Johnson, Patrick

Abstract Background We sought to evaluate key performance indicators related to an internally developed and deployed artificial intelligence (AI)-augmented kidney stone composition test system for potential improvements in test quality, efficiency, cost-effectiveness, and staff satisfaction. Methods We compared quality, efficiency, staff satisfaction, and financial data from the 6 months after the AI-augmented laboratory test system was deployed (test period) with data from the same 6-month period in the previous year (control period) to determine if AI-augmentation improved key performance indicators of this laboratory test. Results In the 6 months following the deployment (test period) of the AI-augmented kidney stone composition test system, 44 830 kidney stones were analyzed. Of these, 92% of kidney stones were eligible for AI-assisted interpretation. Out of these AI-eligible stones, 45% were able to be auto-released by the AI-augmented test system without human secondary review. Furthermore, the new AI-augmented kidney stone test system resulted in an apparent 40% reduction in incorrect laboratory results. Additionally, the new AI-augmented test system improved laboratory efficiency by 20%, improved staff satisfaction, and reduced the average analysis cost per kidney stone by $0.23. Conclusions The AI-augmented test system improved test quality, efficiency, cost-effectiveness and staff satisfaction related to this kidney stone composition test.

BACKGROUND: Subjective evaluations to confirm recovery from neuromuscular blockade with a peripheral nerve stimulator (PNS) is inadequate. Quantitative monitors are the only reliable method to confirm adequate recovery of neuromuscular function. Unfortunately, many clinicians are unfamiliar with such devices and there is concern that the introduction of objective monitoring would be exceedingly laborious and could cause workflow delays. This study investigates how long it takes experienced nurse anesthetists to apply various neuromuscular devices as well as their perception regarding the ease of application. METHODS: Twenty nurse anesthetists were consented and participated in an educational session that familiarized them with 3 devices: SunStim Plus PNS (SunMed, Grand Rapids, MI), the acceleromyography-based IntelliVue NMT device (Philips, Amsterdam, the Netherlands), and electromyography-based TetraGraph device (Senzime B.V., Uppsala, Sweden). Participants were timed while placing each monitor on patients in a real-world setting. For the quantitative devices (IntelliVue NMT and TetraGraph), participants were also timed when obtaining calibrated baseline train-of-four (TOF) ratios. Friedman test and pairwise Wilcoxon signed-rank tests were used to evaluate the difference in time to connect different devices. Participants were surveyed about how easy they found it to utilize these devices. RESULTS: After adjusting for multiple comparison, time to connect was significantly less for PNS (median, 29; range, 16–58 seconds) compared to either the TetraGraph device (median, 62.8; range, 32–101 seconds; P < .001) or the IntelliVue NMT device (median, 46; range: 28–90 seconds; P < .001). The difference in time to connect between the TetraGraph device and the IntelliVue NMT device was not statistically significant ( P = .053), but it took significantly less time to calibrate the TetraGraph device than the IntelliVue NMT device (median difference, −16; range, −88 to 49 seconds; P = .002). The participants found applying either the IntelliVue NMT device ( P = .042) or the TetraGraph device ( P = .048) more difficult than applying a PNS while finding it easier to calibrate the TetraGraph device versus the IntelliVue NMT device ( P < .001). CONCLUSIONS: It takes 19 seconds longer to apply a quantitative neuromuscular monitor (the IntelliVue NMT device) than a PNS. While this difference reached significance, this relatively minimal additional time represents an inappropriate barrier to the application of quantitative monitors. Regardless of which quantitative monitor was utilized, these nurse anesthetists found the application and utilization of such devices relatively straightforward.

Background: Identification of systolic heart failure among patients presenting to the emergency department (ED) with acute dyspnea is challenging. The reasons for dyspnea are often multifactorial. A focused physical evaluation and diagnostic testing can lack sensitivity and specificity. The objective of this study was to assess the accuracy of an artificial intelligence-enabled ECG to identify patients presenting with dyspnea who have left ventricular systolic dysfunction (LVSD). Methods: We retrospectively applied a validated artificial intelligence-enabled ECG algorithm for the identification of LVSD (defined as LV ejection fraction ≤35%) to a cohort of patients aged ≥18 years who were evaluated in the ED at a Mayo Clinic site with dyspnea. Patients were included if they had at least one standard 12-lead ECG acquired on the date of the ED visit and an echocardiogram performed within 30 days of presentation. Patients with prior LVSD were excluded. We assessed the model performance using area under the receiver operating characteristic curve, accuracy, sensitivity, and specificity. Results: A total of 1606 patients were included. Median time from ECG to echocardiogram was 1 day (Q1: 1, Q3: 2). The artificial intelligence-enabled ECG algorithm identified LVSD with an area under the receiver operating characteristic curve of 0.89 (95% CI, 0.86–0.91) and accuracy of 85.9%. Sensitivity, specificity, negative predictive value, and positive predictive value were 74%, 87%, 97%, and 40%, respectively. To identify an ejection fraction <50%, the area under the receiver operating characteristic curve, accuracy, sensitivity, and specificity were 0.85 (95% CI, 0.83–0.88), 86%, 63%, and 91%, respectively. NT-proBNP (N-terminal pro-B-type natriuretic peptide) alone at a cutoff of >800 identified LVSD with an area under the receiver operating characteristic curve of 0.80 (95% CI, 0.76–0.84). Conclusions: The ECG is an inexpensive, ubiquitous, painless test which can be quickly obtained in the ED. It effectively identifies LVSD in selected patients presenting to the ED with dyspnea when analyzed with artificial intelligence and outperforms NT-proBNP. Graphic Abstract: A graphic abstract is available for this article.