Risk factors of mortality in patients with rheumatoid arthritis-associated interstitial lung disease: a single-centre prospective cohort study.

OBJECTIVES: To determine the risk factors for mortality in Korean patients with rheumatoid arthritis (RA)-associated interstitial lung disease (ILD) in comparison to patients with RA but without ILD (RA-nonILD). METHODS: Data were extracted from a single-centre prospective cohort of RA patients with a chest computed tomography scan at an academic referral hospital in Korea. Patients with RA-ILD enroled between May 2017 and August 2022 were selected, and those without ILD were selected as comparators. The mortality rate was calculated, and the causes of each death were investigated. We used Cox proportional hazard regression with Firth's penalised likelihood method to identify the risk factors for mortality in patients with RA-ILD. RESULTS: A total of 615 RA patients were included: 200 with ILD and 415 without ILD. In the RA-ILD group, there were 15 deaths over 540.1 person-years (PYs), resulting in mortality rate of 2.78/100 PYs. No deaths were reported in the RA-nonILD group during the 1669.9 PYs. The primary causes of death were infection (nine cases) and lung cancer (five cases), with only one death attributed to ILD aggravation. High RA activity (adjusted HR 1.87, CI 1.16-3.10), baseline diffusing capacity for carbon monoxide (DLCO) < 60% (adjusted HR 4.88, 95% CI 1.11-45.94), and usual interstitial pneumonia (UIP) pattern (adjusted HR 5.13, 95% CI 1.00-57.36) were identified as risk factors for mortality in RA-ILD patients. CONCLUSION: Patients with RA-ILD have an elevated risk of mortality compared with those without ILD. Infection-related deaths are the main causes of mortality in this population. High RA activity, low DLCO, and the UIP pattern are significantly associated with the mortality in patients with RA-ILD.

Clinical significance of the advanced lung cancer inflammation index in patients with limited-stage small cell lung cancer treated with chemoradiotherapy.

The aim of the study was to investigate the prognostic significance of the advanced lung cancer inflammation index (ALI) in patients with limited-stage small-cell lung cancer (LS-SCLC) undergoing definite chemo-radiotherapy (CRT). We included 87 patients with LS-SCLC from South Korea, treated between 2005 and 2019 with definite CRT. ALI was calculated using body mass index, serum albumin, and neutrophil-lymphocyte ratio. We categorized 38 patients into the high ALI group (ALI ≥ 44.3) and 48 into the low ALI group (ALI < 44.3). Patients in the high ALI group exhibited longer overall survival (OS) than patients in the low ALI group. In multivariate analysis, prophylactic cranial irradiation (hazard ratio [HR] = 0.366, 95% confidence interval [CI] 0.20-0.66, P = 0.0008), and high ALI (HR = 0.475, 95% CI 0.27-0.84, P = 0.0103) were identified as independent prognostic factors for predicting better OS. Notably, a high ALI score was particularly indicative of longer survival in patients treated with the combination of etoposide and cisplatin. In conclusion, this study demonstrated that a high pretreatment ALI was significantly associated with better OS in patients with LS-SCLC undergoing definite CRT. This suggests that ALI could be a useful tool for predicting prognosis and guiding chemotherapy regimen selections in clinical practice for LS-SCLC.

Which is better? Early versus delayed rehabilitation after arthroscopic rotator cuff repair.

PURPOSE: This study aimed to compare the 5-year clinical and functional outcomes, including repaired tendon healing status, between early and delayed rehabilitation after arthroscopic rotator cuff repair METHODS: A total of 75 patients with rotator cuff tears (less than 5 cm) underwent arthroscopic repairs over a 60-month period. Participants were randomly assigned to early and delayed postoperative rehabilitation groups with distinct protocols. Clinical and functional outcome measures included Constant score, University of California at Los Angeles (UCLA) score, visual analogue scale for pain and isokinetic dynamometer test for muscle strength recovery. Clinical and functional scores were compared between baseline and 5 years postoperatively. Radiologic assessment via magnetic resonance imaging was performed at a minimum of 12 months postoperatively for evaluations of tendon integrity and recurrent tears. RESULTS: Baseline characteristics showed no statistically significant differences between groups. Both groups demonstrated equivalent improvement in range of motion and pain scores with no statistical differences. Clinical scores improved significantly in both groups by postoperative 12 months and plateaued. At the postoperative 5-year mark, the early group showed better improvement in the visual analogue scale and UCLA score, while the delayed group had superior Constant scores. Postoperative magnetic resonance imaging revealed six recurrent tears, two in the early group and four in the delayed group, with no statistical differences. Muscle strength recovery showed no differences between the two groups. CONCLUSION: Both the early and the delayed rehabilitation groups showed similar outcomes in postoperative range of motion, functional scores, muscle strength recovery and tendon healing in the short- and mid-term follow-ups. LEVEL OF EVIDENCE: Level III.

Prospective evaluation of deep learning image reconstruction for Lung-RADS and automatic nodule volumetry on ultralow-dose chest CT.

PURPOSE: To prospectively evaluate whether Lung-RADS classification and volumetric nodule assessment were feasible with ultralow-dose (ULD) chest CT scans with deep learning image reconstruction (DLIR). METHODS: The institutional review board approved this prospective study. This study included 40 patients (mean age, 66±12 years; 21 women). Participants sequentially underwent LDCT and ULDCT (CTDIvol, 0.96±0.15 mGy and 0.12±0.01 mGy) scans reconstructed with the adaptive statistical iterative reconstruction-V 50% (ASIR-V50) and DLIR. CT image quality was compared subjectively and objectively. The pulmonary nodules were assessed visually by two readers using the Lung-RADS 1.1 and automatically using a computerized assisted tool. RESULTS: DLIR provided a significantly higher signal-to-noise ratio for LDCT and ULDCT images than ASIR-V50 (all P < .001). In general, DLIR showed superior subjective image quality for ULDCT images (P < .001) and comparable quality for LDCT images compared to ASIR-V50 (P = .01-1). The per-nodule sensitivities of observers for Lung-RADS category 3-4 nodules were 70.6-88.2% and 64.7-82.4% for DLIR-LDCT and DLIR-ULDCT images (P = 1) and categories were mostly concordant within observers. The per-nodule sensitivities of the computer-assisted detection for nodules ≥4 mm were 72.1% and 67.4% on DLIR-LDCT and ULDCT images (P = .50). The 95% limits of agreement for nodule volume differences between DLIR-LDCT and ULDCT images (-85.6 to 78.7 mm3) was similar to the within-scan nodule volume differences between DLIR- and ASIR-V50-LDCT images (-63.9 to 78.5 mm3), with volume differences smaller than 25% in 88.5% and 92.3% of nodules, respectively (P = .65). CONCLUSION: DLIR enabled comparable Lung-RADS and volumetric nodule assessments on ULDCT images to LDCT images.

10-Year Clinical Follow-Up after Decompression of Lipofibromatous Hamartoma of the Median Nerve in a 3-Year-Old Patient: Case Report and Review of the Literature.

Lipofibromatous hamartoma, first reported in 1953, is a rare, slowly progressive soft tissue tumor, the characteristics of which include the enlargement of the affected nerve via the epineurial and perineurial proliferation of adipose and fibrous tissues. Out of 200 previously reported cases of lipofibromatous hamartoma of the median nerve, there have been approximately 25 pediatric cases under the age of 18. Herein, we report a case of lipofibromatous hamatoma of the median nerve in a 3-year-old female patient who was surgically decompressed via carpal tunnel release and epineurolysis. The patient was followed-up on an outpatient clinic basis annually with sonographic evaluations, and the postoperative 10th-year follow-up did not show recurrence or any deficits in motor and sensory functions.

Clinical characteristics of rheumatoid arthritis patients with interstitial lung disease: baseline data of a single-center prospective cohort.

BACKGROUND: To introduce a prospective cohort for rheumatoid arthritis (RA) patients with interstitial lung disease (ILD) and to identify their clinical features in comparison with RA patients without ILD. METHODS: Using a multidisciplinary collaborative approach, a single-center cohort for RA patients with ILD (RA-ILD) was established in May 2017, and enrolment data from May 2017 to March 2021 were used to compare the clinical features of RA patients without ILD (RA-non ILD). Multivariable logistic regression analysis was used to identify factors associated with ILD in RA patients. RESULTS: Among 148 RA-ILD and 410 RA-non ILD patients, participants in the RA-ILD group were older (65.8 ± 9.9 vs. 58.0 ± 10.4 years, P < 0.001) and included more males (35.8% vs. 14.6%, P < 0.001) than in the RA-non ILD group. The RA-ILD group had a higher proportion of late-onset RA patients (age ≥ 60 years) than in the comparator group (43.9% vs. 14.2%, P < 0.001). Multivariable logistic regression analysis showed that higher age at RA onset (OR 1.056, 95% CI 1.021-1.091), higher body mass index (BMI; OR 1.65, 95% CI 1.036-2.629), smoking history (OR 2.484, 95% CI 1.071-5.764), and oral glucocorticoid use (OR 3.562, 95% CI 2.160-5.874) were associated with ILD in RA patients, whereas methotrexate use was less likely to be associated with ILD (OR 0.253, 95% CI 0.155-0.412). CONCLUSIONS: Higher age at RA onset, smoking history, and higher BMI were associated with the presence of ILD among RA patients. Oral glucocorticoids were more frequently used whereas methotrexate was less likely to be used in RA-ILD patients.

Osteoid Osteoma of the Proximal Phalanx of the Great Toe in a 13-Year-Old Female Patient.

Osteoid osteoma (OO) is a benign osteoblastic bone tumor typically involving the diaphysis or metaphysis in long tubular bones. OO in phalanges of the great toe has been rarely reported, and it is often challenging to differentiate with subacute osteomyelitis, bone abscess, or osteoblastoma. This case report describes an uncommon case of a 13-year-old female patient with subperiosteal OO in the proximal phalanx of the great toe. The atypical location of OO should be familiarized to include appropriate differential diagnosis and to ensure accurate diagnosis by radiologic evaluations. Surgical excision remains the benchmark for the treatment of OO with its advantages on direct visualization and histologic confirmation for the diagnosis.

Deep Learning for Estimating Lung Capacity on Chest Radiographs Predicts Survival in Idiopathic Pulmonary Fibrosis.

Background Total lung capacity (TLC) has been estimated with use of chest radiographs based on time-consuming methods, such as planimetric techniques and manual measurements. Purpose To develop a deep learning-based, multidimensional model capable of estimating TLC from chest radiographs and demographic variables and validate its technical performance and clinical utility with use of multicenter retrospective data sets. Materials and Methods A deep learning model was pretrained with use of 50 000 consecutive chest CT scans performed between January 2015 and June 2017. The model was fine-tuned on 3523 pairs of posteroanterior chest radiographs and plethysmographic TLC measurements from consecutive patients who underwent pulmonary function testing on the same day. The model was tested with multicenter retrospective data sets from two tertiary care centers and one community hospital, including (a) an external test set 1 (n = 207) and external test set 2 (n = 216) for technical performance and (b) patients with idiopathic pulmonary fibrosis (n = 217) for clinical utility. Technical performance was evaluated with use of various agreement measures, and clinical utility was assessed in terms of the prognostic value for overall survival with use of multivariable Cox regression. Results The mean absolute difference and within-subject SD between observed and estimated TLC were 0.69 L and 0.73 L, respectively, in the external test set 1 (161 men; median age, 70 years [IQR: 61-76 years]) and 0.52 L and 0.53 L in the external test set 2 (113 men; median age, 63 years [IQR: 51-70 years]). In patients with idiopathic pulmonary fibrosis (145 men; median age, 67 years [IQR: 61-73 years]), greater estimated TLC percentage was associated with lower mortality risk (adjusted hazard ratio, 0.97 per percent; 95% CI: 0.95, 0.98; P < .001). Conclusion A fully automatic, deep learning-based model estimated total lung capacity from chest radiographs, and the model predicted survival in idiopathic pulmonary fibrosis. © RSNA, 2022 Online supplemental material is available for this article. See also the editorial by Sorkness in this issue.

Identification of Stem Cell Related Gene Expression from the Osteosarcoma Cell Core Side.

Osteosarcoma is the most frequent primary malignant bone tumor with higher incidences in children and adolescents. Despite clinical evolutions, patients with osteosacoma have had a poor prognosis. There has been increasing evidence that cancer is a stem cell disease. This study sought to isolate and characterize cancer stem cells from human osteosarcoma with relevant literature reviews. Here we show that the emerging evidence suggests osteosarcoma should be regarded as a differentiation disease such as stem cell disease. Two human osteosarcoma cell lines were cultured in non-adherent culture conditions as sarcospheres. Sarcospheres were observed using histomorphology and alkaline phosphatase (ALP) staining. Expression of the embryonic stem cell marker was analyzed with use of reverse transcriptase-PCR. Sarcospheres could be reproduced consistently throughout multiple passages and produced adherent osteosarcoma cell cultures. Expression of stem cell-associated genes such as those encoding Nanog, octamer-binding transcription factor 3/4, sex determining region Y box 2 , c-Myc and ALP indicated pluripotent stem-like cells. These results support the extension of the cancer stem cell theory to include osteosarcoma. Understanding the cancer stem cell derived from human osteosarcoma could lead to the evolution of diagnosis and treatment for osteosarcoma patients.

Effectiveness and Feasibility of Injectable Escherichia coli-Derived Recombinant Human Bone Morphogenetic Protein-2 for Anterior Lumbar Interbody Fusion at the Lumbosacral Junction in Adult Spinal Deformity Surgery: A Clinical Pilot Study.

OBJECTIVE: To explore the effectiveness and feasibility of injectable Escherichia coli-derived recombinant human bone morphogenetic protein-2 (injectable E-rhBMP-2, a combination of E. coli-derived recombinant human bone morphogenic protein-2 and a hydrogel type beta-tricalcium phosphate carrier) as a bone substitute for anterior lumbar interbody fusion (ALIF) of the lumbosacral junction in adult spinal deformity (ASD) patients. METHODS: A prospective single-institution therapeutic exploratory trial was conducted. Twenty patients (average age: 69.1 years; 19 female and one male; average fusion level: 7.95) diagnosed with ASD with sagittal imbalance who underwent surgical treatment including ALIF at the lumbosacral junction from December 2017 to January 2019 were evaluated. Injectable E-rhBMP-2 was prepared by dissolving 3 mg of E. coli-derived recombinant human bone morphogenetic protein-2 in 1.5 ml H2 O and mixing in situ with 9 g hydrogel type beta-tricalcium phosphate. This bone graft substitute was loaded onto a metal ALIF cage and L5 -S1 ALIF was performed in routine manner. Then posterior column osteotomy with multilevel oblique lumbar interbody fusion or pedicle subtraction osteotomy with accessory rod technique was performed to restore sagittal balance. Patients were followed up for 12 months. CT-based fusion rates were examined at 6 and 12 months after surgery. Also, clinical outcomes (Oswestry Disability Index [ODI], Visual Analog Scale [VAS] score of the back and leg) were evaluated at 6 and 12 months after surgery. All postoperative adverse events were evaluated for the association with injectable E.BMP-2. RESULTS: Of the 20 patients, loss to follow-up occurred with one patient at 6 months after surgery and one patient at 12 months after surgery, resulting in a total of 18 patients who were available for follow-up. Six months after surgery, 68.4% patients achieved solid fusion. Twelve months after surgery, 100% fusion rate was achieved. Compared to baseline values, ODI scores improved to 45.8% and 63.7%, VAS (back) improved to 69.2% and 72.8%, and VAS (leg) improved to 49.2% and 64.8%, respectively, at 6 and 12 months after surgery (p < 0.001 for all). Ten cases of adverse events occurred. But no adverse events were associated with injectable E-rhBMP-2. CONCLUSION: Injectable E-rhBMP-2 will be an effective bone graft substitute when achieving solid interbody fusion in the lumbosacral junction.

The first case report of thorn-induced Alternaria alternata infection of the hand in an immunocompetent host.

BACKGROUND: Fungal infection secondary to a penetrating plant thorn injury in upper extremities is infrequently reported especially in immunocompetent hosts. Alternaria is a dematicaceous hyphomycete, commonly found in decay and plant pathogens, and Alternaria alternata has been regarded as the most frequent species among more than 400 s of its species. This case is the first report of thorn-induced Alternaria alternata infection of the hand in an immunocompetent host. CASE PRESENTATION: A 47-year-old male patient was admitted to our institution with persistent pain and swelling of the right hand even after a prior surgical removal of a previous thorn injury. Upon impression of abscess, chronic extensor tenosynovitis, and septic arthritis at the 3rd metacarpophalangeal joint based on advanced imaging, the patient underwent surgical incision and drainage. Intraoperative culture, biopsy, and gene molecular sequencing results revealed fungal infection with Alternaria alternata. Postoperatively, the patient was treated with oral itraconazole (200 mg q 12 h) for nine consecutive months. CONCLUSIONS: We report the first case of chronic extensor tenosynovitis and septic arthritis of the hand with Alternaria alternata after a thorn injury in an immunocompetent host. Despite rare incidences of fungal extensor tenosynovitis and septic arthritis, the current case strongly suggests a careful examination of social history and surgical debridement along with a prolonged use of appropriate anti-fungal agents in thorn injuries.

Prenatal exposure to paternal smoking and likelihood for autism spectrum disorder.

LAY ABSTRACT: What is Already Known about This Subject: Genetics, (including de novo mutations), environmental factors (including toxic exposures), and their interactions impact autism spectrum disorder etiology. Paternal smoking is a candidate risk for autism spectrum disorder due to biological plausibility, high prevalence, and potential intervention.What This Study Adds: This original study and its replication confirms that paternal factors can substantially contribute to autism spectrum disorder risk for their offspring. It specifically indicates that paternal smoking both before and during pregnancy contributes significantly to autism spectrum disorder risk.Implications for practice, research, or policy: Smoking prevention, especially in pregnancy planning, may decrease autism spectrum disorder risk in offspring.

Giant Infrascapular Rheumatoid Nodules Mimicking Elastofibroma Dorsi: A Case Report.

Rheumatoid nodules are the most common extra-articular presentations of rheumatoid arthritis. Although rheumatoid nodules can develop anywhere in the body, they develop most commonly in the subcutaneous region, where they are easily exposed to repetitive trauma or pressure. However, an infrascapular presentation has not yet been reported. We report a case of giant bilateral rheumatoid nodules that developed in the infrascapular area, complicating its distinction from elastofibroma dorsi on radiological examination.

Automated Lung Segmentation on Chest Computed Tomography Images with Extensive Lung Parenchymal Abnormalities Using a Deep Neural Network.

OBJECTIVE: We aimed to develop a deep neural network for segmenting lung parenchyma with extensive pathological conditions on non-contrast chest computed tomography (CT) images. MATERIALS AND METHODS: Thin-section non-contrast chest CT images from 203 patients (115 males, 88 females; age range, 31-89 years) between January 2017 and May 2017 were included in the study, of which 150 cases had extensive lung parenchymal disease involving more than 40% of the parenchymal area. Parenchymal diseases included interstitial lung disease (ILD), emphysema, nontuberculous mycobacterial lung disease, tuberculous destroyed lung, pneumonia, lung cancer, and other diseases. Five experienced radiologists manually drew the margin of the lungs, slice by slice, on CT images. The dataset used to develop the network consisted of 157 cases for training, 20 cases for development, and 26 cases for internal validation. Two-dimensional (2D) U-Net and three-dimensional (3D) U-Net models were used for the task. The network was trained to segment the lung parenchyma as a whole and segment the right and left lung separately. The University Hospitals of Geneva ILD dataset, which contained high-resolution CT images of ILD, was used for external validation. RESULTS: The Dice similarity coefficients for internal validation were 99.6 ± 0.3% (2D U-Net whole lung model), 99.5 ± 0.3% (2D U-Net separate lung model), 99.4 ± 0.5% (3D U-Net whole lung model), and 99.4 ± 0.5% (3D U-Net separate lung model). The Dice similarity coefficients for the external validation dataset were 98.4 ± 1.0% (2D U-Net whole lung model) and 98.4 ± 1.0% (2D U-Net separate lung model). In 31 cases, where the extent of ILD was larger than 75% of the lung parenchymal area, the Dice similarity coefficients were 97.9 ± 1.3% (2D U-Net whole lung model) and 98.0 ± 1.2% (2D U-Net separate lung model). CONCLUSION: The deep neural network achieved excellent performance in automatically delineating the boundaries of lung parenchyma with extensive pathological conditions on non-contrast chest CT images.

Associations among High Risk for Sleep-disordered Breathing, Related Risk Factors, and Attention Deficit/Hyperactivity Symptoms in Elementary School Children.

OBJECTIVE: : Habitual snoring is a common problem in children. We evaluated the association between a high risk for sleep-disordered breathing and attention deficit/hyperactivity symptoms. METHODS: Parents of 13,560 children aged 6 to 12 years responded to questionnaires including items on habitual snoring and the Korean attention deficit/hyperactivity disorder rating scale. The snoring score comprised the number of "yes" responses to habitual-snoring items, and a high risk for sleep-disordered breathing was defined as a snoring score ≥ 2. RESULTS: The odds ratio (OR) of a high risk for sleep-disordered breathing was significantly higher in boys (OR = 1.47; p < 0.001), overweight children (OR = 2.20; p < 0.001), and children with current secondhand-smoking exposure (OR = 1.38; p < 0.001). The Korean attention deficit/hyperactivity disorder rating scale score increased significantly with the snoring score (0 vs. 1, B = 1.56, p < 0.001; 0 vs. 2, B = 2.44, p < 0.001; 0 vs. 3, B = 2.48, p < 0.001; 0 vs. 4, B = 3.95; p < 0.001). CONCLUSION: Our study confirms several risk factors of sleep-disordered breathing, namely male sex, overweight, and exposure to tobacco smoking, and found a positive association between habitual snoring and attention deficit/hyperactivity symptoms.

Deep learning algorithm for surveillance of pneumothorax after lung biopsy: a multicenter diagnostic cohort study.

OBJECTIVES: Pneumothorax is the most common and potentially life-threatening complication arising from percutaneous lung biopsy. We evaluated the performance of a deep learning algorithm for detection of post-biopsy pneumothorax in chest radiographs (CRs), in consecutive cohorts reflecting actual clinical situation. METHODS: We retrospectively included post-biopsy CRs of 1757 consecutive patients (1055 men, 702 women; mean age of 65.1 years) undergoing percutaneous lung biopsies from three institutions. A commercially available deep learning algorithm analyzed each CR to identify pneumothorax. We compared the performance of the algorithm with that of radiology reports made in the actual clinical practice. We also conducted a reader study, in which the performance of the algorithm was compared with those of four radiologists. Performances of the algorithm and radiologists were evaluated by area under receiver operating characteristic curves (AUROCs), sensitivity, and specificity, with reference standards defined by thoracic radiologists. RESULTS: Pneumothorax occurred in 17.5% (308/1757) of cases, out of which 16.6% (51/308) required catheter drainage. The AUROC, sensitivity, and specificity of the algorithm were 0.937, 70.5%, and 97.7%, respectively, for identification of pneumothorax. The algorithm exhibited higher sensitivity (70.2% vs. 55.5%, p < 0.001) and lower specificity (97.7% vs. 99.8%, p < 0.001), compared with those of radiology reports. In the reader study, the algorithm exhibited lower sensitivity (77.3% vs. 81.8-97.7%) and higher specificity (97.6% vs. 81.7-96.0%) than the radiologists. CONCLUSION: The deep learning algorithm appropriately identified pneumothorax in post-biopsy CRs in consecutive diagnostic cohorts. It may assist in accurate and timely diagnosis of post-biopsy pneumothorax in clinical practice. KEY POINTS: • A deep learning algorithm can identify chest radiographs with post-biopsy pneumothorax in multicenter consecutive cohorts reflecting actual clinical situation. • The deep learning algorithm has a potential role as a surveillance tool for accurate and timely diagnosis of post-biopsy pneumothorax.

[Invasive Pulmonary Aspergillosis in a Immunocompetent Patient after Congenital Heart Disease Surgery: A Case Report]. / ë©´ì—­ì €í•˜ê°€ 없는 환자에서 ì„ ì²œì„± ì‹¬ìž¥ìˆ˜ìˆ í›„ 발생한 폐 아스페르길루스증: 증례 ë³´ê³ .

Invasive pulmonary aspergillosis (IPA) has been known to occur in immunocompromised patients, but has been rarely reported in immunocompetent patients. In immunocompetent patients, pulmonary fungal infections are not initially considered. This results in diagnosis and treatment delays, as well as poor prognosis. We report a case and serial CT findings of IPA in an immunocompetent 29-year-old male after congenital heart disease surgery.

Undetected Lung Cancer at Posteroanterior Chest Radiography: Potential Role of a Deep Learning-based Detection Algorithm.

PURPOSE: To evaluate the performance of a deep learning-based algorithm in detecting lung cancers not reported on posteroanterior chest radiographs during routine practice. MATERIALS AND METHODS: The retrospective test dataset included 168 posteroanterior chest radiographs acquired between March 2017 and December 2018 (168 patients; mean age, 71.9 years ± 9.5 [standard deviation]; age range, 42-91 years) with 187 lung cancers (mean size, 2.3 cm ± 1.2) undetected during initial clinical evaluation, and 50 normal chest radiographs. CT served as the reference standard for ground truth. Four thoracic radiologists independently reevaluated the chest radiographs for lung nodules both without and with the aid of the algorithm. The performances of the algorithm and the radiologists were evaluated and compared on a per-chest radiograph basis and a per-lesion basis, according to the area under the receiver operating characteristic curve (AUROC) and area under the jackknife free-response ROC curve (AUFROC). RESULTS: The algorithm showed excellent diagnostic performances both in terms of per-chest radiograph classification (AUROC, 0.899) and per-lesion localization (AUFROC, 0.744); both of these values were significantly higher than those of the radiologists (AUROC, 0.634-0.663; AUFROC, 0.619-0.651; P < .001 for all). The algorithm also demonstrated higher sensitivity (69.6% [117 of 168] vs 47.0% [316 of 672]; P < .001) and specificity (94.0% [47 of 50] vs 78.0% [156 of 200]; P = .01). When assisted by the algorithm, the radiologists' AUROC (0.634-0.663 vs 0.685-0.724; P < 0.01 for all) and pooled AUFROC (0.636 vs 0.688; P = .03) substantially improved. The false-positive rate of the algorithm, that is, the total number of false-positive nodules divided by the total number of chest radiographs, was similar to that of pooled radiologists (21.1% [46 of 218] vs 19.0% [166 of 872]; P > .05). CONCLUSION: A deep learning-based nodule detection algorithm showed excellent detection performance of lung cancers that were not reported on chest radiographs during routine practice and significantly reduced reading errors when used as a second reader.Supplemental material is available for this article.© RSNA, 2020See also commentary by White in this issue.

Associations between urinary cotinine and symptoms of attention deficit/hyperactivity disorder and autism spectrum disorder.

BACKGROUND: The present study investigated associations between urinary cotinine levels as a biomarker of secondhand smoke exposure and symptoms of attention deficit/hyperactivity disorder (ADHD) and autism spectrum disorder (ASD). METHODS: A total of 520 child participants (200 with ADHD, 67 with ASD, and 253 normal control subjects) were assessed using the Korean version of the ADHD rating scale (K-ARS), Autism spectrum screening questionnaire (ASSQ), and Behavioral Assessment System for Children, second edition (BASC-2). The Korean version of the computer-based continuous performance test was used to assess cognitive function. Urinary cotinine was evaluated as a biomarker of secondhand smoke exposure. RESULTS: Urinary cotinine levels were significantly and positively associated with K-ARS score (B = 4.00, p < 0.001), ASSQ score (B = 1.71, p = 0.030), the behavioral problem subscales of the BASC-2 (B = 1.68-3.52, p < 0.001-0.045), and omission and commission errors in the continuous performance test (B = 6.21-8.42, p < 0.001-0.019). Urinary cotinine levels were also associated with the increased odds ratio of ADHD (OR = 1.55, 95% CI 1.05-2.30, p = 0.028) and ASD (OR = 1.89, 95% CI 1.12-3.21, p = 0.018). CONCLUSION: Urinary cotinine levels were associated with lower behavioral adaptation and cognitive function and increased odds ratios of ADHD and ASD, indicating a negative effect of secondhand smoke exposure on the symptomatic manifestation of ADHD and ASD.

Associations between attention-deficit/hyperactivity disorder symptoms and dietary habits in elementary school children.

OBJECTIVE: The aim of the present study was to investigate the associations between dietary habits and attention deficit/hyperactivity disorder (ADHD) symptoms in elementary school children. METHODS: The parents of 16,831 participating children assessed the ADHD symptoms of their children by responding to the Korean version of the ADHD rating scale (K-ARS). Parents also responded to the food habit questionnaire, which consists of 8 items regarding the eating pace, the frequency of overeating, and patterns of eating six types of food: fast food, soft drinks, instant noodles, fruit and vegetables, and milk. RESULTS: K-ARS scores were positively associated with higher consumption of foods categorized as unhealthy, including fast food, soft drinks, and instant noodles, and negatively associated with higher consumption of fruit and vegetables categorized as healthy foods. K-ARS scores were also higher in the groups who overate more frequently and ate faster or slower compared to other family members. CONCLUSION: Our findings may provide useful clinical information for dietary interventions in children with ADHD.