ABSTRACT
Background: There is conflicting evidence on the efficacy of primary prevention implantable cardioverter-defibrillator (ICD) implantation in the elderly. Objective: The purpose of this study was to determine the efficacy and safety of ICD implantation in patients 70 years and older. Methods: Patients (n = 167) aged 70 years or older and eligible for ICD implantation were randomly assigned (1:1) to receive either optimal medical therapy (OMT) (n = 85) or OMT plus ICD (n = 82). Results: Of the 167 participants (mean age 76.4 years; 165 men), 144 completed the study protocol according to their assigned treatment. Average participant follow-up was 31.5 months. Mortality was similar between the 2 groups: 27 deaths in OMT vs 26 death in ICD (unadjusted hazard ratio 0.92; 95% confidence interval 0.53-1.57), but there was a trend favoring the ICD over the first 36 months of follow-up. Rates of sudden death (7 vs 5; P = .81) and all-cause hospitalization (2.65 events per participant in OMT vs 3.09 in ICD; P = .31) were not statistically significantly different. Eleven participants randomized to ICD received appropriate therapy. Five participants received an inappropriate therapy that included at least 1 ICD shock. Conclusion: The study did not recruit to target sample size, and accumulated data did not show benefit of ICD therapy in patients 70 years or older. Future studies similar in design might be feasible but will need to contend with patient treatment preference given the large number of patients who do not want an ICD implanted. Further research is needed to determine whether the ICD is effective in prolonging life among elderly device candidates.
ABSTRACT
Accurate prediction of a rare and clinically important event following study treatment has been crucial in drug development. For instance, the rarity of an adverse event is often commensurate with the seriousness of medical consequences, and delayed detection of the rare adverse event can pose significant or even life-threatening health risks to patients. In this machine learning case study, we demonstrate with an example originated from a real clinical trial setting how to define and solve the rare clinical event prediction problem using machine learning in pharmaceutical industry. The unique contributions of this work include the proposal of a six-step investigation framework that facilitates the communication with non-technical stakeholders and the interpretation of the model performance in terms of practical consequences in the context of patient screenings for conducting a future clinical trial. In terms of machine learning methodology, for data splitting into the training and test sets, we adapt the rare-event stratified split approach (from scikit-learn) to further account for group splitting for multiple records of a patient simultaneously. To handle imbalanced data due to rare events in model training, the cost-sensitive learning approach is employed to give more weights to the minor class and the metrics precision together with recall are used to capture prediction performance instead of the raw accuracy rate. Finally, we demonstrate how to apply the state-of-the-art SHAP values to identify important risk factors to improve model interpretability.