Med7: A transferable clinical natural language processing model for electronic health records

Kormilitzin, Andrey; Vaci, Nemanja; Liu, Qiang; Nevado‐Holgado, Alejo J.

doi:10.1016/j.artmed.2021.102086

Cited by 91 publications

(61 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These files are of significant value to medical research as they contain rich information about patients. In the current study, the records of prescribed medications along with the cognitive test results including Health of the Nation Outcomes Scales (HoNOS), Montreal Cognitive Assessment (MoCA) scores and Mini-Mental State Examination (MMSE) scores were extracted by means of clinical natural language processing (NLP) models [8][9][10][11][12]. We used an NLP text extraction system designed for CRIS/OX and achieved an F1 score of 92.8% and 98.03% for diagnosis and medication respectively [13].…”

Section: Data Source and Extractionmentioning

confidence: 99%

Validation of UK Biobank data for mental health outcomes: A pilot study using secondary care electronic health records

Kormilitzin

Fernandes

et al. 2022

International Journal of Medical Informatics

Self Cite

View full text Add to dashboard Cite

Section: Data Source and Extractionmentioning

confidence: 99%

Validation of UK Biobank data for mental health outcomes: A pilot study using secondary care electronic health records

Kormilitzin

Fernandes

et al. 2022

International Journal of Medical Informatics

Self Cite

View full text Add to dashboard Cite

“…Various NLP methods have been developed and applied to represent and extract clinically meaningful information from chronologically ordered patients' free-text records (Dalianis, 2018). The common approach was to train an information extraction model (Kormilitzin et al, 2021;Wang et al, 2018) to recognise a predefined set of clinical concepts of interest (e.g. medications, symptoms, health conditions).…”

Section: Natural Language Processing For Longitudinal Patient Representationmentioning

confidence: 99%

CHRONOSIG: Digital Triage for Secondary Mental Healthcare using Natural Language Processing - rationale and protocol

Joyce

Kormilitzin

Hamer-Hunt

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

BackgroundAccessing specialist secondary mental health care in the NHS in England requires a referral, usually from primary or acute care. Community mental health teams triage these referrals deciding on the most appropriate team to meet patients’ needs. Referrals require resource-intensive review by clinicians and often, collation and review of the patient’s history with services captured in their electronic health records (EHR). Triage processes are, however, opaque and often result in patients not receiving appropriate and timely access to care that is a particular concern for some minority and under-represented groups. Our project, funded by the National Institute of Health Research (NIHR) will develop a clinical decision support tool (CDST) to deliver accurate, explainable and justified triage recommendations to assist clinicians and expedite access to secondary mental health care.MethodsOur proposed CDST will be trained on narrative free-text data combining referral documentation and historical EHR records for patients in the UK-CRIS database. This high-volume data set will enable training of end-to-end neural network natural language processing (NLP) to extract ‘signatures’ of patients who were (historically) triaged to different treatment teams. The resulting algorithm will be externally validated using data from different NHS trusts (Nottinghamshire Healthcare, Southern Health, West London and Oxford Health). We will use an explicit algorithmic fairness framework to mitigate risk of unintended harm evident in some artificial intelligence (AI) healthcare applications. Consequently, the performance of the CDST will be explicitly evaluated in simulated triage team scenarios where the tool augments clinician’s decision making, in contrast to traditional “human versus AI” performance metrics.DiscussionThe proposed CDST represents an important test-case for AI applied to real-world process improvement in mental health. The project leverages recent advances in NLP while emphasizing the risks and benefits for patients of AI-augmented clinical decision making. The project’s ambition is to deliver a CDST that is scalable and can be deployed to any mental health trust in England to assist with digital triage.

show abstract

“…At present, the use of data mining and machine learning techniques for medicine has accelerated in growth, focusing on the health of the patient and the ability to predict diseases. Some benefits of medical data analysis are: (a) its patient-centred and structured information, (b) the ability to cluster the population into groups according to features such as diagnosis or disease stage, (c) the ability to carry out analyses of drug effectiveness and effects in people, and (d) clinical patterns [ 2 , 3 ]. Novel information technologies and computational methods can be used to improve the analysis and processing of medical data.…”

Section: Introductionmentioning

confidence: 99%

Multi-Class Classification of Medical Data Based on Neural Network Pruning and Information-Entropy Measures

Sánchez-Gutiérrez

González-Pérez

2022

Entropy

View full text Add to dashboard Cite

Medical data includes clinical trials and clinical data such as patient-generated health data, laboratory results, medical imaging, and different signals coming from continuous health monitoring. Some commonly used data analysis techniques are text mining, big data analytics, and data mining. These techniques can be used for classification, clustering, and machine learning tasks. Machine learning could be described as an automatic learning process derived from concepts and knowledge without deliberate system coding. However, finding a suitable machine learning architecture for a specific task is still an open problem. In this work, we propose a machine learning model for the multi-class classification of medical data. This model is comprised of two components—a restricted Boltzmann machine and a classifier system. It uses a discriminant pruning method to select the most salient neurons in the hidden layer of the neural network, which implicitly leads to a selection of features for the input patterns that feed the classifier system. This study aims to investigate whether information-entropy measures may provide evidence for guiding discriminative pruning in a neural network for medical data processing, particularly cancer research, by using three cancer databases: Breast Cancer, Cervical Cancer, and Primary Tumour. Our proposal aimed to investigate the post-training neuronal pruning methodology using dissimilarity measures inspired by the information-entropy theory; the results obtained after pruning the neural network were favourable. Specifically, for the Breast Cancer dataset, the reported results indicate a 10.68% error rate, while our error rates range from 10% to 15%; for the Cervical Cancer dataset, the reported best error rate is 31%, while our proposal error rates are in the range of 4% to 6%; lastly, for the Primary Tumour dataset, the reported error rate is 20.35%, and our best error rate is 31%.

show abstract

Med7: A transferable clinical natural language processing model for electronic health records

Cited by 91 publications

References 27 publications

Validation of UK Biobank data for mental health outcomes: A pilot study using secondary care electronic health records

Validation of UK Biobank data for mental health outcomes: A pilot study using secondary care electronic health records

CHRONOSIG: Digital Triage for Secondary Mental Healthcare using Natural Language Processing - rationale and protocol

Multi-Class Classification of Medical Data Based on Neural Network Pruning and Information-Entropy Measures

Contact Info

Product

Resources

About