ROCOv2: Radiology Objects in COntext Version 2, an Updated Multimodal Image Dataset.

Automated medical image analysis systems often require large amounts of training data with high quality labels, which are difficult and time consuming to generate. This paper introduces Radiology Object in COntext version 2 (ROCOv2), a multimodal dataset consisting of radiological images and associated medical concepts and captions extracted from the PMC Open Access subset. It is an updated version of the ROCO dataset published in 2018, and adds 35,705 new images added to PMC since 2018. It further provides manually curated concepts for imaging modalities with additional anatomical and directional concepts for X-rays. The dataset consists of 79,789 images and has been used, with minor modifications, in the concept detection and caption prediction tasks of ImageCLEFmedical Caption 2023. The dataset is suitable for training image annotation models based on image-caption pairs, or for multi-label image classification using Unified Medical Language System (UMLS) concepts provided with each image. In addition, it can serve for pre-training of medical domain models, and evaluation of deep learning models for multi-task learning.

Addressing the Contrast Media Recognition Challenge: A Fully Automated Machine Learning Approach for Predicting Contrast Phases in CT Imaging.

OBJECTIVES: Accurately acquiring and assigning different contrast-enhanced phases in computed tomography (CT) is relevant for clinicians and for artificial intelligence orchestration to select the most appropriate series for analysis. However, this information is commonly extracted from the CT metadata, which is often wrong. This study aimed at developing an automatic pipeline for classifying intravenous (IV) contrast phases and additionally for identifying contrast media in the gastrointestinal tract (GIT). MATERIALS AND METHODS: This retrospective study used 1200 CT scans collected at the investigating institution between January 4, 2016 and September 12, 2022, and 240 CT scans from multiple centers from The Cancer Imaging Archive for external validation. The open-source segmentation algorithm TotalSegmentator was used to identify regions of interest (pulmonary artery, aorta, stomach, portal/splenic vein, liver, portal vein/hepatic veins, inferior vena cava, duodenum, small bowel, colon, left/right kidney, urinary bladder), and machine learning classifiers were trained with 5-fold cross-validation to classify IV contrast phases (noncontrast, pulmonary arterial, arterial, venous, and urographic) and GIT contrast enhancement. The performance of the ensembles was evaluated using the receiver operating characteristic area under the curve (AUC) and 95% confidence intervals (CIs). RESULTS: For the IV phase classification task, the following AUC scores were obtained for the internal test set: 99.59% [95% CI, 99.58-99.63] for the noncontrast phase, 99.50% [95% CI, 99.49-99.52] for the pulmonary-arterial phase, 99.13% [95% CI, 99.10-99.15] for the arterial phase, 99.8% [95% CI, 99.79-99.81] for the venous phase, and 99.7% [95% CI, 99.68-99.7] for the urographic phase. For the external dataset, a mean AUC of 97.33% [95% CI, 97.27-97.35] and 97.38% [95% CI, 97.34-97.41] was achieved for all contrast phases for the first and second annotators, respectively. Contrast media in the GIT could be identified with an AUC of 99.90% [95% CI, 99.89-99.9] in the internal dataset, whereas in the external dataset, an AUC of 99.73% [95% CI, 99.71-99.73] and 99.31% [95% CI, 99.27-99.33] was achieved with the first and second annotator, respectively. CONCLUSIONS: The integration of open-source segmentation networks and classifiers effectively classified contrast phases and identified GIT contrast enhancement using anatomical landmarks.

Cutaneous Angiosarcoma Subtypes: A Quantitative Systematic Review of Demographics, Treatments, and Outcomes Within Published Patient-Level Cases.

BACKGROUND: Cutaneous angiosarcoma (cAS) is a highly aggressive malignancy arising from the vascular endothelium. Given its rarity, there is insufficient data detailing patient demographics, management, and survival outcomes. OBJECTIVE: To systematically compile published patient-level cases of cAS and to quantify and analyze data on demographics, management, and outcomes while determining prognostic indicators. MATERIALS AND METHODS: Searches of EBSCOhost, MEDLINE, EMBASE, and the Cochrane Library generated 1,500 cases of cAS with individual level data available. PRISMA guidelines were followed. RESULTS: Cutaneous angiosarcoma presented most often on the scalp of elderly men. Metastasis occurred in 36.3% of cases. Aggregate 5-year survival was 31.6% with the median survival of 25 months. The best 5-year survival was in the radiation-associated subtype (48.8%), whereas the worst was in the Stewart-Treves subtype (21.6%). Using multivariate analysis, gender, age group, disease subtype, treatment modality, and metastasis at presentation had significant effects on survival outcomes ( p < .05). CONCLUSION: The breadth of information obtained enables this study to serve as a resource that clinicians may reference when they encounter cAS.

Optimizing platelet transfusion through a personalized deep learning risk assessment system for demand management.

ABSTRACT: Platelet demand management (PDM) is a resource-consuming task for physicians and transfusion managers of large hospitals. Inpatient numbers and institutional standards play significant roles in PDM. However, reliance on these factors alone commonly results in platelet shortages. Using data from multiple sources, we developed, validated, tested, and implemented a patient-specific approach to support PDM that uses a deep learning-based risk score to forecast platelet transfusions for each hospitalized patient in the next 24 hours. The models were developed using retrospective electronic health record data of 34 809 patients treated between 2017 and 2022. Static and time-dependent features included demographics, diagnoses, procedures, blood counts, past transfusions, hematotoxic medications, and hospitalization duration. Using an expanding window approach, we created a training and live-prediction pipeline with a 30-day input and 24-hour forecast. Hyperparameter tuning determined the best validation area under the precision-recall curve (AUC-PR) score for long short-term memory deep learning models, which were then tested on independent data sets from the same hospital. The model tailored for hematology and oncology patients exhibited the best performance (AUC-PR, 0.84; area under the receiver operating characteristic curve [ROC-AUC], 0.98), followed by a multispecialty model covering all other patients (AUC-PR, 0.73). The model specific to cardiothoracic surgery had the lowest performance (AUC-PR, 0.42), likely because of unexpected intrasurgery bleedings. To our knowledge, this is the first deep learning-based platelet transfusion predictor enabling individualized 24-hour risk assessments at high AUC-PR. Implemented as a decision-support system, deep-learning forecasts might improve patient care by detecting platelet demand earlier and preventing critical transfusion shortages.

Agricultural exposures and risk of childhood neuroblastoma: a systematic review and meta-analysis.

While neuroblastoma accounts for an estimated 8% of childhood cancers, it causes about 15% of childhood cancer deaths in the United States. The role of agricultural exposures in the development of neuroblastoma is unclear. We conducted a systematic review and meta-analysis of studies examining the relationship between agricultural exposures and neuroblastoma. MEDLINE, EMBASE, Scopus, and Google Scholar were searched in February 2022, identifying 742 publications. Seventeen articles met the inclusion criteria; all were published between 1985 and 2020 and included 14 case-control, one cross-sectional, and two cohort studies. Random and fixed effects models were used to calculate summary odds ratios (sORs) and 95% confidence intervals (CIs). An increased odds of developing neuroblastoma with parental exposure to any pesticides (sOR = 1.25, 95% CI: 1.03-1.48; 4 studies), insecticides (sOR = 1.55, 95% CI: 1.19-1.91; 3 studies), and residential exposure to crops/vegetables (sOR = 1.04, 95% CI: 1.01-1.06; 2 studies) was seen. Heterogeneity was low in all analyses, and no publication bias was evident. No significant associations were found with agricultural occupations, herbicides, and agricultural dusts. The studies were limited by exposure measurements and small sample sizes. Further studies are needed to explore mechanisms in the development of neuroblastoma in children with parental agricultural exposures, especially pesticides, and to improve methods of measuring agricultural-related exposures.

Predicting Individual Patient Platelet Demand in a Large Tertiary Care Hospital Using Machine Learning.

Introduction: An increasing shortage of donor blood is expected, considering the demographic change in Germany. Due to the short shelf life and varying daily fluctuations in consumption, the storage of platelet concentrates (PCs) becomes challenging. This emphasizes the need for reliable prediction of needed PCs for the blood bank inventories. Therefore, the objective of this study was to evaluate multimodal data from multiple source systems within a hospital to predict the number of platelet transfusions in 3 days on a per-patient level. Methods: Data were collected from 25,190 (42% female and 58% male) patients between 2017 and 2021. For each patient, the number of received PCs, platelet count blood tests, drugs causing thrombocytopenia, acute platelet diseases, procedures, age, gender, and the period of a patient's hospital stay were collected. Two models were trained on samples using a sliding window of 7 days as input and a day 3 target. The model predicts whether a patient will be transfused 3 days in the future. The model was trained with an excessive hyperparameter search using patient-level repeated 5-fold cross-validation to optimize the average macro F2-score. Results: The trained models were tested on 5,022 unique patients. The best-performing model has a specificity of 0.99, a sensitivity of 0.37, an area under the precision-recall curve score of 0.45, an MCC score of 0.43, and an F1-score of 0.43. However, the model does not generalize well for cases when the need for a platelet transfusion is recognized. Conclusion: A patient AI-based platelet forecast could improve logistics management and reduce blood product waste. In this study, we build the first model to predict patient individual platelet demand. To the best of our knowledge, we are the first to introduce this approach. Our model predicts the need for platelet units for 3 days in the future. While sensitivity underperforms, specificity performs reliably. The model may be of clinical use as a pretest for potential patients needing a platelet transfusion within the next 3 days. As sensitivity needs to be improved, further studies should introduce deep learning and wider patient characterization to the methodological multimodal, multisource data approach. Furthermore, a hospital-wide consumption of PCs could be derived from individual predictions.

Diagnostic Performance of the Darth Vader Sign for the Diagnosis of Lumbar Spondylolysis in Routinely Acquired Abdominal CT.

Spondylolysis is underdiagnosed and often missed in non-musculoskeletal abdominal CT imaging. Our aim was to assess the inter-reader agreement and diagnostic performance of a novel "Darth Vader sign" for the detection of spondylolysis in routine axial images. We performed a retrospective search in the institutional report archives through keyword strings for lumbar spondylolysis and spondylolisthesis. Abdominal CTs from 53 spondylolysis cases (41% female) and from controls (n = 6) without spine abnormalities were identified. A total of 139 single axial slices covering the lumbar spine (86 normal images, 40 with spondylolysis, 13 with degenerative spondylolisthesis without spondylolysis) were exported. Two radiology residents rated all images for the presence or absence of the "Darth Vader sign". The diagnostic accuracy for both readers, as well as the inter-reader agreement, was calculated. The "Darth Vader sign" showed an inter-reader agreement of 0.77. Using the "Darth Vader sign", spondylolysis was detected with a sensitivity and specificity of 65.0-88.2% and 96.2-99.0%, respectively. The "Darth Vader sign" shows excellent diagnostic performance at a substantial inter-reader agreement for the detection of spondylolysis. Using the "Darth Vader sign" in the CT reading routine may be an easy yet effective tool to improve the detection rate of spondylolysis in non-musculoskeletal cases and hence improve patient care.

Diagnostic performance of contrast-enhanced ultrasound in diagnosing hepatic artery occlusion after liver transplantation: A systematic review and meta-analysis.

INTRODUCTION: Hepatic artery occlusion (HAO) is a significant complication post-liver transplantation. Doppler ultrasound (DUS) has been widely used as an initial screening test for detecting HAO; however, its performance is often not sufficient. Although other diagnostic tests such as computed tomography angiography (CTA), magnetic resonance angiography (MRA), and angiogram are more accurate, they are invasive and have several limitations. Contrast-enhanced ultrasound (CEUS) is an emerging tool for detecting HAO; however, the results from previous studies were limited due to a small number of patients. Therefore, we aimed to evaluate its performance by performing a meta-analysis. METHOD: We performed a systemic review and meta-analysis of studies evaluating the performance of CEUS for the detection of HAO in an adult population. A literature search of EMBASE, Scopus, CINAHL, and Medline was conducted through March 2022. Pooled sensitivity, specificity, log diagnostic odd ratio (LDOR), and area under summary receiver operating curve (AUC) were calculated. Publication bias was assessed by Deeks' funnel plot. RESULT: Eight studies were included, with 434 CEUS performed. Using a combination of CTA, MRA, angiography, clinical follow-up, and surgery as the gold standard, the sensitivity, specificity, and LDOR of CEUS for detection of HAO were .969 (.938, .996), .991 (.981, 1.001), and 5.732 (4.539, 6.926), respectively. AUC was .959. The heterogeneity between studies appeared universally low, and no significant publication bias was found (p = .44). CONCLUSION: CEUS appeared to have an excellent performance for the detection of HAO and could be considered as an alternative when DUS is non-diagnostic or when CTA, MRA, and angiogram are not feasible.

Bacterial Pathogens Causing Pneumonia Post Hematopoietic Stem Cell Transplant: The Chronic GVHD Population.

Allogeneic stem cell transplantation is a lifesaving treatment for many malignancies. Post-transplant patients may suffer from graft versus host disease in the acute and/or the chronic form(s). Post-transplantation immune deficiency due to a variety of factors is a major cause of morbidity and mortality. Furthermore, immunosuppression can lead to alterations in host factors that predisposes these patients to infections. Although patients who receive stem cell transplant are at an increased risk of opportunistic pathogens, which include fungi and viruses, bacterial infections remain the most common cause of morbidity. Here, we review bacterial pathogens that lead to pneumonias specifically in the chronic GVHD population.

Peripheral Blood Biomarkers for Rheumatoid Arthritis-Associated Interstitial Lung Disease: A Systematic Review.

BACKGROUND: Biomarkers have been proposed as tools to aid in the identification and prognostication of interstitial lung disease (ILD) in rheumatoid arthritis (RA). We performed a systematic review of studies evaluating peripheral blood biomarkers and their association with RA-ILD and its prognosis. METHODS: Medline, Embase, the Cochrane Library, and Scopus were queried for relevant studies, with the final search update on July 12, 2021. We included studies evaluating peripheral blood biomarkers for the identification and/or prognostication of RA-ILD, extracting the performance of individual biomarkers for identifying RA-ILD, and predicting prognosis. Modified versions of the Quality Assessment of Diagnostic Accuracy Studies 2 and the Quality in Prognosis Studies tools were used for quality assessment. RESULTS: Seventy studies met eligibility criteria. Study and patient characteristics, analytical methods, strength and consistency of associations, and study quality were heterogeneous. A total of 92 biomarkers were positively associated and 12 were negatively associated with RA-ILD among patients with RA in one or more report. Only a small number of biomarkers were evaluated in multiple cohorts using adjusted analyses. Biomarkers most strongly associated with RA-ILD overlapped with those identified for idiopathic pulmonary fibrosis. Few prognostic biomarkers of RA-ILD were identified. CONCLUSION: Several peripheral blood biomarkers are associated with the presence of RA-ILD, but few have been assessed in multivariable models, have been externally validated, have discriminated RA-ILD from other lung disease, or have prognosticated the disease course. High-quality studies investigating and validating peripheral biomarkers in RA-ILD are needed before they can be employed in clinical care.

Seizure burden and neuropsychological outcomes of new-onset refractory status epilepticus: Systematic review.

Background: Long-term sequelae of the new onset refractory status epilepticus (NORSE) include the development of epilepsy, cognitive deficits, and behavioral disturbances. The prevalence of these complications has been previously highlighted in case reports and case series: however, their full scope has not been comprehensively assessed. Methods: We conducted a systematic review of the literature (PROSPERO ID CRD42022361142) regarding neurological and functional outcomes of NORSE at 30 days or longer following discharge from the hospital. A systematic review protocol was developed using guidance from the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA). Results: Of the 1,602 records for unique publications, 33 reports on adults and 52 reports on children met our inclusion criteria. They contained the description of 280 adults and 587 children of whom only 75.7 and 85% of patients, respectively had data on long-term follow-up. The mean age of adult and pediatric patients was 34.3 and 7.9 years, respectively; and the longest duration of follow up were 11 and 20 years, respectively. Seizure outcomes received major attention and were highlighted for 93.4 and 96.6% of the adult and pediatric NORSE patients, respectively. Seizures remained medically refractory in 41.1% of adults and 57.7% of children, while seizure freedom was achieved in only 26 and 23.3% of these patients, respectively. The long-term cognitive outcome data was provided for just 10.4% of the adult patients. In contrast, cognitive health data were supplied for 68.9% of the described children of whom 31.9% were moderately or severely disabled. Long-term functional outcomes assessed with various standardized scales were reported in 62.2 and 25.5% of the adults and children, respectively with majority of patients not being able to return to a pre-morbid level of functioning. New onset psychiatric disorders were reported in 3.3% of adults and 11.2% of children recovering from NORSE. Conclusion: These findings concur with previous observations that the majority of adult and pediatric patients continue to experience recurrent seizures and suffer from refractory epilepsy. Moderate to severe cognitive disability, loss of functional independence, and psychiatric disorders represent a hallmark of chronic NORSE signifying the major public health importance of this disorder.

Dedicated breast computed-tomography in women with a personal history of breast cancer: A proof-of-concept study.

PURPOSE: To compare the subjective image quality assessment using B-CT and digital mammography in women with personal history of breast cancer (PHBC). METHOD: In this retrospective study 32 patients with PHBC were included. Each patient had undergone a B-CT examination and a previous mammogram in a time interval of less than 18 months between the two examinations. Two radiologists evaluated the two examinations independently with regard to the presence of lesions, BI-RADS classification, level of confidence for the overall exam interpretation, scar evaluation and image quality including image degradation due to clip artifacts. Level of confidence and image quality were assessed using a 5-point Likert scale. A p-value of less than 0.01 was considered statistically significant. RESULTS: Thirty-seven operated and 27 non-operated breasts were included. Confidence for the overall interpretation with B-CT was equal or superior to mammography in 63 cases (98.4 %) for reader 1 and in 58 cases (90.6 %) for reader 2 (p <.001). Confidence for scar evaluation with B-CT was equal or superior to mammography in all cases for reader 1 and in 34 cases (91.9 %) for readers 2 (p <.001). One case with local recurrence in B-CT was identified by both readers and no false positive findings were reported. A moderate to high image degradation due to beam-hardening artifacts has been reported by both readers in 29.4 % of cases due to surgical clips in the B-CT volume. CONCLUSIONS: B-CT in patients with PHBC provides high quality images that can be evaluated with confidence equal or superior to mammography.

A review of bidimensional acculturation and STI/HIV-related sexual risk behaviours among Hispanic youth.

A growing body of research suggests that acculturation may play a role in the disproportionate likelihood of sexual risk behaviour and STI/HIV infection among Hispanic youth in the USA. We systematically reviewed the relationship between acculturation and STI/HIV-related sexual risk behaviour among Hispanic youth aged 13-24 by reviewing studies that have used a bidimensional acculturation approach. Electronic databases were searched with the searches limited to articles published in 1992 when the concept of bidimensional acculturation was introduced or later. Two independent researchers screened the full data set to assess eligibility. Six studies were included. Three studies used cross-sectional data, while the other three used longitudinal data. We discovered that sexual risk behaviours differed by Hispanic youth acculturation types and were moderated by gender. We found that Hispanic acculturated youth had lower odds of having multiple sex partners than US acculturated youth. However, the relationship between acculturation and condom use yielded contradictory results and we could find no report on bi-culturation and sexual behaviour. Additional research is needed to explore whether adopting both US and Hispanic-heritage cultures at the same time may reduce or increase the odds of engaging in sexual risk behaviour among Hispanic youth in the USA.

Mobile Health (mHealth) Interventions to Increase Cancer Screening Rates in Hispanic/Latinx Populations: A Scoping Review.

Hispanic/Latinx persons have disproportionately lower breast, cervical, and colorectal cancer screening rates than non-Hispanic White (NHW) persons. This low participation in cancer screening results in late-stage cancer diagnosis among Hispanic persons compared to NHW persons. Mobile health (mHealth) interventions effectively improve cancer screening rates in the general population; however, few reviews about mHealth interventions are tailored to Hispanic populations. This is important to investigate given that Hispanic persons differ from NHW persons with regard to culture, language, and health care utilization. Therefore, in this study, we investigated: (a) What types of mHealth interventions have been undertaken to increase cancer screening rates among Hispanic persons in the United States? (b) How effective have these interventions been? and (c) What features of these interventions help increase cancer screening rates? Searches conducted during December 2020 identified 10 articles published between January 2017 and December 2020 that met our inclusion criteria. The review revealed that mHealth interventions mainly provided education about cancer and cancer screening using videos, PowerPoint slides, and interactive multimedia. mHealth interventions that effectively improved screening behavior were mainly for easy-to-screen cancers like skin and cervical cancer. Finally, reviewed studies did not provide details on how cultural adaptations were made, and it is unclear what specific features of mHealth interventions increase cancer screening rates among Hispanic persons. Future research should identify and evaluate the effects of different components of culturally tailored interventions on cancer screening. Public health practitioners and health care providers should tailor mHealth approaches to their clients or patients and practice environment.

Ascitic calprotectin and lactoferrin for detection of spontaneous bacterial peritonitis: a systematic review and meta-analysis.

Background: Spontaneous bacterial peritonitis (SBP) is a common bacterial infection in cirrhotic patients associated with a high mortality rate. Prompt diagnosis and early antibiotic administration are crucial in minimizing adverse outcomes. Although detection of ≥250 polymorphonuclear leukocytes (PMN) in ascitic fluid is the current gold standard to diagnose SBP, consideration for rapid detection with biomarkers is warranted. Methods: A literature search for studies evaluating ascitic calprotectin and lactoferrin for detection of SBP was performed using PubMed, Embase, Scopus, Google Scholar, Cochrane library, and Clinical Trial Registries. Summary sensitivity, specificity, log diagnostic odds ratio (LDOR), and area under the summary receiver operating curve (AUC) were calculated. Results: In total, 12 and 13 studies evaluated ascitic calprotectin and lactoferrin, respectively, for detection of SBP. Summary sensitivity, specificity, and LDOR for calprotectin were 0.942 (95% CI, 0.916, 0.967), 0.860 (95% CI, 0.799, 0.935), and 4.250 (95% CI, 3.504, 4.990), respectively. AUC for calprotectin was 0.91. Summary sensitivity, specificity, and LDOR for lactoferrin were 0.954 (95% CI, 0.930, 0.979), 0.890 (95% CI, 0.836, 0.945), and 4.630 (95% CI, 3.800, 5.452), respectively. AUC for lactoferrin was 0.958. Conclusions: The overall performance of ascitic calprotectin and lactoferrin was substantial, potentially serving as a screening tool or an alternative to manual cell count. However, a variety of manufacturers, cut-off values, and significant heterogeneity between studies should be noted. Point-of-care testing for calprotectin and lactoferrin may resolve disadvantages associated with the current methods. Future studies on this topic are, therefore, needed.

Clinical assessment of image quality, usability and patient comfort in dedicated spiral breast computed tomography.

OBJECTIVE: To investigate aspects of image quality, feasibility and patient comfort in dedicated spiral breast computed tomography (B-CT) in a large patient cohort. METHODS: This retrospective study was approved by the institutional review board. 2418 B-CT scans from 1222 women examined between 04/16/2019 and 04/13/2022 were analyzed. Patients evaluated their comfort during the examination, radiographers carrying out the scans evaluated the patient's mobility and usability of the B-CT device, whereas radiologists assessed lesion contrast, detectability of calcifications, breast coverage and overall image quality. For semi-quantitative assessment, a Likert-Scale was used and statistical significance and correlations were calculated using ANOVAs and Spearman tests. RESULTS: Comfort, mobility and usability of the B-CT were rated each with either "no" or "negligible" complaints in >99%. Image quality was rated with "no" or "negligible complaints" in 96.7%. Lesion contrast and detectability of calcifications were rated either "optimal" or "good" in 92.6% and 98.4%. "Complete" and "almost complete" breast coverage were reported in 41.9%, while the pectoral muscle was found not to be covered in 56.0%. Major parts of the breast were not covered in 2.1%. Some variables were significantly correlated, such as age with comfort (ρ = -0.168, p < .001) and mobility (ρ = -0.172, p < .001) as well as patient weight with lesion contrast (ρ = 0.172, p < .001) and breast coverage (ρ = -0.109, p < .001). CONCLUSIONS: B-CT provides high image quality and contrast of soft tissue lesions as well as calcifications, while covering the pre-pectoral areas of the breast remains challenging. B-CT is easy to operate for the radiographer and comfortable for the majority of women.

BI-RADS-Based Classification of Mammographic Soft Tissue Opacities Using a Deep Convolutional Neural Network.

The aim of this study was to investigate the potential of a machine learning algorithm to classify breast cancer solely by the presence of soft tissue opacities in mammograms, independent of other morphological features, using a deep convolutional neural network (dCNN). Soft tissue opacities were classified based on their radiological appearance using the ACR BI-RADS atlas. We included 1744 mammograms from 438 patients to create 7242 icons by manual labeling. The icons were sorted into three categories: "no opacities" (BI-RADS 1), "probably benign opacities" (BI-RADS 2/3) and "suspicious opacities" (BI-RADS 4/5). A dCNN was trained (70% of data), validated (20%) and finally tested (10%). A sliding window approach was applied to create colored probability maps for visual impression. Diagnostic performance of the dCNN was compared to human readout by experienced radiologists on a "real-world" dataset. The accuracies of the models on the test dataset ranged between 73.8% and 89.8%. Compared to human readout, our dCNN achieved a higher specificity (100%, 95% CI: 85.4-100%; reader 1: 86.2%, 95% CI: 67.4-95.5%; reader 2: 79.3%, 95% CI: 59.7-91.3%), and the sensitivity (84.0%, 95% CI: 63.9-95.5%) was lower than that of human readers (reader 1:88.0%, 95% CI: 67.4-95.4%; reader 2:88.0%, 95% CI: 67.7-96.8%). In conclusion, a dCNN can be used for the automatic detection as well as the standardized and observer-independent classification of soft tissue opacities in mammograms independent of the presence of microcalcifications. Human decision making in accordance with the BI-RADS classification can be mimicked by artificial intelligence.

Landscape of health sciences librarian-mediated search services.

BACKGROUND: Health librarians have traditionally provided mediated searches to support patient care, education and research. OBJECTIVES: This study aims to discover the types of search result formats used by health science libraries, determine current practice among health science libraries (types of requesters served, fees, deduplication, turnaround time and citation manager use) and uncover innovative methods for providing search results. METHODS: An online survey was distributed to the MEDLIB-L, ExpertSearching, MidContinental Chapter of the Medical Library Association and ICON listservs and through direct email to selected Association of Academic Health Sciences Libraries reference and education librarians. RESULTS: Librarians affiliated with 127 institutions from 11 countries (including the USS) and 36 USS states and territories responded. One hundred and forty-two of the total 150 analysed responses provided information on full-text access, and 81 of those 142 responses (57%) indicated that the institutions' link-resolver links were included in search results provided to the requester. The survey responses provide information on literature search services regarding turnaround time, use of a citation managers, fees and deduplication. CONCLUSION: With the developing landscape of citation managers and the tools offered, these data can be used as a benchmark for librarians who are considering evaluating or modifying their search service delivery.

Performance of Leukocyte Esterase Reagent Strips in the Detection of Spontaneous Bacterial Peritonitis in Cirrhotic Patients: A Systematic Review and Meta-analysis.

Background: Spontaneous bacterial peritonitis (SBP) is a bacterial infection associated with a high mortality rate in cirrhotic patients. The gold standard for the detection of SBP is a manual cell count from ascitic fluid; however, alternative screening methods are under investigation. In particular, leukocyte esterase reagent strips (LERS) has been studied as an alternative method to detect SBP with a low cost and instant turnaround time. Therefore, this study aims to evaluate the performance of LERS in the detection of SBP. Methods: A literature search was performed for studies evaluating LERS for the detection of SBP on PubMed, Embase, Scopus, Cochrane, and clinical trial registries. Summary sensitivity, specificity, log diagnostic odds ratio (LDOR), and the area under the summary receiver operating curve (AUC) were calculated according to the respective manufacturer. Results: In total, 31 studies were evaluated. The summary sensitivity of Aution Sticks, Combur, Multistix, Periscreen reagent strips was 0.962 (95% confidence interval [CI] 0.926, 0.998), 0.892 (95% CI 0.846, 0.938), 0.806 (95% CI 0.738, 0.874), and 0.939 (95% CI 0.900, 0.979), respectively. The summary specificity of Aution Sticks, Combur, Multistix, and Periscreen reagent strips was 0.940 (95% CI 0.904, 0.976), 0.922 (95% CI 0.874, 0.970), 0.974 (95% CI 0.962, 0.985), and 0.672 (95% CI 0.381, 0.963), respectively. Conclusion: LERS appears to have a notable overall performance for the detection of SBP. LERS appeared to be an acceptable alternative to diagnose SBP in facilities without ability to perform cell count. However, there were significant differences in performance between each manufacturer.

Movement disorders associated with antiseizure medications: A systematic review.

New-onset movement disorders have been frequently reported in association with the use of antiseizure medications (ASMs). The frequency of specific motor manifestations and the spectrum of their semiology for various ASMs have not been well characterized. We carried out a systematic review of literature and conducted a search on CINAHL, Cochrane Library, EMBASE, MEDLINE, PsycINFO, and Scopus from inception to April 2021. We compiled the data for all currently available ASMs using the conventional terminology of movement disorders. Among 5123 manuscripts identified by the search, 437 met the inclusion criteria. The largest number of reports of abnormal movements were in association with phenobarbital, valproic acid, lacosamide, and perampanel, and predominantly included tremor and ataxia. The majority of attempted interventions for all agents were discontinuation of the offending drug or dose reduction which led to the resolution of symptoms in most patients. Familiarity with the movement disorder phenomenology previously encountered in relation with specific ASMs facilitates early recognition of adverse effects and timely institution of targeted interventions.