Citations

Artificial intelligence (AI) and machine learning (ML) in medicine are currently areas of intense exploration, showing potential to automate human tasks and even perform tasks beyond human capabilities. Literacy and understanding of AI/ML methods are becoming increasingly important to researchers and clinicians. The first objective of this review is to provide the novice reader with literacy of AI/ML methods and provide a foundation for how one might conduct an ML study. We provide a technical overview of some of the most commonly used terms, techniques, and challenges in AI/ML studies, with reference to recent studies in cardiac electrophysiology to illustrate key points. The second objective of this review is to use examples from recent literature to discuss how AI and ML are changing clinical practice and research in cardiac electrophysiology, with emphasis on disease detection and diagnosis, prediction of patient outcomes, and novel characterization of disease. The final objective is to highlight important considerations and challenges for appropriate validation, adoption, and deployment of AI technologies into clinical practice.

Background: Little is known about the impact of socioeconomic status (SES) as a key element of social determinants of health on intensive care unit (ICU) outcomes for adults. Objective: We assessed whether a validated individual SES index termed HOUSES (HOUsing-based SocioEconomic status index) derived from housing features was associated with short-term outcomes of critical illness including ICU mortality, ICU-free days, hospital-free days, and ICU readmission. Methods: We performed a population-based cohort study of adult patients living in Olmsted County, Minnesota, admitted to 7 intensive care units at Mayo Clinic from 2011 to 2014. We compared outcomes between the lowest SES group (HOUSES quartile 1 [Q1]) and the higher SES group (HOUSES Q2-4). We stratified the cohort based on age (<50 years old and ≥50 years old). Results: Among 4134 eligible patients, 3378 (82%) patients had SES successfully measured by the HOUSES index. Baseline characteristics, severity of illness, and reason for ICU admission were similar among the different SES groups as measured by HOUSES except for larger number of intoxications and overdoses in younger patients from the lowest SES. In all adult patients, there were no overall differences in mortality, ICU-free days, hospital-free days, or ICU readmissions in patients with higher SES compared to lower SES. Among older patients (>50 years), those with higher SES (HOUSES Q2-4) compared to those with lower SES (HOUSES Q1) had lower mortality rates (hazard ratio = 0.72; 95% CI: 0.56-0.93; adjusted P = .01), increased ICU-free days (mean 1.08 days; 95% CI: 0.34-1.84; adjusted P = .004), and increased hospital-free days (mean 1.20 days; 95% CI: 0.45-1.96; adjusted P = .002). There were no differences in ICU readmission rates (OR = 0.74; 95% CI: 0.55-1.00; P = .051). Conclusion: Individual-level SES may be an important determinant or predictor of critical care outcomes in older adults. Housing-based socioeconomic status may be a useful tool for enhancing critical care research and practice.

AbstractIntroductionBrugada syndrome (BrS) is associated with ventricular arrhythmia leading to sudden cardiac death. Risk stratification is challenging, as major arrhythmic events (MAEs) are rare. We assessed the utility of drug challenge testing in BrS by a systematic review and meta‐analysis.Methods and ResultsWe comprehensively searched the databases of MEDLINE and EMBASE from inception to May 2019. Included studies compared the incidence of MAE between spontaneous and drug challenge–induced Type 1. Mixed‐effects Poisson regression was used to calculate the incidence rate ratio (IRR). Eighteen studies from 2006 to 2018 were included (4099 patients, mean follow‐up: 4.5 years). Pooled annual incidences of MAE in spontaneous, drug challenge induced (regardless of symptoms), asymptomatic drug challenge induced, and symptomatic drug challenge–induced Type 1 were 23.8 (95% confidence interval [CI]: 19.8–27.8), 6.5 (95% CI: 3.9–9.1), 2.1 (95% CI: −0.3 to 4.4), and 19.6 (95% CI: 9.9–29.3) per 1000 person‐years, respectively. The incidence of MAE between symptomatic drug challenge induced and asymptomatic spontaneous Type 1 was not statistically different (IRR = 1.0; 95% CI: 0.6–1.7).ConclusionsThe incidence of MAE in drug challenge–induced Type 1 in asymptomatic patients is low. The incidence of MAE between symptomatic drug challenge induced and asymptomatic spontaneous Type 1 was similar.

Study Design: Retrospective cohort study. Objective: To determine if local administration of liposomal bupivacaine (LB) reduces postoperative pain scores and narcotic use in spinal deformity patients. Methods: Adult patients undergoing elective spinal fusion (7 or more levels) for scoliosis or kyphosis were selected for inclusion. Patients received either periincisional injections of combined liposomal and standard bupivacaine (n = 90, group L) or standard bupivacaine only (n = 69, group C). Perioperative pain scores (VAS [visual analogue scale]), opioid use, length of stay, functional outcome (ODI [Oswestry Disability Index]), and perioperative complications were recorded. No external funding was received for this study. Results: A total of 159 patients met inclusion criteria (mean age was 54.2 years of age). No significant baseline demographic differences were noted between the 2 groups. Group L experienced slight improvements in pain control on postoperative day (POD) 1 ( P = .02). No difference in pain scores were otherwise noted. Group L transitioned off of intravenous (IV) narcotics faster with 52.6% less IV use by POD3 ( P = .03). No differences in total narcotic consumption, perioperative complications, lengths of stay, and functional outcome scores were otherwise noted between the 2 cohorts. Conclusions: The use of LB in adult spinal deformity surgery does not appear to provide clinically important improvements in postoperative pain at the manufacturer’s recommended dosage. Furthermore, while patients receiving LB may transition more quickly off of IV narcotics, this does not appear to translate into an overall decrease in narcotic consumption, hasten return of bowel function, or decrease hospital lengths of stay. Future prospective randomized control trials are warranted. The use of varying dosages of LB may also help further clarify the true efficacy of LB in the setting of spinal deformity surgery.

Many spine surgeons enlist the aid of an “access surgeon” to provide anterior exposure of the lumbosacral spine. We proposed that a single, community hospital general surgery practice can successfully develop an anterior spine exposure program with acceptable clinical outcomes. One hundred and forty-three consecutive anterior exposures were performed between 2008 and 2014. Morbidity and 30-day mortality were recorded. The effects of American Society of Anesthesiologists Physical Status classification (ASA class) and number of levels exposed on length of stay (LOS) and estimated blood loss (EBL) was reported. The growth of the program during this period was also evaluated. During the six-year period, there were nine (6.3%) major complications and 17 (11.9%) minor complications with no 30-day mortality. The mean LOS was similar for one-level and two-level exposures (3.8 days). Mean LOS was higher in ASA III patients (4.4 days) than ASA I (2.9 days) or ASA II (3.2 days). Mean EBL for one-level exposures (336.3 mL) was not significantly different than EBL for two-level exposures (425.9 mL). EBLs in ASA class III patients were greater than in class I and class II patients. The program began in July of 2008 with a single spine surgeon and one operation that year. A high of 54 procedures, with seven different spine surgeons, was recorded in 2013. A single, community hospital general surgery practice can successfully develop an anterior approach to spine exposure program with acceptable clinical outcomes and with sustained growth of the program.

Coronavirus disease 2019 (COVID-19) has presented substantial challenges to patient care and impacted healthcare delivery, including cardiac electrophysiology practice throughout the globe. Based upon the undetermined course and regional variability of the pandemic, there is uncertainty as to how and when to resume and deliver electrophysiology services for patients with arrhythmia. This joint document from representatives of the Heart Rhythm Society, American Heart Association, and American College of Cardiology seeks to provide guidance for clinicians and institutions reestablishing safe electrophysiological care. To achieve this aim, we address regional and local COVID-19 disease status, the role of viral screening and serological testing, return-to-work considerations for exposed or infected health care workers, risk stratification and management strategies based on COVID-19 disease burden, institutional preparedness for resumption of elective procedures, patient preparation and communication, prioritization of procedures, and development of outpatient and periprocedural care pathways.