Need of informatics in designing interoperable clinical registries

Rastegar-Mojarad, Majid; Sohn, Sunghwan; Wang, Liwei; Shen, Feichen; Bleeker, Troy C.; Cliby, William A.; Liu, Hongfang

doi:10.1016/j.ijmedinf.2017.10.004

Cited by 18 publications

(10 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Broad adoption of the developed reporting standard has the potential to significantly reduce data and reporting inconsistency and redundancy across systems, promoting collaboration and(or) interoperability between projects 28 29. Promoting such large-scale use could allow for improved data mapping in clinical registries, improving data quality and interoperability 30. As previously exhibited in oncology research, broad adoption of a reporting standard can maximise the value and impact of research studies as well as the associated research data 31.…”

Section: Discussionmentioning

confidence: 99%

Proposed minimum information guideline for kidney disease—research and clinical data reporting: a cross-sectional study

et al. 2019

View full text Add to dashboard Cite

ObjectiveThis project aimed to develop and propose a standardised reporting guideline for kidney disease research and clinical data reporting, in order to improve kidney disease data quality and integrity, and combat challenges associated with the management and challenges of ‘Big Data’.MethodsA list of recommendations was proposed for the reporting guideline based on the systematic review and consolidation of previously published data collection and reporting standards, including PhenX measures and Minimal Information about a Proteomics Experiment (MIAPE). Thereafter, these recommendations were reviewed by domain-specialists using an online survey, developed in Research Electronic Data Capture (REDCap). Following interpretation and consolidation of the survey results, the recommendations were mapped to existing ontologies using Zooma, Ontology Lookup Service and the Bioportal search engine. Additionally, an associated eXtensible Markup Language schema was created for the REDCap implementation to increase user friendliness and adoption.ResultsThe online survey was completed by 53 respondents; the majority of respondents were dual clinician-researchers (57%), based in Australia (35%), Africa (33%) and North America (22%). Data elements within the reporting standard were identified as participant-level, study-level and experiment-level information, further subdivided into essential or optional information.ConclusionThe reporting guideline is readily employable for kidney disease research projects, and also adaptable for clinical utility. The adoption of the reporting guideline in kidney disease research can increase data quality and the value for long-term preservation, ensuring researchers gain the maximum benefit from their collected and generated data.

show abstract

Section: Discussionmentioning

confidence: 99%

Proposed minimum information guideline for kidney disease—research and clinical data reporting: a cross-sectional study

et al. 2019

View full text Add to dashboard Cite

show abstract

“…As previously exhibited in oncology research, widespread utilization of the developed reporting guideline can function to reduce data and reporting inconsistency and redundancy across systems, as well as promote collaboration and(or) interoperability between systems (Biology et al, 2000;Hartwell et al, 2012;MacCarthy et al, 2018). Promoting such broad use could allow for improved data mapping in clinical registries, improving data quality and interoperability (Rastegar-Mojarad et al, 2017). A given standard may be more widely adopted if advocated or endorsed by "omics" databases, funding bodies and scientific journals, geared towards stroke research, specifically.…”

Section: Data Analysis Ementioning

confidence: 99%

Proposed Guideline for Minimum Information Stroke Research and Clinical Data Reporting

Kumuthini

Zass

Chaouch

et al. 2019

CODATA

View full text Add to dashboard Cite

The management and analyses of large datasets is one of the grand challenges of modern biomedical research. Establishing methods to harmonise and standardise data collection, reporting, sharing and the employed data dictionaries, can support the resolution of these challenges whilst improving research quality, data quality and integrity, allowing sustainable knowledge transfer through re-usability, interoperability, reproducibility. The current project aimed to develop and propose a standardised reporting guideline for stroke research and clinical data reporting. Through systematic consolidation and harmonization of published data collection and reporting standards, several recommendations were drafted for the proposed guideline. These recommendations were reviewed by domain-researchers and clinicians using an online survey, developed in REDCap. The survey was completed by 20 international stroke-specialists, majority of respondents were based in Africa (10), followed by America, Europe and Australia (10). Of these respondents; the majority were working as dual clinician-researchers (57%) with more than 10 years' experience in the field (78%). Data elements within the reporting standard were classified as participant-, study-and experiment-level information, further subdivided into essential or optional information, and defined using existing ontologies. The proposed reporting guideline can be employed for research utility and adapted for clinical utility as well. It is accompanied with an associated XML schema for REDCap implementation, to increase the user friendliness of data capturing, sharing, reporting and governance. Ultimately, the adoption of common reporting in stroke research has the potential to ensure that researchers gain the maximum benefit from their generated data and data collections.

show abstract

“…This, in turn, may lead to overfitting, a modeling error that occurs when a complex model adapts to the idiosyncrasies of the training data and fails to generalize the underlying properties of the problem. Unfortunately, the majority of studies reviewed here were limited to the authors' host institutions [8,10,12,15,17,22,24,25,28,[30][31][32][33]35,40,41,44,66,70,76,79,[84][85][86]89,90,94,95,99,105,106,111,113]. Rarely are such datasets freely accessible to the community.…”

Section: Provenancementioning

confidence: 99%

“…Other types of clinical narratives considered include physician notes [84], progress notes [25,40,90], EHR notes [74,81,116], surgical notes [14,79], and emergency department notes [50,109]. Unspecified type of clinical notes [102] were used mostly for classification [9,12,31,61,86,95,103,113], WSD [33], and disambiguation and IE [36,51,99].…”

Section: Types Of Narrativesmentioning

confidence: 99%

Clinical Text Data in Machine Learning: Systematic Review

Spasić¹,

Nenadić²

2020

JMIR Med Inform

219

132

View full text Add to dashboard Cite

Background Clinical narratives represent the main form of communication within health care, providing a personalized account of patient history and assessments, and offering rich information for clinical decision making. Natural language processing (NLP) has repeatedly demonstrated its feasibility to unlock evidence buried in clinical narratives. Machine learning can facilitate rapid development of NLP tools by leveraging large amounts of text data. Objective The main aim of this study was to provide systematic evidence on the properties of text data used to train machine learning approaches to clinical NLP. We also investigated the types of NLP tasks that have been supported by machine learning and how they can be applied in clinical practice. Methods Our methodology was based on the guidelines for performing systematic reviews. In August 2018, we used PubMed, a multifaceted interface, to perform a literature search against MEDLINE. We identified 110 relevant studies and extracted information about text data used to support machine learning, NLP tasks supported, and their clinical applications. The data properties considered included their size, provenance, collection methods, annotation, and any relevant statistics. Results The majority of datasets used to train machine learning models included only hundreds or thousands of documents. Only 10 studies used tens of thousands of documents, with a handful of studies utilizing more. Relatively small datasets were utilized for training even when much larger datasets were available. The main reason for such poor data utilization is the annotation bottleneck faced by supervised machine learning algorithms. Active learning was explored to iteratively sample a subset of data for manual annotation as a strategy for minimizing the annotation effort while maximizing the predictive performance of the model. Supervised learning was successfully used where clinical codes integrated with free-text notes into electronic health records were utilized as class labels. Similarly, distant supervision was used to utilize an existing knowledge base to automatically annotate raw text. Where manual annotation was unavoidable, crowdsourcing was explored, but it remains unsuitable because of the sensitive nature of data considered. Besides the small volume, training data were typically sourced from a small number of institutions, thus offering no hard evidence about the transferability of machine learning models. The majority of studies focused on text classification. Most commonly, the classification results were used to support phenotyping, prognosis, care improvement, resource management, and surveillance. Conclusions We identified the data annotation bottleneck as one of the key obstacles to machine learning approaches in clinical NLP. Active learning and distant supervision were explored as a way of saving the annotation efforts. Future research in this field would benefit from alternatives such as data augmentation and transfer learning, or unsupervised learning, which do not require data annotation.

show abstract

Need of informatics in designing interoperable clinical registries

Cited by 18 publications

References 28 publications

Proposed minimum information guideline for kidney disease—research and clinical data reporting: a cross-sectional study

Proposed minimum information guideline for kidney disease—research and clinical data reporting: a cross-sectional study

Proposed Guideline for Minimum Information Stroke Research and Clinical Data Reporting

Clinical Text Data in Machine Learning: Systematic Review

Contact Info

Product

Resources

About