Deep learning assessment compared to radiologist reporting for metastatic spinal cord compression on CT.

Introduction: Metastatic spinal cord compression (MSCC) is a disastrous complication of advanced malignancy. A deep learning (DL) algorithm for MSCC classification on CT could expedite timely diagnosis. In this study, we externally test a DL algorithm for MSCC classification on CT and compare with radiologist assessment. Methods: Retrospective collection of CT and corresponding MRI from patients with suspected MSCC was conducted from September 2007 to September 2020. Exclusion criteria were scans with instrumentation, no intravenous contrast, motion artefacts and non-thoracic coverage. Internal CT dataset split was 84% for training/validation and 16% for testing. An external test set was also utilised. Internal training/validation sets were labelled by radiologists with spine imaging specialization (6 and 11-years post-board certification) and were used to further develop a DL algorithm for MSCC classification. The spine imaging specialist (11-years expertise) labelled the test sets (reference standard). For evaluation of DL algorithm performance, internal and external test data were independently reviewed by four radiologists: two spine specialists (Rad1 and Rad2, 7 and 5-years post-board certification, respectively) and two oncological imaging specialists (Rad3 and Rad4, 3 and 5-years post-board certification, respectively). DL model performance was also compared against the CT report issued by the radiologist in a real clinical setting. Inter-rater agreement (Gwet's kappa) and sensitivity/specificity/AUCs were calculated. Results: Overall, 420 CT scans were evaluated (225 patients, mean age=60 ± 11.9[SD]); 354(84%) CTs for training/validation and 66(16%) CTs for internal testing. The DL algorithm showed high inter-rater agreement for three-class MSCC grading with kappas of 0.872 (p<0.001) and 0.844 (p<0.001) on internal and external testing, respectively. On internal testing DL algorithm inter-rater agreement (κ=0.872) was superior to Rad 2 (κ=0.795) and Rad 3 (κ=0.724) (both p<0.001). DL algorithm kappa of 0.844 on external testing was superior to Rad 3 (κ=0.721) (p<0.001). CT report classification of high-grade MSCC disease was poor with only slight inter-rater agreement (κ=0.027) and low sensitivity (44.0), relative to the DL algorithm with almost-perfect inter-rater agreement (κ=0.813) and high sensitivity (94.0) (p<0.001). Conclusion: Deep learning algorithm for metastatic spinal cord compression on CT showed superior performance to the CT report issued by experienced radiologists and could aid earlier diagnosis.

A deep learning-based technique for the diagnosis of epidural spinal cord compression on thoracolumbar CT.

PURPOSE: To develop a deep learning (DL) model for epidural spinal cord compression (ESCC) on CT, which will aid earlier ESCC diagnosis for less experienced clinicians. METHODS: We retrospectively collected CT and MRI data from adult patients with suspected ESCC at a tertiary referral institute from 2007 till 2020. A total of 183 patients were used for training/validation of the DL model. A separate test set of 40 patients was used for DL model evaluation and comprised 60 staging CT and matched MRI scans performed with an interval of up to 2 months. DL model performance was compared to eight readers: one musculoskeletal radiologist, two body radiologists, one spine surgeon, and four trainee spine surgeons. Diagnostic performance was evaluated using inter-rater agreement, sensitivity, specificity and AUC. RESULTS: Overall, 3115 axial CT slices were assessed. The DL model showed high kappa of 0.872 for normal, low and high-grade ESCC (trichotomous), which was superior compared to a body radiologist (R4, κ = 0.667) and all four trainee spine surgeons (κ range = 0.625-0.838)(all p < 0.001). In addition, for dichotomous normal versus any grade of ESCC detection, the DL model showed high kappa (κ = 0.879), sensitivity (91.82), specificity (92.01) and AUC (0.919), with the latter AUC superior to all readers (AUC range = 0.732-0.859, all p < 0.001). CONCLUSION: A deep learning model for the objective assessment of ESCC on CT had comparable or superior performance to radiologists and spine surgeons. Earlier diagnosis of ESCC on CT could reduce treatment delays, which are associated with poor outcomes, increased costs, and reduced survival.

Diagnostic stewardship for Clostridioides difficile testing in an acute care hospital: A quality improvement intervention.

Objective: To evaluate the impact of a diagnostic stewardship intervention on Clostridioides difficile healthcare-associated infections (HAI). Design: Quality improvement study. Setting: Two urban acute care hospitals. Interventions: All inpatient stool testing for C. difficile required review and approval prior to specimen processing in the laboratory. An infection preventionist reviewed all orders daily through chart review and conversations with nursing; orders meeting clinical criteria for testing were approved, orders not meeting clinical criteria were discussed with the ordering provider. The proportion of completed tests meeting clinical criteria for testing and the primary outcome of C. difficile HAI were compared before and after the intervention. Results: The frequency of completed C. difficile orders not meeting criteria was lower [146 (7.5%) of 1,958] in the intervention period (January 10, 2022-October 14, 2022) than in the sampled 3-month preintervention period [26 (21.0%) of 124; P < .001]. C. difficile HAI rates were 8.80 per 10,000 patient days prior to the intervention (March 1, 2021-January 9, 2022) and 7.69 per 10,000 patient days during the intervention period (incidence rate ratio, 0.87; 95% confidence interval, 0.73-1.05; P = .13). Conclusions: A stringent order-approval process reduced clinically nonindicated testing for C. difficile but did not significantly decrease HAIs.

Level of Attention to Motherese Speech as an Early Marker of Autism Spectrum Disorder.

Importance: Caregivers have long captured the attention of their infants by speaking in motherese, a playful speech style characterized by heightened affect. Reduced attention to motherese in toddlers with autism spectrum disorder (ASD) may be a contributor to downstream language and social challenges and could be diagnostically revealing. Objective: To investigate whether attention toward motherese speech can be used as a diagnostic classifier of ASD and is associated with language and social ability. Design, Setting, and Participants: This diagnostic study included toddlers aged 12 to 48 months, spanning ASD and non-ASD diagnostic groups, at a research center. Data were collected from February 2018 to April 2021 and analyzed from April 2021 to March 2022. Exposures: Gaze-contingent eye-tracking test. Main Outcomes and Measures: Using gaze-contingent eye tracking wherein the location of a toddler's fixation triggered a specific movie file, toddlers participated in 1 or more 1-minute eye-tracking tests designed to quantify attention to motherese speech, including motherese vs traffic (ie, noisy vehicles on a highway) and motherese vs techno (ie, abstract shapes with music). Toddlers were also diagnostically and psychometrically evaluated by psychologists. Levels of fixation within motherese and nonmotherese movies and mean number of saccades per second were calculated. Receiver operating characteristic (ROC) curves were used to evaluate optimal fixation cutoff values and associated sensitivity, specificity, positive predictive value (PPV), and negative predictive value. Within the ASD group, toddlers were stratified based on low, middle, or high levels of interest in motherese speech, and associations with social and language abilities were examined. Results: A total of 653 toddlers were included (mean [SD] age, 26.45 [8.37] months; 480 males [73.51%]). Unlike toddlers without ASD, who almost uniformly attended to motherese speech with a median level of 82.25% and 80.75% across the 2 tests, among toddlers with ASD, there was a wide range, spanning 0% to 100%. Both the traffic and techno paradigms were effective diagnostic classifiers, with large between-group effect sizes (eg, ASD vs typical development: Cohen d, 1.0 in the techno paradigm). Across both paradigms, a cutoff value of 30% or less fixation on motherese resulted in an area under the ROC curve (AUC) of 0.733 (95% CI, 0.693-0.773) and 0.761 (95% CI, 0.717-0.804), respectively; specificity of 98% (95% CI, 95%-99%) and 96% (95% CI, 92%-98%), respectively; and PPV of 94% (95% CI, 86%-98%). Reflective of heterogeneity and expected subtypes in ASD, sensitivity was lower at 18% (95% CI, 14%-22%) and 29% (95% CI, 24%-34%), respectively. Combining metrics increased the AUC to 0.841 (95% CI, 0.805-0.877). Toddlers with ASD who showed the lowest levels of attention to motherese speech had weaker social and language abilities. Conclusions and Relevance: In this diagnostic study, a subset of toddlers showed low levels of attention toward motherese speech. When a cutoff level of 30% or less fixation on motherese speech was used, toddlers in this range were diagnostically classified as having ASD with high accuracy. Insight into which toddlers show unusually low levels of attention to motherese may be beneficial not only for early ASD diagnosis and prognosis but also as a possible therapeutic target.

Deep Learning Model for Grading Metastatic Epidural Spinal Cord Compression on Staging CT.

Background: Metastatic epidural spinal cord compression (MESCC) is a disastrous complication of advanced malignancy. Deep learning (DL) models for automatic MESCC classification on staging CT were developed to aid earlier diagnosis. Methods: This retrospective study included 444 CT staging studies from 185 patients with suspected MESCC who underwent MRI spine studies within 60 days of the CT studies. The DL model training/validation dataset consisted of 316/358 (88%) and the test set of 42/358 (12%) CT studies. Training/validation and test datasets were labeled in consensus by two subspecialized radiologists (6 and 11-years-experience) using the MRI studies as the reference standard. Test sets were labeled by the developed DL models and four radiologists (2−7 years of experience) for comparison. Results: DL models showed almost-perfect interobserver agreement for classification of CT spine images into normal, low, and high-grade MESCC, with kappas ranging from 0.873−0.911 (p < 0.001). The DL models (lowest κ = 0.873, 95% CI 0.858−0.887) also showed superior interobserver agreement compared to two of the four radiologists for three-class classification, including a specialist (κ = 0.820, 95% CI 0.803−0.837) and general radiologist (κ = 0.726, 95% CI 0.706−0.747), both p < 0.001. Conclusion: DL models for the MESCC classification on a CT showed comparable to superior interobserver agreement to radiologists and could be used to aid earlier diagnosis.

Improved Productivity Using Deep Learning-assisted Reporting for Lumbar Spine MRI.

Background Lumbar spine MRI studies are widely used for back pain assessment. Interpretation involves grading lumbar spinal stenosis, which is repetitive and time consuming. Deep learning (DL) could provide faster and more consistent interpretation. Purpose To assess the speed and interobserver agreement of radiologists for reporting lumbar spinal stenosis with and without DL assistance. Materials and Methods In this retrospective study, a DL model designed to assist radiologists in the interpretation of spinal canal, lateral recess, and neural foraminal stenoses on lumbar spine MRI scans was used. Randomly selected lumbar spine MRI studies obtained in patients with back pain who were 18 years and older over a 3-year period, from September 2015 to September 2018, were included in an internal test data set. Studies with instrumentation and scoliosis were excluded. Eight radiologists, each with 2-13 years of experience in spine MRI interpretation, reviewed studies with and without DL model assistance with a 1-month washout period. Time to diagnosis (in seconds) and interobserver agreement (using Gwet κ) were assessed for stenosis grading for each radiologist with and without the DL model and compared with test data set labels provided by an external musculoskeletal radiologist (with 32 years of experience) as the reference standard. Results Overall, 444 images in 25 patients (mean age, 51 years ± 20 [SD]; 14 women) were evaluated in a test data set. DL-assisted radiologists had a reduced interpretation time per spine MRI study, from a mean of 124-274 seconds (SD, 25-88 seconds) to 47-71 seconds (SD, 24-29 seconds) (P < .001). DL-assisted radiologists had either superior or equivalent interobserver agreement for all stenosis gradings compared with unassisted radiologists. DL-assisted general and in-training radiologists improved their interobserver agreement for four-class neural foraminal stenosis, with κ values of 0.71 and 0.70 (with DL) versus 0.39 and 0.39 (without DL), respectively (both P < .001). Conclusion Radiologists who were assisted by deep learning for interpretation of lumbar spinal stenosis on MRI scans showed a marked reduction in reporting time and superior or equivalent interobserver agreement for all stenosis gradings compared with radiologists who were unassisted by deep learning. © RSNA, 2022 Online supplemental material is available for this article. See also the editorial by Hayashi in this issue.

Large scale validation of an early-age eye-tracking biomarker of an autism spectrum disorder subtype.

Few clinically validated biomarkers of ASD exist which can rapidly, accurately, and objectively identify autism during the first years of life and be used to support optimized treatment outcomes and advances in precision medicine. As such, the goal of the present study was to leverage both simple and computationally-advanced approaches to validate an eye-tracking measure of social attention preference, the GeoPref Test, among 1,863 ASD, delayed, or typical toddlers (12-48 months) referred from the community or general population via a primary care universal screening program. Toddlers participated in diagnostic and psychometric evaluations and the GeoPref Test: a 1-min movie containing side-by-side dynamic social and geometric images. Following testing, diagnosis was denoted as ASD, ASD features, LD, GDD, Other, typical sibling of ASD proband, or typical. Relative to other diagnostic groups, ASD toddlers exhibited the highest levels of visual attention towards geometric images and those with especially high fixation levels exhibited poor clinical profiles. Using the 69% fixation threshold, the GeoPref Test had 98% specificity, 17% sensitivity, 81% PPV, and 65% NPV. Sensitivity increased to 33% when saccades were included, with comparable validity across sex, ethnicity, or race. The GeoPref Test was also highly reliable up to 24 months following the initial test. Finally, fixation levels among twins concordant for ASD were significantly correlated, indicating that GeoPref Test performance may be genetically driven. As the GeoPref Test yields few false positives (~ 2%) and is equally valid across demographic categories, the current findings highlight the ability of the GeoPref Test to rapidly and accurately detect autism before the 2nd birthday in a subset of children and serve as a biomarker for a unique ASD subtype in clinical trials.

Get SET Early to Identify and Treatment Refer Autism Spectrum Disorder at 1 Year and Discover Factors That Influence Early Diagnosis.

OBJECTIVES: To examine the impact of a new approach, Get SET Early, on the rates of early autism spectrum disorder (ASD) detection and factors that influence the screen-evaluate-treat chain. STUDY DESIGN: After attending Get SET Early training, 203 pediatricians administered 57 603 total screens using the Communication and Symbolic Behavior Scales Infant-Toddler Checklist at 12-, 18-, and 24-month well-baby examinations, and parents designated presence or absence of concern. For screen-positive toddlers, pediatricians specified if the child was being referred for evaluation, and if not, why not. RESULTS: Collapsed across ages, toddlers were evaluated and referred for treatment at a median age of 19 months, and those screened at 12 months (59.4% of sample) by 15 months. Pediatricians referred one-third of screen-positive toddlers for evaluation, citing lack of confidence in the accuracy of screen-positive results as the primary reason for nonreferral. If a parent expressed concerns, referral probability doubled, and the rate of an ASD diagnosis increased by 37%. Of 897 toddlers evaluated, almost one-half were diagnosed as ASD, translating into an ASD prevalence of 1%. CONCLUSIONS: The Get SET Early model was effective at detecting ASD and initiating very early treatment. Results also underscored the need for change in early identification approaches to formally operationalize and incorporate pediatrician judgment and level of parent concern into the process.

Does the Lack of Gender-Specific Apnea-Hypopnea Index Cutoff for Obstructive Sleep Apnea Impact Surgical Selection?

PURPOSE: The apnea-hypopnea index (AHI) is the parameter on which the severity of obstructive sleep apnea (OSA) is based and is also the determinant for both clinicians and third-party payers for surgical procedures. The purpose of this retrospective cross-sectional chart review is to examine differences in symptoms and AHI between men and women with OSA and whether this may impact timing and selection of surgical care. METHODS: Retrospective cross-sectional study of patients aged 18 years and older who presented at a single center for surgical evaluation of OSA from January 2017 to 2020. AHI, oxygen desaturation index, respiratory disturbance index, and lowest oxygen saturation were obtained from polysomnography. The predictor variable was gender, and the outcome variable was AHI. Unadjusted and multivariate adjusted linear regression models were used to compare differences in AHI between gender, controlling for age, body mass index (BMI), Epworth sleepiness scale, and fatigue severity scale. Poisson regression analysis with robust error was used to assess the relative risks of antidepressant and anxiolytic medication use between genders. RESULTS: A total of 408 consecutive new patients seen for surgical evaluation to treat OSA (248 men and 160 women) were included. Median patient age was 40 years for men and 41 years for women. Median AHI for men was 22.1 events per hour and 13.7 for women (P < .001). When adjusted for age and BMI, men have 33.2% higher AHI than women, with age contributing to 2% and BMI contributing to 6% of the difference. When controlling for age, BMI, Epworth sleepiness scale, and fatigue severity scale, women have a 2.2 increased relative risk of taking anxiolytic or antidepressant medications. CONCLUSIONS: Women with OSA seeking surgery in a dedicated sleep practice have 33% lower AHI than men when controlling for age, BMI, and symptoms. Based on our findings, non-gender-specific AHI may handicap the surgeon from offering the full range of available procedures to women with OSA.

Unexpected case of pneumomediastinum and subcutaneous emphysema: primary or secondary aetiology?

A 77-year-old man was admitted with a relapse of antineutrophil cytoplasmic antibody-positive vasculitis with pulmonary involvement and acute kidney injury. There was a background of pulmonary fibrosis (non-specific interstitial pneumonia type pattern) and superadded pulmonary haemorrhage, acute pulmonary oedema and sepsis. The patient was intubated for 4 days and remained dependent on high flow oxygen and continuous positive airway pressure after extubation. A chest radiograph performed 2 weeks after extubation demonstrated unexpected, extensive pneumomediastinum and subcutaneous emphysema. This was confirmed on CT which raised the possibility of a tracheal defect at the level of the prior endotracheal tube cuff position. Tracheal injury was considered clinically unlikely due to the considerable interval since extubation and a short, uneventful intubation period. The cardiothoracic team recommended a diagnostic bronchoscopy but this was felt too high risk by the clinical team. The cause of pneumomediastinum and subcutaneous emphysema remained indeterminate.

Developmental and reproductive effects of chemicals associated with unconventional oil and natural gas operations.

Unconventional oil and gas (UOG) operations have the potential to increase air and water pollution in communities located near UOG operations. Every stage of UOG operation from well construction to extraction, operations, transportation, and distribution can lead to air and water contamination. Hundreds of chemicals are associated with the process of unconventional oil and natural gas production. In this work, we review the scientific literature providing evidence that adult and early life exposure to chemicals associated with UOG operations can result in adverse reproductive health and developmental effects in humans. Volatile organic compounds (VOCs) [including benzene, toluene, ethyl benzene, and xylene (BTEX) and formaldehyde] and heavy metals (including arsenic, cadmium and lead) are just a few of the known contributors to reduced air and water quality that pose a threat to human developmental and reproductive health. The developing fetus is particularly sensitive to environmental factors, which include air and water pollution. Research shows that there are critical windows of vulnerability during prenatal and early postnatal development, during which chemical exposures can cause potentially permanent damage to the growing embryo and fetus. Many of the air and water pollutants found near UOG operation sites are recognized as being developmental and reproductive toxicants; therefore there is a compelling need to increase our knowledge of the potential health consequences for adults, infants, and children from these chemicals through rapid and thorough health research investigation.