Clinical Validation of a Deep Learning-Based Hybrid (Greulich-Pyle and Modified Tanner-Whitehouse) Method for Bone Age Assessment

ObjectiveTo evaluate the accuracy and clinical efficacy of a hybrid Greulich-Pyle (GP) and modified Tanner-Whitehouse (TW) artificial intelligence (AI) model for bone age assessment.Materials and MethodsA deep learning-based model was trained on an open dataset of multiple ethnicities. A total of 102 hand radiographs (51 male and 51 female; mean age ± standard deviation = 10.95 ± 2.37 years) from a single institution were selected for external validation. Three human experts performed bone age assessments based on the GP atlas to develop a reference standard. Two study radiologists performed bone age assessments with and without AI model assistance in two separate sessions, for which the reading time was recorded. The performance of the AI software was assessed by comparing the mean absolute difference between the AI-calculated bone age and the reference standard. The reading time was compared between reading with and without AI using a paired t test. Furthermore, the reliability between the two study radiologists'' bone age assessments was assessed using intraclass correlation coefficients (ICCs), and the results were compared between reading with and without AI.ResultsThe bone ages assessed by the experts and the AI model were not significantly different (11.39 ± 2.74 years and 11.35 ± 2.76 years, respectively, p = 0.31). The mean absolute difference was 0.39 years (95% confidence interval, 0.33–0.45 years) between the automated AI assessment and the reference standard. The mean reading time of the two study radiologists was reduced from 54.29 to 35.37 seconds with AI model assistance (p < 0.001). The ICC of the two study radiologists slightly increased with AI model assistance (from 0.945 to 0.990).ConclusionThe proposed AI model was accurate for assessing bone age. Furthermore, this model appeared to enhance the clinical efficacy by reducing the reading time and improving the inter-observer reliability.     

Antiviral and anticancer activities of 13(E)‐labd‐13‐ene‐8α,15‐diol isolated from Brachyglottis monroi

The antiviral activity of 13(E)‐labd‐13‐ene‐8α,15‐diol (1), isolated from Brachyglottis monroi, was examined against human rhinovirus 2 (HRV2) and 3 (HRV3), and the anticancer activity on human cancer cells (A549 and Hep2). Compound (1) showed strong anti‐HRV2 and HRV3 activity with a 50% inhibitory concentration (IC₅₀) of 2.68 and 0.87 µg/mL, respectively, and a 50% cytotoxicity concentration (CC₅₀) of 59.45 µg/mL. Ribavirin only showed anti‐HRV3 activity with an IC₅₀ of 30.48 µg/mL and a CC₅₀ > 100 µg/mL. The addition of compound (1) to HRV‐infected HeLa cells directly reduced the formation of visible cytopathic effect (CPE) and it directly interacted with HRV particles. Furthermore, A549 and Hep2 cells incubated with 32 µg/mL of compound (1) for 48 h exhibited antilung and antilaryngeal cancer activities, with a viability of less than 50%. These results suggest that compound (1) may be used as a potential antiviral and anticancer agent. Copyright © 2009 John Wiley & Sons, Ltd.     

Delayed Influenza Treatment in Children With False-Negative Rapid Antigen Test: A Retrospective Single-Center Study in Korea 2016–2019

BackgroundWe aimed to examine the delay in antiviral initiation in rapid antigen test (RAT) false-negative children with influenza virus infection and to explore the clinical outcomes. We additionally conducted a medical cost-benefit analysis.MethodsThis single-center, retrospective study included children (aged < 10 years) with influenza-like illness (ILI), hospitalized after presenting to the emergency department during three influenza seasons (2016–2019). RAT-false-negativity was defined as RAT-negative and polymerase chain reaction-positive cases. The turnaround time to antiviral treatment (TAT) was from the time when RAT was prescribed to the time when the antiviral was administered. The medical cost analysis by scenarios was also performed.ResultsA total of 1,430 patients were included, 7.5% were RAT-positive (n = 107) and 2.4% were RAT-false-negative (n = 20). The median TAT of RAT-false-negative patients was 52.8 hours, significantly longer than that of 4 hours in RAT-positive patients (19.2–100.1, P < 0.001). In the multivariable analysis, TAT of ≥ 24 hours was associated with a risk of severe influenza infection and the need for mechanical ventilation (odds ratio [OR], 6.8, P = 0.009 and OR, 16.2, P = 0.033, respectively). The medical cost varied from $11.7–187.3/ILI patient.ConclusionAntiviral initiation was delayed in RAT-false-negative patients. Our findings support the guideline that children with influenza, suspected of having severe or progressive infection, should be treated immediately.     

Neuroimaging Findings in Patients with COVID-19: A Systematic Review and Meta-Analysis

ObjectiveCentral nervous system involvement in coronavirus disease 2019 (COVID-19) has been increasingly reported. We performed a systematic review and meta-analysis to evaluate the incidence of radiologically demonstrated neurologic complications and detailed neuroimaging findings associated with COVID-19.Materials and MethodsA systematic literature search of MEDLINE/PubMed and EMBASE databases was performed up to September 17, 2020, and studies evaluating neuroimaging findings of COVID-19 using brain CT or MRI were included. Several cohort-based outcomes, including the proportion of patients with abnormal neuroimaging findings related to COVID-19 were evaluated. The proportion of patients showing specific neuroimaging findings was also assessed. Subgroup analyses were also conducted focusing on critically ill COVID-19 patients and results from studies that used MRI as the only imaging modality.ResultsA total of 1394 COVID-19 patients who underwent neuroimaging from 17 studies were included; among them, 3.4% of the patients demonstrated COVID-19-related neuroimaging findings. Olfactory bulb abnormalities were the most commonly observed (23.1%). The predominant cerebral neuroimaging finding was white matter abnormality (17.6%), followed by acute/subacute ischemic infarction (16.0%), and encephalopathy (13.0%). Significantly more critically ill patients had COVID-19-related neuroimaging findings than other patients (9.1% vs. 1.6%; p = 0.029). The type of imaging modality used did not significantly affect the proportion of COVID-19-related neuroimaging findings.ConclusionAbnormal neuroimaging findings were occasionally observed in COVID-19 patients. Olfactory bulb abnormalities were the most commonly observed finding. Critically ill patients showed abnormal neuroimaging findings more frequently than the other patient groups. White matter abnormalities, ischemic infarctions, and encephalopathies were the common cerebral neuroimaging findings.     

Survival and Prognostic Factors for Breast Cancer Patients with Regional Oligo-Recurrence

PurposeThis study aimed to evaluate survival outcomes and identify prognostic factors for regional oligo-recurrence in breast cancer patients who received salvage local treatment.MethodsIn the breast cancer registry of our institution, 18,790 patients received curative surgery for stage I–III breast cancer between January 1995 and June 2016. Of those patients, only 87 (0.5%)underwent salvage local treatment for isolated nodal recurrence on the axillary lymph nodes (ALNs) (n = 58), supraclavicular lymph nodes (SCNs) (n = 17), or internal mammary lymph nodes (IMNs) (n = 12).ResultsThe median follow-up duration after regional oligo-recurrence was 49 months (range: 6–194 months). For patients with recurrence of ALN, SCN, or IMN, the 5-year progression-free survival (PFS) and overall survival (OS) rates were 40.0%, 32.1%, and 25.0%, respectively (p = 0.3) and 62.7%, 70.0%, and 58.3%, respectively(p = 0.97). In the multivariable analysis for PFS, age at recurrence ≥ 65 years, disease-free interval < 24 months, non-luminal A subtype, and in-field failure (marginally significant) were found to be risk factors (RFs). However, the location of the tumor was not a significant factor for PFS (p = 0.71). When we stratified patients by the number of RFs, the 5-year PFS rates were 67.5% for patients with ≤ 1 RF and 7.3% for those with > 1 RF (p < 0.01). For patients with ≤ 1 RF, the 5-year PFS rates were 73.5% in the ALN group and 51.1% in the SCN/IMN group (p = 0.09). For patients with > 1 RF, the 5-year PFS rates were 7.3% in the ALN group and 7.1% in the SCN/IMN group (p = 1.00).ConclusionIn breast cancer patients with regional oligo-recurrence, clinical outcomes after salvage treatment were favorable in patients with ≤ 1 RF, while patients with > 1 RF had poor prognoses irrespective of the location of recurrence.     

A Retrospective Clinical Evaluation of an Artificial Intelligence Screening Method for Early Detection of STEMI in the Emergency Department

BackgroundRapid revascularization is the key to better patient outcomes in ST-elevation myocardial infarction (STEMI). Direct activation of cardiac catheterization laboratory (CCL) using artificial intelligence (AI) interpretation of initial electrocardiography (ECG) might help reduce door-to-balloon (D2B) time. To prove that this approach is feasible and beneficial, we assessed the non-inferiority of such a process over conventional evaluation and estimated its clinical benefits, including a reduction in D2B time, medical cost, and 1-year mortality.MethodsThis is a single-center retrospective study of emergency department (ED) patients suspected of having STEMI from January 2021 to June 2021. Quantitative ECG (QCG™), a comprehensive cardiovascular evaluation system, was used for screening. The non-inferiority of the AI-driven CCL activation over joint clinical evaluation by emergency physicians and cardiologists was tested using a 5% non-inferiority margin.ResultsEighty patients (STEMI, 54 patients [67.5%]) were analyzed. The area under the curve of QCG score was 0.947. Binned at 50 (binary QCG), the sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV) were 98.1% (95% confidence interval [CI], 94.6%, 100.0%), 76.9% (95% CI, 60.7%, 93.1%), 89.8% (95% CI, 82.1%, 97.5%) and 95.2% (95% CI, 86.1%, 100.0%), respectively. The difference in sensitivity and specificity between binary QCG and the joint clinical decision was 3.7% (95% CI, −3.5%, 10.9%) and 19.2% (95% CI, −4.7%, 43.1%), respectively, confirming the non-inferiority. The estimated median reduction in D2B time, evaluation cost, and the relative risk of 1-year mortality were 11.0 minutes (interquartile range [IQR], 7.3–20.0 minutes), 26,902.2 KRW (22.78 USD) per STEMI patient, and 12.39% (IQR, 7.51–22.54%), respectively.ConclusionAI-assisted CCL activation using initial ECG is feasible. If such a policy is implemented, it would be reasonable to expect some reduction in D2B time, medical cost, and 1-year mortality.     

Induction of growth inhibition and apoptosis in human uterine leiomyoma cells by isoliquiritigenin

Isoliquiritigenin(ISL), a calchone flavonoid, has cancer-preventing properties and is often used in Chinese medicine. In the present study, the authors use ISL to determine its effect on cell proliferation and cell cycle progression in primary cultured human uterine leiomyoma cells. Cell viability and cell proliferation assays were conducted. Flow cytometry, annexin V apoptosis assay, and DNA fragmentation assay were performed to determine the effect of ISL on cell cycle and apoptosis. The expression of cell cycle regulatory-related proteins was evaluated by Western blot. The cell viability and proliferation of uterine leiomyoma cells were significantly reduced by ISL treatment in a dose-dependent manner. Flow cytometry results showed that ISL induced subG1 and G2/M arrest. DNA fragmentation assay and annexin V apoptosis assays revealed apoptosis induction. ISL-induced growth inhibition in uterine leiomyoma cells was associated with increased p21(Cip1/) Waf1 expression in a p53-dependent manner. Activation of caspase-3 and downregulation of Bcl-2, cdk 2/4, and E2F, with a concomitant increase in dephosphorylation of Rb and poly-ADP-ribose polymerase cleavage, were observed. This study demonstrates that ISL inhibits cell proliferation by initiating apoptosis in human uterine leiomyoma cells coupled with increased cell cycle arrest. These results indicate that ISL could prove to be a promising chemopreventive and therapeutic agent against human uterine leiomyoma.