Screening and Selection: The Case of Mammograms.
Ontology highlight
ABSTRACT:
SUBMITTER: Einav L
PROVIDER: S-EPMC8300583 | biostudies-literature | 2020 Dec
REPOSITORIES: biostudies-literature
Publications
Screening and Selection: The Case of Mammograms.
Einav Liran L Finkelstein Amy A Oostrom Tamar T Ostriker Abigail A Williams Heidi H
The American economic review 20201201 12
We analyze selection into screening in the context of recommendations that breast cancer screening start at age 40. Combining medical claims with a clinical oncology model, we document that compliers with the recommendation are less likely to have cancer than younger women who select into screening or women who never screen. We show this selection is quantitatively important: shifting the recommendation from age 40 to 45 results in three times as many deaths if compliers were randomly selected t ...[more]
Similar Datasets
Project description:ObjectiveTo investigate whether decreased anxiety associated with immediate reading of screening mammograms resulted in lower downstream utilization and costs among women with false-positive mammograms.Data sources/study settingWe identified 1,140 women, > or =age 40, with false-positive mammograms and 12-month follow-up after participating in a trial of immediate versus batch mammographic reading between February 1999 and January 2001 in a multispecialty group managed care practice in Massachusetts.Study designWe determined downstream utilization and costs for study participants by immediate and batch reading status.Data collection/extraction methodsDemographic, comorbidity, and medical care utilization data were obtained from survey data and computerized medical record databases. Costs included direct medical costs, patient time, travel and copayments, and additional professional time costs associated with immediate reading.Principal findingsImmediate reading cost an additional $4.40 per screening mammogram. Women with immediate readings had more follow-up mammograms (781 versus 750, p=.018) and fewer diagnostic ultrasounds (176 versus 219, p=.016) than women with batch readings. Costs to the health plan for breast care were approximately 10 percent higher for immediate readings in multivariable analyses (p=.046), but no significant difference was seen in total societal costs (p=.072).ConclusionsImmediate mammogram reading was associated with increased costs to the health plan and changes in follow-up radiology procedures. These costs must be examined alongside beneficial effects of immediate reading.
| S-EPMC1955276 | biostudies-literature
Project description:ObjectiveFat-infiltrated axillary lymph nodes (LNs) are unique sites for ectopic fat deposition. Early studies showed a strong correlation between fatty LNs and obesity-related diseases. Confirming this correlation requires large-scale studies, hindered by scarce labeled data. With the long-term goal of developing a rapid and generalizable tool to aid data labeling, we developed an automated deep learning (DL)-based pipeline to classify the status of fatty LNs on screening mammograms.MethodsOur internal data set included 886 mammograms from a tertiary academic medical institution, with a binary status of the fat-infiltrated LNs based on the size and morphology of the largest visible axillary LN. A two-stage DL model training and fine-tuning pipeline was developed to classify the fat-infiltrated LN status using the internal training and development data set. The model was evaluated on a held-out internal test set and a subset of the Digital Database for Screening Mammography.ResultsOur model achieved 0.97 (95% CI: 0.94-0.99) accuracy and 1.00 (95% CI: 1.00-1.00) area under the receiver operator characteristic curve on 264 internal testing mammograms, and 0.82 (95% CI: 0.77-0.86) accuracy and 0.87 (95% CI: 0.82-0.91) area under the receiver operator characteristic curve on 70 external testing mammograms.ConclusionThis study confirmed the feasibility of using a DL model for fat-infiltrated LN classification. The model provides a practical tool to identify fatty LNs on mammograms and to allow for future large-scale studies to evaluate the role of fatty LNs as an imaging biomarker of obesity-associated pathologies.Advances in knowledgeOur study is the first to classify fatty LNs using an automated DL approach.
| S-EPMC10607412 | biostudies-literature
Project description:ImportanceMammography screening currently relies on subjective human interpretation. Artificial intelligence (AI) advances could be used to increase mammography screening accuracy by reducing missed cancers and false positives.ObjectiveTo evaluate whether AI can overcome human mammography interpretation limitations with a rigorous, unbiased evaluation of machine learning algorithms.Design, setting, and participantsIn this diagnostic accuracy study conducted between September 2016 and November 2017, an international, crowdsourced challenge was hosted to foster AI algorithm development focused on interpreting screening mammography. More than 1100 participants comprising 126 teams from 44 countries participated. Analysis began November 18, 2016.Main outcomes and measurementsAlgorithms used images alone (challenge 1) or combined images, previous examinations (if available), and clinical and demographic risk factor data (challenge 2) and output a score that translated to cancer yes/no within 12 months. Algorithm accuracy for breast cancer detection was evaluated using area under the curve and algorithm specificity compared with radiologists' specificity with radiologists' sensitivity set at 85.9% (United States) and 83.9% (Sweden). An ensemble method aggregating top-performing AI algorithms and radiologists' recall assessment was developed and evaluated.ResultsOverall, 144 231 screening mammograms from 85 580 US women (952 cancer positive ≤12 months from screening) were used for algorithm training and validation. A second independent validation cohort included 166 578 examinations from 68 008 Swedish women (780 cancer positive). The top-performing algorithm achieved an area under the curve of 0.858 (United States) and 0.903 (Sweden) and 66.2% (United States) and 81.2% (Sweden) specificity at the radiologists' sensitivity, lower than community-practice radiologists' specificity of 90.5% (United States) and 98.5% (Sweden). Combining top-performing algorithms and US radiologist assessments resulted in a higher area under the curve of 0.942 and achieved a significantly improved specificity (92.0%) at the same sensitivity.Conclusions and relevanceWhile no single AI algorithm outperformed radiologists, an ensemble of AI algorithms combined with radiologist assessment in a single-reader screening environment improved overall accuracy. This study underscores the potential of using machine learning methods for enhancing mammography screening interpretation.
| S-EPMC7052735 | biostudies-literature
Project description:Breast cancer is the most common cancer diagnosed in women worldwide. Up to 50% of non-palpable breast cancers are detected solely through microcalcification clusters in mammograms. This article presents a novel and completely automated algorithm for the detection of microcalcification clusters in a mammogram. A multiscale 2D non-linear energy operator is proposed for enhancing the contrast between the microcalcifications and the background. Several texture, shape, intensity, and histogram of oriented gradients (HOG)-based features are used to distinguish microcalcifications from other brighter mammogram regions. A new majority class data reduction technique based on data distribution is proposed to counter data imbalance problem. The algorithm is able to achieve 100% sensitivity with 2.59, 1.78, and 0.68 average false positives per image on Digital Database for Screening Mammography (scanned film), INbreast (direct radiography) database, and PGIMER-IITKGP mammogram (direct radiography) database, respectively. Thus, it might be used as a second reader as well as a screening tool to reduce the burden on radiologists.
| S-EPMC6737166 | biostudies-literature
Project description:We sought to estimate the direct cost, from the perspective of the health insurer or purchaser, of breast-care services in the year following a false positive screening mammogram compared with a true negative examination.We identified 21,125 women aged 40 to 80 years enrolled in an integrated healthcare delivery system in Washington State, who participated in screening mammography between January 1, 1998 and July 30, 2002. Pathology and cancer registry data were used to identify breast cancer diagnoses in the year following the screening mammogram. A positive examination was defined as a Breast Imaging Reporting and Data System assessment of 0, 4, or 5. Women with a positive screening mammogram but no breast cancer diagnosed within 1 year were classified as false positives. We used diagnostic and procedure codes in automated health plan data to identify services received in the year following the screening mammogram. Medicare reimbursement rates were applied to all services. We used ordinary least-squares linear regression to estimate the difference in costs following a false positive versus true negative screening mammogram.False positive results occurred in 9.9% of women; most false positives (87.3%) were followed by breast imaging only. The mean cost of breast-care following a false positive mammogram was $527. This was $503 (95% confidence interval, $490-$515) more than the cost of breast-care services for true negative women.The direct costs for breast-related procedures following false positive screening mammograms may contribute substantially to US healthcare spending.
| S-EPMC3079487 | biostudies-literature
Project description:ImportanceA computer algorithm that performs at or above the level of radiologists in mammography screening assessment could improve the effectiveness of breast cancer screening.ObjectiveTo perform an external evaluation of 3 commercially available artificial intelligence (AI) computer-aided detection algorithms as independent mammography readers and to assess the screening performance when combined with radiologists.Design, setting, and participantsThis retrospective case-control study was based on a double-reader population-based mammography screening cohort of women screened at an academic hospital in Stockholm, Sweden, from 2008 to 2015. The study included 8805 women aged 40 to 74 years who underwent mammography screening and who did not have implants or prior breast cancer. The study sample included 739 women who were diagnosed as having breast cancer (positive) and a random sample of 8066 healthy controls (negative for breast cancer).Main outcomes and measuresPositive follow-up findings were determined by pathology-verified diagnosis at screening or within 12 months thereafter. Negative follow-up findings were determined by a 2-year cancer-free follow-up. Three AI computer-aided detection algorithms (AI-1, AI-2, and AI-3), sourced from different vendors, yielded a continuous score for the suspicion of cancer in each mammography examination. For a decision of normal or abnormal, the cut point was defined by the mean specificity of the first-reader radiologists (96.6%).ResultsThe median age of study participants was 60 years (interquartile range, 50-66 years) for 739 women who received a diagnosis of breast cancer and 54 years (interquartile range, 47-63 years) for 8066 healthy controls. The cases positive for cancer comprised 618 (84%) screen detected and 121 (16%) clinically detected within 12 months of the screening examination. The area under the receiver operating curve for cancer detection was 0.956 (95% CI, 0.948-0.965) for AI-1, 0.922 (95% CI, 0.910-0.934) for AI-2, and 0.920 (95% CI, 0.909-0.931) for AI-3. At the specificity of the radiologists, the sensitivities were 81.9% for AI-1, 67.0% for AI-2, 67.4% for AI-3, 77.4% for first-reader radiologist, and 80.1% for second-reader radiologist. Combining AI-1 with first-reader radiologists achieved 88.6% sensitivity at 93.0% specificity (abnormal defined by either of the 2 making an abnormal assessment). No other examined combination of AI algorithms and radiologists surpassed this sensitivity level.Conclusions and relevanceTo our knowledge, this study is the first independent evaluation of several AI computer-aided detection algorithms for screening mammography. The results of this study indicated that a commercially available AI computer-aided detection algorithm can assess screening mammograms with a sufficient diagnostic performance to be further evaluated as an independent reader in prospective clinical trials. Combining the first readers with the best algorithm identified more cases positive for cancer than combining the first readers with second readers.
| S-EPMC7453345 | biostudies-literature
Project description:ObjectiveMammographic 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.MethodsWe 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.ResultsAlthough 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.ConclusionsTo 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.
| S-EPMC10408316 | biostudies-literature
Project description:PurposeTo develop a model that simulates radiologist assessments and use it to explore whether pairing readers based on their individual performance characteristics could optimize screening performance.MethodsLogistic regression models were designed and used to model individual radiologist assessments. For model evaluation, model-predicted individual performance metrics and paired disagreement rates were compared against the observed data using Pearson correlation coefficients. The logistic regression models were subsequently used to simulate different screening programs with reader pairing based on individual true-positive rates (TPR) and/or false-positive rates (FPR). For this, retrospective results from breast cancer screening programs employing double reading in Sweden, England, and Norway were used. Outcomes of random pairing were compared against those composed of readers with similar and opposite TPRs/FPRs, with positive assessments defined by either reader flagging an examination as abnormal.ResultsThe analysis data sets consisted of 936,621 (Sweden), 435,281 (England), and 1,820,053 (Norway) examinations. There was good agreement between the model-predicted and observed radiologists' TPR and FPR (r ≥ 0.969). Model-predicted negative-case disagreement rates showed high correlations (r ≥ 0.709), whereas positive-case disagreement rates had lower correlation levels due to sparse data (r ≥ 0.532). Pairing radiologists with similar FPR characteristics (Sweden: 4.50% [95% confidence interval: 4.46%-4.54%], England: 5.51% [5.47%-5.56%], Norway: 8.03% [7.99%-8.07%]) resulted in significantly lower FPR than with random pairing (Sweden: 4.74% [4.70%-4.78%], England: 5.76% [5.71%-5.80%], Norway: 8.30% [8.26%-8.34%]), reducing examinations sent to consensus/arbitration while the TPR did not change significantly. Other pairing strategies resulted in equal or worse performance than random pairing.ConclusionsLogistic regression models accurately predicted screening mammography assessments and helped explore different radiologist pairing strategies. Pairing readers with similar modeled FPR characteristics reduced the number of examinations unnecessarily sent to consensus/arbitration without significantly compromising the TPR.HighlightsA logistic-regression model can be derived that accurately predicts individual and paired reader performance during mammography screening reading.Pairing screening mammography radiologists with similar false-positive characteristics reduced false-positive rates with no significant loss in true positives and may reduce the number of examinations unnecessarily sent to consensus/arbitration.
| S-EPMC11490068 | biostudies-literature
Project description:Although mammography is the gold standard for breast cancer screening, the high rates of false-positive mammograms remain a concern. Thus, there is an unmet clinical need for a non-invasive and reliable test to differentiate between malignant and benign breast lesions in order to avoid subjecting patients with abnormal mammograms to unnecessary follow-up diagnostic procedures. Serum samples from 116 malignant breast lesions and 64 benign breast lesions were comprehensively profiled for 2,083 microRNAs (miRNAs) using next-generation sequencing. Of the 180 samples profiled, three outliers were removed based on the principal component analysis (PCA), and the remaining samples were divided into training (n = 125) and test (n = 52) sets at a 70:30 ratio for further analysis. In the training set, significantly differentially expressed miRNAs (adjusted p < 0.01) were identified after correcting for multiple testing using a false discovery rate. Subsequently, a predictive classification model using an eight-miRNA signature and a Bayesian logistic regression algorithm was developed. Based on the receiver operating characteristic (ROC) curve analysis in the test set, the model could achieve an area under the curve (AUC) of 0.9542. Together, this study demonstrates the potential use of circulating miRNAs as an adjunct test to stratify breast lesions in patients with abnormal screening mammograms.
| S-EPMC6966622 | biostudies-literature
Project description:Artificial intelligence (AI) algorithms have been retrospectively evaluated as replacement for one radiologist in screening mammography double-reading; however, methods for resolving discordance between radiologists and AI in the absence of 'real-world' arbitration may underestimate cancer detection rate (CDR) and recall. In 108,970 consecutive screens from a population screening program (BreastScreen WA, Western Australia), 20,120 were radiologist/AI discordant without real-world arbitration. Recall probabilities were randomly assigned for these screens in 1000 simulations. Recall thresholds for screen-detected and interval cancers (sensitivity) and no cancer (false-positive proportion, FPP) were varied to calculate mean CDR and recall rate for the entire cohort. Assuming 100% sensitivity, the maximum CDR was 7.30 per 1000 screens. To achieve >95% probability that the mean CDR exceeded the screening program CDR (6.97 per 1000), interval cancer sensitivities ≥63% (at 100% screen-detected sensitivity) and ≥91% (at 80% screen-detected sensitivity) were required. Mean recall rate was relatively constant across sensitivity assumptions, but varied by FPP. FPP > 6.5% resulted in recall rates that exceeded the program estimate (3.38%). CDR improvements depend on a majority of interval cancers being detected in radiologist/AI discordant screens. Such improvements are likely to increase recall, requiring careful monitoring where AI is deployed for screen-reading.
| S-EPMC11869508 | biostudies-literature