Citations

Artificial intelligence (AI) is rapidly moving from an experimental phase to an implementation phase in many fields, including medicine. The combination of improved availability of large datasets, increasing computing power, and advances in learning algorithms has created major performance breakthroughs in the development of AI applications. In the last 5 years, AI techniques known as deep learning have delivered rapidly improving performance in image recognition, caption generation, and speech recognition. Radiology, in particular, is a prime candidate for early adoption of these techniques. It is anticipated that the implementation of AI in radiology over the next decade will significantly improve the quality, value, and depth of radiology's contribution to patient care and population health, and will revolutionize radiologists' workflows. The Canadian Association of Radiologists (CAR) is the national voice of radiology committed to promoting the highest standards in patient-centered imaging, lifelong learning, and research. The CAR has created an AI working group with the mandate to discuss and deliberate on practice, policy, and patient care issues related to the introduction and implementation of AI in imaging. This white paper provides recommendations for the CAR derived from deliberations between members of the AI working group. This white paper on AI in radiology will inform CAR members and policymakers on key terminology, educational needs of members, research and development, partnerships, potential clinical applications, implementation, structure and governance, role of radiologists, and potential impact of AI on radiology in Canada.

Objectives To characterize the individual and combined effects of multimorbidity and functional limitation on healthcare use and mortality in a large, community cohort of individuals with heart failure (HF). Design Prospective cohort study. Setting Eleven southeastern Minnesota counties. Participants Individuals (mean age 74, 54% male) with a first‐ever HF code ( International Classification of Diseases, Ninth Revision code 428 or Tenth Revision code I50) between January 1, 2013 and March 31, 2016 (N=2,692). Measurements Eight activities of daily living measured using a survey on a Likert scale (1=without any difficulty, 5=unable to do; median=8). Participants with a score greater than 8 were categorized as having functional limitation. Multimorbidity was defined as having 2 or more noncardiac comorbidities. Results Twenty‐five percent of participants had neither multimorbidity nor functional limitation, 35% had multimorbidity, 9% had functional limitation, and 31% had both. After adjustment, participants with multimorbidity and functional limitation had greater risks of all outcomes (death: hazard ratio (HR)=4.92, 95% confidence interval (CI)=3.03–8.00; emergency department (ED) visit: HR=3.67, 95% CI=2.94–4.59; hospitalization: HR=3.66, 95% CI=2.85–4.70; outpatient visit: HR=1.73, 95% CI=1.52–1.96) than those with neither. Participants with functional limitation alone had greater risks of death (HR=4.84, 95% CI=2.78–8.43), ED visits (HR=2.35, 95% CI=1.75–3.16), and hospitalizations (HR=2.10, 95% CI=1.52–2.88) but not outpatient visits. Those with multimorbidity alone had similar risks of ED visits and hospitalizations as those with functional limitation alone but were more likely to have outpatient visits (HR=1.50, 95% CI=1.34–1.67). Conclusion Individuals with both multimorbidity and functional limitation have the highest risk of death and healthcare use. Individuals with only functional limitation have similar rates of hospitalizations and ED visits as those with only multimorbidity, underscoring the need to consider both when managing individuals with HF.

Objective To explore differences in clinical manifestations and outcomes in those patients who develop infection after undergoing initial implantation versus reoperation. Methods We compared cases of cardiac implantable electronic device (CIED) infection based on initial implantation versus reoperation from 11 centres. Results There were 432 patients with CIED infection, 178 occurring after initial device placement and 254 after repeat reoperation. No differences were seen in age, sex or device type. Those with infection after initial implant had a higher Charlson Comorbidity Score (median 3 (IQR 2–6) vs 2 (IQR 1–4), p<0.001), shorter time since last procedure (median 8.9 months (IQR 0.9–33.3) vs 19.5 months (IQR 1.1–62.9), p<0.0001) and fewer leads (2.0±0.6vs 2.5±0.9, p<0.001). Pocket infections were more likely to occur after a reoperation (70.1%vs48.9%, p<0.001) and coagulase negative staphylococci (CoNS) was the most frequently isolated organism in this group (p=0.029). In contrast, initial implant infections were more likely to present with higher white cell count (10.5±5.1 g/dL vs 9.5±5.4 g/dL, p=0.025), metastatic foci of infection (16.9%vs8.7%, p=0.016) and sepsis (30.9%vs19.3%, p=0.006). There were no differences in in-hospital (7.9%vs5.2%, p=0.31) or 6-month mortality (21.9%vs14.0%, p=0.056). Conclusions CIED infections after initial device implant occur earlier, more aggressively, and often due to Staphylococcus aureus. In contrast, CIED infections after reoperation occur later, are due to CoNS, and have more indolent manifestations with primary localisation to the pocket.

AbstractBackgroundPublished guidelines mandate complete device removal in cases of cardiovascular implantable electronic device (CIED) infection. Clinical predictors of successful salvage of infected CIEDs have not been defined.MethodsData from the Multicenter Electrophysiologic Device Infection Collaboration, a prospective, observational, multinational cohort study of CIED infection, were used to investigate whether clinical predictors of successful salvage of infected devices could be identified.ResultsOf 433 adult patients with CIED infections, 306 (71%) underwent immediate device explantation. Medical management with device retention and antimicrobial therapy was initially attempted in 127 patients (29%). “Early failure” of attempted salvage occurred in 74 patients (58%) who subsequently underwent device explantation during the index hospitalization. The remaining 53 patients (42%) in the attempted salvage group retained their CIED. Twenty‐six (49%) had resolution of CIED infection (successful salvage group) whereas 27 patients (51%) experienced “late” salvage failure. Upon comparing the salvage failure group, early and late (N = 101), to the group experiencing successful salvage of an infected CIED (N = 26), no clinical or laboratory predictors of successful salvage were identified. However, by univariate analysis, coagulase‐negative staphylococci as infecting pathogens (P = 0.0439) and the presence of a lead vegetation (P = 0.024) were associated with overall failed salvage.ConclusionsIn patients with definite CIED infections, clinical and laboratory variables cannot predict successful device salvage. Until new data are forthcoming, device explantation should remain a mandatory and early management intervention in patients with CIED infection in keeping with existing expert guidelines unless medical contraindications exist or patients refuse device removal.

Limited epidemiological evidence suggests that the etiology of hormone receptor positive (HR+) breast cancer may differ by levels of histologic grade and proliferation. We pooled risk factor and pathology data on 5,905 HR+ breast cancer cases and 26,281 controls from 11 epidemiological studies. Proliferation was determined by centralized automated measures of KI67 in tissue microarrays. Odds ratios (OR), 95% confidence intervals (CI) and p‐values for case–case and case–control comparisons for risk factors in relation to levels of grade and quartiles (Q1–Q4) of KI67 were estimated using polytomous logistic regression models. Case–case comparisons showed associations between nulliparity and high KI67 [OR (95% CI) for Q4 vs. Q1 = 1.54 (1.22, 1.95)]; obesity and high grade [grade 3 vs. 1 = 1.68 (1.31, 2.16)] and current use of combined hormone therapy (HT) and low grade [grade 3 vs. 1 = 0.27 (0.16, 0.44)] tumors. In case–control comparisons, nulliparity was associated with elevated risk of tumors with high but not low levels of proliferation [1.43 (1.14, 1.81) for KI67 Q4 vs. 0.83 (0.60, 1.14) for KI67 Q1]; obesity among women ≥50 years with high but not low grade tumors [1.55 (1.17, 2.06) for grade 3 vs. 0.88 (0.66, 1.16) for grade 1] and HT with low but not high grade tumors [3.07 (2.22, 4.23) for grade 1 vs. 0.85 (0.55, 1.30) for grade 3]. Menarcheal age and family history were similarly associated with HR+ tumors of different grade or KI67 levels. These findings provide insights into the etiologic heterogeneity of HR+ tumors.