Leilei Zhu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Leilei Zhu has a total of 24 co-authors. Here are the top co-authors by number of shared publications:
- Anoop Dinesh Shah
Department of Clinical Pharmacology, University College London Hospitals NHS Foundation Trust, London, UK
2 shared publications - Folkert W. Asselbergs
Department of Cardiology, Amsterdam Cardiovascular Sciences, Amsterdam University Medical Centre, University of Amsterdam, Amsterdam, The Netherlands
2 shared publications - Richard Dobson
King's College London, London, United Kingdom
2 shared publications - Wai Keong Wong
Cambridge University Hospitals, Cambridge CB2 0QQ, UK
2 shared publications - Xi Bai
University College London
2 shared publications - A. K. J. M. Wijayarathne
Postgraduate Institute of Medicine
1 shared publication
Latest Publications
- Open Access
- 27 September 2024
- Published by Springer Nature in Research Square
Design and implementation of a natural language processing system at the point of care: MiADE (Medical information AI Data Extractor)
Background: Well-organised electronic health records (EHR) are essential for high quality patient care, but EHR user interfaces can be cumbersome for entry of structured information, resulting in the majority of information being in free text rather than a structured form. This makes it difficult to retrieve information for clinical purposes and limits the research potential of the data. Natural language processing (NLP) at the point of care has been suggested as a way of improving data quality and completeness, but there is little evidence as to its effectiveness. We sought to generate such evidence by developing an open source, modular, configurable NLP system called MiADE, which is designed to integrate with an EHR. This paper describes the design of MiADE and the deployment at University College London Hospitals (UCLH), and is intended to benefit those who may wish to develop or implement a similar system elsewhere. Results: The MiADE system includes components to extract diagnoses, medications and allergies from a clinical note, and communicate with an EHR system in real time using Health Level 7 Clinical Document Architecture (HL7 CDA) messaging. This enables NLP results to be displayed to a clinician for verification before saving them to the patient's record. MiADE utilises the MedCAT library (part of the Cogstack family of NLP tools) for named entity recognition (NER) and linking to SNOMED CT, as well as context detection. MedCAT models underwent unsupervised and supervised training on patient notes from UCLH, achieving precision of 83.2% (95% CI 77.0, 88.1), and recall of 85.2% (95% CI 79.1, 89.8) for detection of diagnosis concepts. In simulation testing we found that MiADE reduced the time taken for clinicians to enter structured problem lists by 89%. We have commenced a trial implementation of MiADE at UCLH in live clinical use, integrated with the Epic EHR at UCLH. Conclusions: We have developed an open source point of care NLP system called MiADE and successfully integrated it with a live EHR at a major hospital for an evaluation study.
- 27 September 2024
- Published by Springer Nature in Research Square
Open AccessDesign and implementation of a natural language processing system at the point of care: MiADE (Medical information AI Data Extractor)
Background: Well-organised electronic health records (EHR) are essential for high quality patient care, but EHR user interfaces can be cumbersome for entry of structured information, resulting in the majority of information being in free text rather than a structured form. This makes it difficult to retrieve information for clinical purposes and limits the research potential of the data. Natural language processing (NLP) at the point of care has been suggested as a way of improving data quality and completeness, but there is little evidence as to its effectiveness. We sought to generate such evidence by developing an open source, modular, configurable NLP system called MiADE, which is designed to integrate with an EHR. This paper describes the design of MiADE and the deployment at University College London Hospitals (UCLH), and is intended to benefit those who may wish to develop or implement a similar system elsewhere. Results: The MiADE system includes components to extract diagnoses, medications and allergies from a clinical note, and communicate with an EHR system in real time using Health Level 7 Clinical Document Architecture (HL7 CDA) messaging. This enables NLP results to be displayed to a clinician for verification before saving them to the patient's record. MiADE utilises the MedCAT library (part of the Cogstack family of NLP tools) for named entity recognition (NER) and linking to SNOMED CT, as well as context detection. MedCAT models underwent unsupervised and supervised training on patient notes from UCLH, achieving precision of 83.2% (95% CI 77.0, 88.1), and recall of 85.2% (95% CI 79.1, 89.8) for detection of diagnosis concepts. In simulation testing we found that MiADE reduced the time taken for clinicians to enter structured problem lists by 89%. We have commenced a trial implementation of MiADE at UCLH in live clinical use, integrated with the Epic EHR at UCLH. Conclusions: We have developed an open source point of care NLP system called MiADE and successfully integrated it with a live EHR at a major hospital for an evaluation study.
- Open Access
- 24 August 2022
- Published by JMIR Publications Inc. in JMIR Medical Informatics
- Vol. 10 (8) , e38122
Deployment of a Free-Text Analytics Platform at a UK National Health Service Research Hospital: CogStack at University College London Hospitals
Background: As more health care organizations transition to using electronic health record (EHR) systems, it is important for these organizations to maximize the secondary use of their data to support service improvement and clinical research. These organizations will find it challenging to have systems capable of harnessing the unstructured data fields in the record (clinical notes, letters, etc) and more practically have such systems interact with all of the hospital data systems (legacy and current). Objective: We describe the deployment of the EHR interfacing information extraction and retrieval platform CogStack at University College London Hospitals (UCLH). Methods: At UCLH, we have deployed the CogStack platform, an information retrieval platform with natural language processing capabilities. The platform addresses the problem of data ingestion and harmonization from multiple data sources using the Apache NiFi module for managing complex data flows. The platform also facilitates the extraction of structured data from free-text records through use of the MedCAT natural language processing library. Finally, data science tools are made available to support data scientists and the development of downstream applications dependent upon data ingested and analyzed by CogStack. Results: The platform has been deployed at the hospital, and in particular, it has facilitated a number of research and service evaluation projects. To date, we have processed over 30 million records, and the insights produced from CogStack have informed a number of clinical research use cases at the hospital. Conclusions: The CogStack platform can be configured to handle the data ingestion and harmonization challenges faced by a hospital. More importantly, the platform enables the hospital to unlock important clinical information from the unstructured portion of the record using natural language processing technology.
- 24 August 2022
- Published by JMIR Publications Inc. in JMIR Medical Informatics
- Vol. 10 (8) , e38122
Open AccessDeployment of a Free-Text Analytics Platform at a UK National Health Service Research Hospital: CogStack at University College London Hospitals
Background: As more health care organizations transition to using electronic health record (EHR) systems, it is important for these organizations to maximize the secondary use of their data to support service improvement and clinical research. These organizations will find it challenging to have systems capable of harnessing the unstructured data fields in the record (clinical notes, letters, etc) and more practically have such systems interact with all of the hospital data systems (legacy and current). Objective: We describe the deployment of the EHR interfacing information extraction and retrieval platform CogStack at University College London Hospitals (UCLH). Methods: At UCLH, we have deployed the CogStack platform, an information retrieval platform with natural language processing capabilities. The platform addresses the problem of data ingestion and harmonization from multiple data sources using the Apache NiFi module for managing complex data flows. The platform also facilitates the extraction of structured data from free-text records through use of the MedCAT natural language processing library. Finally, data science tools are made available to support data scientists and the development of downstream applications dependent upon data ingested and analyzed by CogStack. Results: The platform has been deployed at the hospital, and in particular, it has facilitated a number of research and service evaluation projects. To date, we have processed over 30 million records, and the insights produced from CogStack have informed a number of clinical research use cases at the hospital. Conclusions: The CogStack platform can be configured to handle the data ingestion and harmonization challenges faced by a hospital. More importantly, the platform enables the hospital to unlock important clinical information from the unstructured portion of the record using natural language processing technology.