Machine Learning, Natural Language Processing, and the Electronic Health Record: Innovations in Mental Health Services Research

Edgcomb, Juliet Beni; Zima, Bonnie T.

doi:10.1176/appi.ps.201800401

Cited by 49 publications

(25 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Natural Language Processing (NLP) emerged in the 1970s. Subfields of computer science and linguistics are still dedicated to nuances of NLP (Edgcomb and Zima, 2019), including its vital role in electronic health management systems. Natural Language Processing in search engines, e.g.…”

Section: Literature Reviewmentioning

confidence: 99%

Artificial intelligence tools and perspectives of university librarians: An overview

Ali

Naeem

Bhatti

2020

Business Information Review

View full text Add to dashboard Cite

The main purpose of this paper is to assess and examine the possible application of Artificial Intelligence (AI) tools in Pakistani academic libraries, particularly those areas of library technical and library user services where AI could be applied in the near future. A secondary purpose is to bring the library perspective on AI to the forefront of the scholarly world. This is a self-exploratory study, in which a qualitative approach interview has been conducted with 10 chief librarians/library heads (5 public + 5 private sectors) from universities regarding their views on the adoption of artificial intelligence tools in Pakistani academic libraries. Results are tabulated in a descriptive format. Librarians are aware of AI technologies. Services based on Natural Language Processing (NLP) are used in libraries, e.g. Google Assistant, Voice Searching, and Google Translate. Pattern recognition methods, such as text data mining, are also used to retrieve library material and conduct online searching. Big data is accessed via services such as cloud computing, OneDrive, and Google Drive. There is a very low level of awareness of robotics and chatbots. This study provides librarians with suggestions as to how AI tools could be used in libraries which either have yet to adopt AI technologies or wish to implement more advanced tools. Pakistani library schools could collaborate with computer science departments to establish AI Labs in the respective library and information science (LIS) departments/libraries. AI challenges funding and technological skills are the key problem to implement with AI in the University Libraries.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Artificial intelligence tools and perspectives of university librarians: An overview

Ali

Naeem

Bhatti

2020

Business Information Review

View full text Add to dashboard Cite

show abstract

“…For instance, a clinician might want to check the practices of psychiatrists in using metformin to control metabolic dysfunction related to antipsychotics. The simplest cohort for this application can be defined by one variable such as psychosis diagnosis code but dimensional phenotyping is used to extract information from combinations of structured and unstructured data (Edgcomb & Zima, 2019). In another example, a clinician might want to identify homeless youths that used psychiatric emergency services.…”

Section: Unstructured Data Analysismentioning

confidence: 99%

“…Narrative reports from the cohort are processed to transform raw texts into structured data. A combination of narrative and structured data can increase the accuracy of cohort identification and identification of latent cohorts (Edgcomb & Zima, 2019). In another case, a researcher might try to develop an algorithm to predict psychiatric hospital readmission for adolescents with depression and a history of suicide attempts.…”

Section: Unstructured Data Analysismentioning

confidence: 99%

Challenges and opportunities beyond structured data in analysis of electronic health records

Tayefi¹,

Ngo²,

Chomutare³

et al. 2021

WIREs Computational Stats

138

View full text Add to dashboard Cite

Electronic health records (EHR) contain a lot of valuable information about individual patients and the whole population. Besides structured data, unstructured data in EHRs can provide extra, valuable information but the analytics processes are complex, time‐consuming, and often require excessive manual effort. Among unstructured data, clinical text and images are the two most popular and important sources of information. Advanced statistical algorithms in natural language processing, machine learning, deep learning, and radiomics have increasingly been used for analyzing clinical text and images. Although there exist many challenges that have not been fully addressed, which can hinder the use of unstructured data, there are clear opportunities for well‐designed diagnosis and decision support tools that efficiently incorporate both structured and unstructured data for extracting useful information and provide better outcomes. However, access to clinical data is still very restricted due to data sensitivity and ethical issues. Data quality is also an important challenge in which methods for improving data completeness, conformity and plausibility are needed. Further, generalizing and explaining the result of machine learning models are important problems for healthcare, and these are open challenges. A possible solution to improve data quality and accessibility of unstructured data is developing machine learning methods that can generate clinically relevant synthetic data, and accelerating further research on privacy preserving techniques such as deidentification and pseudonymization of clinical text. This article is categorized under: Applications of Computational Statistics > Health and Medical Data/Informatics

show abstract

“…While reports about people with disabilities much of the available data (e.g., reports, raw data, case laws) is scattered [1]; the lack of availability of disability data has been identified as a major challenge hindering continuous disability rights monitoring [2,3] and exposing systemic discrimination [4]. Health informatics [5], machine learning [6], particularly Natural Language Processing (NLP) [7], can enable users to search for data [8][9][10] and find semantic similarities within disparate documents [11,12]. Our project aims to create a bilingual wikibase with a smart natural language search capability.…”

Section: Introductionmentioning

confidence: 99%

The Potential of an Artificial Intelligence for Disability Advocacy: The WikiDisability Project

Gorman

Maret

Creighton

et al. 2021

Studies in Health Technology and Informatics

View full text Add to dashboard Cite

Human rights monitoring for people with disabilities is in urgent need for disability data that is shared and available for local and international disability stakeholders (e.g., advocacy groups). Our aim is to use a Wikibase for editing, integrating, storing structured disability related data and to develop a Natural Language Processing (NLP) enabled multilingual search engine to tap into the wikibase data. In this paper, we explain the project first phase.

show abstract

Machine Learning, Natural Language Processing, and the Electronic Health Record: Innovations in Mental Health Services Research

Cited by 49 publications

References 9 publications

Artificial intelligence tools and perspectives of university librarians: An overview

Artificial intelligence tools and perspectives of university librarians: An overview

Challenges and opportunities beyond structured data in analysis of electronic health records

The Potential of an Artificial Intelligence for Disability Advocacy: The WikiDisability Project

Contact Info

Product

Resources

About