XBXi Bai

Xi Bai

*This is an algorithmically generated author record based on publicly available information.

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


Xi Bai has a total of 42 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Design and implementation of a natural language processing system at the point of care: MiADE (Medical information AI Data Extractor)

    by Jennifer Jiang-Kells, James Brandreth, Leilei Zhu, Jack Ross, Yogini Jani, Enrico Costanza, Maisarah Amran, Zeljko Kraljevic, Xi Bai, Roberto Cresta, et al.

    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

    Validating transformers for redaction of text from electronic health records in real-world healthcare

    by Zeljko Kraljevic, Anthony Shek, Joshua Au Yeung, Ewart Jonathan Sheldon, Mohammad Al-Agil, Haris Shuaib, Xi Bai, Kawsar Noor, Anoop D. Shah, Richard Dobson, et al.

    Protecting patient privacy in healthcare records is a top priority, and redaction is a commonly used method for obscuring directly identifiable information in text. Rule-based methods have been widely used, but their precision is often low causing over-redaction of text and frequently not being adaptable enough for non-standardised or unconventional structures of personal health information. Deep learning techniques have emerged as a promising solution, but implementing them in real-world environments poses challenges due to the differences in patient record structure and language across different departments, hospitals, and countries. In this study, we present AnonCAT, a transformer-based model and a blueprint on how deidentification models can be deployed in real-world healthcare. AnonCAT was trained through a process involving manually annotated redactions of real-world documents from three UK hospitals with different electronic health record systems and 3116 documents. The model achieved high performance in all three hospitals with a Recall of 0.99, 0.99 and 0.96. Our findings demonstrate the potential of deep learning techniques for improving the efficiency and accuracy of redaction in global healthcare data and highlight the importance of building workflows which not just use these models but are also able to continually fine-tune and audit the performance of these algorithms to ensure continuing effectiveness in real-world settings. This approach provides a blueprint for the real-world use of de-identifying algorithms through fine-tuning and localisation, the code together with tutorials is available on GitHub (https://github.com/CogStack/MedCAT).


  • Open Access

    Deployment of a Free-Text Analytics Platform at a UK National Health Service Research Hospital: CogStack at University College London Hospitals

    by Kawsar Noor, Lukasz Roguski, Xi Bai, Alex Handy, Roman Klapaukh, Amos Folarin, Luis Romao, Joshua Matteson, Nathan Lea, Leilei Zhu, et al.

    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.


  • Open Access

    Investigating the Use of Digital Health Technology to Monitor COVID-19 and Its Effects: Protocol for an Observational Study (Covid Collab Study)

    by Callum Stewart, Yatharth Ranjan, Pauline Conde, Zulqarnain Rashid, Heet Sankesara, Xi Bai, Richard J B Dobson, Amos A Folarin

    Background: The ubiquity of mobile phones and increasing use of wearable fitness trackers offer a wide-ranging window into people’s health and well-being. There are clear advantages in using remote monitoring technologies to gain an insight into health, particularly under the shadow of the COVID-19 pandemic. Objective: Covid Collab is a crowdsourced study that was set up to investigate the feasibility of identifying, monitoring, and understanding the stratification of SARS-CoV-2 infection and recovery through remote monitoring technologies. Additionally, we will assess the impacts of the COVID-19 pandemic and associated social measures on people’s behavior, physical health, and mental well-being. Methods: Participants will remotely enroll in the study through the Mass Science app to donate historic and prospective mobile phone data, fitness tracking wearable data, and regular COVID-19–related and mental health–related survey data. The data collection period will cover a continuous period (ie, both before and after any reported infections), so that comparisons to a participant’s own baseline can be made. We plan to carry out analyses in several areas, which will cover symptomatology; risk factors; the machine learning–based classification of illness; and trajectories of recovery, mental well-being, and activity. Results: As of June 2021, there are over 17,000 participants—largely from the United Kingdom—and enrollment is ongoing. Conclusions: This paper introduces a crowdsourced study that will include remotely enrolled participants to record mobile health data throughout the COVID-19 pandemic. The data collected may help researchers investigate a variety of areas, including COVID-19 progression; mental well-being during the pandemic; and the adherence of remote, digitally enrolled participants. International Registered Report Identifier (IRRID): DERR1-10.2196/32587


  • Open Access

    Investigating the Use of Digital Health Technology to Monitor COVID-19 and Its Effects: Protocol for an Observational Study (Covid Collab Study) (Preprint)

    by Callum Stewart, Yatharth Ranjan, Pauline Conde, Zulqarnain Rashid, Heet Sankesara, Xi Bai, Richard J B Dobson, Amos A Folarin

    BACKGROUND The ubiquity of mobile phones and increasing use of wearable fitness trackers offer a wide-ranging window into people’s health and well-being. There are clear advantages in using remote monitoring technologies to gain an insight into health, particularly under the shadow of the COVID-19 pandemic. OBJECTIVE Covid Collab is a crowdsourced study that was set up to investigate the feasibility of identifying, monitoring, and understanding the stratification of SARS-CoV-2 infection and recovery through remote monitoring technologies. Additionally, we will assess the impacts of the COVID-19 pandemic and associated social measures on people’s behavior, physical health, and mental well-being. METHODS Participants will remotely enroll in the study through the Mass Science app to donate historic and prospective mobile phone data, fitness tracking wearable data, and regular COVID-19–related and mental health–related survey data. The data collection period will cover a continuous period (ie, both before and after any reported infections), so that comparisons to a participant’s own baseline can be made. We plan to carry out analyses in several areas, which will cover symptomatology; risk factors; the machine learning–based classification of illness; and trajectories of recovery, mental well-being, and activity. RESULTS As of June 2021, there are over 17,000 participants—largely from the United Kingdom—and enrollment is ongoing. CONCLUSIONS This paper introduces a crowdsourced study that will include remotely enrolled participants to record mobile health data throughout the COVID-19 pandemic. The data collected may help researchers investigate a variety of areas, including COVID-19 progression; mental well-being during the pandemic; and the adherence of remote, digitally enrolled participants. INTERNATIONAL REGISTERED REPORT DERR1-10.2196/32587

  • Effects of growth hormone on cognitive, motor, and behavioral development in Prader-Willi syndrome children: a meta-analysis of randomized controlled trials

    by Yunyun Luo, Zhoude Zheng, Yingying Yang, Xi Bai, Hongbo Yang, Huijuan Zhu, Hui Pan, Shi Chen

    Purpose The benefits of growth hormone (GH) therapy in Prader-Willi syndrome (PWS) children are well established, but there is still considerable controversy regarding whether GH treatment can improve cognitive, motor, and behavioral development in PWS children. The objectives of this meta-analysis were to quantitatively evaluate the effects of GH on cognitive, motor function, and behavioral development in PWS children. Methods Randomized controlled trials (RCTs) examining the effects of GH on cognitive, motor, and behavioral development in PWS children were identified by searching the MEDLINE, EMBASE, and Cochrane Library databases. Intervention effects were represented by Hedges’g and pooled to calculate effect sizes using a random-effects model. Results Ten relevant studies comprising data from 302 participants were finally included. We observed no significant difference in cognitive performance between the GH treatment group and the control group (p = 0.197). GH treatment was shown to remarkably improve motor development in PWS children compared with the control treatment (p < 0.001), with moderate positive treatment effects (Hedges’g [95% CI] = 0.71 [0.38, 1.03]). There were no significant differences between the GH group and the control group based on objective assessments of behavioral development (p = 0.53). Conclusions The meta-analysis suggested that GH treatment had a significantly positive effect on motor development, with moderate treatment effects in PWS children; however, there was no evidence of effects on cognitive or behavioral development.