Suchergebnisse

ABSTRACT
ObjectivesElectronic Health Records (EHRs) contain a wealth of routinely-collected data that could potentially be used to inform clinical decisions such as the choice between competing treatment regimens. Apart from structured data about diagnoses and biomarkers, these records often include unstructured data such as free-text medication prescriptions. Disjoint toolsets exist for structured and unstructured data, making it difficult to analyse datasets that comprise both structured and unstructured data. Representing free-text items in a structured and standardised format would enable their statistical analysis. The aim of this study was to develop a generic, analytical pipeline that integrates different tools for text analytics and statistical modelling, and to apply it to data from the UK Renal Registry (UKRR) to answer specific clinical and epidemiological questions on kidney transplant immune suppression.
ApproachThe UKRR database comprises data from all renal units in England, Wales and Northern Ireland and consists of both structured and semi-structured data. Our workflow starts by using rules to extract medication regimen from free-text prescriptions, which is then automatically combined with structured patient's record. The data is then analysed for patterns of transplant immune suppression prescribing by specific centres across the UK.
ResultsWe have developed an analytical pipeline for improving concordance between unstructured and structured medical records, combining new and established text analysis and subsequence analysis tools. Results of the study are underway and will be presented at the conference.
ConclusionsWe have developed new framework that integrates tools for text analytics and statistical modelling, to facilitate the analysis of mixed structured and unstructured data. Our analysis of the UKRR data will help to compare immune suppressive treatment regimens, identify best practice, and explore the associations between transplant medication and transplant outcomes.

ABSTRACT
ObjectivesOur group has investigated the occurrence of psychotic(-like) experiences (PLEs) in Twitter posts, namely auditory hallucinations. Tweets classified as potentially related to auditory hallucinations were proportionately higher between 23:00 and 5:00 in comparison to tweets not classified. This may indicate a clinically significant relationship between sleep and PLEs in the general population, a notion supported by the literature. Based on our previous investigation, the current study aimed to explore whether this methodology could be amended to generate datasets regarding sleep experiences in people who self-report a diagnosis of a psychotic disorder.
ApproachThe current investigation seeks to establish if it is feasible to generate anonymised datasets regarding sleep by extracting information from the timelines of people who self-report a psychotic diagnosis. A text mining method was implemented that utilised rule-based semantic filters that aimed to identify self-reported diagnoses. This focused on occurrences of personal and possessive pronouns to detect the subjectivity of tweets, as well as potential diagnostic verb indicators and any mentions of other related factors. For each diagnostic tweet, we collected information from user timelines. A sleep-related classifier was then implemented, which used lexical features (e.g. bag-of-words, part-of-speech tags) to predict whether a given tweet refers to sleep-related experience.
ResultsAfter training the classifier on the bag-of-words model, the most informative words which contributed to the performance of the classifier were: 'sleep', 'can't awake', 'never', 'stress'. Part-of-speech tags (e.g. verbs, adverbs) were also important features. The classification accuracy of the 'bag-of-words' model was better than the 'part-of-speech' model.
Through the method outlined herein, we were able to improve the quality of the generated datasets in comparison to the previous investigation. This methodology also facilitated the mining of individual Twitter users timelines who stated a personal diagnosis. To this end, an additional filter was implemented to identify tweets regarding sleep experience. The potential relationship between sentiment and temporality expressed in diagnosis and sleep experiences are also discussed.
ConclusionsThe results from this study have implications for mental health research on Twitter. Specifically, the refinements in the methodology enabled retrieval of two high quality datasets regarding psychosis and sleep. Therefore it is feasible other psychosis-related phenomena (e.g. visual hallucinations, delusions, medication) could also be applied as separate filters to create one dataset of psychosis-related experiences within individuals diagnosed with psychosis.

BACKGROUND: Use of routinely collected patient data for research and service planning is an explicit policy of the UK National Health Service and UK government. Much clinical information is recorded in free-text letters, reports and notes. These text data are generally lost to research, due to the increased privacy risk compared with structured data. We conducted a citizens' jury which asked members of the public whether their medical free-text data should be shared for research for public benefit, to inform an ethical policy. METHODS: Eighteen citizens took part over 3 days. Jurors heard a range of expert presentations as well as arguments for and against sharing free text, and then questioned presenters and deliberated together. They answered a questionnaire on whether and how free text should be shared for research, gave reasons for and against sharing and suggestions for alleviating their concerns. RESULTS: Jurors were in favour of sharing medical data and agreed this would benefit health research, but were more cautious about sharing free-text than structured data. They preferred processing of free text where a computer extracted information at scale. Their concerns were lack of transparency in uses of data, and privacy risks. They suggested keeping patients informed about uses of their data, and giving clear pathways to opt out of data sharing. CONCLUSIONS: Informed citizens suggested a transparent culture of research for the public benefit, and continuous improvement of technology to protect patient privacy, to mitigate their concerns regarding privacy risks of using patient text data.

Background Use of routinely collected patient data for research and service planning is an explicit policy of the UK National Health Service and UK government. Much clinical information is recorded in free-text letters, reports and notes. These text data are generally lost to research, due to the increased privacy risk compared with structured data. We conducted a citizens' jury which asked members of the public whether their medical free-text data should be shared for research for public benefit, to inform an ethical policy. Methods Eighteen citizens took part over 3 days. Jurors heard a range of expert presentations as well as arguments for and against sharing free text, and then questioned presenters and deliberated together. They answered a questionnaire on whether and how free text should be shared for research, gave reasons for and against sharing and suggestions for alleviating their concerns. Results Jurors were in favour of sharing medical data and agreed this would benefit health research, but were more cautious about sharing free-text than structured data. They preferred processing of free text where a computer extracted information at scale. Their concerns were lack of transparency in uses of data, and privacy risks. They suggested keeping patients informed about uses of their data, and giving clear pathways to opt out of data sharing. Conclusions Informed citizens suggested a transparent culture of research for the public benefit, and continuous improvement of technology to protect patient privacy, to mitigate their concerns regarding privacy risks of using patient text data.

ABSTRACTObjectivesIncreasing interest to use unstructured electronic patient records for research has attracted attention to automated de-identification methods to conduct large scale removal of Personal Identifiable Information (PII). PII mainly include identifiable information such as person names, dates (e.g., date of birth), reference numbers (e.g., hospital number, NHS number), locations (e.g., hospital names, addresses), contacts (e.g., telephone, e-mail), occupation, age, and other identity information (ethnical, religion, sexual) mentioned in a private context.
De-identification of clinical free-text remains crucial to enable large-scale data access for health research while adhering to legal (Data Protection Act 1998) and ethical obligations. Here we present a computational method developed to automatically remove PII from clinical text.
ApproachIn order to automatically identify PII in clinical text, we have developed and validated a Natural Language Processing (NLP) method which combine knowledge- (lexical dictionaries and rules) and data-driven (linear-chain conditional random fields) techniques. In addition, we have designed a novel two-pass recognition approach that uses the output of the initial pass to create patient-level and run-time dictionaries used to identify PII mentions that lack specific contextual clues considered by the initial entity extraction modules. The labelled data used to model and validate our techniques were generated using six human annotators and two distinct types of free-text from The Christie NHS Foundation Trust: (1) clinical correspondence (400 documents) and (2) clinical notes (1,300 documents).
ResultsThe de-identification approach was developed and validated using a 60/40 percent split between the development and test datasets. The preliminary results show that our method achieves 97% and 93% token-level F1-measure on clinical correspondence and clinical notes respectively. In addition, the proposed two-pass recognition method was found particularly effective for longitudinal records. Notably, the performances are comparable to human benchmarks (using inter annotator agreements) of 97% and 90% F1 respectively.
ConclusionsWe have developed and validated a state-of-the-art method that matches human benchmarks in identification and removal of PII from free-text clinical records. The method has been further validated across multiple institutions and countries (United States and United Kingdom), where we have identified a notable NLP challenge of cross-dataset adaption and have proposed using active learning methods to address this problem. The algorithm, including an active learning component, will be provided as open source to the healthcare community.

Background: Clinical free-text data (eg, outpatient letters or nursing notes) represent a vast, untapped source of rich information that, if more accessible for research, would clarify and supplement information coded in structured data fields. Data usually need to be deidentified or anonymized before they can be reused for research, but there is a lack of established guidelines to govern effective deidentification and use of free-text information and avoid damaging data utility as a by-product. Objective: This study aimed to develop recommendations for the creation of data governance standards to integrate with existing frameworks for personal data use, to enable free-text data to be used safely for research for patient and public benefit. Methods: We outlined data protection legislation and regulations relating to the United Kingdom for context and conducted a rapid literature review and UK-based case studies to explore data governance models used in working with free-text data. We also engaged with stakeholders, including text-mining researchers and the general public, to explore perceived barriers and solutions in working with clinical free-text. Results: We proposed a set of recommendations, including the need for authoritative guidance on data governance for the reuse of free-text data, to ensure public transparency in data flows and uses, to treat deidentified free-text data as potentially identifiable with use limited to accredited data safe havens, and to commit to a culture of continuous improvement to understand the relationships between the efficacy of deidentification and reidentification risks, so this can be communicated to all stakeholders. Conclusions: By drawing together the findings of a combination of activities, we present a position paper to contribute to the development of data governance standards for the reuse of clinical free-text data for secondary purposes. While working in accordance with existing data governance frameworks, there is a need for further work to take forward the recommendations we have proposed, with commitment and investment, to assure and expand the safe reuse of clinical free-text data for public benefit.

IntroductionA significant amount of valuable information in Electronic Health Records (EHR) such as laboratory test results or echocardiogram interpretations is embedded in lengthy free-text fields. Often patients' personal information is also included in these narratives. Privacy legislation in different jurisdictions requires de-identification of this information prior to making it available for research. This process can be challenging and time-consuming. In particular, rule-based algorithms may lead to over-masking of essential medical terms, conditions, or devices that are named after individuals.
Objectives and ApproachWe aimed to enhance ICES' existing rule-based application to make it contextually-driven by applying Artificial Intelligence (AI). The ICES team collaborated with computer scientists at the University of Manchester who had already published work in this area and Evenset, a Toronto-based software company. Based on the Manchester University de-identification framework for name entity recognition, three machine learning-based algorithms for name entity recognition were implemented: CRF, BiLSTM recurrent neural networks with GLoVe and ELMo word embeddings. The models were trained on three different types of ICES data: Laboratory results, Electronic Medical Record (EMR) and echocardiogram data. Evenset developed the user interface and the masking modules.
ResultsPreliminary tests have generated very promising results. To improve accuracy of the models, additional data annotation to expand the training datasets is currently being undertaken at ICES. The final framework will be available as an open-source tool for public.
Conclusion / ImplicationsA collaborative approach for solving complex problems like de-identification of text-based medical data is highly efficient, especially where there are unique sets of expertise, resources, data and clinical knowledge among stakeholders.