Artificial intelligence and machine learning are poised to influence nearly every aspect of the human condition, and cardiology is not an exception to this trend. This paper provides a guide for clinicians on relevant aspects of artificial intelligence and machine learning, reviews selected applications of these methods in cardiology to date, and identifies how cardiovascular medicine could incorporate artificial intelligence in the future. In particular, the paper first reviews predictive modeling concepts relevant to cardiology such as feature selection and frequent pitfalls such as improper dichotomization. Second, it discusses common algorithms used in supervised learning and reviews selected applications in cardiology and related disciplines. Third, it describes the advent of deep learning and related methods collectively called unsupervised learning, provides contextual examples both in general medicine and in cardiovascular medicine, and then explains how these methods could be applied to enable precision cardiology and improve patient outcomes.

No abstract

No abstract

OBJECT Although intracranial arachnoid cysts are a common incidental finding on pediatric brain imaging, only a subset of patients require surgery for them. For the minority who undergo surgery, the comparative effectiveness of various surgical approaches is debated. The authors explored predictors of surgery and compared operative techniques for pediatric patients with an intracranial arachnoid cyst seen at a tertiary care center. METHODS The authors reviewed records of pediatric patients with an intracranial arachnoid cyst. For each patient, data on baseline characteristics, the method of intervention, and surgical outcomes for the initial surgery were extracted, and cyst size at diagnosis was calculated (anteroposterior × craniocaudal × mediolateral). Baseline variables were analyzed as predictors of surgery by using logistic regression modeling, excluding patients whose surgery was not related to cyst size (i.e., those with obstructive hydrocephalus secondary to the cyst compressing a narrow CSF flow pathway or cyst rupture/hemorrhage). Data collected regarding surgical outcomes were analyzed descriptively. RESULTS Among 83 pediatric patients with an intracranial arachnoid cyst seen over a 25-year period (1989–2013), 27 (33%) underwent surgery; all had at least 1 cyst-attributed symptom/finding. In the multivariate model, age at presentation and cyst size at diagnosis were independent predictors of surgery. Cyst size had greater predictive value; specifically, the area under the curve for the receiver-operating-characteristic curve was 0.89 (95% CI 0.82–0.97), with an ideal cutoff point of ≥ 68 cm3. This cutoff point had 100% sensitivity (95% CI 79%–100%), 75% specificity (95% CI 61%–85%), a 53% positive predictive value (95% CI 36%–70%), and a 100% negative predictive value (95% CI 91%–100%); the positive likelihood ratio was 4.0 (95% CI 2.5–6.3), and the negative likelihood ratio was 0 (95% CI 0–0.3). Although the multivariate model excluded 7 patients who underwent surgery (based on prespecified criteria), excluding these 7 cases did not change the overall findings, as shown in a sensitivity analysis that included all the cases. Descriptive results regarding surgical outcomes did not indicate any salient differences among the surgical techniques (endoscopic fenestration, cystoperitoneal shunting, or craniotomy-based procedures) in terms of symptom resolution within 6 months, need for reoperation to date, cyst-size change from before the operation, morbidity, or mortality. CONCLUSIONS The results of these exploratory analyses suggest that pediatric patients with an intracranial arachnoid cyst are more likely to undergo surgery if the cyst is large, compresses a narrow CSF flow pathway to cause hydrocephalus, or has ruptured/hemorrhaged. There were no salient differences among the 3 surgical techniques for several clinically important outcomes. A prospective multicenter study is required to enable more robust analyses, which could ultimately provide a decision-making framework for surgical indications and clarify any differences in the comparative effectiveness of surgical approaches to treating pediatric intracranial arachnoid cysts.