Automatic detection of protected health information from clinic narratives.
Ontology highlight
ABSTRACT:
SUBMITTER: Yang H
PROVIDER: S-EPMC4989090 | biostudies-literature | 2015 Dec
REPOSITORIES: biostudies-literature
Publications
Automatic detection of protected health information from clinic narratives.
Yang Hui H Garibaldi Jonathan M JM
Journal of biomedical informatics 20150729
This paper presents a natural language processing (NLP) system that was designed to participate in the 2014 i2b2 de-identification challenge. The challenge task aims to identify and classify seven main Protected Health Information (PHI) categories and 25 associated sub-categories. A hybrid model was proposed which combines machine learning techniques with keyword-based and rule-based approaches to deal with the complexity inherent in PHI categories. Our proposed approaches exploit a rich set of ...[more]
Similar Datasets
Project description:BACKGROUND:Vast numbers of domestic violence (DV) incidents are attended by the New South Wales Police Force each year in New South Wales and recorded as both structured quantitative data and unstructured free text in the WebCOPS (Web-based interface for the Computerised Operational Policing System) database regarding the details of the incident, the victim, and person of interest (POI). Although the structured data are used for reporting purposes, the free text remains untapped for DV reporting and surveillance purposes. OBJECTIVE:In this paper, we explore whether text mining can automatically identify mental health disorders from this unstructured text. METHODS:We used a training set of 200 DV recorded events to design a knowledge-driven approach based on lexical patterns in text suggesting mental health disorders for POIs and victims. RESULTS:The precision returned from an evaluation set of 100 DV events was 97.5% and 87.1% for mental health disorders related to POIs and victims, respectively. After applying our approach to a large-scale corpus of almost a half million DV events, we identified 77,995 events (15.83%) that mentioned mental health disorders, with 76.96% (60,032/77,995) of those linked to POIs versus 16.47% (12,852/77,995) for the victims and 6.55% (5111/77,995) for both. Depression was the most common mental health disorder mentioned in both victims (22.25%, 3269) and POIs (18.70%, 8944), followed by alcohol abuse for POIs (12.19%, 5829) and various anxiety disorders (eg, panic disorder, generalized anxiety disorder) for victims (11.66%, 1714). CONCLUSIONS:The results suggest that text mining can automatically extract targeted information from police-recorded DV events to support further public health research into the nexus between mental health disorders and DV.
| S-EPMC6231811 | biostudies-other
Project description:Background Maintaining patient privacy when geocoding and linking residential address information with neighborhood-level data can create challenges during research. Challenges may arise when study staff have limited training in geocoding and linking data, or when non-study staff with appropriate expertise have limited availability, are unfamiliar with a study’s population or objectives, or are not affordable for the study team. Opportunities for data breaches may also arise when working with non-study staff who are not on-site. We detail a free, user-friendly protocol for constructing indices of the neighborhood risk environment during multisite, clinic-based cohort studies that rely on participants’ protected health information. This protocol can be implemented by study staff who do not have prior training in Geographic Information Systems (GIS) and can help minimize the operational costs of integrating geographic data into public health projects. Methods This protocol demonstrates how to: (1) securely geocode patients’ residential addresses in a clinic setting and match geocoded addresses to census tracts using Geographic Information System software (Esri, Redlands, CA); (2) ascertain contextual variables of the risk environment from the American Community Survey and ArcGIS Business Analyst (Esri, Redlands, CA); (3) use geoidentifiers to link neighborhood risk data to census tracts containing geocoded addresses; and (4) assign randomly generated identifiers to census tracts and strip census tracts of their geoidentifiers to maintain patient confidentiality. Results Completion of this protocol generates three neighborhood risk indices (i.e., Neighborhood Disadvantage Index, Murder Rate Index, and Assault Rate Index) for patients’ coded census tract locations. Conclusions This protocol can be used by research personnel without prior GIS experience to easily create objective indices of the neighborhood risk environment while upholding patient confidentiality. Future studies can adapt this protocol to fit their specific patient populations and analytic objectives.
| S-EPMC9799318 | biostudies-literature
Project description:Unstructured clinical narratives are continuously being recorded as part of delivery of care in electronic health records, and dedicated tagging staff spend considerable effort manually assigning clinical codes for billing purposes. Despite these efforts, however, label availability and accuracy are both suboptimal. In this retrospective study, we aimed to automate the assignment of top-level International Classification of Diseases version 9 (ICD-9) codes to clinical records from human and veterinary data stores using minimal manual labor and feature curation. Automating top-level annotations could in turn enable rapid cohort identification, especially in a veterinary setting. To this end, we trained long short-term memory (LSTM) recurrent neural networks (RNNs) on 52,722 human and 89,591 veterinary records. We investigated the accuracy of both separate-domain and combined-domain models and probed model portability. We established relevant baseline classification performances by training Decision Trees (DT) and Random Forests (RF). We also investigated whether transforming the data using MetaMap Lite, a clinical natural language processing tool, affected classification performance. We showed that the LSTM-RNNs accurately classify veterinary and human text narratives into top-level categories with an average weighted macro F1 score of 0.74 and 0.68 respectively. In the "neoplasia" category, the model trained on veterinary data had a high validation accuracy in veterinary data and moderate accuracy in human data, with F1 scores of 0.91 and 0.70 respectively. Our LSTM method scored slightly higher than that of the DT and RF models. The use of LSTM-RNN models represents a scalable structure that could prove useful in cohort identification for comparative oncology studies. Digitization of human and veterinary health information will continue to be a reality, particularly in the form of unstructured narratives. Our approach is a step forward for these two domains to learn from and inform one another.
| S-EPMC7307763 | biostudies-literature
Project description:Modern medical research relies on multi-institutional collaborations which enhance the knowledge discovery and data reuse. While these collaborations allow researchers to perform analytics otherwise impossible on individual datasets, they often pose significant challenges in the data integration process. Due to the lack of a unique identifier, data integration solutions often have to rely on patient's protected health information (PHI). In many situations, such information cannot leave the institutions or must be strictly protected. Furthermore, the presence of noisy values for these attributes may result in poor overall utility. While much research has been done to address these challenges, most of the current solutions are designed for a static setting without considering the temporal information of the data (e.g. EHR). In this work, we propose a novel approach that uses non-PHI for linking patient longitudinal data. Specifically, our technique captures the diagnosis dependencies using patterns which are shown to provide important indications for linking patient records. Our solution can be used as a standalone technique to perform temporal record linkage using non-protected health information data or it can be combined with Privacy Preserving Record Linkage solutions (PPRL) when protected health information is available. In this case, our approach can solve ambiguities in results. Experimental evaluations on real datasets demonstrate the effectiveness of our technique.
| S-EPMC5758434 | biostudies-other
Project description:Temporal information in clinical narratives plays an important role in patients' diagnosis, treatment and prognosis. In order to represent narrative information accurately, medical natural language processing (MLP) systems need to correctly identify and interpret temporal information. To promote research in this area, the Informatics for Integrating Biology and the Bedside (i2b2) project developed a temporally annotated corpus of clinical narratives. This corpus contains 310 de-identified discharge summaries, with annotations of clinical events, temporal expressions and temporal relations. This paper describes the process followed for the development of this corpus and discusses annotation guideline development, annotation methodology, and corpus quality.
| S-EPMC3855581 | biostudies-literature
Project description:Objective: Many online and printed media publish health news of questionable trustworthiness and it may be difficult for laypersons to determine the information quality of such articles. The purpose of this work was to propose a methodology for the automatic assessment of the quality of health-related news stories using natural language processing and machine learning. Materials and Methods: We used a database from the website HealthNewsReview.org that aims to improve the public dialogue about health care. HealthNewsReview.org developed a set of criteria to critically analyze health care interventions' claims. In this work, we attempt to automate the evaluation process by identifying the indicators of those criteria using natural language processing-based machine learning on a corpus of more than 1,300 news stories. We explored features ranging from simple n-grams to more advanced linguistic features and optimized the feature selection for each task. Additionally, we experimented with the use of pre-trained natural language model BERT. Results: For some criteria, such as mention of costs, benefits, harms, and "disease-mongering," the evaluation results were promising with an F1 measure reaching 81.94%, while for others the results were less satisfactory due to the dataset size, the need of external knowledge, or the subjectivity in the evaluation process. Conclusion: These used criteria are more challenging than those addressed by previous work, and our aim was to investigate how much more difficult the machine learning task was, and how and why it varied between criteria. For some criteria, the obtained results were promising; however, automated evaluation of the other criteria may not yet replace the manual evaluation process where human experts interpret text senses and make use of external knowledge in their assessment.
| S-EPMC7775604 | biostudies-literature
Project description:BackgroundWith the emergence of new health information technologies, health information can be shared across networks, with or without patients' awareness and/or their consent. It is often argued that there can be an ethical obligation to participate in biomedical research, motivated by altruism, particularly when risks are low. In this study, we explore whether altruism contributes to the belief that there is an ethical obligation to share information about one's health as well as how other health care experiences, perceptions, and concerns might be related to belief in such an obligation.MethodsWe conducted an online survey using the National Opinion Research Center's (NORC) probability-based, nationally representative sample of U.S. adults. Our final analytic sample included complete responses from 2069 participants. We used multivariable logistic regression to examine how altruism, together with other knowledge, attitudes, and experiences contribute to the belief in an ethical obligation to allow health information to be used for research.ResultsWe find in multivariable regression that general altruism is associated with a higher likelihood of belief in an ethical obligation to allow one's health information to be used for research (OR = 1.22, SE = 0.14, p = 0.078). Trust in the health system and in care providers are both associated with a significantly higher likelihood of believing there is an ethical obligation to allow health information to be used (OR = 1.48, SE = 0.76, p<0.001; OR = 1.58, SE = 0.26, p<0.01, respectively).ConclusionsBelief that there is an ethical obligation to allow one's health information to be used for research is shaped by altruism and by one's experience with, and perceptions of, health care and by general concerns about the use of personal information. Altruism cannot be assumed and researchers must recognize the ways encounters with the health care system influence (un)willingness to share one's health information.
| S-EPMC7774955 | biostudies-literature
Project description:Comments and information appearing on the internet and on different social media sway opinion concerning potential remedies for diagnosing and curing diseases. In many cases, this has an impact on citizens' health and affects medical professionals, who find themselves having to defend their diagnoses as well as the treatments they propose against ill-informed patients. The propagation of these opinions follows the same pattern as the dissemination of fake news about other important topics, such as the environment, via social media networks, which we use as a testing ground for checking our procedure. In this article, we present an algorithm to analyse the behaviour of users of Twitter, the most important social network with respect to this issue, as well as a dynamic knowledge graph construction method based on information gathered from Twitter and other open data sources such as web pages. To show our methodology, we present a concrete example of how the associated graph structure of the tweets related to World Environment Day 2019 is used to develop a heuristic analysis of the validity of the information. The proposed analytical scheme is based on the interaction between the computer tool-a database implemented with Neo4j-and the analyst, who must ask the right questions to the tool, allowing to follow the line of any doubtful data. We also show how this method can be used. We also present some methodological guidelines on how our system could allow, in the future, an automation of the procedures for the construction of an autonomous algorithm for the detection of false news on the internet related to health.
| S-EPMC7037767 | biostudies-literature
Project description:There is a great and growing need to ascertain what exactly is the state of a patient, in terms of disease progression, actual care practices, pathology, adverse events, and much more, beyond the paucity of data available in structured medical record data. Ascertaining these harder-to-reach data elements is now critical for the accurate phenotyping of complex traits, detection of adverse outcomes, efficacy of off-label drug use, and longitudinal patient surveillance. Clinical notes often contain the most detailed and relevant digital information about individual patients, the nuances of their diseases, the treatment strategies selected by physicians, and the resulting outcomes. However, notes remain largely unused for research because they contain Protected Health Information (PHI), which is synonymous with individually identifying data. Previous clinical note de-identification approaches have been rigid and still too inaccurate to see any substantial real-world use, primarily because they have been trained with too small medical text corpora. To build a new de-identification tool, we created the largest manually annotated clinical note corpus for PHI and develop a customizable open-source de-identification software called Philter ("Protected Health Information filter"). Here we describe the design and evaluation of Philter, and show how it offers substantial real-world improvements over prior methods.
| S-EPMC7156708 | biostudies-literature
Project description:ObjectiveBiomedical research involving social media data is gradually moving from population-level to targeted, cohort-level data analysis. Though crucial for biomedical studies, social media user's demographic information (eg, gender) is often not explicitly known from profiles. Here, we present an automatic gender classification system for social media and we illustrate how gender information can be incorporated into a social media-based health-related study.Materials and methodsWe used a large Twitter dataset composed of public, gender-labeled users (Dataset-1) for training and evaluating the gender detection pipeline. We experimented with machine learning algorithms including support vector machines (SVMs) and deep-learning models, and public packages including M3. We considered users' information including profile and tweets for classification. We also developed a meta-classifier ensemble that strategically uses the predicted scores from the classifiers. We then applied the best-performing pipeline to Twitter users who have self-reported nonmedical use of prescription medications (Dataset-2) to assess the system's utility.Results and discussionWe collected 67 181 and 176 683 users for Dataset-1 and Dataset-2, respectively. A meta-classifier involving SVM and M3 performed the best (Dataset-1 accuracy: 94.4% [95% confidence interval: 94.0-94.8%]; Dataset-2: 94.4% [95% confidence interval: 92.0-96.6%]). Including automatically classified information in the analyses of Dataset-2 revealed gender-specific trends-proportions of females closely resemble data from the National Survey of Drug Use and Health 2018 (tranquilizers: 0.50 vs 0.50; stimulants: 0.50 vs 0.45), and the overdose Emergency Room Visit due to Opioids by Nationwide Emergency Department Sample (pain relievers: 0.38 vs 0.37).ConclusionOur publicly available, automated gender detection pipeline may aid cohort-specific social media data analyses (https://bitbucket.org/sarkerlab/gender-detection-for-public).
| S-EPMC8220305 | biostudies-literature