Natural language processing (NLP) models such as bidirectional encoder representations from transformers (BERT) hold promise in revolutionizing disease identification from electronic health records (E...
This study aims to develop and validate a BERT model for detecting COVID-19 consultations in general practice EHRs in the Netherlands....
The BERT model was initially pretrained on Dutch language data and fine-tuned using a comprehensive EHR data set comprising confirmed COVID-19 GP consultations and non-COVID-19-related consultations. ...
The model development used 300,359 GP consultations. We developed a highly accurate model for COVID-19 consultations (accuracy 0.97, F...
The developed BERT model was able to accurately identify COVID-19 cases among GP consultations even preceding confirmed cases. The validated efficacy of our BERT model highlights the potential of NLP ...
Family health history has been recognized as an essential factor for cancer risk assessment and is an integral part of many cancer screening guidelines, including genetic testing for personalized clin...
The aim of this study was to develop a natural language processing (NLP) pipeline and assess its contribution to identifying patients who meet genetic testing criteria for hereditary cancers based on ...
Algorithms were developed based on the National Comprehensive Cancer Network (NCCN) guidelines for genetic testing for hereditary breast, ovarian, pancreatic, and colorectal cancers. The NLP-augmented...
Regarding identifying the reference standard patients meeting the NCCN criteria, the NLP-augmented algorithm compared with the structured data algorithm yielded a significantly higher recall of 0.95 (...
Compared with the structured data algorithm, the NLP-augmented algorithm based on both structured and unstructured family health history data in the EHR increased the number of patients identified as ...
Comprehensive sexual health education for young people often remains largely inaccessible, leaving gaps in knowledge about sexual consent, refusals, sexual assault, and sexting. Snapchat's My AI, tail...
To descriptively compare and contrast intervention techniques for preschool children with features of developmental language disorder (outcome: oral vocabulary) and speech sound disorder (outcome: spe...
This is a systematic review with narrative synthesis. The process was supported by an expert steering group consisting of relevant professionals and people with lived experience....
Ovid Emcare, MEDLINE Complete, CINAHL, APA PsycINFO, ERIC, and Communication Source from January 2012 were searched. Relevant studies were obtained from an initial published review (up to January 2012...
Interventions for preschool children (80% aged 2:0-5:11 years) with idiopathic speech or language needs; outcomes relating to either oral vocabulary or speech comprehensibility....
Searches were conducted on 27 January 2023. Two independent researchers screened at abstract and full-text levels. Data regarding intervention content (eg, techniques) and format/delivery (eg, dosage,...
24 studies were included: 18 for oral vocabulary and 6 for speech comprehensibility. There were 11 randomised controlled trials, 2 cohort studies and 11 case series. Similarities included a focus on i...
Similarities and differences between intervention techniques for oral vocabulary and speech comprehensibility have been identified and synthesised. However, analysis of effectiveness was limited due t...
CRD42022373931....
Machine learning has advanced medical event prediction, mostly using private data. The public MIMIC-3 (Medical Information Mart for Intensive Care III) data set, which contains detailed data on over 4...
This study aimed to build and test a machine learning model using the MIMIC-3 data set to determine the effectiveness of information extracted from electronic medical record text using a named entity ...
The MIMIC-3 data set, including demographics, vital signs, laboratory results, and textual data, such as discharge summaries, was used. This study specifically targeted patients diagnosed with Klebsie...
Of 46,520 MIMIC-3 patients, 4046 were identified with bacterial cultures, indicating the presence of K pneumoniae or E coli. After excluding patients who lacked discharge summary text, 3614 patients r...
This study successfully developed a predictive model for ESBL-producing bacterial infections using the MIMIC-3 data set, yielding results consistent with existing literature. This model stands out for...
To develop and externally validate models based on neural networks and natural language processing (NLP) to identify suspected serious infections in emergency department (ED) patients afebrile at init...
This retrospective study included adults who visited the ED afebrile at initial presentation. We developed four models based on artificial neural networks to identify suspected serious infection. Pati...
The training, internal validation, and external validation datasets comprised 150,699, 37,675, and 85,098 patients, respectively. The AUCs (95% CIs) for Models 1 (demographics + vital signs), 2 (demog...
We developed and validated models to identify suspected serious infection in the ED. Extracted information from initial ED physician notes using NLP contributed to increased model performance, permitt...
To evaluate the degree that the Cochin Hand Function Scale (CHFS) generates scores that are comparable across language, sex, and disease subtype....
We included participants enrolled in the Scleroderma Patient-centered Intervention Network (SPIN) Cohort who completed the CHFS at their baseline assessment between April 2014 and September 2020. Conf...
A total of 2,155 participants were included. CFA with covarying error terms supported a good fit of the model (χ...
The CHFS has score comparability in systemic sclerosis regardless of participants' language, sex, and disease subtype....
Aging is a natural phenomenon that elicits slow and progressive cerebrovascular and neurophysiological changes that eventually lead to cognitive decline. The objective of this pilot study is to examin...
Patients with breast cancer have a variety of worries and need multifaceted information support. Their accumulated posts on social media contain rich descriptions of their daily worries concerning iss...
This study aimed to extract and classify multiple worries from text generated by patients with breast cancer using Bidirectional Encoder Representations From Transformers (BERT), a context-aware natur...
A total of 2272 blog posts by patients with breast cancer in Japan were collected. Five worry labels, "treatment," "physical," "psychological," "work/financial," and "family/friends," were defined and...
Among the blog posts, 477 included "treatment," 1138 included "physical," 673 included "psychological," 312 included "work/financial," and 283 included "family/friends." The interannotator agreement v...
This study showed that the BERT model can extract multiple worries from text generated from patients with breast cancer. This is the first application of a multilabel classifier using the BERT model t...
We compared different LLMs, notably chatGPT, GPT4, and Google Bard and we tested whether their performance differs in subspeciality domains, in executing examinations from four different courses of th...
