Citations

Background & Aims: Multi-target stool DNA (mt-sDNA) is an established stool-based colorectal cancer screening test, yet long-term performance is not well-described. We evaluated follow-up colonoscopy rates & quality, neoplasia yield, and repeat-testing adherence over 10 years with an integrated screening program. Methods: We assembled a retrospective cohort of mt-sDNA tests (September 2014–July 2025) within a multi-site health system. A validated large-language-model pipeline extracted colonoscopy, pathology, and quality endpoints from free-text reports. Detection outcomes (adenoma detection rate, advanced neoplasia, modified advanced adenoma, sessile serrated lesion (SSL), and negative exams) were calculated among high-quality exams; adenocarcinoma, bowel preparation adequacy, and cecal intubation rate (CIR) used all screening exams. We assessed colonoscopy completion ≤1 year after positive mt-sDNA, follow-up colonoscopy findings, findings by time-to-colonoscopy, and adherence to repeat mt-sDNA after negative result. Results: Among 148,624 tests in 110,410 individuals, positivity was 13.6%. Of 19,506 positives, 65.1% completed colonoscopy within 12 months (median 82 days). Colonoscopy after a positive mt-sDNA had high yield: advanced adenoma diagnosis was 30.7%; adenocarcinoma was 1.3%. Of patients who had colonoscopy within 3 years of a negative mt-sDNA test, 45.2% had adenoma/serrated lesion, 9.3% had advanced adenoma and 0.5% had colon cancer. Adenoma detection rate after positive mt-sDNA (>50%) exceeded specialty society quality benchmarks and increased over time; Longer intervals (>6 months) to colonoscopy after a positive test were associated with higher advanced adenoma (trend P=0.001).After an initial negative mt-sDNA, only 35.3% were screened again by mt-sDNA testing within 3 years. Conclusions: Over a decade,mt-sDNA screening achieved high colonoscopy qualitybut revealed critical gaps in the care cascade. One-third of positive tests lacked timely follow-up and nearly two-thirds of negative tests were not repeated on schedule, suggesting opportunities for system-level interventions.

Abstract Background While biologic and small molecule therapies have expanded treatment options for moderate to severe ulcerative colitis (UC), prior research revealed that only 26% of patients in routine practice would have qualified for pivotal randomized controlled trials (RCTs) due to stringent eligibility criteria. This study aimed to evaluate contemporary clinical trial eligibility for UC patients in a tertiary care setting based on more recently approved therapies. Methods We performed a retrospective cohort study of adult patients with moderate to severe UC (total Mayo score ≥6) seen between January 2022 and February 2023. Inclusion and exclusion criteria from seven phase III RCTs conducted between 2012 and 2022 (eg, VARSITY, UNIFI, OCTAVE, LUCENT) were applied to determine patient eligibility and identify reasons for ineligibility. Results Of 150 patients (mean age 44.9 years; 55.7% male), only 42.7% were eligible for at least one RCT. The most common exclusion factor was current or prior medication use, followed by anemia, dysplasia, and disease extent. Trial eligibility did not significantly differ by age, gender, or disease duration. Conclusions Despite modest improvements since 2012, over half of real-world UC patients remain ineligible for current RCTs. Expanding inclusion criteria, especially regarding prior medication exposure, and adopting more inclusive trial designs may enhance external validity. Addressing disparities in trial access and participation remains essential to ensuring equitable representation and improving clinical applicability of RCT findings.

Importance Although the Martin-Hopkins equation is widely validated and used to estimate low-density lipoprotein cholesterol (LDL-C) for clinical care, a simplified equation could streamline implementation and enable broader adoption. Objective To develop a simplified machine learning–based alternative to the Martin-Hopkins equation using multivariate adaptive regression splines (LDL-C–MH-MARS) and compare its performance with the Friedewald (LDL-C–F), Sampson–National Institutes of Health (LDL-C–S), Modified Sampson (LDL-C–MS), and Martin-Hopkins (LDL-C–MH) equations. Design, Setting, and Participants The Very Large Database of Lipids is a cross-sectional database of clinical lipid measurements from a population-representative convenience sample of adult and pediatric patients. Lipid measurements were performed by Vertical Auto Profile ultracentrifugation between October 1, 2015, and June 30, 2019. The study included patients with complete lipid panel data who were randomly assigned to a training set and a test set. External validation against preparative ultracentrifugation-based LDL-C measurements was performed in reference laboratory datasets from the Mayo Clinic (broad LDL-C concentrations) and the Further Cardiovascular Outcomes Research With Proprotein Convertase Subtilisin/Kexin Type 9 (PCSK9) Inhibition in Subjects with Elevated Risk (FOURIER) trial (observations from patients with low LDL-C concentrations while taking evolocumab). Study data were analyzed from January to October 2025. Exposures LDL-C–F, LDL-C–S, LDL-C–MS, LDL-C–MH, and LDL-C–MH-MARS equations. Main Outcomes and Measures Accuracy of estimated vs ultracentrifugation-measured LDL-C concentration based on bias, root mean square error (RMSE), and concordance by guideline-based categories. Results The study included 4 939 528 patients (mean [SD] age, 56 [16] years; 2 635 486 female [53%]) with complete lipid panel data who were randomly assigned to a training set (n = 3 292 889) and a test set (n = 1 646 639). LDL-C–MH-MARS equation demonstrated a very low median (IQR) bias of −0.1 (−2.1 to 1.8) mg/dL (to convert to millimoles per liter, multiply by 0.0259), comparable with LDL-C–MH. The median (IQR) difference between the MARS and original Martin-Hopkins equations (ie, LDL-C–MH-MARS – LDL-C–MH) was −0.5 (−1.2 to 0) mg/dL, further suggesting comparability between the 2 methods. The RMSE was smallest for LDL-C–MH-MARS (4.7 mg/dL) and LDL-C–MH (4.9 mg/dL), followed by LDL-C–S (5.8 mg/dL), LDL-C-MS (6.0 mg/dL), and LDL-C–F (7.2 mg/dL). The proportion of patients correctly classified according to clinical categories was nearly identical for LDL-C–MH-MARS (89.7%) and LDL-C–MH (89.6%) but lower for LDL-C–S (86.3%), LDL-C–MS (84.7%), and LDL-C–F (83.1%). The LDL-C–MH-MARS, LDL-C–MH, LDL-C–MS, LDL-C–S, and LDL-C–F equations underestimated LDL-C concentration in 16%, 17%, 28%, 39%, and 60%, respectively, when classifying LDL-C less than 70 mg/dL in patients with triglyceride concentrations of 200 to 399 mg/dL (to convert to millimoles per liter, multiply by 0.0113). The patterns of results were similar in external validation datasets, with the LDL-C–MH-MARS and LDL-C–MH equations demonstrating the highest accuracy. Conclusions and Relevance Study results suggest that the new machine learning–based LDL-C equation provided results comparable with those of the original Martin-Hopkins method while simplifying implementation to a single equation.

Abstract Background Capillary self-collection (CSC) devices allow patients to collect blood samples at home, potentially reducing outpatient phlebotomy visits. This study aimed to (a) assess the patient experience with multiple commercially available CSC devices; (b) determine which laboratory tests are commonly ordered together, which could reduce the need for appointments; and (c) evaluate the analytical performance of these tests using CSC samples. Methods User experience for 3 CSC devices was evaluated. Clinical feasibility was determined by comparing test results in paired sera collected by venipuncture (VP) and CSC devices. VP samples were centrifuged within 2 h and tested immediately. CSC sera were centrifuged and tested both immediately and after delayed processing to simulate shipping temperature extremes (−20°C or 40°C). Basic metabolic panel, lipid panel, thyroid function cascade, and prostate-specific antigen were evaluated. Differences between VP and CSC collections were characterized according to their statistical and clinical differences. Results Patients reported CSC devices were easy to use and painless. Clinically significant differences between VP and CSC sera processed immediately were limited to potassium and bicarbonate. Following delayed processing of CSC serum samples (48 h at room temperature), clinically significant differences in potassium, bicarbonate, and glucose were observed. Frozen samples could not be analyzed. A 48 h delay at 40°C caused clinically significant differences in all analytes except creatinine, lipid panel, prostate-specific antigen, and the thyroid cascade. Conclusion Potassium, bicarbonate, and glucose were not stable at room temperature in CSC sera. CSC serum specimens may be a viable option but require analyte-specific evaluation and consideration of transportation conditions.

INTRODUCTION: Colorectal cancer remains a leading cause of cancer associated death in the United States and colonoscopy the primary screening strategy for prevention. Rates of adenomatous and serrated neoplasia detection are inversely associated with postcolonoscopy colorectal cancer. This crucial quality metric depends on accurate ascertainment of colorectal neoplasia findings from both endoscopy and histopathology records. We aimed to assess the feasibility of a random forest machine learning model to rapidly and accurately categorize colorectal neoplasia from electronic health record data. METHODS: A retrospective cohort study compared neoplasia detection rates among individuals undergoing colonoscopy at a large academic institution to develop a rule-based algorithm to categorize colorectal neoplasia from endoscopy reports and pathology systematized nomenclature of medicine – clinical terms. This cohort provided a large training set to develop a natural language processing system using a random forest approach to automatically classify unstructured pathology findings into adenoma, serrated, or advanced neoplasms. This system was manually validated through an independent holdout set. RESULTS: The training set comprised 35,953 unstructured pathology reports with matched systematized nomenclature of medicine – clinical terms from 95,188 unstructured colonoscopy reports. The final model was assessed on an independent holdout set of 337 manually annotated procedures obtaining an area under the receiver operating characteristic curve of 0.997 (confidence interval [CI] 0.994–1), 0.99 (CI 0.98–1), and 0.99 (CI 0.98–0.99) for prediction of adenoma, serrated, and advanced lesions, respectively. DISCUSSION: The random forest-based hybrid natural language processing system for classification of colonoscopy results was both accurate and explainable. NLP combined with effective machine learning algorithms can provide a scalable strategy for colonoscopy quality monitoring.

The NCCN Guidelines for Colorectal Cancer (CRC) Screening describe various colorectal screening modalities as well as recommended screening schedules for patients at average or increased risk of developing sporadic CRC. They are intended to aid physicians with clinical decision-making regarding CRC screening for patients without defined genetic syndromes. These NCCN Guidelines Insights focus on select recent updates to the NCCN Guidelines, including a section on primary and secondary CRC prevention, and provide context for the panel’s recommendations regarding the age at which to initiate screening in average-risk individuals and those with increased risk based on personal history of childhood, adolescent, and young adult cancer.