Clinician search behaviors may be influenced by search engine design.

BACKGROUND: Searching the Web for documents using information retrieval systems plays an important part in clinicians' practice of evidence-based medicine. While much research focuses on the design of methods to retrieve documents, there has been little examination of the way different search engine capabilities influence clinician search behaviors. OBJECTIVES: Previous studies have shown that use of task-based search engines allows for faster searches with no loss of decision accuracy compared with resource-based engines. We hypothesized that changes in search behaviors may explain these differences. METHODS: In all, 75 clinicians (44 doctors and 31 clinical nurse consultants) were randomized to use either a resource-based or a task-based version of a clinical information retrieval system to answer questions about 8 clinical scenarios in a controlled setting in a university computer laboratory. Clinicians using the resource-based system could select 1 of 6 resources, such as PubMed; clinicians using the task-based system could select 1 of 6 clinical tasks, such as diagnosis. Clinicians in both systems could reformulate search queries. System logs unobtrusively capturing clinicians' interactions with the systems were coded and analyzed for clinicians' search actions and query reformulation strategies. RESULTS: The most frequent search action of clinicians using the resource-based system was to explore a new resource with the same query, that is, these clinicians exhibited a "breadth-first" search behaviour. Of 1398 search actions, clinicians using the resource-based system conducted 401 (28.7%, 95% confidence interval [CI] 26.37-31.11) in this way. In contrast, the majority of clinicians using the task-based system exhibited a "depth-first" search behavior in which they reformulated query keywords while keeping to the same task profiles. Of 585 search actions conducted by clinicians using the task-based system, 379 (64.8%, 95% CI 60.83-68.55) were conducted in this way. CONCLUSIONS: This study provides evidence that different search engine designs are associated with different user search behaviors.

Computerization framework for clinical practice guidelines by extending the XML guidelines element model (GEM).

Contextually sensitive and semantically related evidence-based knowledge play an important role in decision-making. Clinical practice guidelines (CPG) are being developed to provide a rich source of up-to-date knowledge of evidence-based best clinical practices. Such knowledge assists healthcare practitioner in specific clinical circumstances at their decision-points. In many studies, it was shown that the effectiveness of CPG could be improved with their computerization. In this paper, we present our CPG-knowledge computerization framework that has been developed and implemented along the lines of knowledge management approaches. This framework adds context, semantics and related meta-information to the CPGs knowledge content using an extended-knowledge component ontology and UMLS. It also transforms them into a set of structured 'extended-knowledge components'. These extended-knowledge components constitute a 'CPG knowledge base', which is used for providing assistance at point of care.

Peripheral bronchial identification on chest CT using unsupervised machine learning.

PURPOSE: To automatically identify small- to medium-diameter bronchial segments distributed throughout the lungs. METHODS: We segment the peripheral pulmonary vascular tree and construct cross-sectional images perpendicular to the lung vasculature. The bronchi running with pulmonary arteries appear as concentric rings, and potential center points that lie within the bronchi are identified by looking for circles (using the circular Hough transform) and rings (using a novel variable ring filter). The number of candidate bronchial center points are further reduced by using agglomerative hierarchical clustering applied to the points represented with 18 features pertaining to their 3D position, orientation and appearance of the surrounding cross-sectional image. Resulting clusters corresponded to bronchial segments. Parameters of the algorithm are varied and applied to two experimental data sets to find the best values for bronchial identification. The optimized algorithm was then applied to a further 21 CT studies obtained using two different CT vendors. RESULTS: The parameters that result in the most number of true positive bronchial center points with > 95% precision are a tolerance of 0.15 for the hierarchical clustering algorithm and a threshold of 75 HU with 10 spokes for the ring filter. Overall, the performance on all 21 test data sets from CT scans from both vendors demonstrates a mean number of 563 bronchial points detected per CT study, with a mean precision of 96%. The detected points across this group of test data sets are relatively uniformly distributed spatially with respect to spherical coordinates with the origin at the center of the test imaging data sets. CONCLUSION: We have constructed a robust algorithm for automatic detection of small- to medium-diameter bronchial segments throughout the lungs using a combination of knowledge-based approaches and unsupervised machine learning. It appears robust over two different CT vendors with similar acquisition parameters.

Improving computer aided disease detection using knowledge of disease appearance.

The accurate quantification of disease patterns in medical images allows radiologists to track the progress of a disease. Various computer vision techniques are able to automatically detect different patterns that appear on images. However, classical pattern detection approaches do not perform satisfactorily on medical images. The problem is that texture descriptors, alone, do not capture information that is pertinent to medical images, i.e. the disease appearance and distribution. We present a method that uses knowledge of anatomy and specialised knowledge about disease appearance to improve computer-aided detection. The system has been tested on detecting honeycombing - a diffuse lung disease pattern in HRCT images of the lung. The results show that the proposed knowledge guided approach improves the accuracy of honeycombing detection. A paired t-test, shows the improvement in accuracy to be statistically significant (p<0.0001).

E-healthcare for Diabetes Mellitus Type 2 Patients - A Randomised Controlled Trial in Slovenia.

BACKGROUND: Telemonitoring and web-based interventions are increasingly used in primary-care practices in many countries for more effective management of patients with diabetes mellitus (DM). A new approach in treating patients with diabetes mellitus in family practices, based on ICT use and nurse practitioners, has been introduced and evaluated in this study. METHOD: Fifteen Slovene family practices enrolled 120 DM patients treated only with a diet regime and/or tablets into the study. 58 of them were included into the interventional group, and the other 62 DM patients into the control group, within one-year-long interventional, randomised controlled trial. Patients in the control group had conventional care for DM according to Slovenian professional guidelines, while the patients in the interventional group were using also the eDiabetes application. Patients were randomised through a balanced randomisation process. RESULTS: Significant reductions of glycated haemoglobin (HbA1c) values were found after 6 and 12 months among patients using this eDiabetes application (p<0.05). Among these patients, a significant correlation was also found between self-monitored blood pressure and the final HbA1c values. Diabetic patients' involvement in web-based intervention had only transient impact on their functional health status. CONCLUSION: This eDiabetes application was confirmed to be an innovative approach for better self-management of DM type 2 patients not using insulin. Both a significant reduction of HbA1c values and a significant correlation between the average self-measured blood pressure and the final HbA1c values in the interventional group were found. Nurse practitioners - as diabetes care coordinators - could contribute to better adherence in diabetes e-care.

Automatic segmentation and analysis of the main pulmonary artery on standard post-contrast CT studies using iterative erosion and dilation.

PURPOSE: To describe an algorithm for the accurate segmentation of the main pulmonary artery (MPA) and determining its length, mid-cross-sectional area and mid-circumferential perimeter. This will help with accurate, rapid and reproducible MPA measurements which can be used to detect diseases that cause raised pulmonary arterial pressure, and allow standardized serial measurements to assess progression or response to treatment. METHOD: We perform MPA segmentation using a novel approach based on erosion and dilation. A centerline is then determined by skeletonization, graph construction and spline fitting. MPA cross sections perpendicular to the centerline are analyzed in order to determine MPA length, and mid-cross-sectional area and perimeter. The technique was developed using four normal chest CT data sets and then tested on twenty normal post-contrast chest CT studies. Results are compared to manual segmentation and measurement by a thoracic radiologist. RESULTS: The mean MPA length, mid-cross-sectional area and mid-circumferential perimeter of the twenty test data sets, calculated by our algorithm, are 43.6 [Formula: see text] 9.2 mm, 552.9 [Formula: see text] 132.4[Formula: see text] and [Formula: see text], respectively, compared with [Formula: see text] and [Formula: see text] obtained manually by the radiologist. Our technique shows high correlation with the manually determined parameters for both mid- cross-sectional area ([Formula: see text]) and length ([Formula: see text]), and good correlation for mid-circumferential perimeter ([Formula: see text]). CONCLUSION: Our algorithm is a robust accurate automated method for obtaining measurements of the MPA. This allows a more standardized method for determining length, and mid- cross-sectional area/perimeter and therefore allows more accurate comparison of MPA measurements.

Band smearing of PCR amplified bacterial 16S rRNA genes: dependence on initial PCR target diversity.

Band smearing in agarose gels of PCR amplified bacterial 16S rRNA genes is understood to comprise amplicons of varying sizes arising from PCR errors, and requires elimination. We consider that with amplified heterogeneous DNA, delayed electro-migration is caused not by PCR errors but by dsDNA structures that arise from imperfect strand pairing. The extent of band smearing was found to be proportional to the sequence heterogeneity in 16S rRNA variable regions. Denaturing alkaline gels showed that all amplified DNA was of the correct size. A novel bioinformatic approach was used to reveal that band smearing occurred due to imperfectly paired strands of the amplified DNA. Since the smear is a structural fraction of the correct size PCR product, it carries important information on richness and diversity of the target DNA. For accurate analysis, the origin of the smear must first be identified before it is eliminated by examining the amplified DNA in denaturing alkaline gels.

Ray-tracing based registration for HRCT images of the lungs.

Image registration is a fundamental problem in medical imaging. It is especially challenging in lung images compared, for example, with the brain. The challenges include large anatomical variations of human lung and a lack of fixed landmarks inside the lung. This paper presents a new method for lung HRCT image registration. It employs a landmark-based global transformation and a novel ray-tracing-based lung surface registration. The proposed surface registration method has two desirable properties: 1) it is fully reversible, and 2) it ensures that the registered lung will be inside the target lung. We evaluated the registration performance by applying it to lung regions mapping. Tested on 46 scans, the registered regions were 89% accurate compared with the ground-truth.