Static versus dynamic medical images: The role of cue utilization in diagnostic performance

2021 ◽  
Author(s):  
A. J. Carrigan ◽  
P. Stoodley ◽  
K. Ng ◽  
D. Moerel ◽  
M. W. Wiggins
Keyword(s):  
Diagnostic Performance ◽  
Medical Images ◽  
Cue Utilization ◽  
Static Versus Dynamic

scholarly journals Differentiating Experience From Cue Utilization in Radiological Assessments

2020 ◽  
pp. 001872082090257 ◽  
Author(s):  
Ann J. Carrigan ◽  
John Magnussen ◽  
Andrew Georgiou ◽  
Kim M. Curby ◽  
Thomas J. Palmeri ◽  
...  
Keyword(s):  
Cluster Analysis ◽  
Diagnostic Accuracy ◽  
Diagnostic Performance ◽  
Assessment Tool ◽  
Image Interpretation ◽  
Training Needs ◽  
Years Of Experience ◽  
Cue Utilization ◽  
Domain Specific

Objective This research was designed to examine the contribution of self-reported experience and cue utilization to diagnostic accuracy in the context of radiology. Background Within radiology, it is unclear how task-related experience contributes to the acquisition of associations between features with events in memory, or cues, and how they contribute to diagnostic performance. Method Data were collected from 18 trainees and 41 radiologists. The participants completed a radiology edition of the established cue utilization assessment tool EXPERTise 2.0, which provides a measure of cue utilization based on performance on a number of domain-specific tasks. The participants also completed a separate image interpretation task as an independent measure of diagnostic performance. Results Consistent with previous research, a k-means cluster analysis using the data from EXPERTise 2.0 delineated two groups, the pattern of centroids of which reflected higher and lower cue utilization. Controlling for years of experience, participants with higher cue utilization were more accurate on the image interpretation task compared to participants who demonstrated relatively lower cue utilization ( p = .01). Conclusion This study provides support for the role of cue utilization in assessments of radiology images among qualified radiologists. Importantly, it also demonstrates that cue utilization and self-reported years of experience as a radiologist make independent contributions to performance on the radiological diagnostic task. Application Task-related experience, including training, needs to be structured to ensure that learners have the opportunity to acquire feature–event relationships and internalize these associations in the form of cues in memory.

“Experience Isn’t Everything”: How Emotion Affects the Relationship Between Experience and Cue Utilization

2018 ◽  
Vol 60 (5) ◽  
pp. 685-698 ◽  
Author(s):  
Monique Frances Crane ◽  
Sue Brouwers ◽  
Mark William Wiggins ◽  
Thomas Loveday ◽  
Kirsty Forrest ◽  
...  
Keyword(s):  
Clinical Performance ◽  
Experience Level ◽  
Cue Utilization ◽  
Practice Experience ◽  
Negative Arousal ◽  
Range Anxiety ◽  
Research Findings ◽  
Post Hoc ◽  
The Relationship

Objective: This research examined whether negative and positive arousal emotions modify the relationship between experience level and cue utilization among anesthetists. Background: The capacity of a practitioner to form precise associations between clusters of features (e.g., symptoms) and events (e.g., diagnosis) and then act on them is known as cue utilization. A common assumption is that practice experience allows opportunities for cue acquisition and cue utilization. However, this relationship is often not borne out in research findings. This study investigates the role of emotional state in this relationship. Method: An online tool (EXPERTise 2.0) was used to assess practitioner cue utilization for tasks relevant to anesthesia. The experience of positive and negative arousal emotions in the previous three days was measured, and emotion clusters were generated. Experience was measured as the composite of practice years and hours of practice experience. The moderating role of emotion on the relationship between experience and cue utilization was examined. Results: Data on 125 anesthetists (36% female) were included in the analysis. The predicted interaction between arousal emotions and the experience level emerged. In particular, post hoc analyses revealed that anxiety-related emotions facilitated the likelihood of high cue utilization in less experienced practitioners. Conclusion: The findings suggest a role for emotions in cue use and suggest a functional role for normal range anxiety emotions in a simulated work-relevant task. Application: This research illustrates the importance of understanding the potentially functional effects common negative arousal emotions may have on clinical performance, particularly for those with less experience.

DIAGNOSTIC ROLE OF CHEST CT USING CO-RADS CATEGORIZATION IN SARS-COV-2 INFECTION WITH EMPHASIS ON IMPACT OF CT IN PATIENTS WITH DELAYED OR NEGATIVE INITIAL RTPCR TEST

2021 ◽  
pp. 51-52
Author(s):  
Tharani Putta ◽  
Kaushik Deconda
Keyword(s):  
Diagnostic Performance ◽  
Virus Disease ◽  
Vital Role ◽  
Chest Ct ◽  
Lung Involvement ◽  
Test Results ◽  
Rt Pcr ◽  
Diagnostic Role ◽  
Pcr Test

BACKGROUND AND OBJECTIVE: Role of chest CT in diagnosis of corona virus disease 2019 (COVID-19) has been controversial. The purpose of this study is to evaluate the diagnostic performance of chest CT when utilizing COVID-19 Reporting and Data System (CO-RADS). METHODOLOGY: Retrospective study including consecutive patients with positive SARS-CoV-2 RT-PCR test (initial or repeat test) and chest CT done in our institute between June and September 2020. Spectrum of CT ndings, CO-RADS score and 25 point CT severity score (CTSS) were recorded. RESULTS: A total of 300 consecutive patients with SARS-CoV-2 infection were included in the analysis. Out of the 168 patients who underwent CT prior to positive RT-PCR result, 125 (74.4%) had CO-RADS 3, 4 or 5 score on chest CT. 32 study patients (10.6%) had initial negative RT-PCR of which 24 (75%) had CO-RADS 4 or 5 score. Of the total patients with CO-RADS 3 to 5 score (227), 20 (8.8%) had severe lung involvement (CTSS 18-25), 83 (36.6%) had moderate lung involvement (CTSS 8-17) and 124 (54.6%) had mild lung involvement (CTSS 1-7). The mean CTSS was 7.9 with mean lobar score being higher in lower lobes (RLL=1.82, LLL=1.78) compared to the upper and middle lobes (RUL=1.61, RML=1.19, LUL=1.53). CONCLUSION:CT using CO-RADS scoring system has good diagnostic performance. In addition to assessing disease severity, it plays a vital role in triage of patients with suspected COVID-19 especially when there is limited availability of SARS-CoV-2 RT-PCR tests, delay in RT-PCR test results or in negative RT-PCR cases when there is high index of clinical suspicion.

The Role of Clinical “Experience” in Diagnostic Performance

1998 ◽  
Vol 18 (2) ◽  
pp. 163-167 ◽  
Author(s):  
Angelo Fasoli ◽  
Silvia Lucchelli ◽  
Renato Fasoli
Keyword(s):  
Pulmonary Embolism ◽  
Multiple Regression ◽  
Clinical Experience ◽  
Diagnostic Performance ◽  
Roc Curves ◽  
Clinical Findings ◽  
X Ray ◽  
Biochemical Studies ◽  
Recorded Data

Twenty-one physicians examined records of 43 patients who had attended the hospital because of chest pain. Of these patients, 20 had had coronary heart disease (CHD), 15 had had nonspecific pain, and eight had had pulmonary embolism. The physicians indicated the probability of CHD in each case on the basis of 18 clinical findings, not including ECG, x-ray, or biochemical studies. The trial was repeated five years later, using the same records, by 16 of the same physicians. Diagnostic accuracy was evaluated by ROC curves, and the weight ascribed to each cue was inferred by multiple regression with estimated probability of CHD as the dependent variable. No significant change of areas under the ROC curves with increasing length of clinical experience was observed. Multiple regression was significant in 30 of 37 analyses. The distributions of most physicians' estimates of probabilities had similar shapes five years apart. It is concluded that “experience” does not have a clear role in diagnostic performance based on recorded data and that personal calibration and preferences in estimating probabilities often persist for years.

Antibodies to phosphatidylserine/prothrombin (aPS/PT) enhanced the diagnostic performance in Chinese patients with antiphospholipid syndrome

2018 ◽  
Vol 56 (6) ◽  
pp. 939-946 ◽  
Author(s):  
Shulan Zhang ◽  
Ziyan Wu ◽  
Wen Zhang ◽  
Jiuliang Zhao ◽  
Gary L. Norman ◽  
...  
Keyword(s):  
Retrospective Study ◽  
Antiphospholipid Syndrome ◽  
Antiphospholipid Antibodies ◽  
Arterial Thrombosis ◽  
Diagnostic Performance ◽  
Positive Likelihood Ratio ◽  
Chinese Patients ◽  
Healthy Controls ◽  
Patients At Risk

AbstractBackground:Increasing evidence has highlighted the role of non-criteria antiphospholipid antibodies (aPLs) as important supplements to the current criteria aPLs for the diagnosis of antiphospholipid syndrome (APS). In this retrospective study, we evaluated the clinical relevance of antibodies to phosphatidylserine/prothrombin (aPS/PT) in Chinese patients with APS.Methods:A total of 441 subjects were tested, including 101 patients with primary APS (PAPS), 140 patients with secondary APS (SAPS), 161 disease controls (DCs) and 39 healthy controls (HCs). Serum IgG/IgM aPS/PT was determined by ELISA.Results:The levels of IgG/IgM aPS/PT were significantly increased in patients with APS compared with DCs and HCs. IgG and IgM aPS/PT were present in 29.7% and 54.5% of PAPS, and 42.1% and 53.6% of SAPS, respectively. For diagnosis of APS, IgG aCL exhibited the highest positive likelihood ratio (LR+) of 21.60, followed by LA (13.84), IgG aβ2GP1 (9.19) and IgG aPS/PT (8.49). aPS/PT was detected in 13.3% of seronegative PAPS patients and 31.3% of seronegative SAPS patients. LA exhibited the highest OR of 3.64 in identifying patients with thrombosis, followed by IgG aCL (OR, 2.63), IgG aPS/PT (OR, 2.55) and IgG aβ2GP1 (OR, 2.33). LA and IgG aCL were correlated with both arterial and venous thrombosis, whereas IgG aPS/PT and IgG aβ2GP1 correlated with venous or arterial thrombosis, respectively.Conclusions:Our findings suggest that the inclusion of IgG/IgM aPS/PT may enhance the diagnostic performance for APS, especially in those in whom APS is highly suspected, but conventional aPLs are repeatedly negative. In addition, IgG aPS/PT may contribute to identify patients at risk of thrombosis.

The role of precision in determining the performance of a thyrotropin assay in diagnosing hyperthyroidism.

1988 ◽  
Vol 34 (7) ◽  
pp. 1464-1467 ◽  
Author(s):  
T J Wilke ◽  
D J Utley
Keyword(s):  
Lower Limit ◽  
Diagnostic Performance ◽  
Reference Interval ◽  
Major Determinant ◽  
Analytical Sensitivity ◽  
Diagnostic Efficiency ◽  
Immunometric Assay ◽  
Coefficients Of Variations ◽  
The Relationship

Abstract We examined the relationship between analytical sensitivity, precision at the lower limit of the reference interval, and diagnostic performance in hyperthyroidism for one radioimmunoassay and five immunometric assay kits for thyrotropin. The analytical sensitivity of these kits extended from 0.05 to 1.56 milli-int. units/L. Diagnostic efficiencies of the immunometric assays, in discriminating between euthyroidism and hyperthyroidism, ranged between 93% and 98%. There was a highly significant correlation (r = 0.99, P less than 0.001) between analytical sensitivity and diagnostic efficiency. The between-assay coefficients of variations, at the lower limit of the reference interval, ranged from 26% to 87%. There was no correlation (r = 0.36) between precision, at this concentration, and diagnostic efficiency. We conclude that analytical sensitivity and not precision is the major determinant in controlling the diagnostic performance of a thyrotropin assay in hyperthyroidism.

scholarly journals Prediction of Locations in Medical Images Using Orthogonal Neural Networks

2021 ◽  
Author(s):  
Jong Soo Kim ◽  
Yongil Cho ◽  
Tae Ho Lim
Keyword(s):  
Neural Network ◽  
Diagnostic Performance ◽  
Medical Images ◽  
Selection Criterion ◽  
Activation Function ◽  
X Rays ◽  
Ann Model ◽  
Ann Models ◽  
Artificial Neural Network Ann ◽  
Image Localization

Abstract An orthogonal neural network (ONN), a new deep-learning structure for medical image localization, is developed and presented in this paper. This method is simple, efficient, and completely different from a convolution neural network (CNN). The diagnostic performance of ONN for detecting the location of pneumothorax in chest X-rays was assessed and compared to that of CNN. An area under the receiver operating characteristic (ROC) curve (AUC) of 0.870, an accuracy of 85.3%, a sensitivity of 75.0%, and a specificity of 86.5% were achieved; the ONN outperformed the CNN. The diagnostic performance of the ONN with a sigmoid activation function for all the nodes obviously outperformed the ONN with the rectified linear unit (RELU) activation function for all the nodes other than the output nodes. In addition, by applying ONN and CNN to predict the location of the glottis in laryngeal images, we achieved accurate and adjacent prediction rates of 70.5% and 20.5%, respectively, with the ONN. The prediction accuracy of the ONN was compared favorably with that of the CNN. Compared to a CNN, an ONN required only approximately 10% of the computations using a CNN trained on images with an input resolution of 256 × 256 pixels. A fully-connected small artificial neural network (ANN), selected by comparing the test results of several dozens of small ANN models, achieved the best location prediction performance on medical images. This study demonstrated that an ONN can be used as a quick selection criterion to compare ANN models for image localization since an ONN performed well compared decently with the selected ANN model.

scholarly journals Big Data System for Medical Images Analysis

2020 ◽  
Author(s):  
Janusz Bobulski ◽  
Mariusz Kubanek
Keyword(s):  
Big Data ◽  
Medical Images ◽  
Processing System ◽  
Large Data ◽  
Data Systems ◽  
Computer Data ◽  
Fast Processing ◽  
Big Data Systems

Big Data in medicine contains conceivably fast processing of large data volumes, alike new and old in perseverance associate the diagnosis and treatment of patients’ diseases. Backing systems for that kind activities may include pre-programmed rules based on data obtained from the medical interview, and automatic analysis of test diagnostic results will lead to classification of observations to a specific disease entity. The current revolution using Big Data significantly expands the role of computer science in achieving these goals, which is why we propose a computer data processing system using artificial intelligence to analyse and process medical images. We conducted research that confirms the need to use GPUs in Big Data systems that process medical images. The use of this type of processor increases system performance.

Diagnostic performance and role of the contrast enema for low intestinal obstruction in neonates

2020 ◽  
Vol 36 (9) ◽  
pp. 1093-1101
Author(s):  
Michael Baad ◽  
Jorge Delgado ◽  
Jillian S. Dayneka ◽  
Sudha A. Anupindi ◽  
Janet R. Reid
Keyword(s):  
Intestinal Obstruction ◽  
Diagnostic Performance ◽  
Contrast Enema
Sign in / Sign up

Export Citation Format

Share Document