OBJECTIVES: This study aimed to characterize the care pathway of post-MI patients and understand barriers to referral for further SCD risk stratification and management in patients meeting referral criteria.
METHODS: This prospective, nonrandomized, multi-nation study included patients ≥18 years of age, with an acute MI ≤30 days and left ventricular ejection fraction <50% ≤14 days post-MI. The primary endpoint was defined as the physician's decision to refer a patient for SCD stratification and management.
RESULTS: In total, 1,491 post-MI patients were enrolled (60.2 ± 12.0 years of age, 82.4% male). During the study, 26.7% (n = 398) of patients met criteria for further SCD risk stratification; however, only 59.3% of those meeting criteria (n = 236; 95% CI: 54.4%-64.0%) were referred for a visit. Of patients referred for SCD risk stratification and management, 94.9% (n = 224) attended the visit of which 56.7% (n =127; 95% CI: 50.1%-63.0%) met ICD indication criteria. Of patients who met ICD indication criteria, 14.2% (n = 18) were implanted.
CONCLUSIONS: We found that ∼40% of patients meeting criteria were not referred for further SCD risk stratification and management and ∼85% of patients who met ICD indications did not receive a guideline-directed ICD. Physician and patient reasons for refusing referral to SCD risk stratification and management or ICD implant varied by geography suggesting that improvement will require both physician- and patient-focused approaches. (Improve Sudden Cardiac Arrest [SCA] Bridge Study; NCT03715790).
OBJECTIVES: This study aimed to provide a personalized surgical recommendation that enables more confidence in advising patients to pursue surgical treatment.
METHODS: We enrolled 328 patients with uPA harboring KCNJ5 mutations (n = 158) or not (n = 170) who had undergone adrenalectomy. Eighty-seven features were collected, including demographics, various blood and urine test results, and clinical comorbidities. We designed 2 versions of the prediction model: one for institutes with complete blood tests (full version), and the other for institutes that may not be equipped with comprehensive testing facilities (condensed version).
RESULTS: The results show that in the full version, the Light Gradient Boosting Machine outperformed other classifiers, achieving area under the curve and accuracy values of 0.905 and 0.864, respectively. The Light Gradient Boosting Machine also showed excellent performance in the condensed version, achieving area under the curve and accuracy values of 0.867 and 0.803, respectively.
CONCLUSIONS: We simplified the preoperative diagnosis of KCNJ5 mutations successfully using machine learning. The proposed lightweight tool that requires only baseline characteristics and blood/urine test results can be widely applied and can aid personalized prediction during preoperative counseling for patients with uPA.