scholarly journals Recorded atypical hallucinations in psychotic and affective disorders and associations with non-benzodiazepine hypnotic use: the South London and Maudsley Case Register

BMJ Open ◽  
2018 ◽  
Vol 8 (9) ◽  
pp. e025216 ◽  
Author(s):  
Karen Isabel Birnie ◽  
Robert Stewart ◽  
Anna Kolliakou
Keyword(s):  
Natural Language Processing ◽  
Drug Use ◽  
Natural Language ◽  
Language Processing ◽  
Mental Healthcare ◽  
Processing Algorithm ◽  
Retrospective Case ◽  
Healthcare Database ◽  
Case Register ◽  
Natural Language Processing Algorithm

ObjectivesHallucinations are present in many conditions, notably psychosis. Although under-researched, atypical hallucinations, such as tactile, olfactory and gustatory (TOGHs), may arise secondary to hypnotic drug use, particularly non-benzodiazepine hypnotics (‘Z drugs’). This retrospective case-control study investigated the frequency of TOGHs and their associations with prior Z drug use in a large mental healthcare database.MethodsTOGHs were ascertained in 2014 using a bespoke natural language processing algorithm and were analysed against covariates (including use of Z drugs, demographic factors, diagnosis, disorder severity and other psychotropic medications) ascertained prior to 2014.ResultsIn 43 339 patients with International Classification of Diseases, Tenth Edition schizophreniform or affective disorder diagnoses, 324 (0.75%) had any TOGH recorded (0.54% tactile, 0.24% olfactory, 0.06% gustatory hallucinations). TOGHs were associated with male gender, black ethnicity, schizophreniform diagnosis and higher disorder severity on Health of the National Outcome Scales. In fully adjusted models, tactile and olfactory hallucinations remained independently associated with prior mention of Z drugs (ORs 1.86 and 1.60, respectively).ConclusionsWe successfully developed a natural language processing algorithm to identify instances of TOGHs in the clinical record. TOGHs overall, tactile and olfactory hallucinations were shown to be associated with prior mention of Z drugs. This may have implications for the diagnosis and treatment of patients with comorbid sleep and psychiatric conditions.

scholarly journals Natural Language Processing for Surveillance of Cervical and Anal Cancer and Precancer: Algorithm Development and Split-Validation Study (Preprint)

2020 ◽  
Author(s):  
Carlos R Oliveira ◽  
Patrick Niccolai ◽  
Anette Michelle Ortiz ◽  
Sangini S Sheth ◽  
Eugene D Shapiro ◽  
...  
Keyword(s):  
Natural Language Processing ◽  
Human Papillomavirus ◽  
Natural Language ◽  
Language Processing ◽  
Medical Records ◽  
Processing Algorithm ◽  
Accurate Identification ◽  
Pathology Reports ◽  
Manual Review ◽  
Natural Language Processing Algorithm

BACKGROUND Accurate identification of new diagnoses of human papillomavirus–associated cancers and precancers is an important step toward the development of strategies that optimize the use of human papillomavirus vaccines. The diagnosis of human papillomavirus cancers hinges on a histopathologic report, which is typically stored in electronic medical records as free-form, or unstructured, narrative text. Previous efforts to perform surveillance for human papillomavirus cancers have relied on the manual review of pathology reports to extract diagnostic information, a process that is both labor- and resource-intensive. Natural language processing can be used to automate the structuring and extraction of clinical data from unstructured narrative text in medical records and may provide a practical and effective method for identifying patients with vaccine-preventable human papillomavirus disease for surveillance and research. OBJECTIVE This study's objective was to develop and assess the accuracy of a natural language processing algorithm for the identification of individuals with cancer or precancer of the cervix and anus. METHODS A pipeline-based natural language processing algorithm was developed, which incorporated machine learning and rule-based methods to extract diagnostic elements from the narrative pathology reports. To test the algorithm’s classification accuracy, we used a split-validation study design. Full-length cervical and anal pathology reports were randomly selected from 4 clinical pathology laboratories. Two study team members, blinded to the classifications produced by the natural language processing algorithm, manually and independently reviewed all reports and classified them at the document level according to 2 domains (diagnosis and human papillomavirus testing results). Using the manual review as the gold standard, the algorithm’s performance was evaluated using standard measurements of accuracy, recall, precision, and F-measure. RESULTS The natural language processing algorithm’s performance was validated on 949 pathology reports. The algorithm demonstrated accurate identification of abnormal cytology, histology, and positive human papillomavirus tests with accuracies greater than 0.91. Precision was lowest for anal histology reports (0.87, 95% CI 0.59-0.98) and highest for cervical cytology (0.98, 95% CI 0.95-0.99). The natural language processing algorithm missed 2 out of the 15 abnormal anal histology reports, which led to a relatively low recall (0.68, 95% CI 0.43-0.87). CONCLUSIONS This study outlines the development and validation of a freely available and easily implementable natural language processing algorithm that can automate the extraction and classification of clinical data from cervical and anal cytology and histology.

scholarly journals SentiMental: An emotional profiling algorithm for identifying affect patterns in text

2018 ◽  
Author(s):  
Massimo Stella
Keyword(s):  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Processing Algorithm ◽  
Copyright Holder ◽  
The Novel ◽  
Novel Approach ◽  
Technical Report ◽  
Potential Applications ◽  
Natural Language Processing Algorithm

This technical report outlines the mechanisms and potential applications of SentiMental, a suite of natural language processing algorithm designed and implemented by Massimo Stella, Complex Science Consulting. The following technical report briefly outlines the novel approach of SentiMental in performing sentiment and emotional analysis by directly harnessing the whole structure of the mental lexicon rather than by using affect norms. Furthermore, this technical report outlines the direct emotional profiling and the visualisations currently implemented in version 0.1 of SentiMental. Features under development and current limitations are also outlined and discussed.This technical report is not meant as a publication. The author holds full copyright and any reproduction of parts of this report must be authorised by the copyright holder. SentiMental represents a work in progress, so do not hesitate to get in touch with the author for any potential feedback.

scholarly journals Development of a Natural Language Processing Algorithm for the Classification of Suspicious Liver Lesions from Radiology Reports

2021 ◽  
Author(s):  
Jacob Johnson ◽  
Kaneel Senevirathne ◽  
Lawrence Ngo
Keyword(s):  
Deep Learning ◽  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Processing Algorithm ◽  
Liver Lesions ◽  
Radiology Reports ◽  
Natural Language Processing Algorithm

Here, we developed and validated a highly generalizable natural language processing algorithm based on deep-learning. Our algorithm was trained and tested on a highly diverse dataset from over 2,000 hospital sites and 500 radiologists. The resulting algorithm achieved an AUROC of 0.96 for the presence or absence of liver lesions while achieving a specificity of 0.99 and a sensitivity of 0.6.

Sign in / Sign up

Export Citation Format

Share Document