scholarly journals Facilitating the ethical use of health data for the benefit of society: electronic health records, consent and the duty of easy rescue

2016 ◽  
Vol 374 (2083) ◽  
pp. 20160130 ◽  
Author(s):  
Sebastian Porsdam Mann ◽  
Julian Savulescu ◽  
Barbara J. Sahakian
Keyword(s):  
Informed Consent ◽  
Electronic Health Records ◽  
Data Science ◽  
Real Life ◽  
Health Data ◽  
Sensitive Information ◽  
Minimal Risk ◽  
Sensitive Data ◽  
Health Records ◽  
Electronic Health

Advances in data science allow for sophisticated analysis of increasingly large datasets. In the medical context, large volumes of data collected for healthcare purposes are contained in electronic health records (EHRs). The real-life character and sheer amount of data contained in them make EHRs an attractive resource for public health and biomedical research. However, medical records contain sensitive information that could be misused by third parties. Medical confidentiality and respect for patients' privacy and autonomy protect patient data, barring access to health records unless consent is given by the data subject. This creates a situation in which much of the beneficial records-based research is prevented from being used or is seriously undermined, because the refusal of consent by some patients introduces a systematic deviation, known as selection bias, from a representative sample of the general population, thus distorting research findings. Although research exemptions for the requirement of informed consent exist, they are rarely used in practice due to concerns over liability and a general culture of caution. In this paper, we argue that the problem of research access to sensitive data can be understood as a tension between the medical duties of confidentiality and beneficence. We attempt to show that the requirement of informed consent is not appropriate for all kinds of records-based research by distinguishing studies involving minimal risk from those that feature moderate or greater risks. We argue that the duty of easy rescue—the principle that persons should benefit others when this can be done at no or minimal risk to themselves—grounds the removal of consent requirements for minimally risky records-based research. Drawing on this discussion, we propose a risk-adapted framework for the facilitation of ethical uses of health data for the benefit of society. This article is part of the themed issue ‘The ethical impact of data science’.

scholarly journals Patients’ moral attitudes toward electronic health records: Survey study with vignettes and statements

2021 ◽  
Vol 27 (1) ◽  
pp. 146045822098003
Author(s):  
Tania Moerenhout ◽  
Ignaas Devisch ◽  
Laetitia Cooreman ◽  
Jodie Bernaerdt ◽  
An De Sutter ◽  
...  
Keyword(s):  
Electronic Health Records ◽  
De Novo ◽  
Information Access ◽  
Survey Study ◽  
Sensitive Information ◽  
Patient Portal ◽  
Care Providers ◽  
Health Records ◽  
Electronic Health ◽  
Moral Attitudes

Patient access to electronic health records gives rise to ethical questions related to the patient-doctor-computer relationship. Our study aims to examine patients’ moral attitudes toward a shared EHR, with a focus on autonomy, information access, and responsibility. A de novo self-administered questionnaire containing three vignettes and 15 statements was distributed among patients in four different settings. A total of 1688 valid questionnaires were collected. Patients’ mean age was 51 years, 61% was female, 50% had a higher degree (college or university), and almost 50% suffered from a chronic illness. Respondents were hesitant to hide sensitive information electronically from their care providers. They also strongly believed hiding information could negatively affect the quality of care provided. Participants preferred to be informed about negative test results in a face-to-face conversation, or would have every patient decide individually how they want to receive results. Patients generally had little experience using patient portal systems and expressed a need for more information on EHRs in this survey. They tended to be hesitant to take up control over their medical data in the EHR and deemed patients share a responsibility for the accuracy of information in their record.

The process of sourcing and preparing electronic health records data to implement a machine-learning algorithm for early identification of maternal cardiovascular risk (Preprint)

2021 ◽  
Author(s):  
Nawar Shara ◽  
Kelley M. Anderson ◽  
Noor Falah ◽  
Maryam F. Ahmad ◽  
Darya Tavazoei ◽  
...  
Keyword(s):  
Machine Learning ◽  
Cardiovascular Risk ◽  
Electronic Health Records ◽  
Patient Care ◽  
Early Identification ◽  
Health Data ◽  
Patient Specific ◽  
Patient Records ◽  
Health Records ◽  
Electronic Health

BACKGROUND Healthcare data are fragmenting as patients seek care from diverse sources. Consequently, patient care is negatively impacted by disparate health records. Machine learning (ML) offers a disruptive force in its ability to inform and improve patient care and outcomes [6]. However, the differences that exist in each individual’s health records, combined with the lack of health-data standards, in addition to systemic issues that render the data unreliable and that fail to create a single view of each patient, create challenges for ML. While these problems exist throughout healthcare, they are especially prevalent within maternal health, and exacerbate the maternal morbidity and mortality (MMM) crisis in the United States. OBJECTIVE Maternal patient records were extracted from the electronic health records (EHRs) of a large tertiary healthcare system and made into patient-specific, complete datasets through a systematic method so that a machine-learning-based (ML-based) risk-assessment algorithm could effectively identify maternal cardiovascular risk prior to evidence of diagnosis or intervention within the patient’s record. METHODS We outline the effort that was required to define the specifications of the computational systems, the dataset, and access to relevant systems, while ensuring data security, privacy laws, and policies were met. Data acquisition included the concatenation, anonymization, and normalization of health data across multiple EHRs in preparation for its use by a proprietary risk-stratification algorithm designed to establish patient-specific baselines to identify and establish cardiovascular risk based on deviations from the patient’s baselines to inform early interventions. RESULTS Patient records can be made actionable for the goal of effectively employing machine learning (ML), specifically to identify cardiovascular risk in pregnant patients. CONCLUSIONS Upon acquiring data, including the concatenation, anonymization, and normalization of said data across multiple EHRs, the use of a machine-learning-based (ML-based) tool can provide early identification of cardiovascular risk in pregnant patients. CLINICALTRIAL N/A

scholarly journals Quality and Certification of Electronic Health Records

2010 ◽  
Vol 01 (02) ◽  
pp. 149-164 ◽  
Author(s):  
E. Ammenwerth ◽  
A. Hoerbst
Keyword(s):  
Information Systems ◽  
Electronic Health Records ◽  
Qualitative Content Analysis ◽  
Real Life ◽  
Health Records ◽  
Selection Processes ◽  
Quality Certification ◽  
The Us ◽  
Service Oriented ◽  
Electronic Health

Summary Background: Numerous projects, initiatives, and programs are dedicated to the development of Electronic Health Records (EHR) worldwide. Increasingly more of these plans have recently been brought from a scientific environment to real life applications. In this context, quality is a crucial factor with regard to the acceptance and utility of Electronic Health Records. However, the dissemination of the existing quality approaches is often rather limited. Objectives: The present paper aims at the description and comparison of the current major quality certification approaches to EHRs. Methods: A literature analysis was carried out in order to identify the relevant publications with regard to EHR quality certification. PubMed, ACM Digital Library, IEEExplore, CiteSeer, and Google (Scholar) were used to collect relevant sources. The documents that were obtained were analyzed using techniques of qualitative content analysis. Results: The analysis discusses and compares the quality approaches of CCHIT, EuroRec, IHE, openEHR, and EN13606. These approaches differ with regard to their focus, support of service-oriented EHRs, process of (re-)certification and testing, number of systems certified and tested, supporting organizations, and regional relevance. Discussion: The analyzed approaches show differences with regard to their structure and processes. System vendors can exploit these approaches in order to improve and certify their information systems. Health care organizations can use these approaches to support selection processes or to assess the quality of their own information systems. Citation: Hoerbst A, Ammenwerth E. Quality and certification of electronic health records – An overview of current approaches from the US and Europe. Appl Clin Inf 2010; 1: 149–164 http://dx.doi.org/10.4338/ACI-2010-02-R-0009

scholarly journals Patient and public attitudes towards informed consent models and levels of awareness of Electronic Health Records in the UK

2015 ◽  
Vol 84 (4) ◽  
pp. 237-247 ◽  
Author(s):  
Fiona Riordan ◽  
Chrysanthi Papoutsi ◽  
Julie E. Reed ◽  
Cicely Marston ◽  
Derek Bell ◽  
...  
Keyword(s):  
Informed Consent ◽  
Electronic Health Records ◽  
Public Attitudes ◽  
Health Records ◽  
Electronic Health ◽  
The Uk

scholarly journals The OpenDeID corpus for patient de-identification

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Jitendra Jonnagaddala ◽  
Aipeng Chen ◽  
Sean Batongbacal ◽  
Chandini Nekkantti
Keyword(s):  
Electronic Health Records ◽  
Health Information ◽  
Sensitive Information ◽  
Protected Health Information ◽  
Patient Privacy ◽  
Health Records ◽  
Automatic Methods ◽  
Electronic Health ◽  
Pathology Reports ◽  
Privacy And Confidentiality

AbstractFor research purposes, protected health information is often redacted from unstructured electronic health records to preserve patient privacy and confidentiality. The OpenDeID corpus is designed to assist development of automatic methods to redact sensitive information from unstructured electronic health records. We retrieved 4548 unstructured surgical pathology reports from four urban Australian hospitals. The corpus was developed by two annotators under three different experimental settings. The quality of the annotations was evaluated for each setting. Specifically, we employed serial annotations, parallel annotations, and pre-annotations. Our results suggest that the pre-annotations approach is not reliable in terms of quality when compared to the serial annotations but can drastically reduce annotation time. The OpenDeID corpus comprises 2,100 pathology reports from 1,833 cancer patients with an average of 737.49 tokens and 7.35 protected health information entities annotated per report. The overall inter annotator agreement and deviation scores are 0.9464 and 0.9726, respectively. Realistic surrogates are also generated to make the corpus suitable for distribution to other researchers.

Sign in / Sign up

Export Citation Format

Share Document