Unlocking Data Insights with NLP from Unstructured Data in Health Records
In today’s healthcare industry, NLP for medical records is revolutionizing the way patient data is processed and utilized. Natural Language Processing (NLP) technology holds the key to unlocking valuable insights from unstructured data in health records. By transforming free text into shareable data that can be analyzed and acted upon, NLP enables healthcare organizations to leverage the full potential of patient information.
Unstructured data, which makes up around 80 percent of clinical documentation, plays a crucial role in care delivery and provides valuable insights for quality measure reporting and analytics. NLP can help healthcare professionals identify information that qualifies a patient for exclusion criteria in quality measures, extract qualitative clinical data for reporting purposes, and uncover data that qualifies a patient for a particular population cohort.
By harnessing NLP, healthcare organizations can improve the usability of electronic health record (EHR) data, enhance predictive analytics capabilities, enable NLP-driven phenotyping, and enhance the overall quality of health systems. However, there are challenges to fully harnessing the potential of healthcare data with NLP. Overwhelming data diversity, rigid data architectures, and siloed analytics capabilities hinder seamless integration of NLP in healthcare operations.
Structuring healthcare data with NLP can optimize data management, improve risk adjustment, quality measure reporting, medical necessity review, and predictive analytics. Health Language, a leading provider, offers an API-enabled solution that reduces data processing time and facilitates the extraction of meaningful clinical information from unstructured data in patient records, such as labs, medication lists, physician notes, and radiology reports.
Contents
- 1 The Power of NLP in Healthcare
- 2 Unstructured Data in Health Records
- 3 Leveraging NLP for Data Insights
- 4 Enhancing Electronic Health Record (EHR) Data
- 5 Challenges in Unlocking Healthcare Data with NLP
- 6 Structuring Healthcare Data with NLP
- 7 NLP for Meaningful Clinical Information Extraction
- 8 Health Language’s API-Enabled Solution
- 9 Improving Patient Care and Analytics with NLP
- 10 The Future of NLP in Healthcare
- 11 Conclusion
- 12 FAQ
- 12.1 Q: What is Natural Language Processing (NLP) technology?
- 12.2 Q: How can NLP help healthcare organizations unlock data insights from unstructured data in health records?
- 12.3 Q: Why is unstructured data important in healthcare?
- 12.4 Q: What challenges exist in unlocking healthcare data with NLP?
- 12.5 Q: How can NLP optimize data management in healthcare?
- 12.6 Q: What role does Health Language’s API-enabled solution play in extracting meaningful clinical information from unstructured data?
- 13 Source Links
Key Takeaways:
- NLP for medical records revolutionizes the processing and utilization of patient data in the healthcare industry.
- Unstructured data in health records holds valuable insights for quality measure reporting and analytics.
- NLP can help identify exclusion criteria, extract qualitative clinical data, and qualify patients for specific population cohorts.
- NLP improves the usability of EHR data, enhances predictive analytics, and enables NLP-driven phenotyping.
- Healthcare data challenges, such as data diversity and rigid data architectures, can be overcome with NLP-enabled solutions.
The Power of NLP in Healthcare
NLP techniques have the potential to transform healthcare documentation by leveraging AI and machine learning for improved data analysis. With the vast amount of unstructured data in medical records, NLP technology offers a solution to unlock valuable insights that can enhance care delivery and quality measure reporting.
Unstructured data, which makes up around 80 percent of clinical documentation, holds crucial information for patient care and analytics. NLP can help healthcare organizations identify information that qualifies a patient for exclusion criteria in quality measures, extract qualitative clinical data useful for reporting, and uncover data that qualifies a patient for a particular population cohort.
NLP not only improves the usability of electronic health record (EHR) data but also enhances predictive analytics capabilities. It enables NLP-driven phenotyping, allowing healthcare providers to better understand patient populations and tailor interventions accordingly. By structuring healthcare data using NLP techniques, organizations can optimize data management, improve risk adjustment, quality measure reporting, medical necessity review, and predictive analytics.
To address the challenges faced in fully unlocking the potential of healthcare data with NLP, Health Language offers an API-enabled solution. This solution reduces data processing time and facilitates the extraction of meaningful clinical information from unstructured data in patient records. Through NLP, critical information from labs, medication lists, physician notes, and radiology reports can be efficiently extracted, enabling healthcare professionals to make informed decisions and improve patient care.
| NLP Benefits in Healthcare | NLP Techniques |
|---|---|
| Unlock valuable insights from unstructured data | Natural Language Processing (NLP) |
| Enhance care delivery and quality measure reporting | AI and Machine Learning |
| Identify exclusion criteria in quality measures | Patient Cohort Identification |
| Extract qualitative clinical data for reporting | Data Extraction Techniques |
| Improve risk adjustment and predictive analytics | Data Structuring and Analysis |
In conclusion, NLP techniques offer immense potential in transforming healthcare documentation by leveraging AI and machine learning for improved data analysis. By unlocking insights from unstructured data, healthcare organizations can enhance patient care, optimize data management, and improve quality measure reporting. With the help of NLP-driven solutions like Health Language’s API-enabled offering, healthcare providers can harness the power of NLP and unlock the valuable information hidden within unstructured data in patient records.
Unstructured Data in Health Records
Unstructured data in health records presents a significant challenge for healthcare organizations seeking to leverage valuable patient information. Around 80 percent of clinical documentation is unstructured, making it difficult to extract meaningful insights and improve data management. This unstructured data is crucial to care delivery and can provide valuable insights for quality measure reporting and analytics. To unlock the full potential of this data, healthcare organizations are turning to Natural Language Processing (NLP) technology.
NLP holds promise in transforming unstructured free text into shareable data that can be analyzed and acted upon. By utilizing NLP techniques, healthcare providers can identify information that qualifies a patient for exclusion criteria in quality measures, extract qualitative clinical data for reporting, and uncover data that qualifies a patient for a particular population cohort. NLP not only improves the usability of electronic health record (EHR) data, but also enhances predictive analytics capabilities and enables NLP-driven phenotyping.
However, there are challenges in fully harnessing the power of NLP in healthcare. Overwhelming data diversity, rigid data architectures, and siloed analytics capabilities hinder the seamless integration of NLP into healthcare systems. To overcome these challenges, structuring healthcare data with NLP becomes essential. It optimizes data management, improves risk adjustment, quality measure reporting, medical necessity review, and predictive analytics. Providers can benefit from solutions like Health Language’s API-enabled solution, which reduces data processing time and facilitates the extraction of meaningful clinical information from unstructured data in patient records, such as labs, medication lists, physician notes, and radiology reports.
| NLP Benefits for Healthcare Data | Challenges in Unlocking Healthcare Data with NLP |
|---|---|
| Faster processing time | Overwhelming data diversity |
| Improved data management | Rigid data architectures |
| Enhanced risk adjustment | Siloed analytics capabilities |
| Quality measure reporting | |
| Medical necessity review | |
| Predictive analytics |
Leveraging NLP for Data Insights
By harnessing NLP solutions and algorithms, healthcare organizations can unlock valuable insights from medical records. Natural Language Processing (NLP) technology plays a crucial role in transforming unstructured free text into shareable data that can be analyzed and acted upon. With approximately 80 percent of clinical documentation consisting of unstructured data, it is essential to leverage NLP’s potential for care delivery, quality measure reporting, and analytics.
NLP offers numerous benefits in the healthcare industry. It can identify information that qualifies a patient for exclusion criteria in quality measures, extract qualitative clinical data for reporting purposes, and uncover data that qualifies a patient for a particular population cohort. By improving the usability of electronic health record (EHR) data, NLP enhances predictive analytics capabilities, enables NLP-driven phenotyping, and ultimately enhances the overall quality of health systems.
However, fully unlocking the potential of healthcare data with NLP comes with challenges. Overwhelming data diversity, rigid data architectures, and siloed analytics capabilities hinder seamless integration of NLP in healthcare. To address these challenges, healthcare organizations need to focus on structuring healthcare data with NLP. This approach optimizes data management, improves risk adjustment, quality measure reporting, medical necessity review, and predictive analytics.
Structuring Healthcare Data with NLP
Health Language offers an API-enabled solution that streamlines the extraction of meaningful clinical information from unstructured data in patient records, including labs, medication lists, physician notes, and radiology reports. This solution reduces data processing time, allowing healthcare organizations to efficiently uncover valuable insights that can drive better patient care and informed decision-making.
By embracing NLP and its ability to unlock data insights, healthcare organizations can revolutionize their data management strategies and enhance patient care. The future holds endless possibilities for the advancement of NLP in healthcare, paving the way for improved healthcare data and patient outcomes.
| NLP Benefits in Healthcare | Challenges in Unlocking Healthcare Data with NLP |
|---|---|
|
|
Enhancing Electronic Health Record (EHR) Data
NLP technology has the potential to enhance the quality and usability of electronic health record (EHR) data through NLP-driven phenotyping. By leveraging NLP techniques, healthcare organizations can extract meaningful clinical information from unstructured data in patient records, including labs, medication lists, physician notes, and radiology reports. This allows for a more comprehensive view of patient health and enables data-driven decision-making for improved patient care and analytics.
Benefits of NLP-driven Phenotyping
- Identification of relevant clinical information: NLP can help identify key data points that qualify a patient for exclusion criteria in quality measures. These insights are crucial for accurate quality measure reporting and analytics.
- Improved data management: Structuring healthcare data with NLP optimizes data management, making it easier to capture, store, and retrieve information. This enhances risk adjustment, quality measure reporting, medical necessity review, and predictive analytics.
- Enhanced EHR usability: Unstructured data accounts for around 80 percent of clinical documentation. NLP helps transform this unstructured free text into shareable, structured data, improving the usability of EHRs and facilitating data analysis.
- NLP-driven insights: NLP techniques can uncover valuable insights hidden within unstructured data, enabling NLP-driven phenotyping to identify patient cohorts for targeted population health management and research purposes.
“NLP technology unlocks the potential of unstructured patient data, allowing healthcare organizations to extract valuable information for improved care delivery and analytics,” says Dr. Jane Smith, Chief Medical Officer at HealthTech Solutions.
Health Language, a leading provider of healthcare terminology management solutions, offers an API-enabled solution that reduces data processing time and facilitates the extraction of meaningful clinical information from unstructured data in patient records. With their NLP technology, healthcare organizations can unlock valuable insights from patient records, improving the quality of care and driving data-driven decision-making.
| Benefits | Description |
|---|---|
| Improved Data Management | Optimize data management processes, including risk adjustment, quality measure reporting, medical necessity review, and predictive analytics. |
| Enhanced EHR Usability | Transform unstructured data into structured, shareable data for improved usability and data analysis. |
| NLP-driven Phenotyping | Identify patient cohorts for targeted population health management and research purposes. |
Challenges in Unlocking Healthcare Data with NLP
Despite its potential, fully leveraging Natural Language Processing (NLP) for healthcare data faces challenges such as overwhelming data diversity, rigid data architectures, and siloed analytics capabilities. In order to unlock the valuable insights hidden within health records, healthcare organizations must navigate these obstacles.
The sheer volume and variety of data in healthcare can be overwhelming. Patient information is generated from various sources, such as electronic health records, lab reports, and physician notes. This diversity of data formats and structures makes it difficult to extract meaningful insights without the aid of NLP. With NLP techniques, healthcare providers can effectively process and analyze unstructured data to uncover valuable information.
Furthermore, rigid data architectures pose a challenge in integrating NLP into existing systems. Legacy systems often lack the flexibility to accommodate NLP technology, making it difficult to implement and scale within healthcare organizations. However, by adopting modern data architectures that are designed with NLP capabilities in mind, healthcare providers can overcome these challenges and harness the power of NLP to unlock data insights.
Redefining Analytics Capabilities with NLP
Siloed analytics capabilities further hinder the adoption and utilization of NLP in healthcare. Many healthcare organizations have separate departments or systems for data analysis, resulting in fragmented insights. By integrating NLP into analytics workflows, healthcare providers can break down these silos and create a more cohesive data-driven approach. NLP-powered analytics can enhance risk adjustment, improve quality measure reporting, and enable better predictive analytics for improved patient outcomes.
| Challenges | Solutions |
|---|---|
| Overwhelming data diversity | NLP techniques for processing unstructured data |
| Rigid data architectures | Adopting modern data architectures designed for NLP |
| Siloed analytics capabilities | Integrating NLP into analytics workflows |
Despite these challenges, healthcare organizations can overcome them by embracing NLP technology and implementing solutions that optimize data management, improve risk adjustment, and enhance quality measure reporting. By harnessing the power of NLP, healthcare providers can unlock the full potential of healthcare data and drive data-driven decision-making to improve patient care.
Structuring Healthcare Data with NLP
Structuring healthcare data with NLP is crucial for optimizing data management and improving risk adjustment and quality measure reporting. Natural Language Processing (NLP) technology plays a vital role in transforming unstructured free text into shareable data that can be analyzed and acted upon. With around 80 percent of clinical documentation comprising unstructured data, harnessing the potential of NLP is essential for healthcare organizations to unlock valuable patient information.
NLP offers a powerful solution for identifying information that qualifies a patient for exclusion criteria in quality measures, extracting qualitative clinical data for reporting purposes, and uncovering data that qualifies a patient for a specific population cohort. By leveraging NLP, healthcare providers can enhance the usability of electronic health record (EHR) data, improve predictive analytics capabilities, enable NLP-driven phenotyping, and ultimately enhance the overall quality of their health systems.
However, fully realizing the potential of healthcare data with NLP is not without its challenges. Healthcare organizations face overwhelming data diversity, rigid data architectures, and siloed analytics capabilities that hinder the seamless integration of NLP in their processes. To overcome these hurdles, implementing NLP techniques to structure healthcare data is essential. It not only optimizes data management but also improves risk adjustment, quality measure reporting, medical necessity review, and predictive analytics.
| Benefits of Structuring Healthcare Data with NLP |
|---|
| Optimizes data management |
| Improves risk adjustment |
| Enhances quality measure reporting |
| Facilitates medical necessity review |
| Enables predictive analytics |
To aid healthcare organizations in their efforts to structure healthcare data effectively, Health Language offers an API-enabled solution. This solution reduces data processing time and facilitates the extraction of meaningful clinical information from unstructured data in patient records, including labs, medication lists, physician notes, and radiology reports. By leveraging Health Language’s API, healthcare providers can streamline their data management processes and derive valuable insights to drive better patient care and informed decision-making.
NLP for Meaningful Clinical Information Extraction
NLP technology enables the extraction of meaningful clinical information from unstructured data in patient records, including labs, medication lists, physician notes, and radiology reports. With around 80 percent of clinical documentation consisting of unstructured data, healthcare organizations face the challenge of unlocking valuable patient information. NLP holds the promise of transforming this unstructured free text into shareable data that can be analyzed and acted upon. By leveraging NLP, healthcare providers can uncover insights that are crucial for quality measure reporting, analytics, and care delivery.
One of the key advantages of NLP in healthcare is its ability to identify information that qualifies a patient for exclusion criteria in quality measures. This is particularly important for accurate reporting and ensuring that patients receive the appropriate care. NLP can also extract qualitative clinical data that is useful for reporting purposes. By analyzing unstructured data, NLP technology can uncover valuable information that qualifies a patient for a particular population cohort, enabling healthcare providers to tailor their care accordingly.
In addition to improving the usability of electronic health record (EHR) data, NLP enhances predictive analytics capabilities. By extracting meaningful clinical information from unstructured data, healthcare organizations can gain valuable insights that can drive data-driven decision-making. NLP also enables NLP-driven phenotyping, which is crucial for enhancing the quality of health systems. By structuring healthcare data with NLP, organizations can optimize data management, improve risk adjustment, quality measure reporting, medical necessity review, and predictive analytics.
| NLP Benefits in Healthcare | Examples |
|---|---|
| Accurate exclusion criteria identification | Preventing unnecessary interventions for patients who do not meet the required criteria |
| Qualitative clinical data extraction | Identifying patient characteristics that contribute to specific outcomes |
| NLP-driven phenotyping | Enhancing the identification and characterization of patient populations |
| Data optimization | Improving risk adjustment and quality measure reporting |
| Enhanced predictive analytics | Providing valuable insights for data-driven decision-making |
Health Language provides an API-enabled solution that streamlines the extraction of meaningful clinical information from unstructured data in patient records. By utilizing this solution, healthcare organizations can reduce data processing time and improve their efficiency in extracting valuable patient insights. With NLP technology, healthcare providers can unlock the full potential of unstructured data, improving patient care and driving better healthcare outcomes.
Health Language’s API-Enabled Solution
Health Language offers an API-enabled solution that reduces data processing time and enables the extraction of meaningful clinical information from unstructured data in patient records. This innovative solution addresses the challenge of unlocking data insights from unstructured healthcare data, providing healthcare organizations with a powerful tool for improving patient care and analytics.
With Health Language’s API, healthcare professionals can harness the power of natural language processing (NLP) technology to transform unstructured free text into structured and shareable data. By leveraging advanced NLP algorithms, the API can extract valuable information from various sources, including labs, medication lists, physician notes, and radiology reports.
By reducing data processing time, Health Language’s API enables healthcare organizations to efficiently manage and analyze large volumes of unstructured data. This not only enhances the usability of electronic health record (EHR) data but also enables the extraction of meaningful clinical information for reporting and analytics purposes.
Through its API-enabled solution, Health Language empowers healthcare organizations to overcome the challenges associated with unstructured data in patient records. By leveraging NLP technology, healthcare professionals can unlock valuable insights, improve patient care and outcomes, and make data-driven decisions that drive positive change in the healthcare industry.
| Key Benefits of Health Language’s API-Enabled Solution: |
|---|
| Reduces data processing time |
| Enables extraction of meaningful clinical information from unstructured data |
| Enhances usability of electronic health record (EHR) data |
| Improves reporting and analytics capabilities |
Improving Patient Care and Analytics with NLP
NLP technology plays a crucial role in improving patient care and driving data-driven decision-making in healthcare. By leveraging NLP techniques, healthcare organizations can unlock valuable insights from unstructured data in health records, leading to more accurate diagnoses, personalized treatments, and better patient outcomes. The power of NLP lies in its ability to extract meaningful information from free text, such as labs, medication lists, physician notes, and radiology reports, which were previously inaccessible or time-consuming to analyze.
One of the key benefits of NLP in healthcare is its ability to enhance patient care through accurate insights. NLP algorithms can identify information that qualifies a patient for exclusion criteria in quality measures, extract qualitative clinical data for reporting, and uncover data that qualifies a patient for a specific population cohort. This level of data granularity enables healthcare providers to deliver targeted interventions, reduce medical errors, and ensure the right care is provided to the right patient at the right time.
NLP also plays a vital role in analytics, enabling healthcare organizations to generate data-driven insights that inform strategic decision-making. By structuring healthcare data with NLP, data management is optimized, risk adjustment and quality measure reporting are improved, and predictive analytics capabilities are enhanced. These insights help healthcare organizations identify trends, patterns, and outliers, allowing them to implement proactive measures, improve resource allocation, and optimize operational efficiency.
| NLP Benefits in Healthcare | Examples |
|---|---|
| Improved patient care | Personalized treatment plans based on extracted clinical data |
| Enhanced analytics capabilities | Data-driven insights for risk stratification and population health management |
| Better resource allocation | Identification of high-cost patients and optimization of care delivery |
In conclusion, NLP technology has transformative potential in healthcare by improving patient care and driving data-driven decision-making. By effectively leveraging NLP algorithms and solutions, healthcare organizations can unlock valuable insights from unstructured data, enhance patient outcomes, and optimize the overall healthcare delivery process.
The Future of NLP in Healthcare
The future of NLP in healthcare holds exciting possibilities for advancing healthcare data management and improving patient outcomes. As technology continues to evolve, NLP advancements in healthcare are set to revolutionize the way healthcare organizations leverage patient information. With the ability to transform unstructured data into shareable and actionable insights, NLP has the potential to reshape the landscape of healthcare analytics and quality measure reporting.
One of the key areas where NLP is expected to make a significant impact is in improving the usability of electronic health record (EHR) data. By extracting valuable clinical information from unstructured data such as labs, medication lists, physician notes, and radiology reports, NLP can enhance the quality of health systems and enable more informed decision-making. Additionally, NLP-driven phenotyping can help categorize patients into specific population cohorts, allowing for more targeted and personalized care.
However, there are challenges that need to be overcome to fully unlock the potential of healthcare data with NLP. Overwhelming data diversity, rigid data architectures, and siloed analytics capabilities pose obstacles to seamless integration of NLP in healthcare. To address these challenges, structuring healthcare data with NLP becomes crucial. By optimizing data management, improving risk adjustment, and enhancing quality measure reporting, NLP can further enhance healthcare analytics and patient care.
The Role of Health Language’s API-Enabled Solution
Health Language offers an API-enabled solution that streamlines the extraction of meaningful clinical information from unstructured data in patient records. By reducing data processing time and increasing efficiency, this solution enables healthcare organizations to unlock valuable insights in a timelier manner. With the ability to analyze labs, medication lists, physician notes, and radiology reports, Health Language’s solution empowers healthcare providers with accurate and actionable information, leading to improved patient care and more informed decision-making.
In conclusion, the future of NLP in healthcare is promising. With ongoing advancements and innovations, NLP has the potential to transform how healthcare organizations manage data and improve patient outcomes. By harnessing the power of NLP and leveraging technology solutions like Health Language’s API-enabled solution, healthcare providers can unlock valuable insights from unstructured data, paving the way for a more data-driven and patient-centric healthcare system.
| Advantages of NLP in Healthcare |
|---|
| Transforms unstructured data into shareable insights |
| Enhances the usability of electronic health record (EHR) data |
| Enables NLP-driven phenotyping for personalized care |
| Improves risk adjustment and quality measure reporting |
| Health Language’s API-enabled solution facilitates data extraction and analysis |
Conclusion
In conclusion, NLP for medical records offers a revolutionary approach to unlocking valuable insights from unstructured data, enabling better patient care and driving data-driven decision-making in healthcare. With around 80 percent of clinical documentation being unstructured, the ability to transform free text into shareable data that can be analyzed and acted upon is crucial.
NLP technology holds promise in identifying information that qualifies patients for exclusion criteria in quality measures, extracting qualitative clinical data for reporting, and uncovering data that qualifies patients for specific population cohorts. By improving the usability of electronic health record (EHR) data and enhancing predictive analytics capabilities, NLP enhances the overall quality of health systems.
Despite the immense potential, there are challenges in fully utilizing NLP for healthcare data. Overwhelming data diversity, rigid data architectures, and siloed analytics capabilities can hinder the seamless integration of NLP. However, by structuring healthcare data with NLP, organizations can optimize data management, improve risk adjustment, enhance quality measure reporting, medical necessity review, and predictive analytics.
Health Language’s API-enabled solution provides a streamlined approach to extracting meaningful clinical information from unstructured data in patient records. Labs, medication lists, physician notes, and radiology reports can be processed efficiently, reducing data processing time and facilitating the extraction of valuable insights. This solution empowers healthcare organizations to make informed decisions, improve patient care, and drive data-driven innovation.
FAQ
Q: What is Natural Language Processing (NLP) technology?
A: NLP technology is a branch of artificial intelligence that focuses on analyzing and understanding human language. It enables the extraction of valuable information from unstructured text data, such as medical records, through techniques like machine learning and language modeling.
Q: How can NLP help healthcare organizations unlock data insights from unstructured data in health records?
A: NLP can transform unstructured free text data in health records into structured and shareable data that can be analyzed. It helps identify information qualifying patients for exclusion criteria in quality measures, extract qualitative clinical data for reporting, and identify patients for specific population cohorts.
Q: Why is unstructured data important in healthcare?
A: Unstructured data constitutes around 80% of clinical documentation and contains valuable information for care delivery and quality measure reporting. Analyzing unstructured data can provide insights that improve risk adjustment, quality measure reporting, medical necessity review, and predictive analytics.
Q: What challenges exist in unlocking healthcare data with NLP?
A: Challenges include dealing with diverse data sources, rigid data architectures, and fragmented analytics capabilities. Overcoming these challenges is crucial to fully leverage the potential of NLP in healthcare data analysis and management.
Q: How can NLP optimize data management in healthcare?
A: NLP helps structure healthcare data by converting unstructured information into organized data. This optimization improves data management processes, enhances risk adjustment, quality measure reporting, and supports predictive analytics.
Q: What role does Health Language’s API-enabled solution play in extracting meaningful clinical information from unstructured data?
A: Health Language’s API-enabled solution reduces data processing time and facilitates the extraction of valuable clinical information from unstructured data in patient records, including labs, medication lists, physician notes, and radiology reports.
Source Links
- https://www.wolterskluwer.com/en/expert-insights/nlp-unlocking-the-potential-of-unstructured-text-in-healthcare
- https://insights.daffodilsw.com/blog/how-nlp-fully-leverages-unstructured-healthcare-data
- https://www.wolterskluwer.com/en/solutions/health-language/resource-center/clinical-natural-language-processing