Publications

OBJECTIVES

As the real-world electronic health record (EHR) data continue to grow exponentially, novel methodologies involving artificial intelligence (AI) are becoming increasingly applied to enable efficient data-driven learning and, ultimately, to advance healthcare. Our objective is to provide readers with an understanding of evolving computational methods and help in deciding on methods to pursue.

TARGET AUDIENCE

The sheer diversity of existing methods presents a challenge for health scientists who are beginning to apply computational methods to their research. Therefore, this tutorial is aimed at scientists working with EHR data who are early entrants into the field of applying AI methodologies.

SCOPE

This manuscript describes the diverse and growing AI research approaches in healthcare data science and categorizes them into 2 distinct paradigms, the bottom-up and top-down paradigms to provide health scientists venturing into artificial intelligent research with an understanding of the evolving computational methods and help in deciding on methods to pursue through the lens of real-world healthcare data.

INTRODUCTION

In-hospital delirium is more common among older adults and is associated with increased mortality and adverse health-related outcomes. We aim to establish the contemporary prevalence of delirium among older adults undergoing percutaneous coronary intervention (PCI) and the impact of delirium on in-hospital complications.

METHODS

We identified older adults aged ≥75 years in the National Inpatient Sample who underwent inpatient PCI for any reason from 2016 to 2020 and stratified them into those with and without delirium. The primary outcome was in-hospital mortality, and secondary outcomes encompassed post-procedural complications.

RESULTS

Delirium occurred in 14,130 (2.6 %) hospitalizations in which PCI was performed. Patients who developed delirium were older and had more comorbidities. Patients with in-hospital delirium had higher odds of in-hospital mortality (adjusted odds ratio [aOR] 1.27, p = 0.002) and non-home discharge (aOR 3.17, p < 0.001). Delirium was also associated with higher odds of intracranial hemorrhage (aOR 2.49, p < 0.001), gastrointestinal hemorrhage (aOR 1.25, p = 0.030), need for blood transfusion (aOR 1.52, p < 0.001), acute kidney injury (aOR 1.62, p < 0.001), and fall in hospital (aOR 1.97, p < 0.001).

CONCLUSION

Delirium among older adults undergoing PCI is relatively common and associated with higher odds of in-hospital mortality and adverse events. This highlights the importance of vigilant delirium prevention and early recognition in the peri-procedural setting, especially for older adults.

BACKGROUND

The majority of randomized controlled trials of revascularization decision-making excludes left main coronary artery disease (LMD). Therefore, contemporary clinical outcomes of patients with stable coronary artery disease and LMD with proven ischemia remain poorly understood. The aim of this study was to assess the long-term clinical outcomes of physiologically significant LMD according to the treatment strategies of revascularization versus revascularization deferral.

METHODS

In this international multicenter registry of stable LMD interrogated with the instantaneous wave-free ratio, patients with physiologically significant ischemia (instantaneous wave-free ratio ≤0.89) were analyzed according to the coronary revascularization (n=151) versus revascularization deferral (n=74). Propensity score matching was performed to adjust for baseline clinical characteristics. The primary end point was a composite of death, nonfatal myocardial infarction, and ischemia-driven target lesion revascularization of left main stem. The secondary end points were as follows: cardiac death or spontaneous LMD-related myocardial infarction; and ischemia-driven target lesion revascularization of left main stem.

RESULTS

At a median follow-up period of 2.8 years, the primary end point occurred in 11 patients (14.9%) in the revascularized group and 21 patients (28.4%) in the deferred group (hazard ratio, 0.42 [95% CI, 0.20-0.89]; =0.023). For the secondary end points, cardiac death or LMD-related myocardial infarction occurred significantly less frequently in the revascularized group (0.0% versus 8.1%; =0.004). The rate of ischemia-driven target lesion revascularization of left main stem was also significantly lower in the revascularized group (5.4% versus 17.6%; hazard ratio, 0.20 [95% CI, 0.056-0.70]; =0.012).

CONCLUSIONS

In patients who underwent revascularization for stable coronary artery disease and physiologically significant LMD determined by instantaneous wave-free ratio, the long-term clinical outcomes were significantly improved as compared with those in whom revascularization was deferred.