Improve Screening Performance Research Articles

A Quality Improvement Project on Team-Based Care for Depression Screening Before and During the COVID-19 Pandemic in a Specialty Clinic.

Depression screening is an important first step to identifying patients who might benefit from depression treatment. Merit-based incentive payment system (MIPS) quality measures can yield financial benefits or losses for healthcare systems, including depression screening. This study aims to (1) develop a team-based care workflow to improve MIPS depression screening in a specialty clinic and (2) modify the workflow to include a virtual nursing and behavioral health resource after the COVID-19 pandemic hit. A quality improvement project, utilizing Lean Six Sigma process improvement methods, was implemented to improve team-based depression screening in a specialty clinic. A multidisciplinary team implemented plan-do-study-act cycles, created educational materials tailored to each role, developed electronic medical record (EMR) tools to alert and assist team members in screening, and ensured the EMR aligned with the MIPS criteria. The percentage of eligible visits where depression screening was performed was analyzed across four study periods: pre-intervention, post-intervention, COVID-19, and recovery. Recovery strategies included developing telehealth workflows, establishing centralized registered nurse triage groups, and using phone-based triage and support resources at virtual visits. Utilizing team-based strategy and available or newly developed tools, the percentage of eligible visits with completed depression screening was as follows: 1.4% pre-intervention, 58.2% post-intervention, 3.5% COVID-19, and 64.0% recovery. With the COVID-19 pandemic outbreak, initially, improved screening performance declined sharply. Recovery was achieved through the revision of workflows, team members, and support tools. A team-based care approach can successfully improve and maintain depression screening in a specialty clinic and was versatile enough to be readapted to virtual visits during the COVID-19 pandemic. In addition to impacting MIPS quality incentives, the depression screening workflows described in this article can be adapted to other uses, including virtual and in-person visits and in other specialty or chronic disease settings.

Enhancing Radiologist Reading Performance by Ordering Screening Mammograms Based on Characteristics That Promote Visual Adaptation.

Background Mammographic background characteristics may stimulate human visual adaptation, allowing radiologists to detect abnormalities more effectively. However, it is unclear whether density, or another image characteristic, drives visual adaptation. Purpose To investigate whether screening performance improves when screening mammography examinations are ordered for batch reading according to mammographic characteristics that may promote visual adaptation. Materials and Methods This retrospective multireader multicase study was performed with mammograms obtained between September 2016 and May 2019. The screening examinations, each consisting of four mammograms, were interpreted by 13 radiologists in three distinct orders: randomly, by increasing volumetric breast density (VBD), and based on a self-supervised learning (SSL) encoding (examinations automatically grouped as "looking similar"). An eye tracker recorded radiologists' eye movements during interpretation. The area under the receiver operating characteristic curve (AUC), sensitivity, and specificity of random-ordered readings were compared with those of VBD- and SSL-ordered readings using mixed-model analysis of variance. Reading time, fixation metrics, and perceived density were compared using Wilcoxon signed-rank tests. Results Mammography examinations (75 with breast cancer, 75 without breast cancer) from 150 women (median age, 55 years [IQR, 50-63]) were read. The examinations ordered by increasing VBD versus randomly had an increased AUC (0.93 [95% CI: 0.91, 0.96] vs 0.92 [95% CI: 0.89, 0.95]; P = .009), without evidence of a difference in specificity (89% [871 of 975] vs 86% [837 of 975], P = .04) and sensitivity (both 81% [794 of 975 vs 788 of 975], P = .78), and a reduced reading time (24.3 vs 27.9 seconds, P < .001), fixation count (47 vs 52, P < .001), and fixation time in malignant regions (3.7 vs 4.6 seconds, P < .001). For SSL-ordered readings, there was no evidence of differences in AUC (0.92 [95% CI: 0.89, 0.95]; P = .70), specificity (84% [820 of 975], P = .37), sensitivity (80% [784 of 975], P = .79), fixation count (54, P = .05), or fixation time in malignant regions (4.6 seconds, P > .99) compared with random-ordered readings. Reading times were significantly higher for SSL-ordered readings compared with random-ordered readings (28.4 seconds, P = .02). Conclusion Screening mammography examinations ordered from low to high VBD improved screening performance while reducing reading and fixation times. © RSNA, 2024 Supplemental material is available for this article. See also the editorial by Grimm in this issue.

HPVsim: An agent-based model of HPV transmission and cervical disease.

In 2020, the WHO launched its first global strategy to accelerate the elimination of cervical cancer, outlining an ambitious set of targets for countries to achieve over the next decade. At the same time, new tools, technologies, and strategies are in the pipeline that may improve screening performance, expand the reach of prophylactic vaccines, and prevent the acquisition, persistence and progression of oncogenic HPV. Detailed mechanistic modelling can help identify the combinations of current and future strategies to combat cervical cancer. Open-source modelling tools are needed to shift the capacity for such evaluations in-country. Here, we introduce the Human papillomavirus simulator (HPVsim), a new open-source software package for creating flexible agent-based models parameterised with country-specific vital dynamics, structured sexual networks, and co-transmitting HPV genotypes. HPVsim includes a novel methodology for modelling cervical disease progression, designed to be readily adaptable to new forms of screening. The software itself is implemented in Python, has built-in tools for simulating commonly-used interventions, includes a comprehensive set of tests and documentation, and runs quickly (seconds to minutes) on a laptop. Performance is greatly enhanced by HPVsim's multiscale modelling functionality. HPVsim is open source under the MIT License and available via both the Python Package Index (via pip install) and GitHub (hpvsim.org).

Early Indicators of the Impact of Using AI in Mammography Screening for Breast Cancer.

Background Retrospective studies have suggested that using artificial intelligence (AI) may decrease the workload of radiologists while preserving mammography screening performance. Purpose To compare workload and screening performance for two cohorts of women who underwent screening before and after AI system implementation. Materials and Methods This retrospective study included 50-69-year-old women who underwent biennial mammography screening in the Capital Region of Denmark. Before AI system implementation (October 1, 2020, to November 17, 2021), all screenings involved double reading. For screenings conducted after AI system implementation (November 18, 2021, to October 17, 2022), likely normal screenings (AI examination score ≤5 before May 3, 2022, or ≤7 on or after May 3, 2022) were single read by one of 19 senior full-time breast radiologists. The remaining screenings were read by two radiologists with AI-assisted decision support. Biopsy and surgical outcomes were retrieved between October 1, 2020, and April 15, 2023, ensuring at least 180 days of follow-up. Screening metrics were compared using the χ2 test. Reading workload reduction was measured as saved screening reads. Results In total, 60 751 and 58 246 women were screened before and after AI system implementation, respectively (median age, 58 years [IQR, 54-64 years] for both cohorts), with a median screening interval before AI of 845 days (IQR, 820-878 days) and with AI of 993 days (IQR, 968-1013 days; P < .001). After AI system implementation, the recall rate decreased by 20.5% (3.09% before AI [1875 of 60 751] vs 2.46% with AI [1430 of 58 246]; P < .001), the cancer detection rate increased (0.70% [423 of 60 751] vs 0.82% [480 of 58 246]; P = .01), the false-positive rate decreased (2.39% [1452 of 60 751] vs 1.63% [950 of 58 246]; P < .001), the positive predictive value increased (22.6% [423 of 1875] vs 33.6% [480 of 1430]; P < .001), the rate of small cancers (≤1 cm) increased (36.6% [127 of 347] vs 44.9% [164 of 365]; P = .02), the rate of node-negative cancers was unchanged (76.7% [253 of 330] vs 77.8% [273 of 351]; P = .73), and the rate of invasive cancers decreased (84.9% [359 of 423] vs 79.6% [382 of 480]; P = .04). The reading workload was reduced by 33.5% (38 977 of 116 492 reads). Conclusion In a population-based mammography screening program, using AI reduced the overall workload of breast radiologists while improving screening performance. Published under a CC BY 4.0 license. Supplemental material is available for this article. See also the editorial by Lee and Friedewald in this issue.

The performance of single and combination test strategies using visual inspection, cytology, high-risk HPV DNA and HPV16/18 to screen South African women with and without HIV-infection

BackgroundCervical cancer screening strategies should ideally be informed by population-specific data. Strategies recommended for secondary prevention, are often inadequately studied in populations with high cervical disease burdens. This report describes the test performance measured against CIN2 + /CIN3 + histology in HIV-positive women (HPW) and HIV-negative women (HNW) with the aim to determine the most effective strategies to identify South African women at risk.MethodsPrimary screening using visual inspection, cytology and HPV DNA (cobas®) was performed in two South African provinces on 456 HPW and 639 HNW participating in the multicentric DiaVACCS trial. Histology was obtained for 91.7% screen-positive and 42.7% screen-negative participants, and unavailable histology was determined by multiple imputation to adjust for verification bias. Cross-sectional test performance was calculated for single and combination test strategies with and without intermediate risk categories using different cut-offs. Minimum acceptability for sensitivity and specificity, treatment and follow-up numbers were considered to evaluate strategies.ResultsThe only single test to reach acceptability in HPW was cytology (LSIL) [sensitivity 71.2%; specificity 90.5%; treatment 33.4%]; in HNW only HPV (hr) qualified [sensitivity 68.2%; specificity 85.2%; treatment 23.5%]. The universally best performing strategy which also resulted in smaller treatment numbers without intermediate risk group was primary HPV(hr), with treatment of both HPV(16/18) and cytology (ASCUS +) [HPW: sensitivity 73.6%; specificity 89.7%; treatment 34.7%. HNW: sensitivity 59.1%; specificity 93.6%; treatment 13.9%].DNA testing for hrHPV (any) and hrHPV (16/18) was the best universally acceptable strategy with an intermediate risk category (early follow-up) in HPW [sensitivity 82.1%; specificity 96.4%; treatment 17.1%; follow-up 31.4%] and HNW [sensitivity 68.2%; specificity 96.7%; treatment 7.6%; follow-up 15.9%]. In comparison, using both HPV (16/18) and cytology (ASCUS +) as secondary tests in hrHPV positive women, decreased follow-up [HPW 13.8%, HNW 9.6%], but increased treatment [HPW 34.7%, HNW 13.9%].ConclusionUsing hrHPV (any) as primary and both HPV16/18 and cytology as secondary tests, was universally acceptable without an intermediate risk group. Strategies with follow-up groups improved screening performance with smaller treatment numbers, but with effective management of the intermediate risk group as prerequisite.

Evaluation of reticulocyte indices and mathematical formulas for beta-thalassemia carriers screening among Egyptian beta-thalassemia patients’ families

Background Egypt lies within the global thalassemia belt, where beta-thalassemia presents a notable socioeconomic burden. Patients and methods One hundred fifty-seven relatives of beta-thalassemia patients were included in this cross-sectional study. It aimed to ascertain a cost-efficient and accurate screening approach for identifying beta-thalassemia carriers (BTC) by evaluating some erythrocyte and reticulocyte parameters measured on Advia 2120 analyzer (Siemens) and assessing four mathematical Formulas (Metzner index, Green and King et al., Roth et al., and Vicinanza et al. formulas). Results Participants were stratified into distinct categories: BTC (42%), normal (24.2%), mild iron-deficiency anemia (IDA) (17.2%), severe IDA (3.8%), and a subset with both IDA and BTC (mix group) accounting for 12.7%. Receiver operating characteristic curve analysis identified absolute reticulocyte count as the optimal discriminator (area under a curve=0.837) between BTC and IDA. The Mentzer index and Green and King et al. formula demonstrated superior diagnostic utility among the evaluated formulas. However, none of the formulas effectively distinguished between BTC and the mix group, a frequently overlooked and challenging group for diagnosis. Interestingly, our data highlighted absolute reticulocyte count and percentage as the sole parameters capable of distinguishing BTC from the mix group. Consequently, two algorithms were developed. The first one had a good agreement (κ=0.62) with 77.3% concordance, while the second one demonstrated improved screening performance (κ=0.66) with 79.8% agreement. Conclusion The optimal screening strategy involves distinguishing between various categories of both IDA and BTC. Our algorithms, designed as a low-cost and user-friendly mass screening tool, may serve this purpose effectively.

Risk Model–Based Lung Cancer Screening and Racial and Ethnic Disparities in the US

The revised 2021 US Preventive Services Task Force (USPSTF) guidelines for lung cancer screening have been shown to reduce disparities in screening eligibility and performance between African American and White individuals vs the 2013 guidelines. However, potential disparities across other racial and ethnic groups in the US remain unknown. Risk model-based screening may reduce racial and ethnic disparities and improve screening performance, but neither validation of key risk prediction models nor their screening performance has been examined by race and ethnicity. To validate and recalibrate the Prostate, Lung, Colorectal, and Ovarian Cancer Screening Trial 2012 (PLCOm2012) model-a well-established risk prediction model based on a predominantly White population-across races and ethnicities in the US and evaluate racial and ethnic disparities and screening performance through risk-based screening using PLCOm2012 vs the USPSTF 2021 criteria. In a population-based cohort design, the Multiethnic Cohort Study enrolled participants in 1993-1996, followed up through December 31, 2018. Data analysis was conducted from April 1, 2022, to May 19. 2023. A total of 105 261 adults with a smoking history were included. The 6-year lung cancer risk was calculated through recalibrated PLCOm2012 (ie, PLCOm2012-Update) and screening eligibility based on a 6-year risk threshold greater than or equal to 1.3%, yielding similar eligibility as the USPSTF 2021 guidelines. Predictive accuracy, screening eligibility-incidence (E-I) ratio (ie, ratio of the number of eligible to incident cases), and screening performance (sensitivity, specificity, and number needed to screen to detect 1 lung cancer). Of 105 261 participants (60 011 [57.0%] men; mean [SD] age, 59.8 [8.7] years), consisting of 19 258 (18.3%) African American, 27 227 (25.9%) Japanese American, 21 383 (20.3%) Latino, 8368 (7.9%) Native Hawaiian/Other Pacific Islander, and 29 025 (27.6%) White individuals, 1464 (1.4%) developed lung cancer within 6 years from enrollment. The PLCOm2012-Update showed good predictive accuracy across races and ethnicities (area under the curve, 0.72-0.82). The USPSTF 2021 criteria yielded a large disparity among African American individuals, whose E-I ratio was 53% lower vs White individuals (E-I ratio: 9.5 vs 20.3; P < .001). Under the risk-based screening (PLCOm2012-Update 6-year risk ≥1.3%), the disparity between African American and White individuals was substantially reduced (E-I ratio: 15.9 vs 18.4; P < .001), with minimal disparities observed in persons of other minoritized groups, including Japanese American, Latino, and Native Hawaiian/Other Pacific Islander. Risk-based screening yielded superior overall and race and ethnicity-specific performance to the USPSTF 2021 criteria, with higher overall sensitivity (67.2% vs 57.7%) and lower number needed to screen (26 vs 30) at similar specificity (76.6%). The findings of this cohort study suggest that risk-based lung cancer screening can reduce racial and ethnic disparities and improve screening performance across races and ethnicities vs the USPSTF 2021 criteria.

OC16.05: First trimester anomaly scan: which anomalies can we reliably detect and how can we improve screening performance?

OC16.05: First trimester anomaly scan: which anomalies can we reliably detect and how can we improve screening performance?

Synthetic Mammography: Benefits, Drawbacks, and Pitfalls.

Digital breast tomosynthesis (DBT) allows three-dimensional assessment of breast tissue; however, DBT requires a two-dimensional (2D) image for comparison with prior mammograms and accurate interpretation of calcifications. Traditionally, full-field digital mammography (FFDM) has been performed after the DBT image acquisition. Synthetic mammography (SM), the 2D reconstruction of the tomosynthesis slice dataset, has been designed to replace FFDM. Advantages of SM include decreased image acquisition time and decreased radiation exposure, with maintained or improved screening performance metrics. Because SM algorithms give extra weight to lesion-like characteristics (eg, calcifications and architectural distortions), they may enable increased visibility of these characteristics relative to that at FFDM. Although SM algorithms were designed to improve lesion identification, they have led to varied outcomes in studies reported in the literature. Compared with FFDM, SM has been reported to be associated with a higher false-positive rate for calcifications, decreased conspicuity of asymmetries, lower breast density assessments, and imaging artifacts (eg, metallic artifact, bright-band artifact, blurring of the axilla, and truncation artifact). The authors review the literature on SM, including its implementation, benefits, and artifacts. ©RSNA, 2023 Quiz questions for this article are available through the Online Learning Center.

Optimizing the Pairs of Radiologists That Double Read Screening Mammograms.

Background Despite variation in performance characteristics among radiologists, the pairing of radiologists for the double reading of screening mammograms is performed randomly. It is unknown how to optimize pairing to improve screening performance. Purpose To investigate whether radiologist performance characteristics can be used to determine the optimal set of pairs of radiologists to double read screening mammograms for improved accuracy. Materials and Methods This retrospective study was performed with reading outcomes from breast cancer screening programs in Sweden (2008-2015), England (2012-2014), and Norway (2004-2018). Cancer detection rates (CDRs) and abnormal interpretation rates (AIRs) were calculated, with AIR defined as either reader flagging an examination as abnormal. Individual readers were divided into performance categories based on their high and low CDR and AIR. The performance of individuals determined the classification of pairs. Random pair performance, for which any type of pair was equally represented, was compared with the performance of specific pairing strategies, which consisted of pairs of readers who were either opposite or similar in AIR and/or CDR. Results Based on a minimum number of examinations per reader and per pair, the final study sample consisted of 3 592 414 examinations (Sweden, n = 965 263; England, n = 837 048; Norway, n = 1 790 103). The overall AIRs and CDRs for all specific pairing strategies (Sweden AIR range, 45.5-56.9 per 1000 examinations and CDR range, 3.1-3.6 per 1000; England AIR range, 68.2-70.5 per 1000 and CDR range, 8.9-9.4 per 1000; Norway AIR range, 81.6-88.1 per 1000 and CDR range, 6.1-6.8 per 1000) were not significantly different from the random pairing strategy (Sweden AIR, 54.1 per 1000 examinations and CDR, 3.3 per 1000; England AIR, 69.3 per 1000 and CDR, 9.1 per 1000; Norway AIR, 84.1 per 1000 and CDR, 6.3 per 1000). Conclusion Pairing a set of readers based on different pairing strategies did not show a significant difference in screening performance when compared with random pairing. © RSNA, 2023.

The Current Role of the sFlt-1/PlGF Ratio and the Uterine-Umbilical-Cerebral Doppler Ultrasound in Predicting and Monitoring Hypertensive Disorders of Pregnancy: An Update with a Review of the Literature.

Regarding the hypertensive disorders of pregnancy, pre-eclampsia (PE) remains one of the leading causes of severe and life-threatening maternal and fetal complications. Screening of early-onset PE (<34 weeks of pregnancy), as well as late-onset PE (≥34 weeks), shows poor performance if based solely on clinical features. In recent years, biochemical markers from maternal blood-the pro-angiogenic protein placental growth factor (PlGF) and the antiangiogenic protein soluble FMS-like tyrosine kinase 1 (sFlt-1)-and Doppler velocimetry indices-primarily the mean uterine pulsatility index (PI), but also the uterine resistivity index (RI), the uterine systolic/diastolic ratio (S/D), uterine and umbilical peak systolic velocity (PSV), end-diastolic velocity (EDV), and uterine notching-have all shown improved screening performance. In this review, we summarize the current status of knowledge regarding the role of biochemical markers and Doppler velocimetry indices in early prediction of the onset and severity of PE and other placenta-related disorders, as well as their role in monitoring established PE and facilitating improved obstetrical surveillance of patients categorized as high-risk in order to prevent adverse outcomes. A sFlt-1/PlGF ratio ≤ 33 ruled out early-onset PE with 95% sensitivity and 94% specificity, whereas a sFlt-1/PlGF ≥88 predicted early-onset PE with 88.0% sensitivity and 99.5% specificity. Concerning the condition's late-onset form, sFlt-1/PlGF ≤ 33 displayed 89.6% sensitivity and 73.1% specificity in ruling out the condition, whereas sFlt-1/PlGF ≥ 110 predicted the condition with 58.2% sensitivity and 95.5% specificity. The cut-off values of the sFlt-1/PlGF ratio for the screening of PE were established in the PROGNOSIS study: a sFlt-1/PlGF ratio equal to or lower than 38 ruled out the onset of PE within one week, regardless of the pregnancy's gestational age. The negative predictive value in this study was 99.3%. In addition, sFlt-1/PlGF > 38 showed 66.2% sensitivity and 83.1% specificity in predicting the occurrence of PE within 4 weeks. Furthermore, 2018 ISUOG Practice Guidelines stated that a second-trimester mean uterine artery PI ≥ 1.44 increases the risk of later PE development. The implementation of a standard screening procedure based on the sFlt-1/PlGF ratio and uterine Doppler velocimetry may improve early detection of pre-eclampsia and other placenta-related disorders.

Evaluation of first trimester maternal serum inhibin-A for preeclampsia screening.

International professional organizations recommend aspirin prophylaxis to women screened high risk for preterm preeclampsia (PE) in the first trimester. The UK Fetal Medicine Foundation (FMF) screening test for preterm PE using mean arterial pressure (MAP), uterine artery pulsatility index (UTPI) and placental growth factor (PlGF) was demonstrated to have lower detection rate (DR) in Asian population studies. Additional biomarkers are therefore needed in Asian women to improve screening DRs as a significant proportion of women with preterm and term PE are currently not identified. To evaluate maternal serum inhibin-A at 11-13 weeks as an alternative to PlGF or as an additional biomarker within the FMF screening test for preterm PE. This is a nested case-control study using pregnancies initially screened at 11-13 weeks for preterm PE using the FMF triple test in a non-intervention study conducted between December 2016 and June 2018. Inhibin-A levels were retrospectively measured in 1,792 singleton pregnancies, 112 (1.7%) with PE matched for time of initial screening with 1,680 unaffected pregnancies. Inhibin-A levels were transformed to multiple of the expected median (MoM). The distribution of log10 inhibin-A MoM in PE and unaffected pregnancies and the association between log10 inhibin-A MoM and gestational age (GA) at delivery in PE were assessed. The screening performance determined by area under receiver operating characteristic curves (AUC) and detection rates (DRs) at a 10% fixed false positive rate (FPR), for preterm and term PE was determined. All risks for preterm and term PE were based on the FMF competing risk model and Bayes theorem. Differences in AUC (ΔAUC) between different biomarker combinations were compared using the Delong test. McNemar's test was used to assess the off-diagonal change in screening performance at a fixed 10% FPR after adding inhibin-A or replacing PlGF in the preterm PE adjusted risk estimation model. Inhibin-A levels in unaffected pregnancies were significantly dependent on GA, maternal age and weight and were lower in parous women with no previous history of PE. Mean log10 inhibin-A MoM in any-onset PE (p<0.001), preterm (p<0.001) and term PE (p = 0.015) pregnancies were all significantly higher than that of unaffected pregnancies. Log10 inhibin-A MoM was inversely but not significantly correlated (p = 0.165) with GA at delivery in PE pregnancies. Replacing PlGF with inhibin-A in the FMF triple test reduced AUC and DR from 0.859 and 64.86% to 0.837 and 54.05%, the ΔAUC was not statistically significant. AUC and DR when adding inhibin-A to the FMF triple test were 0.814, 54.05% and the -0.045 reduction in AUC was statistically significant (p = 0.001). At a fixed 10% FPR, replacing PlGF with inhibin-A identified 1 (2.7%) additional pregnancy but missed 5 (13.5%) pregnancies which subsequently developed preterm PE identified by the FMF triple test. Adding inhibin-A missed 4 (10.8%) pregnancies and did not identify any additional pregnancies with preterm PE. Replacing PlGF by inhibin-A or adding inhibin-A as an additional biomarker in and to the FMF triple screening test for preterm PE does not improve screening performance and will fail to identify pregnancies that are currently identified by the FMF triple test.

Multi-vendor evaluation of artificial intelligence as an independent reader for double reading in breast cancer screening on 275,900 mammograms

BackgroundDouble reading (DR) in screening mammography increases cancer detection and lowers recall rates, but has sustainability challenges due to workforce shortages. Artificial intelligence (AI) as an independent reader (IR) in DR may provide a cost-effective solution with the potential to improve screening performance. Evidence for AI to generalise across different patient populations, screening programmes and equipment vendors, however, is still lacking.MethodsThis retrospective study simulated DR with AI as an IR, using data representative of real-world deployments (275,900 cases, 177,882 participants) from four mammography equipment vendors, seven screening sites, and two countries. Non-inferiority and superiority were assessed for relevant screening metrics.ResultsDR with AI, compared with human DR, showed at least non-inferior recall rate, cancer detection rate, sensitivity, specificity and positive predictive value (PPV) for each mammography vendor and site, and superior recall rate, specificity, and PPV for some. The simulation indicates that using AI would have increased arbitration rate (3.3% to 12.3%), but could have reduced human workload by 30.0% to 44.8%.ConclusionsAI has potential as an IR in the DR workflow across different screening programmes, mammography equipment and geographies, substantially reducing human reader workload while maintaining or improving standard of care.Trial registrationISRCTN18056078 (20/03/2019; retrospectively registered).

Sure Joint Screening for High Dimensional Cox's Proportional Hazards Model Under the Case-Cohort Design.

This study develops a sure joint feature screening method for the case-cohort design with ultrahigh-dimensional covariates. Our method is based on a sparsity-restricted Cox proportional hazards model. An iterative reweighted hard thresholding algorithm is proposed to approximate the sparsity-restricted, pseudo-partial likelihood estimator for joint screening. We rigorously show that our method possesses the sure screening property, with the probability of retaining all relevant covariates tending to 1 as the sample size goes to infinity. Our simulation results demonstrate that the proposed procedure has substantially improved screening performance over some existing feature screening methods for the case-cohort design, especially when some covariates are jointly correlated, but marginally uncorrelated, with the event time outcome. A real data illustration is provided using breast cancer data with high-dimensional genomic covariates. We have implemented the proposed method using MATLAB and made it available to readers through GitHub.

Fractionated Bilirubin Among 252 892 Utah Newborns with and Without Biliary Atresia: A 15-year Historical Birth Cohort Study

To determine whether neonatal conjugated or direct bilirubin levels were elevated in infants with biliary atresia, and to estimate the number of newborns that would have positive screens in the nursery necessitating repeat testing following discharge. We used administrative data from a large integrated healthcare network in Utah to identify newborns who had a fractionated bilirubin recorded during birth admission from 2005 through 2019. Elevated conjugated bilirubin was defined as greater than 0.2 mg/dL and direct bilirubin was defined as greater than 0.5 mg/dL (>97.5th percentile for the assays). We performed simulations to estimate the anticipated number of false positive screens. There were 32 cases of biliary atresia and 468,161 live births during the study period (1/14,700). 252,892 newborns had fractionated bilirubin assessed including 26 of those subsequently confirmed to have biliary atresia. Conjugated or direct bilirubin was elevated in all 26 infants with biliary atresia and an additional 3,246 (1.3%) newborns without biliary atresia. Simulated data suggest nine to 21 per 1,000 screened newborns will have an elevated conjugated or direct bilirubin using laboratory-based thresholds for a positive screen. Screening characteristics improved with higher thresholds without increasing false negative tests. This study validates the previous findings that conjugated or direct bilirubin are elevated in the newborn period in patients with biliary atresia. A higher threshold for conjugated bilirubin improved screening performance. Future studies are warranted to determine the optimal screening test for biliary atresia and to assess the effectiveness and cost-effectiveness of implementing such a program.

Australian women's judgements about using artificial intelligence to read mammograms in breast cancer screening.

Mammographic screening for breast cancer is an early use case for artificial intelligence (AI) in healthcare. This is an active area of research, mostly focused on the development and evaluation of individual algorithms. A growing normative literature argues that AI systems should reflect human values, but it is unclear what this requires in specific AI implementation scenarios. Our objective was to understand women's values regarding the use of AI to read mammograms in breast cancer screening. We ran eight online discussion groups with a total of 50 women, focused on their expectations and normative judgements regarding the use of AI in breast screening. Although women were positive about the potential of breast screening AI, they argued strongly that humans must remain as central actors in breast screening systems and consistently expressed high expectations of the performance of breast screening AI. Women expected clear lines of responsibility for decision-making, to be able to contest decisions, and for AI to perform equally well for all programme participants. Women often imagined both that AI might replace radiographers and that AI implementation might allow more women to be screened: screening programmes will need to communicate carefully about these issues. To meet women's expectations, screening programmes should delay implementation until there is strong evidence that the use of AI systems improves screening performance, should ensure that human expertise and responsibility remain central in screening programmes, and should avoid using AI in ways that exacerbate inequities.

Screening for obstructive sleep apnoea in post-treatment cancer patients.

For cancer patients, comorbid obstructive sleep apnea (OSA) poses additional risk to their surgical/anaesthetic outcomes, quality of life, and survival. However, OSA screening is not well-established in oncology settings. We tested two screening tools (STOP-Bang questionnaire [SBQ] and the at-home monitoring device, ApneaLink™Air), for predicting polysomnography (PSG) confirmed OSA in post-treatment cancer patients. Breast (n=56), endometrial (n=37) and melanoma patients (n=50) were recruited from follow-up clinics at Westmead Hospital (Sydney, Australia). All underwent overnight PSG, 137 completed SBQ, and 99 completed ApneaLink™Air. Positive (PPV) and negative (NPV) predictive values for PSG-determined moderate-to-severe OSA and severe OSA, were calculated using an SBQ threshold ≥3 au and ApneaLink™Air apnoea-hypopnea index thresholds of ≥10, ≥15 and ≥30 events/h. Both SBQ and ApneaLink™Air had high NPVs (92.7% and 85.2%-95.6% respectively) for severe OSA, but NPVs were lower for moderate-to-severe OSA (69.1% and 59.1%-75.5%, respectively). PPV for both tools were relatively low (all <73%). Combining both tools did not improve screening performance. These screening tools may help identify cancer patients without severe OSA, but both are limited in identifying those with moderate-to-severe or severe OSA. PSG remains optimal for adequately identifying and managing comorbid OSA in cancer patients.

Methylation of HPV16 and EPB41L3 in oral gargles and the detection of early and late oropharyngeal cancer.

As oropharyngeal cancer (OPC) associated with human papillomavirus (HPV) increases in men, the need for a screening test to diagnose OPC early is crucial. While HPV‐associated OPC has a favorable prognosis, recurrence is likely, and metastatic OPC is often incurable regardless of HPV status. Our previous study of pretreatment, male OPC cases (n = 101) and age‐ and smoking‐matched controls (n = 101) found methylation of the host EPB41L3 tumor suppressor gene and HPV16 in the oral gargle was correlated with these biomarkers in the tumor. Methylation of these genes in the oral gargle was significantly (p < 0.0001) higher among cases compared to controls. To further study the utility of HPV16/EPB41L3 methylation, we expanded the sample size and specifically increased the number of early OPC cases (T1‐T2, N0‐N1; small tumors with a single ipsilateral node <3 cm) to evaluate these biomarkers in early and late OPC. This study included 228 OPC cases, 92 of which were early cases and frequency matched to 142 healthy controls. In logistic regression, the AUC for HPV16/EPB41L3 methylation for all OPC cases was 0.82. Among early and late OPC cases, the AUC was 0.78 and 0.85, respectively. For early cases, 76% sensitivity was achieved, replicating results from our prior study, with a specificity of 65%, indicating room for improvement. The ability of HPV16/EPB41L3 methylation to distinguish OPC from healthy controls highlights its utility as a potential biomarker for OPC. However, the inability to predict early OPC better than late stage OPC indicates the need for additional biomarkers to improve screening performance.

Cervical cancer screening guidelines and screening practices in 11 countries: A systematic literature review

The World Health Organization (WHO) advocates population-based screening programs to reduce the global incidence of cervical cancer. However, screening guidelines and practice continually change to reflect scientific developments. Here we describe and compare cervical cancer screening guidelines and clinical practice in 11 countries across North America, Europe, and Asia-Pacific. We conducted a systematic literature review (SLR) complemented by a targeted literature review (TLR) to identify relevant peer-reviewed publications and policy documents, which include 120 publications, of which 86 were identified from the SLR and 34 from the TLR. Only six of 11 countries assessed have population-based screening programs in place. Considerable differences persist across countries’ screening guidelines, even among comparable systems. Moreover, methods of data collection are also heterogenous, and systematic data collection is often not established. As future changes in screening guidelines and clinical practice occur (e.g., when the first cohorts of women vaccinated against HPV reach screening age), systematic collection of screening data is essential to monitor and improve screening performance.

Synthetic Mammography: Review of Benefits and Drawbacks in Clinical Use.

Digital breast tomosynthesis (DBT) has been widely adopted as a breast cancer screening tool, demonstrating decreased recall rates and other improved screening performance metrics when compared to digital mammography (DM) alone. Drawbacks of DBT when added to 2D DM include the increased radiation dose and longer examination time. Synthetic mammography (SM), a 2D reconstruction from the tomosynthesis slices, has been introduced to eliminate the need for a separate acquisition of 2D DM. Data show that the replacement of 2D DM by SM, when used with DBT, maintains the benefits of DBT, such as decreased recall rates, improved cancer detection rates, and similar positive predictive values. Key differences between SM and 2D DM include how the image is acquired, assessment of breast density, and visualization of mammographic findings, such as calcifications. Although SM is approved by the Food and Drug Administration and has been shown to be non-inferior when used with DBT, concerns surrounding SM include image quality and artifacts. The purpose of this review article is to review the benefits, drawbacks, and screening performance metrics of SM versus DBT.