Content Analysis of Reporting Templates and Free-Text Radiology Reports

BACKGROUND Named entity recognition (NER) plays an important role in extracting the features of descriptions for mining free-text radiology reports. However, the performance of existing NER tools is limited because the number of entities depends on its dictionary lookup. Especially, the recognition of compound terms is very complicated because there are a variety of patterns. OBJECTIVE The objective of the study is to develop and evaluate a NER tool concerned with compound terms using the RadLex for mining free-text radiology reports. METHODS We leveraged the clinical Text Analysis and Knowledge Extraction System (cTAKES) to develop customized pipelines using both RadLex and SentiWordNet (a general-purpose dictionary, GPD). We manually annotated 400 of radiology reports for compound terms (Cts) in noun phrases and used them as the gold standard for the performance evaluation (precision, recall, and F-measure). Additionally, we also created a compound-term-enhanced dictionary (CtED) by analyzing false negatives (FNs) and false positives (FPs), and applied it for another 100 radiology reports for validation. We also evaluated the stem terms of compound terms, through defining two measures: an occurrence ratio (OR) and a matching ratio (MR). RESULTS The F-measure of the cTAKES+RadLex+GPD was 32.2% (Precision 92.1%, Recall 19.6%) and that of combined the CtED was 67.1% (Precision 98.1%, Recall 51.0%). The OR indicated that stem terms of “effusion”, "node", "tube", and "disease" were used frequently, but it still lacks capturing Cts. The MR showed that 71.9% of stem terms matched with that of ontologies and RadLex improved about 22% of the MR from the cTAKES default dictionary. The OR and MR revealed that the characteristics of stem terms would have the potential to help generate synonymous phrases using ontologies. CONCLUSIONS We developed a RadLex-based customized pipeline for parsing radiology reports and demonstrated that CtED and stem term analysis has the potential to improve dictionary-based NER performance toward expanding vocabularies.

Download Full-text

Multi-task weak supervision enables anatomically-resolved abnormality detection in whole-body FDG-PET/CT

Nature Communications ◽

10.1038/s41467-021-22018-1 ◽

2021 ◽

Vol 12 (1) ◽

Author(s):

Sabri Eyuboglu ◽

Geoffrey Angus ◽

Bhavik N. Patel ◽

Anuj Pareek ◽

Guido Davidzon ◽

...

Keyword(s):

Fdg Pet ◽

Location Estimation ◽

Supervised Machine Learning ◽

Whole Body ◽

Free Text ◽

Abnormality Detection ◽

Weak Supervision ◽

Radiology Reports ◽

Pet Ct ◽

Fdg Pet Ct

AbstractComputational decision support systems could provide clinical value in whole-body FDG-PET/CT workflows. However, limited availability of labeled data combined with the large size of PET/CT imaging exams make it challenging to apply existing supervised machine learning systems. Leveraging recent advancements in natural language processing, we describe a weak supervision framework that extracts imperfect, yet highly granular, regional abnormality labels from free-text radiology reports. Our framework automatically labels each region in a custom ontology of anatomical regions, providing a structured profile of the pathologies in each imaging exam. Using these generated labels, we then train an attention-based, multi-task CNN architecture to detect and estimate the location of abnormalities in whole-body scans. We demonstrate empirically that our multi-task representation is critical for strong performance on rare abnormalities with limited training data. The representation also contributes to more accurate mortality prediction from imaging data, suggesting the potential utility of our framework beyond abnormality detection and location estimation.

Download Full-text

A Mixed Methods Analysis of Parental Perspectives on Diagnosis and Prognosis of Neonatal Intensive Care Unit Graduates With Cerebral Palsy

Journal of Child Neurology ◽

10.1177/0883073820901412 ◽

2020 ◽

Vol 35 (5) ◽

pp. 336-343

Author(s):

Katherine Guttmann ◽

John Flibotte ◽

Sara B. DeMauro ◽

Holli Seitz

Keyword(s):

Intensive Care Unit ◽

Cerebral Palsy ◽

Content Analysis ◽

Intensive Care ◽

Neonatal Intensive Care Unit ◽

Thematic Analysis ◽

Neonatal Intensive Care ◽

Free Text ◽

Word Count ◽

Linguistic Inquiry

This study aimed to evaluate how parents of former neonatal intensive care unit patients with cerebral palsy perceive prognostic discussions following neuroimaging. Parent members of a cerebral palsy support network described memories of prognostic discussions after neuroimaging in the neonatal intensive care unit. We analyzed responses using Linguistic Inquiry and Word Count, manual content analysis, and thematic analysis. In 2015, a total of 463 parents met eligibility criteria and 266 provided free-text responses. Linguistic Inquiry and Word Count analysis showed that responses following neuroimaging contained negative emotion. The most common components identified through the content analysis included outcome, uncertainty, hope/hopelessness, and weakness in communication. Thematic analysis revealed 3 themes: (1) Information, (2) Communication, and (3) Impact. Parents of children with cerebral palsy report weakness in communication relating to prognosis, which persists in parents’ memories. Prospective work to develop interventions to improve communication between parents and providers in the neonatal intensive care unit is necessary.

Download Full-text

What are the concerns and goals of women attending a urogynaecology clinic? Content analysis of free-text data from an electronic pelvic floor assessment questionnaire (ePAQ-PF)

International Urogynecology Journal ◽

10.1007/s00192-018-3697-0 ◽

2018 ◽

Vol 30 (1) ◽

pp. 33-41 ◽

Cited By ~ 3

Author(s):

Thomas Gray ◽

Scarlett Strickland ◽

Sarita Pooranawattanakul ◽

Weiguang Li ◽

Patrick Campbell ◽

...

Keyword(s):

Content Analysis ◽

Pelvic Floor ◽

Free Text ◽

Text Data ◽

Assessment Questionnaire

Download Full-text

The Effect of Image Resolution on Automated Classification of Chest X-rays

10.1101/2021.07.30.21261225 ◽

2021 ◽

Author(s):

Md Inzamam Ul Haque ◽

Abhishek K Dubey ◽

Jacob D Hinkle

Keyword(s):

High Resolution ◽

Automated Analysis ◽

Image Resolution ◽

Free Text ◽

X Rays ◽

Training Time ◽

X Ray ◽

Radiology Reports ◽

Chest X Ray ◽

High Resolution Images

Deep learning models have received much attention lately for their ability to achieve expert-level performance on the accurate automated analysis of chest X-rays. Although publicly available chest X-ray datasets include high resolution images, most models are trained on reduced size images due to limitations on GPU memory and training time. As compute capability continues to advance, it will become feasible to train large convolutional neural networks on high-resolution images. This study is based on the publicly available MIMIC-CXR-JPG dataset, comprising 377,110 high resolution chest X-ray images, and provided with 14 labels to the corresponding free-text radiology reports. We find, interestingly, that tasks that require a large receptive field are better suited to downscaled input images, and we verify this qualitatively by inspecting effective receptive fields and class activation maps of trained models. Finally, we show that stacking an ensemble across resolutions outperforms each individual learner at all input resolutions while providing interpretable scale weights, suggesting that multi-scale features are crucially important to information extraction from high-resolution chest X-rays.

Download Full-text

Increasing the Efficiency on Producing Radiology Reports for Breast Cancer Diagnosis by Means of Structured Reports

Methods of Information in Medicine ◽

10.3414/me16-01-0091 ◽

2017 ◽

Vol 56 (03) ◽

pp. 248-260 ◽

Cited By ~ 8

Author(s):

Rosana Medina ◽

Ignacio Blanquer ◽

Luis Martí-Bonmatí ◽

J. Damian Segrelles

Keyword(s):

Breast Cancer ◽

Clinical Practice ◽

Cancer Diagnosis ◽

Web Application ◽

Breast Cancer Diagnosis ◽

Software Tools ◽

Free Text ◽

Anova Test ◽

Radiology Reports ◽

Structured Reports

SummaryBackground: Radiology reports are commonly written on free-text using voice recognition devices. Structured reports (SR) have a high potential but they are usually considered more difficult to fill-in so their adoption in clinical practice leads to a lower efficiency. However, some studies have demonstrated that in some cases, producing SRs may require shorter time than plain-text ones. This work focuses on the definition and demonstration of a methodology to evaluate the productivity of software tools for producing radiology reports. A set of SRs for breast cancer diagnosis based on BI-RADS have been developed using this method. An analysis of their efficiency with respect to free-text reports has been performed.Material and Methods: The methodology proposed compares the Elapsed Time (ET) on a set of radiological reports. Free-text reports are produced with the speech recognition devices used in the clinical practice. Structured reports are generated using a web application generated with TRENCADIS framework. A team of six radiologists with three different levels of experience in the breast cancer diagnosis was recruited. These radiologists performed the evaluation, each one introducing 50 reports for mammography, 50 for ultrasound scan and 50 for MRI using both approaches. Also, the Relative Efficiency (REF) was computed for each report, dividing the ET of both methods. We applied the T-Student (T-S) test to compare the ETs and the ANOVA test to compare the REFs. Both tests were computed using the SPSS software.Results: The study produced three DICOM- SR templates for Breast Cancer Diagnosis on mammography, ultrasound and MRI, using RADLEX terms based on BIRADs 5th edition. The T-S test on radiologists with high or intermediate profile, showed that the difference between the ET was only statistically significant for mammography and ultrasound. The ANOVA test performed grouping the REF by modalities, indicated that there were no significant differences between mammograms and ultrasound scans, but both have significant statistical differences with MRI. The ANOVA test of the REF for each modality, indicated that there were only significant differences in Mammography (ANOVA p = 0.024) and Ultrasound (ANOVA p = 0.008). The ANOVA test for each radiologist profile, indicated that there were significant differences on the high profile (ANOVA p = 0.028) and medium (ANOVA p=0.045).Conclusions: In this work, we have defined and demonstrated a methodology to evaluate the productivity of software tools for producing radiology reports in Breast Cancer. We have evaluated that adopting Structured Reporting in mammography and ultrasound studies in breast cancer diagnosis improves the performance in producing reports.

Download Full-text

Physiotherapists’ views on the Australian Physiotherapy Association’s Choosing Wisely recommendations: a content analysis

BMJ Open ◽

10.1136/bmjopen-2019-031360 ◽

2019 ◽

Vol 9 (9) ◽

pp. e031360 ◽

Cited By ~ 2

Author(s):

Joshua Zadro ◽

Aimie L Peek ◽

Rachael H Dodd ◽

Kirsten McCaffery ◽

Christopher Maher

Keyword(s):

Content Analysis ◽

Decision Rules ◽

Choosing Wisely ◽

Secondary Outcome ◽

Free Text ◽

Similar Response ◽

Physiotherapy Practice ◽

Free Text Response ◽

Key Terms ◽

The Impact

ObjectivesChoosing Wisely holds promise for increasing awareness of low-value care in physiotherapy. However, it is unclear how physiotherapists’ view Choosing Wisely recommendations. The aim of this study was to evaluate physiotherapists’ feedback on Choosing Wisely recommendations and investigate agreement with each recommendation.SettingThe Australian Physiotherapy Association emailed a survey to all 20 029 physiotherapist members in 2015 seeking feedback on a list of Choosing Wisely recommendations.ParticipantsA total of 9764 physiotherapists opened the email invitation (49%) and 543 completed the survey (response rate 5.6%). Participants were asked about the acceptability of the wording of recommendations using a closed (Yes/No) and free-text response option (section 1). Then using a similar response format, participants were asked whether they agreed with each Choosing Wisely recommendation (sections 2–6).Primary and secondary outcomesWe performed a content analysis of free-text responses (primary outcome) and used descriptive statistics to report agreement and disagreement with each recommendation (secondary outcome).ResultsThere were 872 free-text responses across the six sections. A total of 347 physiotherapists (63.9%) agreed with the ‘don’t’ style of wording. Agreement with recommendations ranged from 52.3% (electrotherapy for back pain) to 76.6% (validated decision rules for imaging). The content analysis revealed that physiotherapists felt that blanket rules were inappropriate (range across recommendations: 13.9%–30.1% of responses), clinical experience is more valuable than evidence (11.7%–28.3%) and recommendations would benefit from further refining or better defining key terms (7.3%–22.4%).ConclusionsAlthough most physiotherapists agreed with both the style of wording for Choosing Wisely recommendations and with the recommendations, their feedback highlighted a number of areas of disagreement and suggestions for improvement. These findings will support the development of future recommendations and are the first step towards increasing the impact Choosing Wisely has on physiotherapy practice.

Download Full-text

Development of a System that Generates Structured Reports for Chest X-ray Radiography

Methods of Information in Medicine ◽

10.3414/me09-01-0014 ◽

2010 ◽

Vol 49 (04) ◽

pp. 360-370 ◽

Cited By ~ 4

Author(s):

Y. Matsumura ◽

N. Mihara ◽

Y. Kawakami ◽

K. Sasai ◽

H. Takeda ◽

...

Keyword(s):

Narrative Form ◽

Free Text ◽

X Rays ◽

Sentence Structure ◽

X Ray ◽

Radiology Reports ◽

Chest X Ray ◽

Structured Reports ◽

Description Framework ◽

Resource Description

Summary Objectives: Radiology reports are typically made in narrative form; this is a barrier to the implementation of advanced applications for data analysis or a decision support. We developed a system that generates structured reports for chest x-ray radiography. Methods: Based on analyzing existing reports, we determined the fundamental sentence structure of findings as compositions of procedure, region, finding, and diagnosis. We categorized the observation objects into lung, mediastinum, bone, soft tissue, and pleura and chest wall. The terms of region, finding, and diagnosis were associated with each other. We expressed the terms and the relations between the terms using a resource description framework (RDF) and developed a reporting system based on it. The system shows a list of terms in each category, and modifiers can be entered using templates that are linked to each term. This system guides users to select terms by highlighting associated terms. Fifty chest x-rays with abnormal findings were interpreted by five radiologists and reports were made either by the system or by the free-text method. Results: The system decreased the time needed to make a report by 12.5% compared with the free-text method, and the sentences generated by the system were well concordant with those made by free-text method (F-measure = 90%). The results of the questionnaire showed that our system is applicable to radiology reports of chest x-rays in daily clinical practice. Conclusions: The method of generating structured reports for chest x-rays was feasible, because it generated almost concordant reports in shorter time compared with the free-text method.

Download Full-text

Automating Stroke Data Extraction From Free-Text Radiology Reports Using Natural Language Processing: Instrument Validation Study (Preprint)

10.2196/preprints.24381 ◽

2020 ◽

Author(s):

Amy Y X Yu ◽

Zhongyu A Liu ◽

Chloe Pou-Prom ◽

Kaitlyn Lopes ◽

Moira K Kapral ◽

...

Keyword(s):

Natural Language Processing ◽

Natural Language ◽

Language Processing ◽

Predictive Value ◽

Large Vessel ◽

Free Text ◽

Imaging Data ◽

Large Vessel Occlusion ◽

Vessel Occlusion ◽

Radiology Reports

BACKGROUND Diagnostic neurovascular imaging data are important in stroke research, but obtaining these data typically requires laborious manual chart reviews. OBJECTIVE We aimed to determine the accuracy of a natural language processing (NLP) approach to extract information on the presence and location of vascular occlusions as well as other stroke-related attributes based on free-text reports. METHODS From the full reports of 1320 consecutive computed tomography (CT), CT angiography, and CT perfusion scans of the head and neck performed at a tertiary stroke center between October 2017 and January 2019, we manually extracted data on the presence of proximal large vessel occlusion (primary outcome), as well as distal vessel occlusion, ischemia, hemorrhage, Alberta stroke program early CT score (ASPECTS), and collateral status (secondary outcomes). Reports were randomly split into training (n=921) and validation (n=399) sets, and attributes were extracted using rule-based NLP. We reported the sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and the overall accuracy of the NLP approach relative to the manually extracted data. RESULTS The overall prevalence of large vessel occlusion was 12.2%. In the training sample, the NLP approach identified this attribute with an overall accuracy of 97.3% (95.5% sensitivity, 98.1% specificity, 84.1% PPV, and 99.4% NPV). In the validation set, the overall accuracy was 95.2% (90.0% sensitivity, 97.4% specificity, 76.3% PPV, and 98.5% NPV). The accuracy of identifying distal or basilar occlusion as well as hemorrhage was also high, but there were limitations in identifying cerebral ischemia, ASPECTS, and collateral status. CONCLUSIONS NLP may improve the efficiency of large-scale imaging data collection for stroke surveillance and research.

Download Full-text

Automating Stroke Data Extraction From Free-Text Radiology Reports Using Natural Language Processing: Instrument Validation Study

JMIR Medical Informatics ◽

10.2196/24381 ◽

2021 ◽

Vol 9 (5) ◽

pp. e24381

Author(s):

Amy Y X Yu ◽

Zhongyu A Liu ◽

Chloe Pou-Prom ◽

Kaitlyn Lopes ◽

Moira K Kapral ◽

...

Keyword(s):

Natural Language Processing ◽

Natural Language ◽

Language Processing ◽

Predictive Value ◽

Large Vessel ◽

Free Text ◽

Imaging Data ◽

Large Vessel Occlusion ◽

Vessel Occlusion ◽

Radiology Reports

Background Diagnostic neurovascular imaging data are important in stroke research, but obtaining these data typically requires laborious manual chart reviews. Objective We aimed to determine the accuracy of a natural language processing (NLP) approach to extract information on the presence and location of vascular occlusions as well as other stroke-related attributes based on free-text reports. Methods From the full reports of 1320 consecutive computed tomography (CT), CT angiography, and CT perfusion scans of the head and neck performed at a tertiary stroke center between October 2017 and January 2019, we manually extracted data on the presence of proximal large vessel occlusion (primary outcome), as well as distal vessel occlusion, ischemia, hemorrhage, Alberta stroke program early CT score (ASPECTS), and collateral status (secondary outcomes). Reports were randomly split into training (n=921) and validation (n=399) sets, and attributes were extracted using rule-based NLP. We reported the sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and the overall accuracy of the NLP approach relative to the manually extracted data. Results The overall prevalence of large vessel occlusion was 12.2%. In the training sample, the NLP approach identified this attribute with an overall accuracy of 97.3% (95.5% sensitivity, 98.1% specificity, 84.1% PPV, and 99.4% NPV). In the validation set, the overall accuracy was 95.2% (90.0% sensitivity, 97.4% specificity, 76.3% PPV, and 98.5% NPV). The accuracy of identifying distal or basilar occlusion as well as hemorrhage was also high, but there were limitations in identifying cerebral ischemia, ASPECTS, and collateral status. Conclusions NLP may improve the efficiency of large-scale imaging data collection for stroke surveillance and research.

Download Full-text