spent with patients
  7. Provider’s follow-up with patients
  8. Clarity of care plan instructions
  9. Patient loyalty
  10. General Feedback

Payers can use these 10 patient experience categories to analyze feedback about each provider in their network. Subsequently, they can share insights and trends with their networks of providers to help guide better patient experiences.

Open-text, or unstructured, feedback allows patients to communicate their exact feelings and observations. In contrast, multiple-choice answers force survey respondents to compromise on the closest fit response. NLP technology allows payers to rapidly process this free-response feedback. First, the software detects patient sentiment through words and phrases in patient feedback. It can then easily quantify and translate those insights into patient experience scores.

Reducing the time period between care delivery and patient experience feedback is critical. In order to assist, software tools can integrate with APIs and health system EMRs for immediate, high-quality feedback. In addition, payers can publish this member-generated content on their websites and provide profiles to be transparent and consumer-friendly.

Here are ways insurers and managed care organizations can increase transparency by sharing patient experience data:

  • Create a Patient Experience score alongside Cost and Quality metrics for search pages and provider profiles
  • Allow patients to sort and filter patient experience scores by specific key performance indicators
  • Showcase provider feedback on member portals to encourage patient content

Supporting Providers, Solving Workflow Funnels, and Making Value-Based Care Possible for Payers

As payers capture patient feedback data to optimize their networks, they can also improve provider experience. Insights about network providers and staff will help payers understand how to support providers in their network.

  • Provider Performance Management: Use custom patient experience reports to understand trends and benchmarks for providers.
  • Referral Insights: Share patient experience insights with PCPs to broaden the data scope on referrals for members.
  • Internal Stakeholders: Optimize health plans and networks through Root Cause Analysis.

Provider feedback could be particularly useful as healthcare reimbursement shifts from fee-for-service based models to value-based payment programs. In order to keep the focus on patient care and maintain high-performance results, alternative payment models need to reduce provider burdens.

Provider feedback data will be an important source for effective change for payers through this value-based care reimbursement transition. Therefore, payers should track how their policies are affecting providers’ ability to care for their patients.

Insurance companies could also track how changes affect provider satisfaction. Happy providers lead to happy patient members, which make loyal customers. Not to mention, provider survey data is key to achieving the Quadruple Aim of healthcare, which you can read about here.

For more on payers and patient experience, browse these related posts:


4 Use Cases for Natural Language Processing (NLP) in Healthcare

nlp-in-healthcareHealthcare organizations have more access than ever to data-driven technology that can improve healthcare outcomes and drive business opportunities. It’s not easy for these enterprise systems to harness the trillions of gigabytes of health data and web content, but Natural Language Processing (NLP) in healthcare is a promising part of the solution.

As the digitization of healthcare continues, the industry is also looking to make better use of unstructured data. NLP describes the ways in which artificial intelligence systems gather and analyze unstructured data from human language to extract patterns, uncover meaning and formulate responses.  In other words, NLP attempts to get to the heart of language formation and use that understanding to automate and improve human processes.

Leveraged properly, the technology enables providers to automate administrative workflows, invest more time in patient care and improve patient experience using real-time data.

In this article, we will cover the most beneficial uses of NLP for healthcare companies, including benchmarking patient experience, review management and sentiment analysis, dictation and EMR implications and predictive analytics.

Here are some of the top use cases for NLP technology in healthcare:

1. Patient Experience and Value-Based Care

The unstructured clinical record and the patient feedback that comes after a visit contain insights into the patient experience that aren’t available in the structured record. NLP technology can identify these gaps by pulling key words and phrases from free text that will inform care decisions and benchmark the patient experience across physicians and locations.

This type of data mining in healthcare, made possible by NLP, can help reduce subjectivity in decision-making and help organizations deliver better, more efficient care to patients.

Meanwhile, the shift to value-based reimbursement means healthcare organizations need to measure provider performance and identify gaps in care for reporting to payers and regulators.

The value-based care model incentivizes both providers and payers to demonstrate positive patient outcomes after leaving the clinical setting. Data-rich health systems are now using natural language processing to analyze post-care survey feedback, online reviews, social media posts, and many other sources of unstructured text. These insights are key to identifying positive and negative patient experience factors that, if optimized or improved, will lead to higher CAHPS scores and provider ratings.

Use Case:

French research group developed an NLP-based algorithm that would help monitor, detect and prevent hospital acquired infections. It made sense of unstructured data from clinical notes and patient feedback, and used those insights to identify early signs of infections and notify clinicians.

2. Review Management and Sentiment Analysis

In addition to patient experience improvements, NLP can help healthcare organizations manage online reviews in a highly regulated industry.

Natural Language Processing technology can collect and analyze the thousands of healthcare reviews posted every day on third-party listings, finding protected health information (PHI), profanity or other content relevant to HIPAA compliance. It can also quickly analyze and evaluate human sentiment of unstructured comments, along with the context of how they are being used.

In this case study, learn how Temple University Health System leverages Binary Fountain’s NLP technology to analyze unstructured survey responses with an accuracy rate greater than 90%, turning qualitative data into quantitative business intelligence about patient experience.

Many healthcare systems also use text analytics to monitor the Voice of Consumer in reviews, so physicians understand how patients talk about their care and can better communicate using a shared vocabulary. Similarly, NLP systems can track consumer sentiment about your healthcare brand by pulling insights from positive and negative words or phrases within reviews or social media posts.

Use Case:

A Sant Baba Bhag Singh University study found that using sentiment analysis from social media data helped providers improve treatments by understanding how patients talk about their Type-1 and Type-2 Diabetes treatments, drugs and diet regiments.

3. Dictation and EMR Implications

An average EMR record runs between 50 and 150 MB per million records, and the average clinical note record is 150 times as large. To manage that administrative workflow, many physicians are replacing handwriting or typing with voice notes, which NLP tools can easily interpret and add to EMR systems.

This application of NLP allows physicians to automatically transcribe their conversation with patients, which means they can commit more time to improving the quality of care. But its implications go further.

Many of the clinical notes in EMRs are in unstructured form, but NLP offers a way to effectively, and automatically, interpret clinical notes. It can pull details from diagnostic reports and physicians’ letters, ensuring that all relevant information is uploaded to the patient health profile. For example, NLP systems could extract any notes in a patient’s electronic record that mention prescribed medications and if they were effective.

Use Case:

2018 study used NLP to process radiology reports looking for pulmonary embolism and postoperative venous thromboembolism, and found that unstructured data analysis identified 50% more cases than structured data alone.

4. Root Cause Analysis and Predictive Analytics

Another exciting, but more complex, benefit of NLP is how predictive analytics can solve population health problems.

Applying NLP to vast caches of electronic medical records can help identify subsets of geographic regions, ethnic groups or other population segments that face different types of health disparities. Existing administrative databases can’t analyze socio-cultural impacts on health at such a scale, but NLP could pave the way for further research.

NLP-healthcare-use-caseAn often-cited example of this NLP application for healthcare companies is its use for Kawasaki diseases, where delays in diagnosis can lead to critical complications. In a 2016 study, an NLP-based algorithm identified at-risk patients with a sensitivity of 93.6% and specificity of 77.5% compared to notes manually reviewed by clinicians.

At the same time, NLP can be used to analyze unstructured feedback and find the root cause of patients’ concerns or poor outcomes.

For example, healthcare-specific NLP can recognize phrases like “emailed us a video” as a positive sentiment concerning the topic of “Helping Patients Understand” within the “Provider” category. Monitoring long-term trends of sentiment surrounding topics in these categories, like “patient care,” “non-clinical staff” or “facilities,” can help organizations nail down the origins of negative patient experiences for providers or locations.

When patient experience personnel have a true understanding of a patient’s sentiment, they can conduct the appropriate outreach, perform service recovery and build a deeper relationship between the hospital and the patient.

Use Case:

2018 study used NLP to predict suicide attempts by monitoring social media, showing clear indicators of imminent suicide risk by Twitter users who changed their speech patterns on the platform in specific ways. The system’s prediction rate hit 70%, with just a 10% false positive rate.

NLP Made Specifically for Healthcare

Data-driven health systems looking to optimize patient experience, reduce costs and improve care outcomes should consider the myriad insights hidden in unstructured data. With a wealth of patient feedback available, it is imperative for healthcare providers to begin investing and implementing NLP-powered patient feedback management solutions to secure and ensure patient loyalty.

Natural Language Processing is not a one-size-fits-all solution, so NLP systems in the healthcare industry need to understand the sublanguage used by medical professionals and by patients. Binary Fountain’s NLP-driven technology platform was built specifically for the healthcare industry, and can help your organization get the most from both real-time and historical feedback data.

Book a free demo to learn more.


Request a Demo