Optimisation of natural language processing for real-time structured clinical data capture in electronic health records

Lead Research Organisation: University College London
Department Name: Institute of Health Informatics

Abstract

Information stored in electronic health records (EHRs) can play an important role in supporting clinical decision making (for example, it can help clinicians select the most appropriate medication for a patient), resulting in improved quality of patient care in the NHS. Much of the information in EHRs is recorded as "free text", that is, in ordinary language without any restriction on format, as this is the natural way in which people communicate. Although computers can be used to interpret free text, they cannot always get it right. However, if a standardised, structured format was used for recording information from the outset, this problem could be avoided. However, it can be very time-consuming and cumbersome for clinicians to enter the information in a structured way. This can mean that information is incomplete, or that clinicians are so busy on the computer that they do not have time to listen to their patients.

We are currently developing a system called "MiADE" which can analyse text entered by clinicians; this method is called "natural language processing" (NLP). We are testing out the MiADE system within a specific EHR system called Epic at University College London Hospitals (UCLH). The scope of the current work, which is funded by the National Institute of Health Research, is to extract just basic information about diagnoses. The information extracted includes the diagnosis code, and whether a diagnosis is confirmed, suspected or negative. More detailed information such as diagnosis date, cause, manifestations and evidence cannot be handled by Epic's existing user interface. This limits the potential benefits of the current system.

The aim of this new project is to improve the design of artificial intelligence systems to make it easier for clinicians to record information and thus support clinical decision making. The project will extend the scope of the MiADE system, with the aim to enable future systems to be as useful, effective and easy to use as possible.

The first objective is to develop more advanced NLP methods that can capture more details about diagnoses. We will develop new NLP methods to extract information about date, cause, manifestations and evidence for a diagnosis from free text. We will use EHR data from UCLH to develop and test the NLP methods. We will then use the new methods to study patients with fluid overload due to impaired heart function ('heart failure') in UCLH data. We will extract information from clinical notes about the subtype and cause of their heart failure, and the severity of their symptoms.

The second objective is to create and test an experimental user interface to enable clinicians to interact with the NLP system more easily. The user interface will allow clinicians to enter new information about diagnoses in a structured way, and integrate it with information already in the record. We will enable clinicians to test the user interface with simulated patients to ensure that it is easy to use.

The third objective is to find out how necessary it is for NLP systems to 'learn' from local data provided by the healthcare environment in which they are going to be used. We will compare the performance of different NLP systems on patient records from Great Ormond Street Hospital (GOSH), a specialist children's hospital. We will compare the performance of an NLP system trained on GOSH data, an NLP system trained on UCLH data, and a commercial NLP system that was developed without access to hospital data.

Overall, this project will provide an evidence base for improving the way that EHR systems can use NLP to make it easier for clinicians to record detailed information at the point of care. This will support the wider adoption of NLP integrated within EHR systems, resulting in improved patient safety and quality of care. It will also improve the usefulness of health records for research, which will benefit future patients.

Publications

10 25 50
 
Description We are at an early stage in this work so we do not yet have results to share.

The overall aim of this project is to improve the design of artificial intelligence systems to make it easier for clinicians to record information and thus support clinical decision making. The project will extend the scope of our existing NIHR-funded MiADE system which converts diagnoses to structured data at the point of care, and is currently being tested in a feasibility study at University College London Hospitals.

The first objective is to develop more advanced natural language processing models able to capture rich, detailed information about clinical findings and diagnoses in a structured way. This will include handling information about date, cause, manifestations and evidence for a diagnosis.

The second objective is to create and test an experimental user interface to enable clinicians to interact with the natural language processing system more easily. The user interface will allow clinicians to enter new information in a structured way and integrate it with information already in the record without taking any additional time.

The third objective is to find out how necessary it is for a natural language processing system to 'learn' from local data provided by the healthcare environment in which it is going to be used. We will compare the performance of natural language processing systems trained in two different hospitals, and will also compare it with a commercial system that was developed without any access to hospital data.
Exploitation Route The outputs of this project will be useful for a wide range of beneficiaries, including NLP researchers, clinical epidemiologists, clinical software developers and companies developing and marketing natural language processing (NLP) systems. Downstream beneficiaries include clinicians, patients and NHS Trusts.

Benefits for researchers: The new clinical NLP algorithms will be designed to facilitate data entry but may also be used on existing EHRs for retrospective analysis. Richer clinical data will enable a broader range of epidemiological studies to be performed using health record data.

Benefits for companies, implementers and NHS organisations: Evidence of the benefit of point of care NLP tools (including health economic findings) will enable business cases to be drawn up for commissioners and NHS organisations to fund future deployments of such systems.

Benefits for clinicians and patients: When these NLP systems are implemented in clinical care, it will be easier for clinicians to enter high quality structured data at the point of care. This in turn will make it easier for clinicians to retrieve previous medical information in future consultations, and patients will benefit from safer care. In the longer term, there will also be benefits for patients from research using the enhanced datasets.
Sectors Digital/Communication/Information Technologies (including Software)

Healthcare

URL https://www.ucl.ac.uk/health-informatics/research/medical-information-ai-data-extractor-miade
 
Description Collaboration with between UCLH, UCL and Great Ormond Street Hospital 
Organisation Great Ormond Street Hospital for Children NHS Foundation Trust
Country United Kingdom 
Sector Hospitals 
PI Contribution University College London Hospital (UCLH) as the primary clinical site in this study will provide access to clinical notes from patient electronic health records for development and testing of NLP algorithms, as well as access to the Epic electronic health record system for testing the system in live clinical implementation. We were awarded additional funding from EPSRC to extend this work including the testing of NLP algorithms at different sites.
Collaborator Contribution This project is a collaboration between the University College London (UCL) as the academic partner providing expertise in natural language processing and human computer-interaction, UCLH as the primary clinical site where the MiADE point of care NLP system is to be developed and tested, and Great Ormond Street Hospital (GOSH) which will provide a second site to test that the MiADE system.
Impact A collaboration agreement is in place and an evaluation study is being planned for testing the MiADE system in UCLH. Meetings with GOSH have been held and plans are being put in place to create a test implementation of the MiADE system at GOSH.
Start Year 2020
 
Description Collaboration with between UCLH, UCL and Great Ormond Street Hospital 
Organisation University College London
Country United Kingdom 
Sector Academic/University 
PI Contribution University College London Hospital (UCLH) as the primary clinical site in this study will provide access to clinical notes from patient electronic health records for development and testing of NLP algorithms, as well as access to the Epic electronic health record system for testing the system in live clinical implementation. We were awarded additional funding from EPSRC to extend this work including the testing of NLP algorithms at different sites.
Collaborator Contribution This project is a collaboration between the University College London (UCL) as the academic partner providing expertise in natural language processing and human computer-interaction, UCLH as the primary clinical site where the MiADE point of care NLP system is to be developed and tested, and Great Ormond Street Hospital (GOSH) which will provide a second site to test that the MiADE system.
Impact A collaboration agreement is in place and an evaluation study is being planned for testing the MiADE system in UCLH. Meetings with GOSH have been held and plans are being put in place to create a test implementation of the MiADE system at GOSH.
Start Year 2020
 
Description Engagement with UCLH clinical teams to inform clinicians about the MiADE feasibility study 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach Local
Primary Audience Professional Practitioners
Results and Impact Talks were given at clinical governance or teaching meetings for four clinical departments at UCLH in Dec 2023 to Feb 2024 to inform them about the MiADE study, which is recruiting clinicians to trial a new point of care natural language processing system integrated with the electronic health record. The talks included information about current recording of structured information, the need to improve structured data recording, training on the use of the new system and informaiton about the trial.

The departments were: infectious diseases, clinical pharmacology and internal medicine, medicine for the elderly and respiratory medicine.
Year(s) Of Engagement Activity 2023,2024
URL https://www.ucl.ac.uk/health-informatics/research/miade/feasibility-study-miade