Explore the vast range of titles available.

Background: Missed findings in chest X-ray interpretation are common and can have serious consequences. Methods: Our study included 2407 chest radiographs (CXRs) acquired at three Indian and five US sites. To identify CXRs reported as normal, we used a proprietary radiology report search engine based on natural language processing (mPower, Nuance). Two thoracic radiologists reviewed all CXRs and recorded the presence and clinical significance of abnormal findings on a 5-point scale (1—not important; 5—critical importance). All CXRs were processed with the AI model (Qure.ai) and outputs were recorded for the presence of findings. Data were analyzed to obtain area under the ROC curve (AUC). Results: Of 410 CXRs (410/2407, 18.9%) with unreported/missed findings, 312 (312/410, 76.1%) findings were clinically important: pulmonary nodules (n = 157), consolidation (60), linear opacities (37), mediastinal widening (21), hilar enlargement (17), pleural effusions (11), rib fractures (6) and pneumothoraces (3). AI detected 69 missed findings (69/131, 53%) with an AUC of up to 0.935. The AI model was generalizable across different sites, geographic locations, patient genders and age groups. Conclusion: A substantial number of important CXR findings are missed; the AI model can help to identify and reduce the frequency of important missed findings in a generalizable manner.

Purpose: We assessed whether a CXR AI algorithm was able to detect missed or mislabeled chest radiograph (CXR) findings in radiology reports. Methods: We queried a multi-institutional radiology reports search database of 13 million reports to identify all CXR reports with addendums from 1999–2021. Of the 3469 CXR reports with an addendum, a thoracic radiologist excluded reports where addenda were created for typographic errors, wrong report template, missing sections, or uninterpreted signoffs. The remaining reports contained addenda (279 patients) with errors related to side-discrepancies or missed findings such as pulmonary nodules, consolidation, pleural effusions, pneumothorax, and rib fractures. All CXRs were processed with an AI algorithm. Descriptive statistics were performed to determine the sensitivity, specificity, and accuracy of the AI in detecting missed or mislabeled findings. Results: The AI had high sensitivity (96%), specificity (100%), and accuracy (96%) for detecting all missed and mislabeled CXR findings. The corresponding finding-specific statistics for the AI were nodules (96%, 100%, 96%), pneumothorax (84%, 100%, 85%), pleural effusion (100%, 17%, 67%), consolidation (98%, 100%, 98%), and rib fractures (87%, 100%, 94%). Conclusions: The CXR AI could accurately detect mislabeled and missed findings. Clinical Relevance: The CXR AI can reduce the frequency of errors in detection and side-labeling of radiographic findings.

PurposeTo determine the rate of missed CT findings of ileal carcinoid tumor prior to pathologic diagnosis and the resultant diagnostic delay.MethodsInitially, 74 patients with abdominal and pelvic CT prior to pathologically-proven diagnosis of ileal carcinoid were identified. Patients were excluded when the original CT study (n = 6) or report (n = 4) was not available, resulting in a final cohort of 64 patients (mean age, 58.3 years; 29 M/35F); 27 (42%) patients had more than one abdominal CT prior to diagnosis. All available CT studies prior to diagnosis were retrospectively reviewed for the presence of the primary ileal tumor and metastatic disease (mesenteric and hepatic).ResultsPrimary ileal tumors were prospectively missed on at least one CT scan in 64% (32/50) of patients with retrospectively identifiable disease. CT findings of mesenteric spread were missed at least once in 46% (25/54) of cases where present in retrospect. By the final pre-operative CT, hepatic metastases and bowel wall thickening were present in 55% (35/64) and 52% (33/64) of cases, respectively. In patients with missed ileal and/or mesenteric findings resulting in diagnostic delay, mean delay was 40 months (range 4–98 months).ConclusionInitial presentation of ileal carcinoid tumor, even with mesenteric involvement, is often missed prospectively at abdominal CT, leading to delay in diagnosis until bowel or mesenteric findings become more obvious, or hepatic metastatic disease manifests. Radiologists should make a concerted effort to evaluate the bowel and mesentery in patients with long-standing vague abdominal symptoms.

This study aims (1) to evaluate the spectrum of musculoskeletal (MSK) findings detected on trauma-related torso CT exams performed in the emergency department and (2) to identify the findings of high clinical importance that are underreported. Following IRB approval, two fellowship-trained MSK radiologists independently reviewed 200 consecutive trauma CT torso examinations performed at a level 1 trauma center, focusing on MSK findings. Discrepancies were resolved by consensus. Findings were categorized as of high, moderate, or low clinical importance based on criteria established with an orthopedic trauma surgeon. Findings evident on only one series (scout, axial, or sagittal/coronal reformations) were documented. The consensus reading was compared to the final report. Unreported findings of high clinical importance were entered into our departmental QA system. Eighty-two percent (164/200) of the studies had at least one MSK finding. There were 433 total findings of varying importance and the overall detection rate was 61 % (266/433). The detection rate for high importance findings was 80 % (177/221) with the majority representing acute fractures (99 %). For findings of high clinical importance, the lowest detection rates were for fractures of the sternum, proximal humerus, and forearm. Of the high severity findings, 6.3 % (14/221) were detected only on sagittal or coronal reformatted or scout images. Twenty percent of musculoskeletal findings of high clinical importance on trauma-related CT torso exams were not reported. Fractures of the sternum, proximal humerus, and forearm were the most commonly missed fractures and review of scout and multiplanar reformations can increase detection.

Numerous guidelines exist for the management of pancreatic cysts. We sought to compare the guideline-directed management strategies for pancreatic cysts by comparing 2 approaches (2017 International Consensus Guidelines and 2015 American Gastroenterological Association Guidelines) that differ significantly in their thresholds for imaging, surveillance, and surgery. We developed a Monte Carlo model to evaluate the outcomes for a cohort of 10,000 patients managed per each guideline. The primary outcome was mortality related to pancreatic cyst management. Secondary outcomes included all-cause mortality, missed cancers, number of surgeries, number of imaging studies, cumulative cost, and quality-adjusted life years. Deaths because of pancreatic cyst management and quality-adjusted life years were similar in both guidelines at a significantly higher cost of $3.6 million per additional cancer detected in the Consensus Guidelines. Deaths from \"unrelated\" causes (1,422) vastly outnumbered deaths related to pancreatic cysts (125). Secondary outcomes included more missed cancers in the American Gastroenterological Association guideline (71 vs 49), more surgeries and imaging studies in the Consensus guideline (711 vs 163; 116,997 vs 68,912), and higher cost in the Consensus guideline ($168.3 million vs $89.4 million). As the rate of malignant transformation increases, a more-intensive guideline resulted in fewer deaths related to pancreatic cyst management. Our study demonstrates trade-offs between more- and less-intensive management strategies for pancreatic cysts. Although deaths related to pancreatic cyst management were similar in each strategy, fewer missed cancers in the more-intensive surveillance strategy is offset by a greater number of surgical deaths and higher cost. In conclusion, our study identifies that if the rate malignant transformation of pancreatic cysts is low (0.12% annually), a less-intensive guideline will result in similar deaths to a more-intensive guideline at a much lower cost.

Pedunculated uvular tumors, though rare, may cause airway symptoms when enlarged or elongated. This case highlights how diminished attention to basic oropharyngeal inspection in routine care can lead to missed diagnoses with potentially serious consequences. Reinforcing fundamental physical examination skills remains essential in emergency and general clinical practice. Endoscopic view of a pedunculated uvular tumor shifting toward the airway during insufflation.

Background The incidence of tuberculosis (TB) is high in Uganda; yet, TB case detection is low. The population-based survey on the prevalence of TB in Uganda revealed that only 16% of presumptive TB patients seeking care at health facilities were offered sputum microscopy or chest-X ray (CXR). This study aimed to determine the magnitude of, and patient factors associated with missed opportunities in TB investigation at public health facilities of Wakiso District in Uganda. Methods A facility-based cross-sectional survey was conducted at 10 high volume public health facilities offering comprehensive TB services in Wakiso, Uganda, among adults (≥18 years) with at least one symptom suggestive of TB predefined according to the World Health Organisation criteria. Using exit interviews, data on demographics, TB symptoms, and clinical data relevant to TB diagnosis were collected. A missed opportunity in TB investigation was defined as a patient with symptoms suggestive of TB who did not have sputum and/or CXR evaluation to rule out TB. Poisson regression analysis was performed to determine factors associated with missed opportunities in TB investigation. Results Two hundred forty-seven (247) patients with presumptive TB exiting at antiretroviral therapy (ART) clinics ( n  = 132) or general outpatient clinics ( n  = 115) at public health facilities were recruited into this study. Majority of participants were female (161/247, 65.2%) with a mean + SD age of 35.1 + 11.5 years. Overall, 138 (55.9%) patients with symptoms suggestive of TB disease did not have sputum and/or CXR examinations. Patients who did not inform health workers about their TB related symptoms were more likely to miss a TB investigation (adjusted prevalence ratio (aPR): 1.68, 95%CI; 1.36–2.08, P  < 0.001). However, patients who reported duration of cough of 2 weeks or more were less likely to be missed for TB screening (aPR; 0.69, 95%CI; 0.56–0.86, p  < 0.001). Conclusion There are substantial missed opportunities for TB diagnosis in Wakiso District. While it is important that patients should be empowered to report symptoms, health workers need to proactively implement the WHO TB symptom screen tool and complete the subsequent steps in the TB diagnostic cascade.

PurposeFalse-negative findings in radiological reports can lead to serious adverse patient outcomes. We determined the frequency and tendency of false-negative findings in radiological reports by searching for words related to “visible in retrospect”.MethodsIn the period of 34 months, we extracted radiological reports containing words related to “visible in retrospect”. Of these reports, we extracted false-negative findings that were not described in past reports and were first detected retrospectively. Misinterpretations were excluded. The occurrences of the terms that we identified were analyzed by all examinations, modality, month, and anatomical and lesion classifications were analyzed.ResultsOf the 135,251 examinations, 941 reports (0.71%) with 962 findings were detected, with an average of 1.4 findings per business day. By modality, 713 of 81,899 (0.87%) CT examinations, 208 of 36,174 (0.57%) MR, 34 of 9,585 (0.35%) FDG-PET-CT, 2 of 2,258 (0.09%) digital radiography, and 5 of 5,335 (0.09%) other nuclear medicine examinations were found. By anatomical classification, there were 383 (40%) in chest, 353 (37%) in abdomen, 162 (17%) in head, 42 (4.4%) in face and neck, 9 (0.93%) in extremity, and 13 (1.4%) in others. By lesion classification, we identified 665 (69%) for localized lesion, 170 (18%) for vascular lesion, 83 (8.6%) for inflammatory lesion, 14 (1.5%) for traumatic lesion, 12 (1.2%) for organ dysfunction, 11 (1.1%) for degenerative lesion, and 7 (0.7%) for the others. Notable high-frequency specific site diseases by modality were 210 (22%) of localized lesions in lung on CT.ConclusionOur results demonstrated that missed lung localized lesions on CT, which account for about a fifth of false-negative findings, were the most common false-negative finding.

Pheochromocytomas are known to be rare causes of sudden death. A 49-year-old man with a medical history of arterial hypertension and diabetes mellitus complained about nausea and malaise in the morning. During the day his condition deteriorated. He went to the emergency department, where he was given intravenous drugs against nausea and was sent home. On the way back, his condition deteriorated dramatically so that his wife drove back to the emergency room, where he collapsed and sustained cardiac arrest; resuscitation efforts were unsuccessful. Autopsy revealed a large tumour of the left adrenal gland. The strong suspicion of pheochromocytoma was confirmed by histology, immunohistochemistry and biochemical investigations. An acute hypertensive crisis, caused by the hitherto unknown pheochromocytoma was ascertained as the cause of death. The morphological findings are presented, the difficulty to diagnose pheochromocytoma and the medico-legal implications are discussed.