METHODS: We collected data from 7954 asymptomatic subjects (age, 50-75 y) who received screening colonoscopy examinations at 14 sites in Asia. We randomly assigned 5303 subjects to the derivation cohort and the remaining 2651 to the validation cohort. We collected data from the derivation cohort on age, sex, family history of colorectal cancer, smoking, drinking, body mass index, medical conditions, and use of nonsteroidal anti-inflammatory drugs or aspirin. Associations between the colonoscopic findings of APN and each risk factor were examined using the Pearson χ2 test, and we assigned each participant a risk score (0-15), with scores of 0 to 3 as average risk and scores of 4 or higher as high risk. The scoring system was tested in the validation cohort. We used the Cochran-Armitage test of trend to compare the prevalence of APN among subjects in each group.

RESULTS: In the validation cohort, 79.5% of patients were classified as average risk and 20.5% were classified as high risk. The prevalence of APN in the average-risk group was 1.9% and in the high-risk group was 9.4% (adjusted relative risk, 5.08; 95% CI, 3.38-7.62; P < .001). The score included age (61-70 y, 3; ≥70 y, 4), smoking habits (current/past, 2), family history of colorectal cancer (present in a first-degree relative, 2), and the presence of neoplasia in the distal colorectum (nonadvanced adenoma 5-9 mm, 2; advanced neoplasia, 7). The c-statistic of the score was 0.74 (95% CI, 0.68-0.79), and for distal findings alone was 0.67 (95% CI, 0.60-0.74). The Hosmer-Lemeshow goodness-of-fit test statistic was greater than 0.05, indicating the reliability of the validation set. The number needed to refer was 11 (95% CI, 10-13), and the number needed to screen was 15 (95% CI, 12-17).

METHODS AND ANALYSIS: The measurement challenge has been established as an international resource to offer a common set of anonymised mammogram images for measurement and analysis. To date, full field digital mammogram images and core data from 1650 cases and 1929 controls from five countries have been collated. The measurement challenge is an ongoing collaboration and we are continuing to expand the resource to include additional image sets across different populations (from contributors) and to compare additional measurement methods (by challengers). The intended use of the measurement challenge resource is for refinement and validation of new and existing mammographic measurement methods. The measurement challenge resource provides a standardised dataset of mammographic images and core data that enables investigators to directly compare methods of measuring mammographic density or other mammographic features in case/control sets of both raw and processed images, for the purposes of the comparing their predictions of breast cancer risk.

OBJECTIVE: To employ machine learning (ML) and stacked ensemble learning (EL) methods in predicting short- and long-term mortality in Asian patients diagnosed with NSTEMI/UA and to identify the associated features, subsequently evaluating these findings against established risk scores.

METHODS: We analyzed data from the National Cardiovascular Disease Database for Malaysia (2006-2019), representing a diverse NSTEMI/UA Asian cohort. Algorithm development utilized in-hospital records of 9,518 patients, 30-day data from 7,133 patients, and 1-year data from 7,031 patients. This study utilized 39 features, including demographic, cardiovascular risk, medication, and clinical features. In the development of the stacked EL model, four base learner algorithms were employed: eXtreme Gradient Boosting (XGB), Support Vector Machine (SVM), Naive Bayes (NB), and Random Forest (RF), with the Generalized Linear Model (GLM) serving as the meta learner. Significant features were chosen and ranked using ML feature importance with backward elimination. The predictive performance of the algorithms was assessed using the area under the curve (AUC) as a metric. Validation of the algorithms was conducted against the TIMI for NSTEMI/UA using a separate validation dataset, and the net reclassification index (NRI) was subsequently determined.

RESULTS: Using both complete and reduced features, the algorithm performance achieved an AUC ranging from 0.73 to 0.89. The top-performing ML algorithm consistently surpassed the TIMI risk score for in-hospital, 30-day, and 1-year predictions (with AUC values of 0.88, 0.88, and 0.81, respectively, all p < 0.001), while the TIMI scores registered significantly lower at 0.55, 0.54, and 0.61. This suggests the TIMI score tends to underestimate patient mortality risk. The net reclassification index (NRI) of the best ML algorithm for NSTEMI/UA patients across these periods yielded an NRI between 40-60% (p < 0.001) relative to the TIMI NSTEMI/UA risk score. Key features identified for both short- and long-term mortality included age, Killip class, heart rate, and Low-Molecular-Weight Heparin (LMWH) administration.