Search Results (1,100)

Machine learning (ML) excels over regression by automatically capturing complex, non-linear relationships and interactions, enabling more flexible and accurate predictions without strict assumptions. This study focuses on developing ML-based predictive models for key post-PCI outcomes: 30-day mortality, in-hospital major bleeding, and one-year mortality. Data from 104,665 consecutive PCI cases in the Victorian Cardiac Outcomes Registry (VCOR), collected between 2013 and 2022, will be analyzed. Candidate variables, informed by prior systematic reviews and dataset availability, will undergo multiple imputations for missing values. The Boruta method will be applied to identify influential predictors. Risk-adjusted models will be developed using sophisticated ML algorithms, with performance compared across standard metrics for validation. The dataset will be split, optimized via 10-fold cross-validation, and class imbalance addressed using Adaptive Synthetic resampling technique. SHapley Additive exPlanations will interpret the most influential predictors. The variables from the best model will be converted into simplified numeric scores. External validation will be performed using the Tasmanian dataset or equivalent datasets. This study is expected to identify the most influential variables associated with 30-day all-cause mortality, in-hospital major bleeding, and long-term mortality post-PCI. These variables will form the basis for developing robust risk-scoring models to support clinical decision-making and outcome prediction. Full article

Background: Childhood cancers (CC) are rare and treatable; however, survival rates vary across Europe, with poorer outcomes in Eastern countries. Stage at diagnosis is one of the major prognostic factors. The BENCHISTA-Ita project aims to promote the use of the Toronto Guidelines by population-based cancer registries (PBCR) to standardize stage at diagnosis data collection. In Italy, regional cancer registries ensure data quality, while national clinical registries centralize pediatric cancer data. The aim of the study is to promote the linkage between PBCRs and national clinical registries to enhance data completeness. This study presents the results of linking BENCHISTA-Ita neuroblastoma cases with the Italian Neuroblastoma Registry (RINB) as a pilot study. Methods: The linkage process involved probabilistic matching using R software, considering variables such as sex, year of birth, and residence at diagnosis. The study included 294 neuroblastoma cases from BENCHISTA-Ita and 578 from RINB, diagnosed between 2013 and 2017. Results: Results showed that 272 of 294 BENCHISTA-Ita cases matched with RINB cases, improving the completeness of clinical variables such as stage at diagnosis, N-Myc amplification, and relapse/progression. The linkage increased the completeness of clinical variables in PBCR, such as stage at diagnosis from 81% to 99%, N-Myc from 47% to 86%, and relapse/progression from 68% to 98%. Additionally, the linkage improved RINB’s follow-up completeness from 59% to 97% and added new cases in both PBCR and RINB. Conclusions: This linkage demonstrates the potential to enrich both databases, improving data quality and harmonization of cancer indicators. The study highlights the importance of collaboration between PBCRs and clinical registries to ensure comprehensive data collection and enhance more informative population-based studies. Future efforts will focus on expanding the linkage to other national clinical registries. Full article

Background/Objectives: Endometrial hyperplasia (EH) is a pathology of the uterus, which is a pathological overgrowth of the endometrial glands associated with the risk of progression to endometrial cancer (EC). The purpose of this study was to conduct a retrospective comparative analysis of the medical and social characteristics of women with endometrial hyperplasia (EH) across two time periods (2016–2017 and 2023–2024) in Almaty, the largest city in Kazakhstan. Methods: A retrospective comparative analysis included 376 women (188 per period) with histologically confirmed EH treated in public and private healthcare facilities. Data were extracted from electronic medical systems (Damumed, Avicenna). Group differences were evaluated using the χ² test, Fisher’s exact test, and Mann–Whitney U test. Odds ratios (OR) with 95% confidence intervals (CI) were calculated; significance was set at p < 0.05. Results: The proportion of postmenopausal women increased from 22.3% to 37.8% (OR: 2.11, 95% CI: 1.34–3.32, p < 0.001), and self-referrals to private clinics rose from 17.6% to 37.2% (OR: 2.79, 95% CI 1.73–4.49, p < 0.001). Women with higher education became more prevalent (from 26.1% to 43.6%, OR: 2.19, 95% CI: 1.42–3.39, p < 0.001), along with an increase in endocrine and metabolic disorders such as thyroid disease (from 4.8% to 12.2%, OR: 2.77, 95% CI: 1.25–6.16) and overweight status (from 51.6% to 65.4%, OR: 1.78, 95% CI: 1.17–2.69, p = 0.020). Asymptomatic cases were more frequently detected (from 18.6% to 28.2%, OR: 1.72, CI: 1.06–2.79, p = 0.028), and diagnostic approaches shifted from blind curettage (78.2% vs. 47.3%, OR: 0.25, CI: 0.16–0.39, p < 0.001) toward hysteroscopy with biopsy (from 21.3% to 53.7%, OR: 4.30, CI: 2.73–6.75, p < 0.001). Conclusions: Over seven years, the clinical and socio-demographic composition of women with EH in Almaty has changed toward older, more educated, and metabolically burdened populations, with broader access to minimally invasive diagnostic methods. The findings describe observable structural changes and risk group patterns, emphasizing the importance of prospective, registry-based, and molecularly oriented studies to refine clinical strategies for prevention and early detection. Full article

Background: Cancer patients are particularly vulnerable to severe outcomes from COVID-19 due to immune suppression, treatment effects, and comorbidities. This population-based study aimed to assess how vaccination, circulating variants, and comorbidities influenced infections and severe disease risks in cancer patients compared with the general population. Methods: The study included 538,516 residents of Reggio Emilia Province, Italy, alive on 20 February 2020, followed until 30 September 2022. Cancer diagnoses (1996–2021) were obtained from the Reggio Emilia Cancer Registry and linked with COVID-19 surveillance, vaccination, hospitalization, and mortality data. Vaccination and prior infection were modelled as time-dependent variables. Hazard ratios for infection (HRs) and odds ratios for severe disease in those infected (ORs) were estimated using Cox and logistic regression models adjusting for sex, age, and comorbidities. Results: Among the 33,307 residents who had cancer, 9135 SARS-CoV-2 infections were recorded. Infection risk was similar to the general population before Omicron (HR 1.00; 95%CI 0.96–1.05) and slightly higher during Omicron (HR 1.08; 95%CI 1.05–1.11). Cancer patients showed higher probability of severe disease once infected (OR 1.33 pre-Omicron; 1.67 Omicron), with the greatest excess in recent diagnoses. Vaccination substantially reduced infections and severe outcomes in both groups in the pre-Omicron period; while only hybrid immunity reached high protection from Omicron infection. Conclusions: Vaccinations were effective in the populations with and without cancer; hybrid immunity conferred the strongest protection. However, because cancer patients, especially those recently diagnosed, retain a higher baseline risk of severe disease, vaccination yields even greater individual and public health benefits. Full article

Background: Biological sex differences are well-recognized as non-negligible factors in implementing precision medicine practice. Sex chromosomes influence protein expression and signaling, and thus cellular pathways are often regulated differently. Additionally, the importance of sex as a biological variable has gained significant traction in biomedical research, including transfusion medicine. Regarding transfusion medicine, several studies reveal the role of gender in blood transfusion, blood donors’ behavior towards donation, blood products’ composition and storage, transfusion therapy, and possibly post-transfusion patient outcomes. Methods: In this review, the role of sex and gender in the whole transfusion chain (from the blood donor to the blood product and the patient) is assessed and summarized using data from observational studies, registry analyses, and randomized trials. Results: Female donors face higher deferral rates due to biological factors (iron deficiency, low hemoglobin, pregnancy) and sociocultural factors (caregiving responsibilities, misinformation). However, women are more likely to donate based on empathy, moral duty, or community responsibility and are more consistent in sustaining voluntary donation during crises. Men donate more frequently, typically driven by external motivators, and provide red blood cell (RBC) products with higher hemoglobin content, whereas RBCs from female donors exhibit greater metabolic stability and reduced hemolysis during storage. Plasma from multiparous women possibly contains alloantibodies associated with adverse transfusion reactions, namely transfusion-related acute lung injury (TRALI). Platelet function also varies by sex, though its possible clinical impact is still unknown. Although observational studies suggest sex-mismatched transfusions are associated with increased morbidity and mortality—particularly in transfusions from female donors to male recipients—large registries and randomized controlled trials show inconsistent or negligible effect on survival. Conclusions: Donor and recipient sex are emerging variables of possible clinical importance in transfusion practice. Incorporating sex-informed insights into donor recruitment, blood product handling and transfusion policies may improve safety while advancing precision medicine. Further large-scale trials are needed to elucidate the impact of sex in transfusion, identify and eliminate possible risks, and bridge the gap between biological insights and clinical practice. Full article

Primary ciliary dyskinesia (PCD) is a rare hereditary disorder belonging to the group of ciliopathies, with autosomal recessive, autosomal dominant, and, less frequently, X-linked inheritance patterns. The aim of this study was to investigate the genetic heterogeneity of the Russian population of PCD patients based on national registry data. The study included patients with PCD confirmed by molecular genetic testing. Quantitative data were analyzed using non-parametric statistical methods. Differences were considered statistically significant at p < 0.05. The study included 109 patients with PCD. Molecular genetic testing identified pathogenic variants in 29 autosomal recessive genes. The analysis of pathogenic variant distribution in the Russian PCD cohort revealed the highest number of changes in the DNAH5 and DNAH11 genes. 26 genetic variants in 13 genes were identified for the first time in the Russian population. Variants in the DNAH5 gene were significantly more frequent in Kartagener’s syndrome (KS) patients (32/55%) compared to those without KS (11/21.5%) (χ² = 12.8; p = 0.0004; OR = 4.48). Preliminary data indicate that the frequency spectrum of DNAH5 and DNAH11 genes in Russian patients is similar to international trends. Additionally, there is an accumulation of pathogenic variants in the DNAH5, DNAH11, CCDC39, and CFAP300 genes. Full article

Background: Prostate cancer is a major public health concern in Ghana, where most cases present late and mortality remains high. Community education is essential for improving awareness and early detection. Traditional health talks are widely used, but interactive approaches such as board games have received little evaluation. Aim: To compare the effectiveness of a Social Cognitive Theory–Socioecological Model-based literacy board game (S-S-LIBOG) with a traditional health talk in improving prostate cancer knowledge, attitudes, and perceptions. Methods: A quasi-experimental, two-arm interventional study was conducted in a semi-urban Ghanaian cohort. Participants (n = 197) were allocated to either the board game arm (n = 80) or the health talk arm (n = 61) after accounting for attrition. A structured questionnaire measured knowledge, attitudes, and perceptions (KAP) before and after intervention. Statistical analyses at 5% alpha level included chi-square tests, two-proportion Z-tests, Wilcoxon signed-rank tests, and multivariate logistic regression. Results: Among participants, 29.4% were female, 64.5% male, and 6.1% other genders. Tertiary education was reported by 81.7%, secondary 9.6%, postgraduate 5.6%, and primary 3.0%. Ethnicities: Ewe 41.6%, Akan 26.9%, Northern 13.7%, Ga 6.6%, Guan 1.5%, others 9.6%. Rural dwellers: 29.9%. LIBOG improved ‘good knowledge level’ from 35.0% at baseline to 60.0% post-intervention, compared to 35.0% to 62.3% by the Health Talk (HT). S-S-LIBOG also narrowed gender, education, and lifestyle disparities in KAP, with males showing higher odds of positive attitude (OR = 4.16, p = 0.004) and perception (OR = 2.79, p = 0.047), and rural residents having increased odds of good knowledge (OR = 4.39, p = 0.041) post—its intervention. HT similarly equalized disparities, except for perception, which remained linked to education. The significant improvements in knowledge were (LIBOG: z = 2.85, p = 0.004; HT: z = 3.10, p = 0.002). Even though health talks achieved higher overall knowledge gains, no statistically significant difference in overall effectiveness was observed between the two methods (Wilcoxon W = 102.0, p = 0.107). Acceptability of the board game was high, with over 80% of participants reporting satisfaction. Conclusions: The S-S-LIBOG board game was not inferior to the traditional health talk, showing particular strengths in enhancing attitudes and perceptions. Its interactive and culturally adapted design makes it a feasible adjunct to conventional health education methods. Future studies should examine long-term impacts and application in more diverse populations. This study was retrospectively registered by the Pan African Clinical Trial Registry on 10 October 2025; with the Trial Registration number PACTR202510512711680. Full article

Background: Pericardial mesothelioma (PM) is an extremely rare cancer with a poor prognosis and no consensus on diagnostic and therapeutic management. We conducted a registry-based study on PM cases in Italy diagnosed between 1993 and 2021. Methods: Based on data from the Italian National Mesothelioma Registry (ReNaM), we performed a descriptive analysis of PM cases including clinical presentation, diagnostic work-up, asbestos exposure, and therapeutic management. Overall survival was calculated. Hazard ratios (HRs) and 95% confidence intervals (CI) for selected variables were estimated with univariate and multivariate Cox models. Results: We identified 72 cases (46 men and 26 women). Median age was 66 years (range 22–89). The most frequent histological subtypes were epithelioid and unspecified mesothelioma. Almost two-thirds of cases had been exposed to asbestos. The most common clinical presentation was pericardial effusion. Overall median survival was 2.8 months (95% CI 1.2–6.6) and older age at diagnosis was a negative prognostic factor. Clinical and treatment data were available for 47 patients (65%). Approximately one out of two patients underwent surgery (palliative, in one-third of cases). Adjuvant therapy was administered to seven patients (15%). In cases with treatment information, sarcomatoid subtype (HR 2.74, 95% CI: 1.06–7.06) was a negative prognostic factor; adjuvant therapy was associated with better survival (HR 0.38, 95% CI 0.14–1.02), but confounding by indication cannot be excluded. Conclusions: We confirmed the very poor prognosis of PM. An international network collecting PM cases with treatment information is needed to improve patient quality of life and survival. Full article

Polymethyl methacrylate (PMMA) is widely used in modern dentistry, particularly in prosthodontics, orthodontics, and maxillofacial surgery. To improve the properties of PMMA, silver nanoparticles (AgNPs) are incorporated to enhance the antibacterial, antiviral, and antifungal effects of this material. This study aims to evaluate the antimicrobial properties of AgNPs as an additive to PMMA. Medical databases covered by the ACM, BASE, PubMed, and Scopus engines were searched. Of the 670 identified records, 23 studies were included that assessed the antibacterial and antifungal properties gained by incorporating AgNPs into PMMA. All of the studies included also contained a control group—PMMA without additives. Studies that evaluated nanoparticles other than AgNPs or materials other than PMMA were excluded. The data collected from the articles included the size and concentration of the nanoparticles, the method of sample preparation, sample size, information on the effect of nanoparticles on antimicrobial properties, and the contact time between the sample and the test tube containing fungi or bacteria. The data were presented in tables and graphs. The analysis indicated that increasing the weight percent concentration of AgNPs or extending the incubation time increases the antifungal efficacy. The result of Tau Kendall correlation showed that the pairs of data, concentration/incubation time and outcomes, are inversely proportional for fungi (p < 0.01). The results of the study are not entirely conclusive. Some limitations suggest the need for more standardized studies, which ideally should be conducted on human research groups and followed by a study of these properties and their effects on the human body. This systematic review followed PRISMA 2020 guidelines. The protocol was submitted to the Open Science Framework Registries (1 December 2024). Full article

Background: The paucity of data on the epidemiology of chronic intestinal failure (CIF) in pediatric patients is a matter of particular concern. The objective of this article is to provide a comprehensive description of the epidemiology of CIF in Spain, encompassing its incidence, geographical distribution, underlying causes, and demographic and clinical characteristics. These findings are based on data collected from the multicentre REPAFI registry. Methods: This is a national, multicentre, ambispective cohort study including patients who initiated home parenteral nutrition (HPN) between January 2015 and January 2025. The data collected encompassed various demographic details, underlying diagnoses, the type of HPN utilized, and the nutritional status of the subjects at the commencement of HPN treatment. Results: The study included 163 patients (55.2% male) from 10 hospitals. The principal cause of CIF was short bowel syndrome (SBS) in 77.3% of cases, followed by severe motility disorders (12.9%), congenital enteropathies (CE) (5.5%), and other causes (4.3%). Among patients diagnosed with SBS, necrotizing enterocolitis was identified as the most prevalent underlying cause (32.5%). The most prevalent anatomical configuration was identified as type 2 (jejuno-colic anastomosis). A significant proportion, amounting to 62.7%, exhibited a lack of an ileocecal valve (ICV), while 23% demonstrated a residual bowel length (RBL) of less than 15 centimetres. The median RBL was 35 cm (IQR: 15.7–52.5). Patients diagnosed with SBS exhibited a lower gestational age and birthweight compared with the other groups (p < 0.05). Patients diagnosed with SBS and CE exhibited a lower mean age at the onset of HPN (p < 0.05). Furthermore, patients with CE exhibited the lowest weight-for-age Z-score at the initiation of HPN (p < 0.05). Conclusions: The present study provides the first epidemiological data on the state of pediatric CIF in Spain. The most prevalent cause of CIF was SBS, with a younger age at the initiation of HPN in comparison to other published studies. Patients with CE exhibited the most severe degree of malnutrition at the initiation of HPN. Full article

Objectives: To study the associations of central retinal vein occlusion (CRVO) with glaucoma and cataract before and after the onset of CRVO. Methods: This study included 439 fundus photographically verified CRVO cases and a 5:1 set of 2195 registry-based age- and sex-matched control subjects without a record of CRVO. The study assessed rates of cataract and glaucoma before and after CRVO based on diagnoses, procedures, and prescriptions and analyzed their association with CRVO. Odds ratio (OR) and incidence rate ratio (IRR) estimates for 10 years prior to a subject’s first CRVO and incident comorbidity after CRVO were compared. Results: The median age at the time of presentation of 439 eligible patients with CRVO was 71 years (interquartile range 11 years). In the 10 years leading up to the incidence of CRVO, the ORs for glaucoma and cataract were 6.01 (95% confidence interval (CI95) 4.05 to 8.94) and 2.13 (CI95 1.45 to 3.12), respectively. During a mean follow-up of 5.7 years after CRVO, the incidence rate ratios for glaucoma and cataract were 16.7 (CI95 9.32–30.1) and 1.99 (CI95 1.39–2.84), respectively. Conclusions: Glaucoma and cataract occurred at elevated rates compared with the background population, both before and after the clinical presentation of CRVO. The results fit a disease model where retinal perfusion is compromised by chronic venous congestion, leading to glaucomatous retinal degeneration. Chronic venous congestion may subsequently convert to clinically manifest CRVO when retinal capillaries have been sufficiently weakened to produce hemorrhage, edema and vision loss. Full article

Background: Conservative management of grade 2 cervical intraepithelial neoplasia (CIN2) is now supported by international guidelines, especially in young women or those seeking fertility. However, identifying subgroups at increased risk of progression remains a clinical priority, especially in settings with prolonged surveillance. Objectives: To evaluate the clinical evolution of CIN2 in an HPV-positive cohort followed under active surveillance for a maximum follow-up of 48 months, with particular attention to the risk of progression, persistence and regression, and associated predictors. Methods: Retrospective observational study conducted on a cohort of 237 HPV-positive women with a histological diagnosis of CIN2. Three possible clinical outcomes (progression, persistence, and regression) were analyzed. Patients underwent structured follow-up including cytology and colposcopy every 6 months, and HPV testing annually. Excisional treatment was performed only in case of progression or poor compliance. Logistic regression (univariate and multivariate) was applied to identify independent predictors of progression and regression. Results: After a maximum follow-up of 48 months. 61.3% of lesions regressed spontaneously, 13.1% persisted, and 25.5% progressed to CIN3. In multivariate analysis, high-grade cytology (ASC-H/HSIL) and HPV 16/18 infection were independently associated with a reduced likelihood of regression (OR ≈ 0.5, p < 0.01) and an increased risk of progression (OR ≈ 2.0, p < 0.05). Lesion size and age were not significant predictors. Importantly, no invasive carcinoma occurred during follow-up. Conclusions: Active surveillance for CIN2 remains a valid strategy in low-risk subgroups, but it is not universally safe. Data suggest that the combination of high-grade cytology and HPV 16/18 represents a high oncological risk profile, for which prompt treatment is indicated. Persistence beyond 36 months should be considered a cumulative risk marker, with implications for personalized follow-up and risk management. Further prospective, registry-linked studies are required to validate long-term safety and refine risk-based management strategies for CIN2. Full article

Background: Environmental problems can significantly influence population health. Cardiovascular diseases (CVDs) are the most common cause of death in developed countries including in Kazakhstan. The aim of our study was to assess the relationship between exposure to ionizing radiation and mortality risks from major CVDs for the population of Kazakhstan living in areas adjacent to the Semipalatinsk nuclear test site (SNTS). Materials and Methods: The study of the structure and dynamics of cardiovascular mortality was based on the State Scientific Automated Medical Registry (SSAMR) database. Among members of the exposed group, the median equivalent radiation dose was 864.0 mSv, compared to 64.4 mSv in the control group. It should be noted that almost the entire population of the Semipalatinsk region was exposed to some degree of radiation; however, the Kokpekti district received the lowest radiation doses. Results: Mortality rates from CVD were statistically significantly higher in the radiation-exposed population from 1960 to 1994, with RR fluctuating from 1.118 to 8.7. The predominant mortality events were chronic coronary heart disease, chronic cerebrovascular disease, and hemorrhagic stroke throughout the study period, and acute myocardial infarction within 20 years of the start of nuclear testing. In the exposed group, RR = 10.35 for chronic cerebrovascular disease, RR = 3.56 for hemorrhagic stroke, and RR = 5.77 for peripheral arterial atherosclerosis. A dose of 100–500 mSv increased the risk of mortality from CVD by 3.14 times, and a dose of >600 mSv increased it by 7.05 times. Conclusions: A link has been established between long-term exposure to ionizing radiation and increased risks of mortality from CVD in the population of areas contaminated with radiation as a result of nuclear testing. Full article

Background: Pulmonary embolism (PE) remains a major cause of cardiovascular morbidity and mortality. Classical risk factors explain only part of the interindividual variability in thrombotic risk. Non-O blood groups are associated with higher plasma levels of von Willebrand factor and factor VIII, suggesting a potential prothrombotic mechanism. This systematic review and limited meta-analysis examined the relationship between ABO blood group and PE risk. Methods: Following PRISMA 2020 guidelines, PubMed, Embase, and Web of Science were searched through August 2025 for observational studies reporting ABO blood group and objectively confirmed PE in adults. Eligible designs included cohort, case–control, and registry-based studies. Two reviewers independently extracted data and assessed risk of bias using the Newcastle–Ottawa Scale. Comparable effect estimates were pooled using a random-effects model (DerSimonian–Laird method, inverse-variance weighting). Results: Four studies met inclusion criteria, comprising more than 300,000 participants from North America, Europe, and Asia. All reported a higher incidence of PE among non-O compared with O blood groups. Pooled analysis of two large population-based cohorts yielded a summary relative risk of 1.36 (95% CI 1.20–1.54; I² = 2.6%), indicating a modest but consistent association. Data on recurrence, severity, and mortality were limited and heterogeneous. Conclusions: Non-O blood groups are associated with an approximately 30–40% higher risk of PE across diverse populations. While evidence is insufficient for causal inference, ABO phenotype represents a biologically plausible and readily available marker that may complement multifactorial models of thromboembolic risk. Full article

Background/Objectives: Pulmonary arterial hypertension (PAH) is a complex cardiovascular disease with a high burden of morbidity and mortality. Although several risk prediction models have been proposed, the exact significance of distinct clinical parameters in predicting survival in PAH remains unclear. It is important to emphasize that this study does not aim to validate or contradict existing clinical risk assessment calculators provided by the ESC or other scientific societies. Instead, the goal of this research is to identify and rank clinical parameters according to their importance in predicting mortality in PAH patients using machine learning techniques. Methods: Using the Database of Pulmonary Hypertension in the Polish population (BNP-PL) registry, 1755 adult patients with PAH were selected. Feature engineering was conducted using domain knowledge, guided by European Society of Cardiology (ESC) recommendations. Features were reduced using LASSO regression and sequential feature elimination algorithms. A classification model was built using the XGBoost algorithm, utilizing 17 features. The model was tested on a preselected subset of the BNP-PL data. The Shapley Additive Explanations (SHAP) method was used to explain the model’s predictions and to rank feature importance. Results: The model achieved satisfactory results across evaluated metrics, including an area under the curve of 0.767, accuracy of 0.738, specificity of 0.733, and sensitivity of 0.800. SHAP values effectively ranked the features, corroborating the significance of parameters present in the ESC risk stratification tables. Furthermore, local interpretation of results using SHAP enabled individualized assessment of feature importance, enhancing clinical applicability. Conclusions: The proposed artificial intelligence-based model demonstrates satisfactory predictive capability, highlighting the potential of machine learning techniques to support more personalized approaches to the management of PAH patients. This approach offers complementary insights into traditional risk assessment methods, providing clinicians with a novel tool for individualized risk evaluation and decision-making. Full article