A deep-learning enhanced algorithm for the automated detection of DR, achieves significantly better performance than a previously reported, otherwise essentially identical, algorithm that does not employ deep learning. Deep learning enhanced algorithms have the potential to improve the efficiency of DR screening, and thereby to prevent visual loss and blindness from this devastating disease.

No abstract

Further research should explore whether these findings are time or cohort bound, address the potential heterogeneity of the proxy-respondent effects based on the reason for and relationship of the proxy to the target person, and evaluate the effects of a broader spectrum of performance-based cognitive abilities. In the interim, the significant predictors identified here should be included in future studies.

In clinical endpoint bioequivalence (BE) studies, the primary analysis for assessing equivalence between a generic and an innovator product is based on the observed per-protocol (PP) population (usually completers and compliers). However, missing data and noncompliance are post-randomization intercurrent events and may introduce selection bias. Therefore, PP analysis is generally not causal. The FDA Missing Data Working Group recommended using "causal estimands of primary interest." In this paper, we propose a principal stratification causal framework and co-primary causal estimands to test equivalence, which was also recommended by the recently published ICH E9 (R1) addendum to address intercurrent events. We identify three conditions under which the current PP estimator is unbiased for one of the proposed co-primary causal estimands - the "Survivor Average Causal Effect" (SACE) estimand. Simulation shows that when these three conditions are not met, the PP estimator is biased and may inflate Type 1 error and/or change power. We also propose a tipping point sensitivity analysis to evaluate the robustness of the current PP estimator in testing equivalence when the sensitivity parameters deviate from the three identified conditions, but stay within a clinically meaningful range. Our work is the first causal equivalence assessment in equivalence studies with intercurrent events.

Summary Patients often do not know or understand their bone density test results, and pharmacological treatment rates are low. In a clinical trial of 7749 patients, we used a tailored patient-activation result letter accompanied by a bone health brochure to improve appropriate pharmacological treatment. Treatment rates, however, did not improve. Introduction Patients often do not know or understand their dual-energy x-ray absorptiometry (DXA) test results, which may lead to suboptimal care. We tested whether usual care augmented by a tailored patient-activation DXA result letter accompanied by an educational brochure would improve guideline-concordant pharmacological treatment compared to usual care only. Methods We conducted a randomized, controlled, double-blinded, pragmatic clinical trial at three health care centers in the USA. We randomized 7749 patients ≥50 years old and presenting for DXA between February 2012 and August 2014. The primary clinical endpoint at 12 and 52 weeks post-DXA was receiving guideline-concordant pharmacological treatment. We also examined four of the steps along the pathway from DXA testing to that clinical endpoint, including (1) receiving and (2) understanding their DXA results and (3) having subsequent contact with their provider and (4) discussing their results and options. Results Mean age was 66.6 years, 83.8 % were women, and 75.3 % were non-Hispanic whites. Intention-to-treat analyses revealed that guideline-concordant pharmacological treatment was not improved at either 12 weeks (65.1 vs. 64.3 %, p = 0.506) or 52 weeks (65.2 vs. 63.8 %, p = 0.250) post-DXA, even though patients in the intervention group were more likely (all p < 0.001) to recall receiving their DXA results letter at 12 weeks, correctly identify their results at 12 and 52 weeks, have contact with their provider at 52 weeks, and have discussed their results with their provider at 12 and 52 weeks. Conclusion A tailored DXA result letter and educational brochure failed to improve guideline-concordant care in patients who received DXA.