Citations

AbstractSupervised learning is the most common form of machine learning utilized in medical research. It is used to predict outcomes of interest or classify positive and/or negative cases with a known ground truth. Supervised learning describes a spectrum of techniques, ranging from traditional regression modeling to more complex tree boosting, which are becoming increasingly prevalent as the focus on “big data” develops. While these tools are becoming increasingly popular and powerful, there is a paucity of literature available that describe the strengths and limitations of these different modeling techniques. Typically, there is no formal training for health care professionals in the use of machine learning models. As machine learning applications throughout medicine increase, it is important that physicians and other health care professionals better understand the processes underlying application of these techniques. The purpose of this study is to provide an overview of commonly used supervised learning techniques with recent case examples within the orthopedic literature. An additional goal is to address disparities in the understanding of these methods to improve communication within and between research teams.

AbstractBackgroundIn 2016, the IDWeek program committee was charged with ensuring gender equity in speaker sessions. Whether this charge also resulted in more opportunities for historically underrepresented speakers is unknown.MethodsWe conducted a retrospective analysis of trends in the demographic composition of IDWeek speakers and program committee members between 2013 and 2021. We used descriptive statistics to summarize data, χ2 tests to compare speaker demographics between 2013–2016 (before 2016) and 2017–2021 (after 2016), and Cochran–Armitage tests for trend. Each speaker slot was considered an independent event.ResultsA total of 5482 speaker slots were filled by 3389 individuals from 2013 to 2021. There was a linear increase in female speakers from 38.6% in 2013 to 58.4% in 2021 (P < .001). The proportion of white speakers decreased overall from 84.9% in 2013 to 63.5% in 2021. Compared with white speakers, more slots were filled by Asian speakers after 2016 versus before 2016 (20.1% vs 14.8%, respectively; P < .001). Program committee members from 2013–2021 were >80% non-Hispanic white; <5% of committee members identified as black, American Indian, Alaska Native, Native Hawaiian, Pacific Islander, or Hispanic. More program committee slots were filled by women after 2016 than before 2016 (52.7% vs 33.9%; P = .004).ConclusionsIntentional consideration of gender equity by the program committee was associated with equitable gender representation of invited speakers at IDWeek after 2016. Gradually, the proportions of IDWeek speakers from historically excluded racial/ethnic approached their respective proportions in the IDSA membership. White speakers remained overrepresented relative to membership proportions until 2021, and gaps in program committee racial/ethnic demographic representation highlights opportunities for continued inclusion, diversity, access, and equity at IDWeek.

Abstract Introduction Treatment recommendations for Peyronie's Disease (PD) differ based on whether a patient is in the acute/active versus chronic/stable phase of the disease, yet there are no agreed upon criteria for defining these clinical entities. Objectives To review the criteria used to define acute and chronic phase PD in modern PD intervention studies Methods We performed a search engine review to identify indexed publications for PD intervention studies and review articles / meta-analyses from the year 2011-2020. Outcomes results were catalogued and summarized across articles. As a result of the substantial heterogeneity of outcome measures and follow-up intervals, meta-analytic techniques were not applied to the data analysis. Results We identified a total of 104 studies that met inclusion criteria and had available information for review (n = 79 primary intervention studies; n = 25 review articles/meta-analyses/guidelines). Among the queried studies, we were unable to identify a consensus with respect to the criteria used to define acute and chronic phases of PD. 33% of primary intervention studies did not specifically define their criteria for acute and chronic phase PD, despite referencing these populations as part of the inclusion criteria in many instances. Studies used heterogenous criteria including total symptom duration, duration of “stable” symptoms, and presence/absence of pain. Conclusion Due to varying definitions across the literature, we were unable to create a standardized definition of acute and chronic phase Peyronie's in terms of time. Our findings emphasize the need for greater consensus in defining the treatment cohorts with future studies that assess treatment for men with PD.

Abstract Aims Shock severity predicts mortality in patients with cardiogenic shock (CS). We evaluated the association between pre-cannulation Society for Cardiovascular Angiography and Intervention (SCAI) shock classification and mortality among patients receiving venoarterial (VA) extracorporeal membrane oxygenation (ECMO) support for CS. Methods and results We included Extracorporeal Life Support Organization (ELSO) Registry patients from 2010 to 2020 who received VA ECMO for CS. SCAI shock stage was assigned based on hemodynamic support requirements prior to ECMO initiation. In-hospital mortality was analyzed using multivariable logistic regression. We included 12 106 unique VA ECMO patient runs with a median age of 57.9 (interquartile range: 46.8, 66.1) years and 31.8% were females; 3472 (28.7%) were post-cardiotomy. The distribution of SCAI shock stages at ECMO initiation was: B, 821 (6.8%); C, 7518 (62.1%); D, 2973 (24.6%); and E, 794 (6.6%). During the index hospitalization, 6681 (55.2%) patients died. In-hospital mortality increased incrementally with SCAI shock stage (adjusted OR: 1.24 per SCAI shock stage, 95% CI: 1.17–1.32, P < 0.001): B, 47.5%; C, 52.8%; D, 60.8%; E, 65.1%. A higher SCAI shock stage was associated with increased in-hospital mortality in key subgroups, although the SCAI shock classification was only predictive of mortality in non-surgical (medical) CS and not in post-cardiotomy CS. Conclusion The severity of shock prior to cannulation is a strong predictor of in-hospital mortality in patients receiving VA ECMO for CS. Using the pre-cannulation SCAI shock classification as a risk stratification tool can help clinicians refine prognostication for ECMO recipients and guide future investigations to improve outcomes.

Background Dual antiplatelet therapy (DAPT) is recommended over single antiplatelet therapy (SAPT) in patients following coronary artery bypass grafting (CABG). The compilation of evidence has focused on the efficacy of DAPT to limit risk of graft occlusion, however the safety, especially in the on-pump CABG population, is less well described. The aim of this study was to assess the safety of DAPT versus SAPT after on-pump CABG. Methods This was a single-center, retrospective cohort analysis of adult patients following isolated on-pump CABG between January 2012 and December 2019 not on oral anticoagulation at discharge. The primary endpoint was occurrence of a composite bleeding event identified by pre-specified ICD codes. Secondary endpoints consisted of 30-day and 1-year mortalities along with individual bleeding components. Results Of the 2341 patients included 1250 patients were in the SAPT arm and 1091 patients in the DAPT arm. The study populations differed by age, prior MI, PAD, and CHF status/stage. Bleeding events occurred in a total of 70 patients (3.0%), with 36 patients (2.9%) in the SAPT arm and 34 patients (3.1%) in the DAPT arm ( P = .74). 30-day (SAPT 0.7% vs DAPT 0.4%) and 1-year (SAPT 3.3% vs DAPT 2.3%) mortality were not significantly different between groups. The most frequent bleed event was in the gastrointestinal tract. Conclusion In this study, DAPT was not associated with an increase in composite bleeding compared to SAPT. This study could reduce the barrier to prescribing of DAPT given previous efficacy data.

Two Letters to Blood address the risks of COVID-19 in populations with precursors of hematological disease. In the first article, Miller and colleagues report on whether clonal hematopoiesis of intermediate potential (CHIP) is associated with adverse outcomes with COVID-19, finding no association between CHIP and 28-day mortality while providing data indirectly linking IL-6 signaling and patient outcomes. In the second article, Ho and colleagues investigate the outcomes of patients with monoclonal gammopathy of undetermined significance (MGUS) with COVID-19, reporting that one-fourth had a severe infection and that on multivariable analysis, adverse outcomes are more likely if immunoparesis is present.

Abstract The treatment landscape for relapsed multiple myeloma (MM) has increased. In this study we aimed to characterize 2nd (n = 1439) and 3rd (n = 1104) line regimens and compare the results between subgroups based on the year of treatment initiation (2nd line: 2003–2008, 2009–2015, 2016–2021; 3rd line: 2004–2009, 2010–2015, and 2016–2021). In both 2nd and 3rd line we observed increasing use of novel agents (from 78–95% and from 77–95%, respectively) and triplet regimens (from 15–69% and from 21–71%, respectively). Most frequently used regimens in the last studied periods included lenalidomide-dexamethasone (RD; 14%), carfilzomib-RD (12%) and daratumumab-RD (10%) for 2nd line, and daratumumab-pomalidomide-dexamethasone (11%) and daratumumab-RD (10%) for 3rd line. Median time to next treatment from 2nd line therapy has improved from 10.4 months (95% CI 8.4–12.4) to 16.6 months (95% CI 13.3–20.3; p < 0.001). The median overall survival from 1st relapse increased from 30.9 months (95% CI 26.8–183.0) to 65.8 months (95% CI 50.7–72.8; p < 0.001). Over the last two decades more patients were treated with newer agents and triplets for relapsed MM. The landscape of regimens has become more diverse, and the survival after 1st relapse is continually improving.

Importance In patients with severe aortic valve stenosis at intermediate surgical risk, transcatheter aortic valve replacement (TAVR) with a self-expanding supra-annular valve was noninferior to surgery for all-cause mortality or disabling stroke at 2 years. Comparisons of longer-term clinical and hemodynamic outcomes in these patients are limited. Objective To report prespecified secondary 5-year outcomes from the Symptomatic Aortic Stenosis in Intermediate Risk Subjects Who Need Aortic Valve Replacement (SURTAVI) randomized clinical trial. Design, Setting, and Participants SURTAVI is a prospective randomized, unblinded clinical trial. Randomization was stratified by investigational site and need for revascularization determined by the local heart teams. Patients with severe aortic valve stenosis deemed to be at intermediate risk of 30-day surgical mortality were enrolled at 87 centers from June 19, 2012, to June 30, 2016, in Europe and North America. Analysis took place between August and October 2021. Intervention Patients were randomized to TAVR with a self-expanding, supra-annular transcatheter or a surgical bioprosthesis. Main Outcomes and Measures The prespecified secondary end points of death or disabling stroke and other adverse events and hemodynamic findings at 5 years. An independent clinical event committee adjudicated all serious adverse events and an independent echocardiographic core laboratory evaluated all echocardiograms at 5 years. Results A total of 1660 individuals underwent an attempted TAVR (n = 864) or surgical (n = 796) procedure. The mean (SD) age was 79.8 (6.2) years, 724 (43.6%) were female, and the mean (SD) Society of Thoracic Surgery Predicted Risk of Mortality score was 4.5% (1.6%). At 5 years, the rates of death or disabling stroke were similar (TAVR, 31.3% vs surgery, 30.8%; hazard ratio, 1.02 [95% CI, 0.85-1.22]; P = .85). Transprosthetic gradients remained lower (mean [SD], 8.6 [5.5] mm Hg vs 11.2 [6.0] mm Hg; P &amp;lt; .001) and aortic valve areas were higher (mean [SD], 2.2 [0.7] cm 2 vs 1.8 [0.6] cm 2 ; P &amp;lt; .001) with TAVR vs surgery. More patients had moderate/severe paravalvular leak with TAVR than surgery (11 [3.0%] vs 2 [0.7%]; risk difference, 2.37% [95% CI, 0.17%- 4.85%]; P = .05). New pacemaker implantation rates were higher for TAVR than surgery at 5 years (289 [39.1%] vs 94 [15.1%]; hazard ratio, 3.30 [95% CI, 2.61-4.17]; log-rank P &amp;lt; .001), as were valve reintervention rates (27 [3.5%] vs 11 [1.9%]; hazard ratio, 2.21 [95% CI, 1.10-4.45]; log-rank P = .02), although between 2 and 5 years only 6 patients who underwent TAVR and 7 who underwent surgery required a reintervention. Conclusions and Relevance Among intermediate-risk patients with symptomatic severe aortic stenosis, major clinical outcomes at 5 years were similar for TAVR and surgery. TAVR was associated with superior hemodynamic valve performance but also with more paravalvular leak and valve reinterventions.

ABSTRACT Both medical and surgical therapy represent potential management options for patients with asymptomatic primary hyperparathyroidism (PHPT). Because uncertainty remains regarding both medical and surgical therapy, this systematic review addresses the efficacy and safety of medical therapy in asymptomatic patients or symptomatic patients who decline surgery and surgery in asymptomatic patients. We searched Medline, Embase, Cochrane Central Register of Controlled Trials, and PubMed from inception to December 2020, and included randomized controlled trials in patients with PHPT that compared nonsurgical management with medical therapy versus without medical therapy and surgery versus no surgery in patients with asymptomatic PHPT. For surgical complications we included observational studies. Paired reviewers addressed eligibility, assessed risk of bias, and abstracted data for patient-important outcomes. We conducted random-effects meta-analyses to pool relative risks and mean differences with 95% confidence intervals and used Grading of Recommendations, Assessment, Development, and Evaluation (GRADE) to assess quality of evidence for each outcome. For medical therapy, 11 trials reported in 12 publications including 438 patients proved eligible: three addressed alendronate, one denosumab, three cinacalcet, two vitamin D, and two estrogen therapy. Alendronate, denosumab, vitamin D, and estrogen therapy all increased bone density. Cinacalcet probably reduced serum calcium and parathyroid hormone (PTH) levels. Cinacalcet and vitamin D may have a small or no increase in overall adverse events. Very-low-quality evidence raised the possibility of an increase in serious adverse events with alendronate and denosumab. The trials also provided low-quality evidence for increased bleeding and mastalgia with estrogen therapy. For surgery, six trials presented in 12 reports including 441 patients proved eligible. Surgery achieved biochemical cure in 96.1% (high quality). We found no convincing evidence supporting an impact of surgery on fracture, quality of life, occurrence of kidney stones, and renal function, but the evidence proved low or very low quality. Surgery was associated with an increase in bone mineral density. For patients with symptomatic and asymptomatic PHPT, who are not candidates for parathyroid surgery, cinacalcet probably reduced serum calcium and PTH levels; anti-resorptives increased bone density. For patients with asymptomatic PHPT, surgery usually achieves biochemical cure. These results can help to inform patients and clinicians regarding use of medical therapy and surgery in PHPT. © 2022 The Authors. Journal of Bone and Mineral Research published by Wiley Periodicals LLC on behalf of American Society for Bone and Mineral Research (ASBMR).