Clinical records anonymisation and text extraction (CRATE): an open-source software system

Cardinal, Rudolf N.

doi:10.1186/s12911-017-0437-1

Cited by 41 publications

(35 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Clinician-recorded diagnoses were present in coded data. Medicine information was extracted from free text using GATE-based natural language processing (NLP) software (15). The diseases we focused on included dementia (recorded with ICD-10 codes F00-F03 and G30, or indicated by mentions of cholinesterase inhibitors or glutamate receptor antagonists), substance misuse (F10-F19), severe (serious) mental illness (F20-F29, F30, and F31, or taking antipsychotics), depression (F32 or F33, or taking antidepressants), anxiety (F41 or F42), reaction to severe stress/adjustment disorders (F43), eating disorders (F50), personality disorders (F60-F69), intellectual disability (F70-F79), intentional self-harm (X60-X84), diabetes mellitus (E10-E14, or taking hypoglycemic agents), hypertension or cardiovascular or cerebrovascular disease (I10-I13, I15, I21-I25, and I60-I69, or taking ACE inhibitors, angiotensin-II receptor antagonists, beta blockers, calcium channel antagonists, or diuretics), dyslipidemia (E78, or taking lipid-lowering medications), asthma or chronic obstructive pulmonary disease (COPD) (J44, J45, or taking oral or inhaled corticosteroids, bronchodilators, or antiinflammatory drugs used for airways disease, accepting that oral corticosteroids may also indicate other inflammatory disorders), and cancer (C00-C97, or taking drugs specifically licensed for cancer).…”

Section: Variablesmentioning

confidence: 99%

The Medium-Term Impact of COVID-19 Lockdown on Referrals to Secondary Care Mental Health Services: A Controlled Interrupted Time Series Study

et al. 2020

Self Cite

View full text Add to dashboard Cite

To date, there is a paucity of information regarding the effect of COVID-19 or lockdown on mental disorders. We aimed to quantify the medium-term impact of lockdown on referrals to secondary care mental health clinical services. We conducted a controlled interrupted time series study using data from Cambridgeshire and Peterborough NHS Foundation Trust (CPFT), UK (catchment population ~0.86 million). The UK lockdown resulted in an instantaneous drop in mental health referrals but then a longer-term acceleration in the referral rate (by 1.21 referrals per day per day, 95% confidence interval [CI] 0.41–2.02). This acceleration was primarily for urgent or emergency referrals (acceleration 0.96, CI 0.39–1.54), including referrals to liaison psychiatry (0.68, CI 0.35–1.02) and mental health crisis teams (0.61, CI 0.20–1.02). The acceleration was significant for females (0.56, CI 0.04–1.08), males (0.64, CI 0.05–1.22), working-age adults (0.93, CI 0.42–1.43), people of White ethnicity (0.98, CI 0.32–1.65), those living alone (1.26, CI 0.52–2.00), and those who had pre-existing depression (0.78, CI 0.19–1.38), severe mental illness (0.67, CI 0.19–1.15), hypertension/cardiovascular/cerebrovascular disease (0.56, CI 0.24–0.89), personality disorders (0.32, CI 0.12–0.51), asthma/chronic obstructive pulmonary disease (0.28, CI 0.08–0.49), dyslipidemia (0.26, CI 0.04–0.47), anxiety (0.21, CI 0.08–0.34), substance misuse (0.21, CI 0.08–0.34), or reactions to severe stress (0.17, CI 0.01–0.32). No significant post-lockdown acceleration was observed for children/adolescents, older adults, people of ethnic minorities, married/cohabiting people, and those who had previous/pre-existing dementia, diabetes, cancer, eating disorder, a history of self-harm, or intellectual disability. This evidence may help service planning and policy-making, including preparation for any future lockdown in response to outbreaks.

show abstract

Section: Variablesmentioning

confidence: 99%

The Medium-Term Impact of COVID-19 Lockdown on Referrals to Secondary Care Mental Health Services: A Controlled Interrupted Time Series Study

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…Privacy protection is a critical issue in clinical data sharing for both research and clinical practices, and privacy violations often incur legal problems with substantial consequences. The privacy component embedded in the infrastructure offers technical solutions to deidentify or anonymize patient-level data, such as CRATE [26] and DEDUCE [27]. CRATE is an open-source software system that anonymizes an electronic health records database to create a research database with anonymized patients' data.…”

Section: Resultsmentioning

confidence: 99%

“…First of all, practical implementation requires a more thorough privacy and security component. The privacy and security component is part of the proposed architecture and currently implemented in the prototype using CRATE [26] and HTTPS. However, since only anonymized datasets are used in the evaluation, the deidentification toolkit, CRATE, was not validated.…”

Section: Discussionmentioning

confidence: 99%

A Lightweight API-Based Approach for Building Flexible Clinical NLP Systems

Shen

Krimpen

Spruit

2019

Journal of Healthcare Engineering

View full text Add to dashboard Cite

Natural language processing (NLP) has become essential for secondary use of clinical data. Over the last two decades, many clinical NLP systems were developed in both academia and industry. However, nearly all existing systems are restricted to specific clinical settings mainly because they were developed for and tested with specific datasets, and they often fail to scale up. Therefore, using existing NLP systems for one’s own clinical purposes requires substantial resources and long-term time commitments for customization and testing. Moreover, the maintenance is also troublesome and time-consuming. This research presents a lightweight approach for building clinical NLP systems with limited resources. Following the design science research approach, we propose a lightweight architecture which is designed to be composable, extensible, and configurable. It takes NLP as an external component which can be accessed independently and orchestrated in a pipeline via web APIs. To validate its feasibility, we developed a web-based prototype for clinical concept extraction with six well-known NLP APIs and evaluated it on three clinical datasets. In comparison with available benchmarks for the datasets, three high F1 scores (0.861, 0.724, and 0.805) were obtained from the evaluation. It also gained a low F1 score (0.373) on one of the tests, which probably is due to the small size of the test dataset. The development and evaluation of the prototype demonstrates that our approach has a great potential for building effective clinical NLP systems with limited resources.

show abstract

“…In addition, there are specific psychiatric databases being developed for researchers with some attention paid to the sensitivity of such data and the development of highly sophisticated systems to protect anonymity while also allowing researcher access. 13 There is however no consistency in the kinds of psychiatric databases which currently exist which is arguably ethically and practically problematic. In a 'snapshot' overview of mental health databases available globally, there were no definable boundaries in BD sets in mental health with some generic health databases containing mental health information and with others more specialised and related solely to mental health conditions.…”

Section: Bd and Mental Health Researchmentioning

confidence: 99%

Mental health, big data and research ethics: Parity of esteem in mental health research from a UK perspective

Morton

O’Reilly

2019

Clinical Ethics

View full text Add to dashboard Cite

Central to ethical debates in contemporary mental health research are the rhetoric of parity of esteem, challenges underpinned by the social construct of vulnerability and the tendency to homogenise the population diagnosed with mental health conditions. Such ethical dimensions are further complicated by the contemporary endeavour to work with ‘big data’ which has led to ambitious claims for discovery and knowledge. Research in mental health is challenging due to the perceived constraints of ethical principles such as the protection of autonomy, consent, risk and harms. This article discusses how ethical considerations need to be reconceptualised when using big data sets. The argument is foregrounded with an appraisal of the prevailing political discourse of parity of esteem demonstrating that ongoing disparities in services and research should also be considered when inquiry uses big data.

show abstract

Clinical records anonymisation and text extraction (CRATE): an open-source software system

Cited by 41 publications

References 15 publications

The Medium-Term Impact of COVID-19 Lockdown on Referrals to Secondary Care Mental Health Services: A Controlled Interrupted Time Series Study

The Medium-Term Impact of COVID-19 Lockdown on Referrals to Secondary Care Mental Health Services: A Controlled Interrupted Time Series Study

A Lightweight API-Based Approach for Building Flexible Clinical NLP Systems

Mental health, big data and research ethics: Parity of esteem in mental health research from a UK perspective

Contact Info

Product

Resources

About