2022
DOI: 10.1371/journal.pdig.0000135
|View full text |Cite
|
Sign up to set email alerts
|

A roadmap to reduce information inequities in disability with digital health and natural language processing

Abstract: People with disabilities disproportionately experience negative health outcomes. Purposeful analysis of information on all aspects of the experience of disability across individuals and populations can guide interventions to reduce health inequities in care and outcomes. Such an analysis requires more holistic information on individual function, precursors and predictors, and environmental and personal factors than is systematically collected in current practice. We identify 3 key information barriers to more … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2

Citation Types

0
2
0

Year Published

2023
2023
2024
2024

Publication Types

Select...
5

Relationship

1
4

Authors

Journals

citations
Cited by 5 publications
(2 citation statements)
references
References 91 publications
0
2
0
Order By: Relevance
“…The first one is investing in making functionomics data more structured, for example by creating new validated measurement tools and implementing these tools in standard clinical and research practice. However, as mentioned above, data on functioning is very context sensitive, using measurement tools we may lose this context and may not accurately present the patient’s perspective [ 38 ]. The second approach is to apply free text mining, like natural language processing (NLP), to extract meaningful concepts from the free text and convert them to structured formats.…”
Section: Discussionmentioning
confidence: 99%
“…The first one is investing in making functionomics data more structured, for example by creating new validated measurement tools and implementing these tools in standard clinical and research practice. However, as mentioned above, data on functioning is very context sensitive, using measurement tools we may lose this context and may not accurately present the patient’s perspective [ 38 ]. The second approach is to apply free text mining, like natural language processing (NLP), to extract meaningful concepts from the free text and convert them to structured formats.…”
Section: Discussionmentioning
confidence: 99%
“… 7 , 21 , 34 , 43 In addition, data sources need to be representative of the population to avoid the incorporation of inequities and social bias into the models. 44 Finally, using NLP methods requires high optimization for the local environment and extensive domain knowledge, which can be expensive, and stakeholders’ lack of financial resources or prioritization could halt their implementation. Thus, efficacy and cost-effectiveness trials are important to demonstrate the value of the intervention and facilitate its adoption.…”
Section: Discussionmentioning
confidence: 99%