BACKGROUND: The modern model of healthcare requires a paradigm shift in the thinking of healthcare managers, doctors, and patients. A personalized approach, identification of possible causes of diseases, and prevention of pathologies are the components of successful and quality healthcare delivery in our country. Dentistry is a field in which preventive, prophylactic, and personalized medicine is an integral part of patient care. One of the important tasks of modern digital dentistry is to find indicators that allow for predicting dental implant complications. The solution to this problem could be the creation of a medical decision support system that allows predicting outcomes before implant surgery. AIMS: To reliably identify predictors of early (up to 6 months) risk of dental implant rejection by applying hierarchical Bayesian survival analysis models. METHODS: Data collected retrospectively for patients who underwent dental implant placement between 2013 and 2022 were considered information bases. Data were generated from multicenter surveys conducted in dental implant centers in Stavropol, Moscow, and Penza. The total number of observed cases was 1472. A group of defined factors was considered candidate risk predictors, and the Bayesian hierarchical Cox model (Gsslasso Cox) was used to identify risk predictors. RESULTS: After retrospective analysis of the collected data and screening out incomplete and poor-quality information, the database included a total of 39 variables (factors) for 1472 observations (implants). The multivariate analysis yielded the following predictors of risk of early dental implant rejection: male sex (hazard ratio [HR] 2.388, 95% confidence interval [CI] 1.345; 4.240, p=0.003), age at implantation (years; HR1.034, 95% CI 1.0081.041, p=0.011), oral hygiene (SilnesLow index; HR 2.439, 95% CI 1.2054.701, p=0.051), osteoporosis (HR 5.512, 95% CI 3.6848.248, p 0.001), bone width (mm; HR 0.823, 95% CI 0.7160.944, p=0.006), anesthetic type (local; HR 0.469, 95% CI 0.2340.944, p=0.034), localized periodontitis (HR 2.024, 95% CI 1.4522.821, p=0.039), and low-festooned, thick gingiva (HR=0.485; 95% CI: 0.358-0.658; p=0.0104). CONCLUSIONS: This study shows that predictors of risk of dental implant rejection can be identified separately in the early postoperative period (up to 6 months) by using hierarchical Bayesian survival analysis models, and risk predictors different from those in the longer term are identified in this period.