Named entity recognition of follow-up and time information in 20 000 radiology reports

Objective

To develop a system to extract follow-up information from radiology reports. The method may be used as a component in a system which automatically generates follow-up information in a timely fashion.

Methods

A novel method of combining an LSP (labeled sequential pattern) classifier with a CRF (conditional random field) recognizer was devised. The LSP classifier filters out irrelevant sentences, while the CRF recognizer extracts follow-up and time phrases from candidate sentences presented by the LSP classifier.

Measurements

The standard performance metrics of precision (P), recall (R), and F measure (F) in the exact and inexact matching settings were used for evaluation.

Results

Four experiments conducted using 20 000 radiology reports showed that the CRF recognizer achieved high performance without time-consuming feature engineering and that the LSP classifier further improved the performance of the CRF recognizer. The performance of the current system is P=0.90, R=0.86, F=0.88 in the exact matching setting and P=0.98, R=0.93, F=0.95 in the inexact matching setting.

Conclusion

The experiments demonstrate that the system performs far better than a baseline rule-based system and is worth considering for deployment trials in an alert generation system. The LSP classifier successfully compensated for the inherent weakness of CRF, that is, its inability to use global information.     

Patient-controlled sharing of medical imaging data across unaffiliated healthcare organizations

Background

Current image sharing is carried out by manual transportation of CDs by patients or organization-coordinated sharing networks. The former places a significant burden on patients and providers. The latter faces challenges to patient privacy.

Objective

To allow healthcare providers efficient access to medical imaging data acquired at other unaffiliated healthcare facilities while ensuring strong protection of patient privacy and minimizing burden on patients, providers, and the information technology infrastructure.

Methods

An image sharing framework is described that involves patients as an integral part of, and with full control of, the image sharing process. Central to this framework is the Patient Controlled Access-key REgistry (PCARE) which manages the access keys issued by image source facilities. When digitally signed by patients, the access keys are used by any requesting facility to retrieve the associated imaging data from the source facility. A centralized patient portal, called a PCARE patient control portal, allows patients to manage all the access keys in PCARE.

Results

A prototype of the PCARE framework has been developed by extending open-source technology. The results for feasibility, performance, and user assessments are encouraging and demonstrate the benefits of patient-controlled image sharing.

Discussion

The PCARE framework is effective in many important clinical cases of image sharing and can be used to integrate organization-coordinated sharing networks. The same framework can also be used to realize a longitudinal virtual electronic health record.

Conclusion

The PCARE framework allows prior imaging data to be shared among unaffiliated healthcare facilities while protecting patient privacy with minimal burden on patients, providers, and infrastructure. A prototype has been implemented to demonstrate the feasibility and benefits of this approach.     

Valuable Radiographic Tool for Odontogenic Jaw Keratocyst Diagnosis and Surgical Planning

Objective:

To investigate the clinical use of cone beam computed tomography in the diagnosis of patients with odontogenic jaw keratocyst and to guide computer-aided surgical treatment planning.

Methods:

Imaging, image processing, and visualization technologies were used to produce clear diagnosis, provide proper treatment, and formulate favourable prognosis. Cone beam computed tomography was used to collect medical information including site, extent, shape, and other characteristic features of a patient with large odontogenic jaw keratocyst.

Results:

The imaging technique produced excellent results in imaging, image processing and threedimensional (3D) visualization.

Conclusion:

The 3D digital reconstruction model of the odontogenic jaw keratocyst was shown intuitively.     

Research and applications: Supervised machine learning and active learning in classification of radiology reports

Objective

This paper presents an automated system for classifying the results of imaging examinations (CT, MRI, positron emission tomography) into reportable and non-reportable cancer cases. This system is part of an industrial-strength processing pipeline built to extract content from radiology reports for use in the Victorian Cancer Registry.

Materials and methods

In addition to traditional supervised learning methods such as conditional random fields and support vector machines, active learning (AL) approaches were investigated to optimize training production and further improve classification performance. The project involved two pilot sites in Victoria, Australia (Lake Imaging (Ballarat) and Peter MacCallum Cancer Centre (Melbourne)) and, in collaboration with the NSW Central Registry, one pilot site at Westmead Hospital (Sydney).

Results

The reportability classifier performance achieved 98.25% sensitivity and 96.14% specificity on the cancer registry''s held-out test set. Up to 92% of training data needed for supervised machine learning can be saved by AL.

Discussion

AL is a promising method for optimizing the supervised training production used in classification of radiology reports. When an AL strategy is applied during the data selection process, the cost of manual classification can be reduced significantly.

Conclusions

The most important practical application of the reportability classifier is that it can dramatically reduce human effort in identifying relevant reports from the large imaging pool for further investigation of cancer. The classifier is built on a large real-world dataset and can achieve high performance in filtering relevant reports to support cancer registries.     

A personally controlled electronic health record for Australia

Objective

On July 1, 2012 Australia launched a personally controlled electronic health record (PCEHR) designed around the needs of consumers. Using a distributed model and leveraging key component national eHealth infrastructure, the PCEHR is designed to enable sharing of any health information about a patient with them and any other health practitioner involved in their care to whom the patient allows access. This paper discusses the consumer-facing part of the program.

Method

Design of the system was through stakeholder consultation and the development of detailed requirements, followed by clinical design assurance.

Results

Patients are able to access any posted information through a web-accessible ‘consumer portal.’ Within the portal they are able to assert access controls on all or part of their record. The portal includes areas for consumers to record their own personal information.

Discussion

The PCEHR has the potential to transform the ability of patients to actively engage in their own healthcare, and to enable the emerging partnership model of health and healthcare in medicine. The ability to access health information traditionally kept within the closed walls of institutions also raises challenges for the profession, both in the language clinicians choose and the ethical issues raised by the changed roles and responsibilities.

Conclusions

The PCEHR is aimed at connecting all participants and their interventions, and is intended to become a system-wide activity.     

MITRE system for clinical assertion status classification

Objective

To describe a system for determining the assertion status of medical problems mentioned in clinical reports, which was entered in the 2010 i2b2/VA community evaluation ‘Challenges in natural language processing for clinical data’ for the task of classifying assertions associated with problem concepts extracted from patient records.

Materials and methods

A combination of machine learning (conditional random field and maximum entropy) and rule-based (pattern matching) techniques was used to detect negation, speculation, and hypothetical and conditional information, as well as information associated with persons other than the patient.

Results

The best submission obtained an overall micro-averaged F-score of 0.9343.

Conclusions

Using semantic attributes of concepts and information about document structure as features for statistical classification of assertions is a good way to leverage rule-based and statistical techniques. In this task, the choice of features may be more important than the choice of classifier algorithm.     

Lumbar radiculopathy caused by foraminal stenosis in rheumatoid arthritis

Study design

Case-series study.

Objective

To describe the clinical presentation, characteristic findings of imaging studies, and treatment of lumbar radiculopathy caused by foraminal stenosis in rheumatoid arthritis.

Background

Lumbar lesions in rheumatoid arthritis are relatively rare, with a limited number of systemic reports.

Methods

Six patients with lumbar radiculopathy caused by foraminal stenosis in rheumatoid arthritis were treated. The patients were all women with a mean age of 69 years and mean rheumatoid arthritis duration of 15 years. The medical records and imaging studies of all patients were reviewed.

Results

The affected nerve roots were L4 in four patients and L3 in two patients. Foraminal stenosis was not demonstrated in magnetic resonance images in four of the six patients. Selective radiculography with nerve root block reproduced pain, manifested blocking effect, and demonstrated compression of the nerve root by the superior articular process of the lower vertebra in all patients. Conservative treatment was performed on one patient, and surgery was conducted for the rest of the five patients; radiculopathy was improved in all patients.

Conclusions

Lumbar foraminal stenosis is a characteristic pathology of rheumatoid arthritis, and should be kept in mind in the diagnosis of lumbar radiculopathy. Selective radiculography is useful in the diagnosis of affected nerve roots.     

A Novel Hybrid Approach to Automated Negation Detection in Clinical Radiology Reports

Objective

Negation is common in clinical documents and is an important source of poor precision in automated indexing systems. Previous research has shown that negated terms may be difficult to identify if the words implying negations (negation signals) are more than a few words away from them. We describe a novel hybrid approach, combining regular expression matching with grammatical parsing, to address the above limitation in automatically detecting negations in clinical radiology reports.

Design

Negations are classified based upon the syntactical categories of negation signals, and negation patterns, using regular expression matching. Negated terms are then located in parse trees using corresponding negation grammar.

Measurements

A classification of negations and their corresponding syntactical and lexical patterns were developed through manual inspection of 30 radiology reports and validated on a set of 470 radiology reports. Another 120 radiology reports were randomly selected as the test set on which a modified Delphi design was used by four physicians to construct the gold standard.

Results

In the test set of 120 reports, there were a total of 2,976 noun phrases, of which 287 were correctly identified as negated (true positives), along with 23 undetected true negations (false negatives) and 4 mistaken negations (false positives). The hybrid approach identified negated phrases with sensitivity of 92.6% (95% CI 90.9–93.4%), positive predictive value of 98.6% (95% CI 96.9–99.4%), and specificity of 99.87% (95% CI 99.7–99.9%).

Conclusion

This novel hybrid approach can accurately locate negated concepts in clinical radiology reports not only when in close proximity to, but also at a distance from, negation signals.     

Research and applications: MilxXplore: a web-based system to explore large imaging datasets

Objective

As large-scale medical imaging studies are becoming more common, there is an increasing reliance on automated software to extract quantitative information from these images. As the size of the cohorts keeps increasing with large studies, there is a also a need for tools that allow results from automated image processing and analysis to be presented in a way that enables fast and efficient quality checking, tagging and reporting on cases in which automatic processing failed or was problematic.

Materials and methods

MilxXplore is an open source visualization platform, which provides an interface to navigate and explore imaging data in a web browser, giving the end user the opportunity to perform quality control and reporting in a user friendly, collaborative and efficient way.

Discussion

Compared to existing software solutions that often provide an overview of the results at the subject''s level, MilxXplore pools the results of individual subjects and time points together, allowing easy and efficient navigation and browsing through the different acquisitions of a subject over time, and comparing the results against the rest of the population.

Conclusions

MilxXplore is fast, flexible and allows remote quality checks of processed imaging data, facilitating data sharing and collaboration across multiple locations, and can be easily integrated into a cloud computing pipeline. With the growing trend of open data and open science, such a tool will become increasingly important to share and publish results of imaging analysis.     

Computed tomography and magnetic resonance imaging of multiple focal nodular hyperplasias of the liver with congenital absence of the portal vein in a Chinese girl: case report and review of the literature

Background

Patients with congenital absence of the portal vein (CAPV) often suffer from additional medical complications such as hepatic tumors and cardiac malformations.

Case presentation

Congenital absence of the portal vein (CAPV) is a rare malformation. We present a case of a 16-year-old Chinese girl with CAPV with multiple pathology-proven hepatic focal nodular hyperplasias (FNHs) and ventricular septal defect (VSD). The CT and MRI features of this case are described, and previously reported cases are reviewed.

Conclusions

CAPV is a rare congenital anomaly and in such patients, clarifying the site of portosystemic shunts, liver disease, and other anomalies is critical for appropriate treatment selection and accurate prognosis determination. Close follow-up, including laboratory testing and radiologic imaging, is recommended for all CAPV patients.     

Hepatic portal venous gas – three non-fatal cases and review of the literature

Background

Hepatic portal venous gas is a rare imaging finding most commonly associated with intestinal ischaemia and high mortality. Increased use of advanced imaging techniques has resulted in increased reporting and recognition of hepatic portal venous gas. Advanced imaging can also recognise the many associated pathologies which have variable management strategies and prognoses.

Methods

We report 3 non-fatal cases and review the pathogenesis, aetiology, diagnosis, management and prognosis of hepatic portal venous gas.

Conclusion

Once considered an indication for urgent surgery, hepatic portal venous gas is a rare imaging finding. More recently, HPVG has been recognised to be associated with various benign causes many of which may be treated non-operatively. However, intestinal ischaemia remains the most common cause and the most important to exclude. CT is the diagnostic modality of choice. The underlying cause determines the treatment strategy and outcome.     

Sociotechnical challenges to developing technologies for patient access to health information exchange data

Background

Providing patients with access to their medical data is widely expected to help educate and empower them to manage their own health. Health information exchange (HIE) infrastructures could potentially help patients access records across multiple healthcare providers. We studied three HIE organizations as they developed portals to give consumers access to HIE data previously exchanged only among healthcare organizations.

Objective

To follow the development of new consumer portal technologies, and to identify barriers and facilitators to patient access to HIE data.

Methods

Semistructured interviews of 15 key informants over a 2-year period spanning the development and early implementation of three new projects, coded according to a sociotechnical framework.

Results

As the organizations tried to develop functionality that fully served the needs of both providers and patients, plans were altered by technical barriers (primarily related to data standardization) and cultural and legal issues surrounding data access. Organizational changes also played an important role in altering project plans. In all three cases, patient access to data was significantly scaled back from initial plans.

Conclusions

This prospective study revealed how sociotechnical factors previously identified as important in health information technology success and failure helped to shape the evolution of three novel consumer informatics projects. Barriers to providing patients with seamless access to their HIE data were multifactorial. Remedies will have to address technical, organizational, cultural, and other factors.     

Development and Implementation of a Clinician Reporting System for Advanced Stage Cancer: Initial Lessons Learned

Objective

Innovative approaches can strengthen patient-caregiver-clinician information exchange and more effectively address the physical and psychosocial challenges of advanced disease. This study reports initial findings from implementation of the Clinician Report (CR)—a patient and caregiver status report tool accessible by the oncology clinic team.

Design

The CR tracks and communicates essential information from cancer patients and caregivers to the oncology team. The CR conveys patient symptoms, emotional strain, and key concerns.

Measurements

Authors used a model developed to explain acceptance, implementation, and sustainability of Interactive Health Communication Systems (IHCS) to evaluate implementation of the new CR system. The study carried out qualitative analyses of interviews with clinicians regarding their experience utilizing the Clinician Report.

Results

Primary CR benefits included enhancement of patients'' clinic visit experiences, greater caregiver involvement, and facilitation of earlier interventions. Challenges included CR functional issues, users'' desire for greater depth of information, user privacy concerns, and limited patient use. These findings are discussed using parameters of the implementation model. Limitations of this study include its small clinician sample size, which represented only a portion of existing organizational settings in which CR systems might be implemented.

Conclusion

Though in its early implementation stages, the CR demonstrates the potential to positively impact care delivery in the cancer clinic setting, particularly by facilitating earlier interventions and improving patient-caregiver-clinician communication both during and between clinic visits.     

Use of a support vector machine for categorizing free-text notes: assessment of accuracy across two institutions

Background

Electronic health record (EHR) users must regularly review large amounts of data in order to make informed clinical decisions, and such review is time-consuming and often overwhelming. Technologies like automated summarization tools, EHR search engines and natural language processing have been shown to help clinicians manage this information.

Objective

To develop a support vector machine (SVM)-based system for identifying EHR progress notes pertaining to diabetes, and to validate it at two institutions.

Materials and methods

We retrieved 2000 EHR progress notes from patients with diabetes at the Brigham and Women''s Hospital (1000 for training and 1000 for testing) and another 1000 notes from the University of Texas Physicians (for validation). We manually annotated all notes and trained a SVM using a bag of words approach. We then used the SVM on the testing and validation sets and evaluated its performance with the area under the curve (AUC) and F statistics.

Results

The model accurately identified diabetes-related notes in both the Brigham and Women''s Hospital testing set (AUC=0.956, F=0.934) and the external University of Texas Faculty Physicians validation set (AUC=0.947, F=0.935).

Discussion

Overall, the model we developed was quite accurate. Furthermore, it generalized, without loss of accuracy, to another institution with a different EHR and a distinct patient and provider population.

Conclusions

It is possible to use a SVM-based classifier to identify EHR progress notes pertaining to diabetes, and the model generalizes well.     

How outcomes are achieved through patient portals: a realist review

Objective

To examine how patient portals contribute to health service delivery and patient outcomes. The specific aims were to examine how outcomes are produced, and how variations in outcomes can be explained.

Methods

We used a realist review method, which aims to describe how ‘an intervention works, for whom, and in what circumstances’ by analyzing patterns between context, mechanism, and outcomes. We reviewed 32 evaluation studies of patient portals published since 2003.

Results

The reviewed evaluations indicate that as a complement to existing health services, patient portals can lead to improvements in clinical outcomes, patient behavior, and experiences. Four different mechanisms are reported to yield the reported outcome improvements. These are patient insight into personal health information, activation of information, interpersonal continuity of care, and service convenience. The vast majority of evaluations were conducted in integrated health service networks in the USA, and we detected no substantial variation in outcomes across these networks.

Discussion and conclusions

Patient portals may impact clinical outcomes and health service delivery through multiple mechanisms. Given the relative uniformity of evaluation contexts, we were not able to detect patterns in how patient portals work in different contexts. Nonetheless, it appears from the overwhelming proportion of patient portal evaluations coming from integrated health service networks, that these networks provide more fertile contexts for patient portals to be effective. To improve the understanding of how patient portals work, future evaluations of patient portals should capture information about mechanisms and context that influence their outcomes.     

Research and applications: Automatic glaucoma diagnosis through medical imaging informatics

Background

Computer-aided diagnosis for screening utilizes computer-based analytical methodologies to process patient information. Glaucoma is the leading irreversible cause of blindness. Due to the lack of an effective and standard screening practice, more than 50% of the cases are undiagnosed, which prevents the early treatment of the disease.

Objective

To design an automatic glaucoma diagnosis architecture automatic glaucoma diagnosis through medical imaging informatics (AGLAIA-MII) that combines patient personal data, medical retinal fundus image, and patient''s genome information for screening.

Materials and methods

2258 cases from a population study were used to evaluate the screening software. These cases were attributed with patient personal data, retinal images and quality controlled genome data. Utilizing the multiple kernel learning-based classifier, AGLAIA-MII, combined patient personal data, major image features, and important genome single nucleotide polymorphism (SNP) features.

Results and discussion

Receiver operating characteristic curves were plotted to compare AGLAIA-MII''s performance with classifiers using patient personal data, images, and genome SNP separately. AGLAIA-MII was able to achieve an area under curve value of 0.866, better than 0.551, 0.722 and 0.810 by the individual personal data, image and genome information components, respectively. AGLAIA-MII also demonstrated a substantial improvement over the current glaucoma screening approach based on intraocular pressure.

Conclusions

AGLAIA-MII demonstrates for the first time the capability of integrating patients’ personal data, medical retinal image and genome information for automatic glaucoma diagnosis and screening in a large dataset from a population study. It paves the way for a holistic approach for automatic objective glaucoma diagnosis and screening.     

Temporal reasoning over clinical text: the state of the art

Objectives

To provide an overview of the problem of temporal reasoning over clinical text and to summarize the state of the art in clinical natural language processing for this task.

Target audience

This overview targets medical informatics researchers who are unfamiliar with the problems and applications of temporal reasoning over clinical text.

Scope

We review the major applications of text-based temporal reasoning, describe the challenges for software systems handling temporal information in clinical text, and give an overview of the state of the art. Finally, we present some perspectives on future research directions that emerged during the recent community-wide challenge on text-based temporal reasoning in the clinical domain.     

Spiral CT Angiography: Applications in Neurovascular Imaging

Background

The advent of Spiral Computed Tomographic (CT) angiography has provided the patients a non-invasive, accurate and fast modality of imaging the vasculature.

Methods

Spiral CT angiography was performed in 30 patients to evaluate intracranial circulation using standard protocols of data acquisition. The images were processed and reconstructed in 3-dimension to delineate anatomy and pathology accurately.

Results

The study established that CT angiography is an accurate modality for evaluating the intracranial circulation in a variety of abnormalities. It is safe both in terms of being non-invasive and exposure to radiation. It has a distinct advantage over other non-invasive modalities of imaging like MRI in the evaluation of patients with metallic stents and clips.

Conclusion

CT angiography has tremendous potential in imaging the intracranial vasculature. It is unquestionably safer than catheter angiography as it avoids arterial puncture and intra-arterial catheter manipulation. It is fast and capable of producing excellent 3-dimensional images of the intracranial vasculature.Key Words: Neurovascular imaging, Spiral CT, CT Angiography     

Effects of librarian-provided services in healthcare settings: a systematic review

Objective

To assess the effects of librarian-provided services in healthcare settings on patient, healthcare provider, and researcher outcomes.

Materials and methods

Medline, CINAHL, ERIC, LISA (Library and Information Science Abstracts), and the Cochrane Central Register of Controlled Trials were searched from inception to June 2013. Studies involving librarian-provided services for patients encountering the healthcare system, healthcare providers, or researchers were eligible for inclusion. All librarian-provided services in healthcare settings were considered as an intervention, including hospitals, primary care settings, or public health clinics.

Results

Twenty-five articles fulfilled our eligibility criteria, including 22 primary publications and three companion reports. The majority of studies (15/22 primary publications) examined librarians providing instruction in literature searching to healthcare trainees, and measured literature searching proficiency. Other studies analyzed librarian-provided literature searching services and instruction in question formulation as well as the impact of librarian-provided services on patient length of stay in hospital. No studies were found that investigated librarians providing direct services to researchers or patients in healthcare settings.

Conclusions

Librarian-provided services directed to participants in training programs (eg, students, residents) improve skills in searching the literature to facilitate the integration of research evidence into clinical decision-making. Services provided to clinicians were shown to be effective in saving time for health professionals and providing relevant information for decision-making. Two studies indicated patient length of stay was reduced when clinicians requested literature searches related to a patient''s case.