Laboratory specimen rejection rate and associated factors among referred specimens at Debre Markos Referral Hospital, Ethiopia: prospective cross-sectional study.

Introduction: laboratory errors mostly emerge from the pre-analytical phase, mainly those related to collection, handling, transportation, and storage of diagnostic specimens. Specimen rejection due to improper sample collection, may lead to poor patient outcomes, such as incorrect diagnosis, inappropriate treatment, and death. This study aimed to assess the specimen rejection rate and associated factors among referred specimens at Debre Markos Referral Hospital. Methods: a prospective cross-sectional study design was applied from January 2020 to April 2020 to investigate specimen rejection rate and associated factors among referred specimens. The study population was all laboratory specimens referred for viral load, CD4 count, gene expert, and early infant diagnosis to the Debre Markos Referral Hospital laboratory. The statistical analysis was done with Statistical Package for Social Sciences version 20.0 software. Results: of the total of 2750 specimens submitted to the laboratory from January 2020 to April 2020, 37 (1.34%) specimens were rejected due to different reasons like insufficient volume, hemolysis, and an inappropriate specimen container. Specimen collector training status and experience had a significant association with the specimen rejection rate. Conclusion: the results of our study show that the specimen rejection rate among referred specimens was high, indicating that more interventions are required to decrease the specimen rejection rate.

Performance evaluation of ChatGPT in detecting diagnostic errors and their contributing factors: an analysis of 545 case reports of diagnostic errors.

BACKGROUND: Manual chart review using validated assessment tools is a standardised methodology for detecting diagnostic errors. However, this requires considerable human resources and time. ChatGPT, a recently developed artificial intelligence chatbot based on a large language model, can effectively classify text based on suitable prompts. Therefore, ChatGPT can assist manual chart reviews in detecting diagnostic errors. OBJECTIVE: This study aimed to clarify whether ChatGPT could correctly detect diagnostic errors and possible factors contributing to them based on case presentations. METHODS: We analysed 545 published case reports that included diagnostic errors. We imputed the texts of case presentations and the final diagnoses with some original prompts into ChatGPT (GPT-4) to generate responses, including the judgement of diagnostic errors and contributing factors of diagnostic errors. Factors contributing to diagnostic errors were coded according to the following three taxonomies: Diagnosis Error Evaluation and Research (DEER), Reliable Diagnosis Challenges (RDC) and Generic Diagnostic Pitfalls (GDP). The responses on the contributing factors from ChatGPT were compared with those from physicians. RESULTS: ChatGPT correctly detected diagnostic errors in 519/545 cases (95%) and coded statistically larger numbers of factors contributing to diagnostic errors per case than physicians: DEER (median 5 vs 1, p<0.001), RDC (median 4 vs 2, p<0.001) and GDP (median 4 vs 1, p<0.001). The most important contributing factors of diagnostic errors coded by ChatGPT were 'failure/delay in considering the diagnosis' (315, 57.8%) in DEER, 'atypical presentation' (365, 67.0%) in RDC, and 'atypical presentation' (264, 48.4%) in GDP. CONCLUSION: ChatGPT accurately detects diagnostic errors from case presentations. ChatGPT may be more sensitive than manual reviewing in detecting factors contributing to diagnostic errors, especially for 'atypical presentation'.

The discrepancy of antemortem clinical diagnosis and postmortem autopsy diagnosis of lung pathologies in under-five deaths and the reasons for discrepancies: a case series analysis.

BACKGROUND: Diagnostic autopsy is the most reliable approach to definitively ascertain the cause of death and evaluate the accuracy of antemortem clinical diagnoses. Identifying diagnostic discrepancies is vital to understanding common gaps in antemortem clinical diagnoses and modifying antemortem diagnostic approaches to increase the accuracy of clinical diagnosis. The objective of this study was to determine the frequency of diagnostic discrepancies between antemortem clinical diagnoses and postmortem autopsies on lung pathologies and to understand the reasons for diagnostic discrepancies among cases included in Child Health and Mortality Prevention Surveillance (CHAMPS) in Ethiopia. METHODS: A clinical case series study of deaths among children under-five in the CHAMPS study at three sites in Ethiopia between October 2019 and April 2022 was conducted. The antemortem clinical diagnoses and postmortem pathological diagnoses of the lung were compared for each case. Two senior physicians assessed the findings for both agreement and disagreement. McNemar's test was used to assess for statistically significant differences between antemortem and postmortem diagnoses. RESULTS: Seventy-five cases were included (73.3% male). Over half (54.7%) died between the 1st and 7th day of life. Sepsis (66.7%), pneumonia (6.7%), and meconium aspiration syndrome (5.0%) were the most common immediate causes of death. Half (52%) of cases were correctly diagnosed antemortem. The magnitude of diagnostic discrepancy was 35% (95% CI: 20-47%). The most common contributing factors to diagnostic discrepancy were gaps in knowledge (22/75, 35.5%) and problems in consultation and teamwork (22/75, 35.5%). CONCLUSIONS: Misdiagnoses were common among young children who died with positive lung pathology findings. In-service education initiatives and multidisciplinary collaboration are needed to mitigate high rates of diagnostic discrepancies among young children to potentially prevent future deaths.

Clinical distinctions in symptomatology and psychiatric comorbidities between misdiagnosed bipolar I and bipolar II disorder versus major depressive disorder.

BACKGROUND: To explore the demographic and clinical features of current depressive episode that discriminate patients diagnosed with major depressive disorder (MDD) from those with bipolar I (BP-I) and bipolar II (BP-II) disorder who were misdiagnosed as having MDD . METHODS: The Mini-International Neuropsychiatric Interview (MINI) assessment was performed to establish DSM-IV diagnoses of MDD, and BP-I and BP-II, previously being misdiagnosed as MDD. Demographics, depressive symptoms and psychiatric comorbidities were compared between 1463 patients with BP-I, BP-II and MDD from 8 psychiatric settings in mainland China. A multinomial logistic regression model was performed to assess clinical correlates of diagnoses. RESULTS: A total of 14.5% of the enrolled patients initially diagnosed with MDD were eventually diagnosed with BP. Broad illness characteristics including younger age, higher prevalence of recurrence, concurrent dysthymia, suicidal attempts, agitation, psychotic features and psychiatric comorbidities, as well as lower prevalence of insomnia, weight loss and somatic symptoms were featured by patients with BP-I and/or BP-I, compared to those with MDD. Comparisons between BP-I and BP-II versus MDD indicated distinct symptom profiles and comorbidity patterns with more differences being observed between BP-II and MDD, than between BP-I and MDD . CONCLUSION: The results provide evidence of clinically distinguishing characteristics between misdiagnosed BP-I and BP- II versus MDD. The findings have implications for guiding more accurate diagnoses of bipolar disorders.

Collective Intelligence Increases Diagnostic Accuracy in a General Practice Setting.

BACKGROUND: General practitioners (GPs) work in an ill-defined environment where diagnostic errors are prevalent. Previous research indicates that aggregating independent diagnoses can improve diagnostic accuracy in a range of settings. We examined whether aggregating independent diagnoses can also improve diagnostic accuracy for GP decision making. In addition, we investigated the potential benefit of such an approach in combination with a decision support system (DSS). METHODS: We simulated virtual groups using data sets from 2 previously published studies. In study 1, 260 GPs independently diagnosed 9 patient cases in a vignette-based study. In study 2, 30 GPs independently diagnosed 12 patient actors in a patient-facing study. In both data sets, GPs provided diagnoses in a control condition and/or DSS condition(s). Each GP's diagnosis, confidence rating, and years of experience were entered into a computer simulation. Virtual groups of varying sizes (range: 3-9) were created, and different collective intelligence rules (plurality, confidence, and seniority) were applied to determine each group's final diagnosis. Diagnostic accuracy was used as the performance measure. RESULTS: Aggregating independent diagnoses by weighing them equally (i.e., the plurality rule) substantially outperformed average individual accuracy, and this effect increased with increasing group size. Selecting diagnoses based on confidence only led to marginal improvements, while selecting based on seniority reduced accuracy. Combining the plurality rule with a DSS further boosted performance. DISCUSSION: Combining independent diagnoses may substantially improve a GP's diagnostic accuracy and subsequent patient outcomes. This approach did, however, not improve accuracy in all patient cases. Therefore, future work should focus on uncovering the conditions under which collective intelligence is most beneficial in general practice. HIGHLIGHTS: We examined whether aggregating independent diagnoses of GPs can improve diagnostic accuracy.Using data sets of 2 previously published studies, we composed virtual groups of GPs and combined their independent diagnoses using 3 collective intelligence rules (plurality, confidence, and seniority).Aggregating independent diagnoses by weighing them equally substantially outperformed average individual GP accuracy, and this effect increased with increasing group size.Combining independent diagnoses may substantially improve GP's diagnostic accuracy and subsequent patient outcomes.

Is Myocardial Infarction Overdiagnosed?

This Viewpoint examines whether overdiagnosis rather than underdiagnosis may now be the dominant form of myocardial infarction misdiagnosis.

Enhanced accuracy and reduced delay in diagnosing bone tumors within an expert sarcoma network: A nationwide study.

INTRODUCTION: Primary bone tumors encompass a range of rare and diverse lesions. Pathological diagnosis poses significant challenges, with histological discrepancies extensively studied in soft tissue sarcomas but lacking specific investigation in bone lesions. This study aimed to determine the rate of major diagnostic discrepancies in primary bone tumors, assessing whether initial histological analysis within an expert referral center network reduces this rate and final diagnostic delay. Additionally, we examined the impact of mandatory systematic re-reading by expert pathologists on diagnostic variation and readjustment. METHODS: Our study cohort comprised patients with primary bone tumors, drawn from the national prospective French sarcoma network database. A total of 1075 patients were included from 2018 to 2019. RESULTS: The cohort exhibited a major discrepancy rate of 24%. Within the expert referral centers network, 49 cases (7%) showed major diagnostic discrepancies in the initial analysis, compared to 207 cases (57%) outside the network (p < 0.001). Regarding the final diagnostic delay, a mean of 2.8 weeks (±4.9) was observed within the network, contrasting with 6.5 weeks (±9.1) outside the network (p < 0.001). Systematic re-reading by an expert pathologist facilitated diagnosis readjustment in 75% of the 256 cases, with 68% of all diagnostic variations occurring preoperatively. CONCLUSION: Early management within the expert network significantly reduced major diagnostic discrepancies and shortened the diagnosis delay by approximately a month. Expert pathologist systematic re-readings were responsible for diagnosis readjustments in three-quarters of cases, with two-thirds of all diagnostic variations occurring preoperatively, thereby mitigating the consequences of mistreatment.

Retrospective Analysis of US Litigations Involving Dermatologists From 2011 to 2022.

BACKGROUND: Physician malpractice lawsuits are climbing, and the reasons underlying litigation against dermatologists are unclear. OBJECTIVE: To determine the reasons patients pursue litigation against dermatologists or dermatology practices. MATERIALS AND METHODS: A retrospective analysis of all state and federal cases between 2011 and 2022 was performed after a query using "Dermatology" and "dermatologist" as search terms on 2 national legal data repositories. RESULTS: The authors identified a total of 48 (37 state and 11 federal) lawsuits in which a practicing dermatologist or dermatology group practice was the defendant. The most common reason for litigation was unexpected harm (26 cases, 54.2%), followed by diagnostic error (e.g. incorrect or delayed diagnoses) (16 cases, 33.3%). Six cases resulted from the dermatologist failing to communicate important information, such as medication side effects or obtaining informed consent. Male dermatologists were sued at a rate 3.1 times higher than female dermatologists. CONCLUSION: Although lawsuits from patients against dermatologists largely involve injury from elective procedures, clinicians should practice caution regarding missed diagnoses and ensure critical information is shared with patients to safeguard against easily avoidable litigation.

Histopathologic evaluation of gastric intestinal metaplasia in non-neoplastic biopsy specimens: Accuracy and interobserver reliability among general pathologists and pathology residents.

OBJECTIVES: This study aimed to evaluate the accuracy and interobserver reliability of diagnosing and subtyping gastric intestinal metaplasia (IM) among general pathologists and pathology residents at a university hospital in Thailand, focusing on the challenges in the histopathologic evaluation of gastric IM for less experienced practitioners. METHODS: The study analyzed 44 non-neoplastic gastric biopsies, using a consensus diagnosis of gastrointestinal pathologists as the reference standard. Participants included 6 general pathologists and 9 pathology residents who assessed gastric IM and categorized its subtype (complete, incomplete, or mixed) on digital slides. After initial evaluations and receiving feedback, participants reviewed specific images of gastric IM, as agreed by experts. Following a one-month washout period, a reevaluation of the slides was conducted. RESULTS: Diagnostic accuracy, interobserver reliability, and time taken for diagnosis improved following training, with general pathologists showing higher accuracies than residents (median accuracy of gastric IM detection: 100 % vs. 97.7 %). Increased years of experience were associated with more IM detection accuracy (p-value<0.05). However, the overall median accuracy for diagnosing incomplete IM remained lower than for complete IM (86.4 % vs. 97.7 %). After training, diagnostic errors occurred in 6 out of 44 specimens (13.6 %), reported by over 40 % of participants. Errors involved omitting 5 slides with incomplete IM and 1 with complete IM, all showing a subtle presence of IM. CONCLUSIONS: The study highlights the diagnostic challenges in identifying incomplete gastric IM, showing notable discrepancies in accuracy and interobserver agreement. It underscores the need for better diagnostic protocols and training to enhance detection and management outcomes.

Misdiagnosis in the Emergency Department: Time for a System Solution.

This Viewpoint offers 3 insights in response to the AHRQ report on diagnostic errors made in US emergency departments: focus on the delivery systems instead of individuals, establish ways to set definitions and assess error rates, and design safe delivery systems to prevent errors.

The Impact of Emerging Plasmodium knowlesi on Accurate Diagnosis by Light Microscopy: A Systematic Review and Modeling Analysis.

The five major Plasmodium spp. that cause human malaria appear similar under light microscopy, which raises the possibility that misdiagnosis could routinely occur in clinical settings. Assessing the extent of misdiagnosis is of particular importance for monitoring P. knowlesi, which cocirculates with the other Plasmodium spp. We performed a systematic review and meta-analysis of studies comparing the performance of microscopy and polymerase chain reaction (PCR) for diagnosing malaria in settings with co-circulation of the five Plasmodium spp. We assessed the extent to which co-circulation of Plasmodium parasites affects diagnostic outcomes. We fit a Bayesian hierarchical latent class model to estimate variation in microscopy sensitivity and specificity measured against PCR as the gold standard. Mean sensitivity of microscopy was low, yet highly variable across Plasmodium spp., ranging from 65.7% (95% confidence interval: 48.1-80.3%) for P. falciparum to 0.525% (95% confidence interval 0.0210-3.11%) for P. ovale. Observed PCR prevalence was positively correlated with estimated microscopic sensitivity and negatively correlated with estimated microscopic specificity, though the strength of the associations varied by species. Our analysis suggests that cocirculation of Plasmodium spp. undermines the accuracy of microscopy. Sensitivity was considerably lower for P. knowlesi, P. malariae, and P. ovale. The negative association between specificity and prevalence imply that less frequently encountered species may be misdiagnosed as more frequently encountered species. Together, these results suggest that the burden of P. knowlesi, P. malariae, and P. ovale may be underappreciated in a clinical setting.

Diagnostic error rates and associated factors for lower gastrointestinal perforation.

Lower gastrointestinal perforation is rare and challenging to diagnose in patients presenting with an acute abdomen. However, no study has examined the frequency and associated factors of diagnostic errors related to lower gastrointestinal perforation. This large-scale multicenter retrospective study investigated the frequency of diagnostic errors and identified the associated factors. Factors at the level of the patient, symptoms, situation, and physician were included in the analysis. Data were collected from nine institutions, between January 1, 2015 and December 31, 2019. Timely diagnosis was defined as diagnosis at the first visit in computed tomography (CT)-capable facilities or referral to an appropriate medical institution immediately following the first visit to a non-CT-capable facility. Cases not meeting this definition were defined as diagnostic errors that resulted in delayed diagnosis. Of the 439 cases of lower gastrointestinal perforation identified, delayed diagnosis occurred in 138 cases (31.4%). Multivariate logistic regression analysis revealed a significant association between examination by a non-generalist and delayed diagnosis. Other factors showing a tendency with delayed diagnosis included presence of fever, absence of abdominal tenderness, and unavailability of urgent radiology reports. Initial misdiagnoses were mainly gastroenteritis, constipation, and small bowel obstruction. In conclusion, diagnostic errors occurred in about one-third of patients with a lower gastrointestinal perforation.

Characteristics of Disease-Specific and Generic Diagnostic Pitfalls: A Qualitative Study.

Importance: Progress in understanding and preventing diagnostic errors has been modest. New approaches are needed to help clinicians anticipate and prevent such errors. Delineating recurring diagnostic pitfalls holds potential for conceptual and practical ways for improvement. Objectives: To develop the construct and collect examples of "diagnostic pitfalls," defined as clinical situations and scenarios vulnerable to errors that may lead to missed, delayed, or wrong diagnoses. Design, Setting, and Participants: This qualitative study used data from January 1, 2004, to December 31, 2016, from retrospective analysis of diagnosis-related patient safety incident reports, closed malpractice claims, and ambulatory morbidity and mortality conferences, as well as specialty focus groups. Data analyses were conducted between January 1, 2017, and December 31, 2019. Main Outcomes and Measures: From each data source, potential diagnostic error cases were identified, and the following information was extracted: erroneous and correct diagnoses, presenting signs and symptoms, and areas of breakdowns in the diagnostic process (using Diagnosis Error Evaluation and Research and Reliable Diagnosis Challenges taxonomies). From this compilation, examples were collected of disease-specific pitfalls; this list was used to conduct a qualitative analysis of emerging themes to derive a generic taxonomy of diagnostic pitfalls. Results: A total of 836 relevant cases were identified among 4325 patient safety incident reports, 403 closed malpractice claims, 24 ambulatory morbidity and mortality conferences, and 355 focus groups responses. From these, 661 disease-specific diagnostic pitfalls were identified. A qualitative review of these disease-specific pitfalls identified 21 generic diagnostic pitfalls categories, which included mistaking one disease for another disease (eg, aortic dissection is misdiagnosed as acute myocardial infarction), failure to appreciate test result limitations, and atypical disease presentations. Conclusions and Relevance: Recurring types of pitfalls were identified and collected from diagnostic error cases. Clinicians could benefit from knowledge of both disease-specific and generic cross-cutting pitfalls. Study findings can potentially inform educational and quality improvement efforts to anticipate and prevent future errors.

Inter-laboratory comparison of semiquantitative allergen-specific Immunoglobulin E test: 7 years of experience in Korea.

INTRODUCTION: Multiple allergen simultaneous test (MAST) is widely used as a screening tool for allergic diseases and has the advantage of providing specific IgE (sIgE) results for various allergens in semiquantitative class. We have continuously conducted external quality assessment (EQA) since 2012 for clinical laboratories performing MAST using AdvanSure allergy screen test (LG CHEM, Korea). This study provides an account of the EQA experience. METHODS: Samples were prepared using pooled sera collected from patients with suspected allergic disease and sent to each laboratory twice a year. Each round included 4-6 serum samples with sIgE for 10-20 inhaled or food allergens. The acceptable class value was the most frequently reported MAST class ±1 titer that exceeded 80% of the total laboratory results. RESULTS: The average number of participating laboratories was 76 (49-90) and the average response rate was 97.3% during the entire survey period. The acceptable rates were consistently high at 97.7% ± 3.7%. Of the total 537 trials, 18 trials (3.4%) were regarded as nonconsensus results, in which acceptable answers did not exceed 80%. For unacceptable results, the false-negative rate (1.5% ± 2.8%) was higher than the false-positive rate (0.8% ± 2.7%) (p < 0.001). MAST class results were correlated with quantitative IgE results by ImmunoCAP (Spearman's correlation coefficient of 0.682 (p < 0.001) and gamma index of 0.777 (p < 0.001). CONCLUSION: Although EQA for MAST showed a high level of acceptable answer, some allergen assays require harmonization. Continuous performance of systematic EQA is needed to improve the accuracy of sIgE assays and quality control in clinical laboratories.

Diagnostic comparison between cord blood and filter paper for the screening of congenital hypothyroidism.

BACKGROUND: Cord-blood and heel-prick TSH levels are essential in diagnosing and preventing the serious complications of congenital hypothyroidism, which mainly include intellectual disability. The study aimed to compare between cord-blood and heel-prick TSH sensitivity and specificity in detecting congenital hypothyroidism (CH) among newborn screened babies. METHOD: The study included 21,012 newborn screened babies for congenital hypothyroidism starting from September 2013 until March 2019. Both cord-blood and heel-prick TSH were collected from each newborn. Heel prick and cord-blood TSH cutoff values of >21 µU/ml and >30 mIU/L respectively were considered positive. RESULTS: Out of the total screened newborns, 12 were confirmed for having primary congenital hypothyroidism. Nine cases were positive for cord-blood TSH (Sensitivity 75%, specificity 99.9%, and a recall rate of 0.004%), while 139 cases were positive for heel-prick blood TSH (Sensitivity of 100%, specificity of 99.3%, and a recall rate of 0.60%). CONCLUSION: For the screening of CH, heel prick is considered a superior method, but cord blood remains a practical option due to its cost-effectiveness, immediate action, and lower recall rate. Therefore, whenever recall is difficult and/or early discharge is the practice, cord blood is an alternative method to heel prick but not with cases of prematurity.

Overnight radiology resident discrepancies at a large pediatric hospital: categorization by year of training, program, imaging modality, and report type.

BACKGROUND: Overnight radiology resident discrepancies have been described in multiple studies; however, study of resident discrepancies specific to pediatric radiology is limited. PURPOSE: To examine radiology resident discrepancies as they pertain to a large pediatric hospital system. MATERIAL AND METHODS: A total of 21,560 preliminary reports issued by 39 residents over a one-year period were scored as agreement, minor discrepancy, or major discrepancy by faculty members using a modification of the 2009 RADPEER scoring system. Residents were trainees of three different diagnostic radiology programs: large university-based, medium-sized community-based, or small community-based. Discrepancy rates were evaluated based on resident postgraduate year, program, and imaging modality. The effect of a general pediatric radiology report versus pediatric neuroradiology report of a CT scan was also tested. CT was the only modality in which there were comparable numbers of studies scored by both general pediatric radiologists and neuroradiologists. RESULTS: The rate of major resident to faculty assessment discrepancies was 1.01%, and the rate of minor resident to faculty assessment discrepancies was 4.47%. Major discrepancy rates by postgraduate years 3-5 were 1.08%, 0.75%, and 1.59%, respectively. Major discrepancy rates were highest for MR (11.22%), followed by CT (1.82%), radiographs (0.91%), and ultrasound (0.56%). There was no significant difference in discrepancy rate between residency programs and general pediatric radiology report of a CT versus pediatric neuroradiology report of a CT. CONCLUSION: Radiology discrepancy rates for residents issuing preliminary reports at a large children's hospital system are similar to those reported for adult procedures.

Not so FAST-Chest ultrasound underdiagnoses traumatic pneumothorax.

BACKGROUND: Ultrasonography for trauma is a widely used tool in the initial evaluation of trauma patients with complete ultrasonography of trauma (CUST) demonstrating equivalence to computed tomography (CT) for detecting clinically significant abdominal hemorrhage. Initial reports demonstrated high sensitivity of CUST for the bedside diagnosis of pneumothorax. We hypothesized that the sensitivity of CUST would be greater than initial supine chest radiograph (CXR) for detecting pneumothorax. METHODS: A retrospective analysis of patients diagnosed with pneumothorax from 2018 through 2020 at a Level I trauma center was performed. Patients included had routine supine CXR and CUST performed prior to intervention as well as confirmatory CT imaging. All CUST were performed during the initial evaluation in the trauma bay by a registered sonographer. All imaging was evaluated by an attending radiologist. Subgroup analysis was performed after excluding occult pneumothorax. Immediate tube thoracostomy was defined as tube placement with confirmatory CXR within 8 hours of admission. RESULTS: There were 568 patients screened with a diagnosis of pneumothorax, identifying 362 patients with a confirmed pneumothorax in addition to CXR, CUST, and confirmatory CT imaging. The population was 83% male, had a mean age of 45 years, with 85% presenting due to blunt trauma. Sensitivity of CXR for detecting pneumothorax was 43%, while the sensitivity of CUST was 35%. After removal of occult pneumothorax (n = 171), CXR was 78% sensitive, while CUST was 65% sensitive (p < 0.01). In this subgroup, CUST had a false-negative rate of 36% (n = 62). Of those patients with a false-negative CUST, 50% (n = 31) underwent tube thoracostomy, with 85% requiring immediate placement. CONCLUSION: Complete ultrasonography of trauma performed on initial trauma evaluation had lower sensitivity than CXR for identification of pneumothorax including clinically significant pneumothorax requiring tube thoracostomy. Using CUST as the primary imaging modality in the initial evaluation of chest trauma should be considered with caution. LEVEL OF EVIDENCE: Diagnostic Test study, Level IV.

Single Shot Multibox Detector Automatic Polyp Detection Network Based on Gastrointestinal Endoscopic Images.

PURPOSE: In order to resolve the situation of high missed diagnosis rate and high misdiagnosis rate of the pathological analysis of the gastrointestinal endoscopic images by experts, we propose an automatic polyp detection algorithm based on Single Shot Multibox Detector (SSD). METHOD: In the paper, SSD is based on VGG-16, the fully connected layer is changed to a convolutional layer, and four convolutional layers with successively decreasing scales are added as a new network structure. In order to verify the practicability, it is not only compared with manual polyp detection but also with Mask R-CNN. RESULTS: Multiple experimental results show that the mean Average Precision (mAP) of the SSD network is 95.74%, which is 12.4% higher than the manual detection and 5.7% higher than the Mask R-CNN. When detecting a single frame of image, the detection speed of SSD is 8.41 times that of manual detection. CONCLUSION: Based on the traditional pattern recognition algorithm and the target detection algorithm using deep learning, we select a variety of algorithms to identify and classify polyps to achieve efficient detection results. Our research demonstrates that deep learning has a lot of room for development in the field of gastrointestinal image recognition.