Objective: With the recent development of various MRI-conditional cardiac implantable electronic devices (CIEDs), the accurate identification and characterization of CIEDs have become critical when performing MRI in patients with CIEDs. We aimed to develop and evaluate a deep learning-based algorithm (DLA) that performs the detection and characterization of parameters, including MRI safety, of CIEDs on chest radiograph (CR) in a single step and compare its performance with other related algorithms that were recently developed. Materials and Methods: We developed a DLA (X-ray CIED identification [XCID]) using 9912 CRs of 958 patients with 968 CIEDs comprising 26 model groups from 4 manufacturers obtained between 2014 and 2019 from one hospital. The performance of XCID was tested with an external dataset consisting of 2122 CRs obtained from a different hospital and compared with the performance of two other related algorithms recently reported, including PacemakerID (PID) and Pacemaker identification with neural networks (PPMnn). Results: The overall accuracies of XCID for the manufacturer classification, model group identification, and MRI safety characterization using the internal test dataset were 99.7% (992/995), 97.2% (967/995), and 98.9% (984/995), respectively. These were 95.8% (2033/2122), 85.4% (1813/2122), and 92.2% (1956/2122), respectively, with the external test dataset. In the comparative study, the accuracy for the manufacturer classification was 95.0% (152/160) for XCID and 91.3% for PPMnn (146/160), which was significantly higher than that for PID (80.0%,128/160; p < 0.001 for both). XCID demonstrated a higher accuracy (88.1%; 141/160) than PPMnn (80.0%; 128/160) in identifying model groups (p < 0.001). Conclusion The remarkable and consistent performance of XCID suggests its applicability for detection, manufacturer and model identification, as well as MRI safety characterization of CIED on CRs. Further studies are warranted to guarantee the safe use of XCID in clinical practice.

BACKGROUND: Many epidemiological studies have reported that hyperuricemia was related to cardiovascular diseases, insulin resistance and the metabolic syndrome. However, there are few studies on the relationship between serum uric acid concentration and the metabolic syndrome among Korean adults. We performed this study to assess the relationship between serum uric acid level and the factors of the metabolic syndrome among healthy Korean men. METHODS: We consecutively selected 206 male subjects who underwent health screening examination from February 2005 to April 2005 at the Health Promotion Center of Seoul Paik Hospital. Insulin resistance measured by HOMA-IR and the metabolic syndrome factors were assessed by the quartiles of serum uric acid level. RESULTS: Body mass index (P<0.001), systolic blood pressure (P=0.015), diastolic blood pressure (P=0.015), fasting insulin (P=0.038), and triglyceride (P=0.005) level increased and high density lipoprotein cholesterol (P=0.008) decreased significantly from the lowest quartile to the highest quartile of seum uric acid level. The proportions of the metabolic syndrome in each quartile were 13.7%, 15.7%, 18.9%, and 36.0%, respectively (P=0.007). However, insulin resistance measured by HOMA-IR was not associated with serum uric acid. When compared with the lowest quartile group, the odds ratio for the metabolic syndrome of the second, the third, and the highest quartile groups were 1.42 (0.39-5.14), 1.14 (0.33-3.92), and 4.00 (1.15-13.89), respectively. CONCLUSION: We found that high uric acid level was significantly related to the factors of the metabolic syndrome and increased the risk of the metabolic syndrome. Further prospective studies with large sample size are necessary to establish whether uric acid level can pose as a risk factor for the development of the metabolic syndrome.
Adult ; Blood Pressure ; Body Mass Index ; Cardiovascular Diseases ; Cholesterol, HDL ; Fasting ; Health Promotion ; Humans ; Hyperuricemia ; Insulin ; Insulin Resistance ; Male ; Mass Screening ; Odds Ratio ; Risk Factors ; Sample Size ; Seoul ; Triglycerides ; Uric Acid*