Chest Image Interpretation Research Articles

The effect of a digital training tool to aid chest image interpretation: Hybridising eye tracking technology and a decision support tool

IntroductionEye tracking technology, checklists and search strategies have been demonstrated as useful aids in image interpretation. A training tool was developed, by the research team, which included these features. This study aimed to evaluate the effect of the training tool on participant image interpretation performance. MethodsThe study was carried out with reporting radiographers who had either commenced training in chest image interpretation (n = 12) or were trained in musculoskeletal image interpretation (n = 23) (total n = 35). Participants were allocated to a control or intervention group. Participants completed an initial assessment at recruitment and re-attended nine months later for a follow-up assessment. The intervention group were given unlimited access to a digital training tool.During assessments participants interpreted 20 chest images whilst using eye tracking technology (total of 1400 images were interpreted). A confidence level was obtained from participants on their diagnosis and a questionnaire, to obtain demographic data, was completed following the assessment. ResultsImprovements were seen in the confidence of intervention group participants (p < 0.05). False Positive (FP) scores decreased for both the control and intervention group (p < 0.05), this decrease was from 4.20 to 3.20 for the control group and from 5.87 to 3.27 for the intervention group. True Negative (TN) scores increased, from 5.13 to 6.73 for the intervention group (p < 0.05). Mean decision time decreased for both the control and intervention group. ConclusionThe tool led to positive effects on participant performance and could be a useful aid in chest image interpretation learning. Implications for practiceImprovements in performance were observed with a digital tool. The tool could improve image interpretation methods and training.

Advancing Clinical Practice and Education With a Digital Training Platform of Chest Image Interpretation

Various systems and devices have been tested for their effectiveness in the education of advanced practice healthcare and medical staff. A search strategy with checklists within image interpretation is a method employed to ensure that all aspects of the image have been checked for abnormal features. A digital training platform, including a search strategy and eye tracking technology, and its potential impact will be discussed. A digital training platform was developed consisting of a search strategy training tool and an educational multimedia tool using eye tracking technology. Intervention participants accessed the tools for a nine month study period; control participants had no access to the tools. Image interpretation using 20 chest radiographic images was investigated in combination with eye tracking technology assessment at the beginning and end of the study by both the intervention and control group. This is a work in progress and all results will be available April 2018, but preliminary results for one intervention cohort consisting of reporting radiographers training in chest image interpretation (n=5) identified more true positives (p=0.033) and less false positives (p=0.024) following the intervention. The devised training package can be used by all healthcare staff when interpreting chest images, with the potential to improve training and accuracy by adopting systematic interpretation of the entire image. Correct image diagnosis directly impacts how a patient is treated and could increase the efficacy of reporting to reduce treatment delay by decreasing reporting times. Vast differences remain in the education standards achieved by radiographers throughout Europe. Growth of advanced practice roles within the profession means standardised education and knowledge within chest image interpretation becomes an achievable imperative. Improved education methods and image interpretation standards could be obtained by all healthcare professions through use of digital training platforms of the type discussed.

Digital training platform for interpreting radiographic images of the chest

IntroductionTime delays and errors exist which lead to delays in patient care and misdiagnosis. Reporting clinicians follow guidance to form their own search strategy. However, little research has tested these training guides. With the use of eye tracking technology and expert input we developed a digital training platform to be used in chest image interpretation learning. MethodsTwo sections of a digital training platform were planned and developed; A) a search strategy training tool to assist reporters during their interpretation of images, and B) an educational tool to communicate the search strategies of expert viewers to trainees by using eye tracking technology. ResultsA digital training platform for use in chest image interpretation was created based on evidence within the literature, expert input and two search strategies previously used in clinical practice. Images and diagrams, aiding translation of the platform content, were incorporated where possible. The platform is structured to allow the chest image interpretation process to be clear, concise and methodical. ConclusionA search strategy was incorporated within the tool to investigate its use, with the possibility that it could be recommended as an evidence based approach for use by reporting clinicians. Eye tracking, a checklist and voice recordings have been combined to form a multi-dimensional learning tool, which has never been used in chest image interpretation learning before. The training platform for use in chest image interpretation learning has been designed, created and digitised. Future work will establish the efficacy of the developed approaches.

Interobserver Reliability of the Berlin ARDS Definition and Strategies to Improve the Reliability of ARDS Diagnosis

Failure to reliably diagnose ARDS may be a major driver of negative clinical trials and underrecognition and treatment in clinical practice. We sought to examine the interobserver reliability of the Berlin ARDS definition and examine strategies for improving the reliability of ARDS diagnosis. Two hundred five patients with hypoxic respiratory failure from four ICUs were reviewed independently by three clinicians, who evaluated whether patients had ARDS, the diagnostic confidence of the reviewers, whether patients met individual ARDS criteria, and the time when criteria were met. Interobserver reliability of an ARDS diagnosis was "moderate" (kappa= 0.50; 95%CI, 0.40-0.59). Sixty-seven percent of diagnostic disagreements between clinicians reviewing the same patient was explained by differences in how chest imaging studies were interpreted, with other ARDS criteria contributing less (identification of ARDS risk factor, 15%; cardiac edema/volume overload exclusion, 7%). Combining the independent reviews of three clinicians can increase reliability to "substantial" (kappa= 0.75; 95%CI, 0.68-0.80). When a clinician diagnosed ARDS with "high confidence," all other clinicians agreed with the diagnosis in 72%of reviews. There was close agreement between clinicians about the time when a patient metall ARDS criteria if ARDS developed within the first 48 hours of hospitalization (median difference, 5 hours). The reliability of the Berlin ARDS definition is moderate, driven primarily by differences in chest imaging interpretation. Combining independent reviews by multiple clinicians or improving methods to identify bilateral infiltrates on chest imaging are important strategies for improving the reliability of ARDS diagnosis.

Decreased Risk of Mortality in Patients With Septic Shock Complicated by Acute Respiratory Distress Syndrome Who Had Early Lactate Clearance in a Single Institution

SESSION TITLE: Sepsis I SESSION TYPE: Original Investigation Poster PRESENTED ON: Wednesday, October 26, 2016 at 01:30 PM - 02:30 PM PURPOSE: Recent research has revealed that early lactate clearance is associated with a reduction in inflammatory markers and improved clinical outcomes in septic shock. Acute respiratory distress syndrome (ARDS) is a well-established complication of septic shock, yet little is known about the relationship between ARDS and lactate clearance. The aim here was to evaluate whether improved lactate clearance is associated with improved outcomes in patients with septic shock complicated by ARDS. METHODS: A retrospective cohort of all patients diagnosed with septic shock in an ICU at a community hospital during a three-month period of time was compiled. Patients were excluded if they did not meet criteria for septic shock on manual review, or if they had heart disease that would preclude the diagnosis of ARDS such as severe valvular heart disease or heart failure with reduced ejection fraction measured by echocardiogram. ARDS was defined based on the Berlin Criteria using review of arterial blood gas, x-ray and/or CT chest imaging and radiologist interpretation. Lactate clearance was calculated as a repeat lactate level (4-24 hours after initial) divided by lactate level at the time of septic shock diagnosis. Additional variables were collected including demographics, source of infection, and possible confounders (medications, cirrhosis, and transfusion). A multivariate logistic regression analysis was employed where in-hospital mortality was the dependent variable, and lactate level as well as lactate clearance (along with other covariates of interest) were the independent variables, to identify whether any relationship was present. RESULTS: Of the 268 patients reviewed, 135 were excluded (47 did not meet criteria for septic shock, 88 had significant heart disease, and 15 had missing data). Of the included patients, 61% were female, 29% were non-white, mean age was 67 years. Ultimately, 117 septic shock patients were included in this analysis and 57 died in hospital. Mean lactate level was 4.24 mmol/L (SD 3.63), and lactate clearance of at least 10% from baseline was observed in 45/63 cases (71%). As expected, baseline lactate levels were a strong predictor of mortality - an increase of 1 mmol/L was associated with a 15% increased risk of death (HR 1.15, 95% CI 1.07-1.23, p<0.001). Additionally, in patients with septic shock complicated by ARDS, lactate clearance of at least 10% from baseline was associated with a reduced mortality risk of 97% (HR=0.03, 95% CI 0.002-0.44, p=0.01). CONCLUSIONS: Lactate clearance is associated with decreased mortality in patients with septic shock complicated by ARDS. CLINICAL IMPLICATIONS: Lactate clearance in addition to lactate levels should be futher examined to risk stratify patients with septic shock complicated by ARDS. DISCLOSURE: The following authors have nothing to disclose: Mohammad Elballat, Martin Aldana-Campos, Brian Garnet, Varun Shah, Atif Shah, Elie Donath, Samer Fahmy No Product/Research Disclosure Information

Advanced Chest Imaging Interpretation of Acute Pulmonary Disorders

Bedside and advanced practice nurses in acute and critical care often view chest radiologic images of their patients. Correlation of findings on chest radiologic images with results of physical and other diagnostic assessments can provide information for making appropriate clinical judgments. Radiologic images of the chest available for acutely ill patients now include frontal/lateral chest radiographs and computed tomography (CT) scans. The purpose of this article is for the reader to review basic skills for interpreting chest radiographs, gain skill in reviewing CT scans of the chest, and be able to apply more advanced interpretation skills for both chest radiographs and chest CT scans. Several chest images are included for review.

Advanced chest imaging interpretation of acute pulmonary disorders.

Bedside and advanced practice nurses in acute and critical care often view chest radiologic images of their patients. Correlation of findings on chest radiologic images with results of physical and other diagnostic assessments can provide information for making appropriate clinical judgments. Radiologic images of the chest available for acutely ill patients now include frontal/lateral chest radiographs and computed tomography (CT) scans. The purpose of this article is for the reader to review basic skills for interpreting chest radiographs, gain skill in reviewing CT scans of the chest, and be able to apply more advanced interpretation skills for both chest radiographs and chest CT scans. Several chest images are included for review.

The effect of a chest imaging lecture on emergency department doctors’ ability to interpret chest CT images

To assess the chest computed tomography (CT) imaging interpreting skills of emergency department (ED) doctors and to study the effect of a CT chest imaging interpretation lecture on these skills. Sixty doctors in two EDs were randomized, using computerized randomization, to either attend a chest CT interpretation lecture or not to attend this lecture. Within 2 weeks of the lecture, the participants completed a questionnaire on demographic variables, anatomical knowledge, and diagnostic interpretation of 10 chest CT studies. Outcome measures included anatomical knowledge score, diagnosis score, and the combined overall score, all expressed as a percentage of correctly answered questions (0-100). Data on 58 doctors were analyzed, of which 27 were randomized to attend the lecture. The CT interpretation lecture did not have an effect on anatomy knowledge scores (72.9 vs. 70.2%), diagnosis scores (71.2 vs. 69.2%), or overall scores (71.4 vs. 69.5%). Twenty-nine percent of doctors stated that they had a systematic approach to chest CT interpretation. Overall self-perceived competency for interpreting CT imaging (brain, chest, abdomen) was low (between 3.2 and 5.2 on a 10-point Visual Analogue Scale). A single chest CT interpretation lecture did not improve chest CT interpretation by ED doctors. Less than one-third of doctors had a systematic approach to chest CT interpretation. A standardized systematic approach may improve interpretation skills.

Detection of Small Pulmonary Nodules Using Direct Digital Radiography and Picture Archiving and Communication Systems

To evaluate the detection of small pulmonary nodules, in the diameter range of 5.4 to 15 mm, using direct digital chest imaging and soft copy interpretation on picture archiving and communication systems. The results of clinical computed tomography (CT) scans of the thorax were retrospectively reviewed from our radiology information system and picture archiving and communication systems archives. Patients with CT studies containing between 1 and 6 nodules, who also had a digital chest examination within 1 month of the CT scan were selected. Thirty patients with suitable nodules and 30 without nodules were included and form the data base for this study. The nodules were between 5.4 and 15 mm in average diameter. Four separate observers independently viewed the frontal and lateral chest studies of the 60 patients. The presence or absence of nodules was determined. Data were analyzed with Kappa, McNemar and Fischer exact tests for agreement and differences between observers, nodule size, and nodule zone. A total of 42 nodules between 5.4 and 15 mm were present. The overall detection rate for the 4 observers was 41.7%. For nodules between 5.4 and 8 mm the detection rate was 26.2%. Agreement between observer's detection was poor to moderate. Differences between observers for both nodule size and zone were not significant. Only 1 observer had a relationship between nodule detection and nodule size. Observer detection of pulmonary nodules in the range of 5 to 15 mm using current digital radiography systems is not reliable in the confusing environment of the lung. Additional modification of these systems is required to increase nodule conspicuity.

How do radiologists do it? The influence of experience and training on searching for chest nodules

Four observer groups with different levels of expertise were tested to investigate the nature of expert performance. The task was the detection and localisation of significant pulmonary nodules in postero-anterior views of the chest. One hundred and twenty digitised chest images were used. The observer groups were 8 experienced radiologists, 5 experienced radiographers before and after six months training in chest image interpretation, and 8 undergraduate radiography students. Eye tracking was carried out to investigate differences in visual search strategies between observers. Detection performance was measured with an Alternate Free Response Operating Characteristic technique. Performance measures showed the experienced group of radiologists plus radiographers after training were better at the task than the remainder ( t-test p = 0.046). Differences were shown in the eye-tracking parameters between the groups: saccadic amplitude (ANOVA p = 0.00047), number of fixations before and after training ( t-test p = 0.041), and scrutiny time per decision and per film for the experienced versus the inexperienced observers ( t-test p = 0.02). Visual coverage reduced with increasing level of experience but this result did not reach significance. Generally there were distinct differences in the search strategies between the experienced and inexperienced observers and we discuss the significance of these findings. We believe the results support some recent theoretical models of expert performance and that the findings may prove to be helpful in ‘fast-track’ educational programmes of image interpretation for non-radiology practitioners.

Receiver operating characteristic analysis of chest image interpretation with conventional, laser-printed, and high-resolution workstation images.

The differences among radiologists in interpreting conventional and digitized images obtained with different radiologic procedures is an important research issue in these times of implementation and growth of the digital modalities. The authors performed a multiobserver study to determine the performance of radiologists reading posteroanterior conventional radiographs, digitized radiographs laser printed onto film, and images displayed on a high-resolution workstation (video monitor). A total of 300 images were evaluated by seven radiologists who recorded their ordinal confidence rating of the presence or absence of one or more of the following abnormalities: interstitial disease, nodule, and pneumothorax. Receiver operating characteristic analysis showed statistically significant differences for the detection of different abnormalities by individual readers. The group as a whole showed a significant reduction in observer performance for the detection of interstitial disease and pneumothorax when the laser-printed radiographs or the workstation was used rather than conventional radiographs.