e.g. mhealth
Search Results (1 to 10 of 13 Results)
Download search results: CSV END BibTex RIS
Skip search results from other journals and go to results- 7 Journal of Medical Internet Research
- 2 JMIR Dermatology
- 1 Interactive Journal of Medical Research
- 1 JMIR Bioinformatics and Biotechnology
- 1 JMIR Formative Research
- 1 JMIR Medical Informatics
- 0 Medicine 2.0
- 0 iProceedings
- 0 JMIR Research Protocols
- 0 JMIR Human Factors
- 0 JMIR Public Health and Surveillance
- 0 JMIR mHealth and uHealth
- 0 JMIR Serious Games
- 0 JMIR Mental Health
- 0 JMIR Rehabilitation and Assistive Technologies
- 0 JMIR Preprints
- 0 JMIR Medical Education
- 0 JMIR Cancer
- 0 JMIR Challenges
- 0 JMIR Diabetes
- 0 JMIR Biomedical Engineering
- 0 JMIR Data
- 0 JMIR Cardio
- 0 Journal of Participatory Medicine
- 0 JMIR Pediatrics and Parenting
- 0 JMIR Aging
- 0 JMIR Perioperative Medicine
- 0 JMIR Nursing
- 0 JMIRx Med
- 0 JMIRx Bio
- 0 JMIR Infodemiology
- 0 Transfer Hub (manuscript eXchange)
- 0 JMIR AI
- 0 JMIR Neurotechnology
- 0 Asian/Pacific Island Nursing Journal
- 0 Online Journal of Public Health Informatics
- 0 JMIR XR and Spatial Computing (JMXR)
Deidentification can be a problematic approach to mitigating privacy risks in many public health contexts because it can cause both individual and group harm that offsets its benefits [38-40]. In the absence of informed consent, data controllers frequently rely on deidentification before sharing data.
There are 2 principal motivations for deidentifying data [27]. First, laws might allow data to be used or shared with fewer restrictions if deidentified.
J Med Internet Res 2025;27:e70983
Download Citation: END BibTex RIS
However, deidentification processes involve obfuscation of important details, including dates and locations. This may alter the semantic underpinnings of a given text, making it difficult for an LLM to accurately identify and label SDo H within a given note.
J Med Internet Res 2024;26:e63445
Download Citation: END BibTex RIS
Deidentification is the process of tagging and removing personally identifiable information (PII) to prevent incidental privacy breaches. Unfortunately, manual deidentification is an expensive and error-prone process [1,2], and automated deidentification remains an unsolved challenge [3,4]. Since the first published automated deidentification system [5], a variety of systems using a range of technologies have been released.
J Med Internet Res 2024;26:e55676
Download Citation: END BibTex RIS
The Costs of Anonymization: Case Study Using Clinical Data
deidentification
J Med Internet Res 2024;26:e49445
Download Citation: END BibTex RIS
Best Practices in Evolving Privacy Frameworks for Patient Age Data: Census Data Study
The HIPAA (Health Insurance Portability and Accountability Act) of 1996, in its Safe Harbor approach to the deidentification of data sets [3], gives a maximum age of 90 years to which all higher values should be lowered.
The risk of reidentification, or “disclosure risk,” is related to the amount of utility that a data set of personal information contains. As the risk is reduced, so is the value of the data set in terms of its usefulness.
JMIR Form Res 2024;8:e47248
Download Citation: END BibTex RIS
As a result, the deidentification step becomes a critical data processing step to protect the privacy of individuals. However, the study by Cannon and Lucci [2] indicated that up to 65% of important clinical information is recorded in unstructured texts in medical reports written by medical personnel. Compared with structured data, which can be deidentified by encrypting private patient information fields, the deidentification of unstructured data is more challenging.
J Med Internet Res 2024;26:e48443
Download Citation: END BibTex RIS
The goal of the deidentification process in unstructured EHR text notes is to identify SHI by inspecting entire medical records. Deidentification by medical experts is time-consuming, error prone, and expensive [6]. In contrast, automated deidentification techniques based on recent advances in artificial intelligence can be used to simplify the entire process [7]. Automated deidentification techniques require an annotated corpus to identify SHI [8].
J Med Internet Res 2023;25:e48145
Download Citation: END BibTex RIS
However, manual deidentification has been proven to be a time-consuming and labor-intensive task [6].
In the past decade, researchers have investigated many different automated deidentification approaches including rule-based matching [7-9] and machine learning (ML) models [10-14]. Hand-written regular expressions and ad hoc knowledge dictionaries are used in rule-based deidentification approaches for a specific free-text data set [15].
Interact J Med Res 2023;12:e46322
Download Citation: END BibTex RIS
Consent and Deidentification of Patient Images in Dermatology Journals: Observational Study
Nonetheless, requirements for the deidentification of patient images and for the acquisition of consent to publish such images vary across governing bodies and journals. Our objective was to describe leading dermatology journals’ instructions regarding deidentification and consent to publish patient images as well as the content and readability of consent forms.
This study was exempt from institutional review board review as data were publicly available.
JMIR Dermatol 2022;5(3):e37398
Download Citation: END BibTex RIS
Facial features, tattoos, jewelry, birthmarks, and other identity-informative background features are additional features that are considered identifying; facial feature deidentification is considered the most challenging task, given a lack of expert consensus and a lack of testing infrastructure and quantitative metrics for adequacy of automatic and manual facial image deidentification algorithms.
JMIR Dermatol 2022;5(2):e35497
Download Citation: END BibTex RIS