Personalized Prediction Model Research Articles

Personalized prediction model specific for sudden cardiac death in the population: a machine learning study based on EHR

Abstract Background Predicting sudden cardiac death (SCD) in the general population remains a significant challenge, particularly at the individual level. SCD and myocardial infarction (MI) share similar pattern of characteristics and risk factors, making their specific prediction highly difficult. As a result, the current prediction models exhibit low specificity. Methods To estimate the specific risk of SCD over three months, we trained a machine learning model on electronic health record (EHR) data representing 8,566,229 drug prescriptions and 801,352 of hospital diagnoses up to five years prior to SCD. The data were obtained from a French cohort of 12,338 SCD and from a cohort of 12,338 controls from 2011 to 2015. We then validated the results on two external cohorts: one temporal cohort in the same area between 2016 and 2020 with 11,620 SCD cases and 11,620 controls and one geographical cohort from the USA with 892 SCD cases and 892 controls from 2013 to 2021. In order to address the specificity of our prediction model for SCD, SCD cases collected between 2016 and 2020 were also matched with a group of 35 000 controls who had myocardial infarction, with no SCD, following the same protocol as for the controls issued from the general population. Findings: The analysis reveals three distinct patterns of distribution for SCD cases, controls, and MI cases. We observed a semi linear increase of SCD cases over the deciles of predicted risk, and our model detected 24% (2,908) of SCD cases with a predicted risk exceeding 90% (highest decile). We observed the opposite among the controls that decreased linearly with increasing deciles of predicted risk: most of the controls were accurately identified in the lowest deciles, and there were only 214 controls (2%) in the highest decile. Interestingly, we observed a relatively stable distribution of MI cases across the deciles, with 10% of MI cases in the highest decile (Figure 1). Interpretation: We developed and validated a personalized prediction model that is able to identify subjects at high-risk for SCD specifically. Figure 1: Histogram of predicted risks for sudden cardiac death cases, controls and myocardial infarction cases in the validation cohort.Figure 1

Personal Bankruptcy Prediction Using Logistic Regression Model

According to the Insolvency Department of Malaysia, as of December 2023, 233,483 Malaysians are currently involved in bankruptcy cases due to their defaults on hire purchase loans, credit card loans, personal loans, housing loans, and business loans. This is indeed a critical issue because the growing number of personal bankruptcy cases will hurt the Malaysian economy as well as society. From an individual's economic perspective, bankruptcy minimizes their chances of getting a job. Apart from that, their accounts will be frozen, they will lose control of their properties and assets, and they will not be allowed to start any business or be a part of any company's Board of Directors. Bankrupts also will be rejected from any loan application. This paper examines this problem by developing a personal bankruptcy prediction model using the logistic regression technique. This paper defines "bankrupt" as terminated members who failed to settle their loans. The sample comprised 24,546 cases with 17% settled cases and 83% terminated cases. The data included a dependent variable, i.e., bankruptcy status (Y=1(bankrupt), Y=0(non-bankrupt)), and 12 predictors. Upon completion, this paper succeeds in coming out with a reliable personal bankruptcy prediction model and significant variables of personal bankruptcy. The findings of this paper are very beneficial and significant to creditors, banks, the Malaysia Department of Insolvency, potential borrowers, members of AKPK, and society in general in raising awareness of personal bankruptcy risks and such information may help them to take preventive measures in minimizing the number of personal bankruptcy cases.

Decentralized and Secure Collaborative Framework for Personalized Diabetes Prediction.

Diabetes is a global epidemic with severe consequences for individuals and healthcare systems. While early and personalized prediction can significantly improve outcomes, traditional centralized prediction models suffer from privacy risks and limited data diversity. This paper introduces a novel framework that integrates blockchain and federated learning to address these challenges. Blockchain provides a secure, decentralized foundation for data management, access control, and auditability. Federated learning enables model training on distributed datasets without compromising patient privacy. This collaborative approach facilitates the development of more robust and personalized diabetes prediction models, leveraging the combined data resources of multiple healthcare institutions. We have performed extensive evaluation experiments and security analyses. The results demonstrate good performance while significantly enhancing privacy and security compared to centralized approaches. Our framework offers a promising solution for the ethical and effective use of healthcare data in diabetes prediction.

Nomograms for prognosis prediction in esophageal adenocarcinoma: realities and challenges.

Prognostic assessment is of great significance for individualized treatment and care of cancer patients. Although the TNM staging system is widely used as the primary prognostic classifier for solid tumors in clinical practice, the complexity of tumor occurrence and development requires more personalized probability prediction models than an ordered staging system. By integrating clinical, pathological, and molecular factors into digital models through LASSO and Cox regression, a nomogram could provide more accurate personalized survival estimates, helping clinicians and patients develop more appropriate treatment and care plans. Esophageal adenocarcinoma (EAC) is a common pathological subtype of esophageal cancer with poor prognosis. Here, we screened and comprehensively reviewed the studies on EAC nomograms for prognostic prediction, focusing on performance evaluation and potential prognostic factors affecting survival. By analyzing the strengths and limitations of the existing nomograms, this study aims to provide assistance in constructing high-quality prognostic models for EAC patients.

Development and validation of an automatic machine learning model to predict abnormal increase of transaminase in valproic acid-treated epilepsy.

Valproic acid (VPA) is a primary medication for epilepsy, yet its hepatotoxicity consistently raises concerns among individuals. This study aims to establish an automated machine learning (autoML) model for forecasting the risk of abnormal increase of transaminase levels while undergoing VPA therapy for 1995 epilepsy patients. The study employed the two-tailed T test, Chi-square test, and binary logistic regression analysis, selecting six clinical parameters, including age, stature, leukocyte count, Total Bilirubin, oral dosage of VPA, and VPA concentration. These variables were used to build a risk prediction model using "H2O" autoML platform, achieving the best performance (AUC training = 0.855, AUC test = 0.789) in the training and testing data set. The model also exhibited robust accuracy (AUC valid = 0.742) in an external validation set, underscoring its credibility in anticipating VPA-induced transaminase abnormalities. The significance of the six variables was elucidated through importance ranking, partial dependence, and the TreeSHAP algorithm. This novel model offers enhanced versatility and explicability, rendering it suitable for clinicians seeking to refine parameter adjustments and address imbalanced data sets, thereby bolstering classification precision. To summarize, the personalized prediction model for VPA-treated epilepsy, established with an autoML model, displayed commendable predictive capability, furnishing clinicians with valuable insights for fostering pharmacovigilance.

Predicting Drug Resistance in Gastric Cancer with Mutation in the Human Epidermal Growth Factor Receptor 2 (HER2) And Machine Learning Technique

Gastric cancer with mutations in the human epidermal growth factor receptor (HER2) can be regarded as one of the leading causes of cancer mortality in the world. Targeted tyrosine kinase inhibitors (TKIs) developed against HER2 yielded optimistic results in improving patients' survival rates and life quality. Nevertheless, drug resistance can influence the critical supportive documents of treatment plans and decrease the treatment effectiveness after about one year. Predicting the efficacy of HER2-TKI drugs or therapies for patients with HER2-mutated gastric cancer is a critical research field. In the present study, a personalized drug response prediction model based on molecular dynamics simulations and machine learning is presented to predict response to first-generation drugs approved by the Ministry of Health in patients with gastric cancer. In the molecular dynamics simulation, the patient's mutation status is considered. The patient's unique mutation status was modeled using molecular dynamics simulations to extract geometric features at the molecular level.Furthermore, additional clinical features are incorporated into the machine learning model to predict drug response. The complete features encompass demographic and clinical characteristics, geometrical properties of the drug-target binding site, and binding free energy (RBFE) of the drug-target complex from molecular dynamics simulations. Drug response prediction utilizes the XGBoost classifier, which achieved leading-edge performance for a 4-level drug response prediction task (PDRP) with 97.5% accuracy, 93% sensitivity, 96.5% specificity, and 94% F1 score. The present research has demonstrated that modeling the binding cavity geometry, in tandem with the binding free energy, can effectively predict drug response. Interestingly, the clinical information, while significant, did not significantly influence the model's performance. This exciting finding opens up new avenues for testing the proposed model on various types of cancers, potentially revolutionizing drug development strategies. DOI: https://doi.org/10.52783/pst.391

Investigating Personalization Techniques for Improved Cybersickness Prediction in Virtual Reality Environments.

In recent cybersickness research, there has been a growing interest in predicting cybersickness using real-time physiological data such as heart rate, galvanic skin response, eye tracking, postural sway, and electroencephalogram. However, the impact of individual factors such as age and gender, which are pivotal in determining cybersickness susceptibility, remains unknown in predictive models. Our research seeks to address this gap, underscoring the necessity for a more personalized approach to cybersickness prediction to ensure a better, more inclusive virtual reality experience. We hypothesize that a personalized cybersickness prediction model would outperform non-personalized models in predicting cybersickness. Evaluating this, we explored four personalization techniques: 1) data grouping, 2) transfer learning, 3) early shaping, and 4) sample weighing using an open-source cybersickness dataset. Our empirical results indicate that personalized models significantly improve prediction accuracy. For instance, with early shaping, the Deep Temporal Convolutional Neural Network (DeepTCN) model achieved a 69.7% reduction in RMSE compared to its non-personalized version. Our study provides evidence of personalization techniques' benefits in improving cybersickness prediction. These findings have implications for developing personalized cybersickness prediction models tailored to individual differences, which can be used to develop personalized cybersickness reduction techniques in the future.

Prospective prediction of anxiety onset in the Canadian longitudinal study on aging (CLSA): A machine learning study

BackgroundAnxiety disorders are among the most common mental health disorders in the middle aged and older population. Because older individuals are more likely to have multiple comorbidities or increased frailty, the impact of anxiety disorders on their overall well-being is exacerbated. Early identification of anxiety disorders using machine learning (ML) can potentially mitigate the adverse consequences associated with these disorders. MethodsWe applied ML to the data from the Canadian Longitudinal Study on Aging (CLSA) to predict the onset of anxiety disorders approximately three years in the future. We used Shapley value-based methods to determine the top factor for prediction. We also investigated whether anxiety onset can be predicted by baseline depression-related predictors alone. ResultsOur model was able to predict anxiety onset accurately (Area under the Receiver Operating Characteristic Curve or AUC = 0.814 ± 0.016 (mean ± standard deviation), balanced accuracy = 0.741 ± 0.016, sensitivity = 0.743 ± 0.033, and specificity = 0.738 ± 0.010). The top predictive factors included prior depression or mood disorder diagnosis, high frailty, anxious personality, and low emotional stability. Depression and mood disorders are well known comorbidity of anxiety; however a prior depression or mood disorder diagnosis could not predict anxiety onset without other factors. LimitationWhile our findings underscore the importance of a prior depression diagnosis in predicting anxiety, they also highlight that it alone is inadequate, signifying the necessity to incorporate additional predictors for improved prediction accuracy. ConclusionOur study showcases promising prospects for using machine learning to develop personalized prediction models for anxiety onset in middle-aged and older adults using easy-to-access survey data.

Overcoming limitations in current measures of drug response may enable AI-driven precision oncology

Machine learning (ML) models of drug sensitivity prediction are becoming increasingly popular in precision oncology. Here, we identify a fundamental limitation in standard measures of drug sensitivity that hinders the development of personalized prediction models – they focus on absolute effects but do not capture relative differences between cancer subtypes. Our work suggests that using z-scored drug response measures mitigates these limitations and leads to meaningful predictions, opening the door for sophisticated ML precision oncology models.

Cohort profile: Worldwide Collaboration on OsteoArthritis prediCtion for the Hip (World COACH) – an international consortium of prospective cohort studies with individual participant data on hip osteoarthritis

PurposeHip osteoarthritis (OA) is a major cause of pain and disability worldwide. Lack of effective therapies may reflect poor knowledge on its aetiology and risk factors, and result in the...

Visual Insights in Lung Cancer Prediction: Leveraging Data Visualization and Analysis for Building and Tuning Machine Learning Models

Lung cancer stands as a significant global health challenge with its high occurrence rates and fatal lethality. Given lung cancer's severity and complicated symptoms in later stages, healthcare facilities must detect them early. Traditional diagnostic methodologies are often burdened by high cost and specialized expertise, prompting exploration of alternative methods, such as machine Learning. This paper utilizes a dataset from a Nature Medicine study involving 462,000 participants in China and employs machine learning to predict lung cancer risk. Through the application of Exploratory Data Analysis (EDA), this paper explored the correlation between demographic variables, environmental factors, and lifestyle habits with the probability of lung cancer occurrence. The neural network architecture incorporates dynamic layers, rectified linear unit (ReLU) activation, and the Adam optimizer with dropout regularization. Results from EDA reveal correlations between lifestyle factors and lung cancer risk. The machine learning model achieved 70% accuracy on predictions and was refined to 90% through EDA and utilizing the LIME interpreter. This study aimed to advance lung cancer prediction by applying an amalgamation of techniques and technologies, like data visualization, extensive data analysis, and machine learning. This research aimed to contribute to the showcase of applying the latest technological advancements for the era of big data within the medical research and healthcare industry. The success of this model suggests the viability of creating machine learning models targeted for cancer predictions and indicates further advancements, such as personalized prediction models.

Impact of lighting environment on human performance and prediction modeling of personal visual comfort in enclosed cabins

Enclosed cabins are of great significance in various fields, including national defense, scientific research, and industrial applications. It is important to clarify the impact of the lighting environment in these cabins on the people operating within them. This study investigated the effects of the lighting environment in enclosed cabins on the physiological, operational, and comfort performance of operators through simulated experiments. In Addition, using the Random Forest Algorithm and ExpandNet technique, we developed a prediction model to evaluate the comfort level of the lighting environment for personnel in enclosed cabins. The results indicated that pupil diameter exhibited the highest sensitivity to ambient light. The appropriate luminance combination of the screen and the ambient scene have a positive effect on human performance. In particular, it was observed that the average cognitive performance and comfort of participants tended to be relatively high in the luminance combinations 13, 14, and 15 at CCT 5500 K. The screen luminance of these combinations are all 284.75 cd/m2. Although no statistically significant relationship was found between the cognitive performance of the participants and their comfort, the comfort of the participants tended to decrease after the cognitive operations was completed. According to the proposed personal comfort prediction model, the visual comfort of different people varies even under the same lighting conditions. This study provides a solid theoretical basis for improving the design of lighting environments in enclosed spaces and contributes to developing a pleasant and productive working environment within limited cabins.

Optimizing prediction models for pancreatic fistula after pancreatectomy: Current status and future perspectives

Postoperative pancreatic fistula (POPF) is a frequent complication after pancreatectomy, leading to increased morbidity and mortality. Optimizing prediction models for POPF has emerged as a critical focus in surgical research. Although over sixty models following pancreaticoduodenectomy, predominantly reliant on a variety of clinical, surgical, and radiological parameters, have been documented, their predictive accuracy remains suboptimal in external validation and across diverse populations. As models after distal pancreatectomy continue to be progressively reported, their external validation is eagerly anticipated. Conversely, POPF prediction after central pancreatectomy is in its nascent stage, warranting urgent need for further development and validation. The potential of machine learning and big data analytics offers promising prospects for enhancing the accuracy of prediction models by incorporating an extensive array of variables and optimizing algorithm performance. Moreover, there is potential for the development of personalized prediction models based on patient- or pancreas-specific factors and postoperative serum or drain fluid biomarkers to improve accuracy in identifying individuals at risk of POPF. In the future, prospective multicenter studies and the integration of novel imaging technologies, such as artificial intelligence-based radiomics, may further refine predictive models. Addressing these issues is anticipated to revolutionize risk stratification, clinical decision-making, and postoperative management in patients undergoing pancreatectomy.

Personalized motor imagery prediction model based on individual difference of ERP

Objective. Motor imagery-based brain–computer interaction (MI-BCI) is a novel method of achieving human and external environment interaction that can assist individuals with motor disorders to rehabilitate. However, individual differences limit the utility of the MI-BCI. In this study, a personalized MI prediction model based on the individual difference of event-related potential (ERP) is proposed to solve the MI individual difference. Approach. A novel paradigm named action observation-based multi-delayed matching posture task evokes ERP during a delayed matching posture task phase by retrieving picture stimuli and videos, and generates MI electroencephalogram through action observation and autonomous imagery in an action observation-based motor imagery phase. Based on the correlation between the ERP and MI, a logistic regression-based personalized MI prediction model is built to predict each individual’s suitable MI action. 32 subjects conducted the MI task with or without the help of the prediction model to select the MI action. Then classification accuracy of the MI task is used to evaluate the proposed model and three traditional MI methods. Main results. The personalized MI prediction model successfully predicts suitable action among 3 sets of daily actions. Under suitable MI action, the individual’s ERP amplitude and event-related desynchronization (ERD) intensity are the largest, which helps to improve the accuracy by 14.25%. Significance. The personalized MI prediction model that uses the temporal ERP features to predict the classification accuracy of MI is feasible for improving the individual’s MI-BCI performance, providing a new personalized solution for the individual difference and practical BCI application.

A personalized prediction model for urinary tract infections in type 2 diabetes mellitus using machine learning.

Patients with type 2 diabetes mellitus (T2DM) are at higher risk for urinary tract infections (UTIs), which greatly impacts their quality of life. Developing a risk prediction model to identify high-risk patients for UTIs in those with T2DM and assisting clinical decision-making can help reduce the incidence of UTIs in T2DM patients. To construct the predictive model, potential relevant variables were first selected from the reference literature, and then data was extracted from the Hospital Information System (HIS) of the Sichuan Academy of Medical Sciences and Sichuan Provincial People's Hospital for analysis. The data set was split into a training set and a test set in an 8:2 ratio. To handle the data and establish risk warning models, four imputation methods, four balancing methods, three feature screening methods, and eighteen machine learning algorithms were employed. A 10-fold cross-validation technique was applied to internally validate the training set, while the bootstrap method was used for external validation in the test set. The area under the receiver operating characteristic curve (AUC) and decision curve analysis (DCA) were used to evaluate the performance of the models. The contributions of features were interpreted using the SHapley Additive ExPlanation (SHAP) approach. And a web-based prediction platform for UTIs in T2DM was constructed by Flask framework. Finally, 106 variables were identified for analysis from a total of 119 literature sources, and 1340 patients were included in the study. After comprehensive data preprocessing, a total of 48 datasets were generated, and 864 risk warning models were constructed based on various balancing methods, feature selection techniques, and a range of machine learning algorithms. The receiver operating characteristic (ROC) curves were used to assess the performances of these models, and the best model achieved an impressive AUC of 0.9789 upon external validation. Notably, the most critical factors contributing to UTIs in T2DM patients were found to be UTIs-related inflammatory markers, medication use, mainly SGLT2 inhibitors, severity of comorbidities, blood routine indicators, as well as other factors such as length of hospital stay and estimated glomerular filtration rate (eGFR). Furthermore, the SHAP method was utilized to interpret the contribution of each feature to the model. And based on the optimal predictive model a user-friendly prediction platform for UTIs in T2DM was built to assist clinicians in making clinical decisions. The machine learning model-based prediction system developed in this study exhibited favorable predictive ability and promising clinical utility. The web-based prediction platform, combined with the professional judgment of clinicians, can assist to make better clinical decisions.

Design of a Personal Credit Risk Prediction Model and Legal Prevention of Financial Risks

Design of a Personal Credit Risk Prediction Model and Legal Prevention of Financial Risks

A metabolic-inflammatory-nutritional score (MINS) is associated with lymph node metastasis and prognostic stratification for endometrial cancer patients.

Objective: This study aims to propose a personalized cancer prediction model based on the metabolic-inflammatory-nutritional score (MINS) for predicting lymph node metastasis (LNM) in endometrial cancer (EC) and validated prediction of survival probability in patients with a family history of Lynch syndrome-associated cancers (LSAC). Methods: A total of 676 patients diagnosed with EC were enrolled in this study. We calculated the optimal cutoff value using restricted cubic splines (RCS) analysis or the mean value. Our feature selection process for constructing the MINS involved using the LASSO regression model. MINS were evaluated for LNM using logistic regression analysis. To assess the prognostic value of the MINS, we generated survival curves using the Kaplan-Meier method with a log-rank test. Furthermore, we constructed a nomogram to validate the prognostic significance of the MINS. The predictive accuracy of nomogram was evaluated using the concordance index (C-index) and calibration plot. Results: LNM risk was associated with family history of LSAC and MINS group (all adjusted p<0.05). Patients in the high-risk MINS group or patients with a family history of LSAC exhibited poorer overall survival (p=0.038, p=0.001, respectively). Additionally, a nomogram was demonstrated effective predictive performance with a C-index of 0.778 (95% CI: 0.725-0.832). Conclusion: Preoperative MINS has been determined to be associated with the risk of LNM in EC patients. Utilizing MINS as a basis, the development of a prognostic nomogram holds promise as an effective tool for risk stratification in clinical settings among EC patients with a family history of LSAC.

Development and validation of a nomogram for predicting the risk of poor prognosis in patients with cerebral infarction

ObjectiveTo identify factors related to poor prognosis in patients with cerebral infarction (CI) and to construct and validate a personalized prediction model based on these factors. MethodsA retrospective analysis was conducted on the clinical and follow-up data of 857 patients with CI who were diagnosed in the neurology department of a tertiary A hospital in Anhui Province, China from April 2020 to March 2022. Based on follow-up data and the Modified Rankin Scale (mRS) score one year after discharge, patients were divided into a good prognosis group (793 cases, mRS ≤2) and a poor prognosis group (64 cases, mRS >2). Multivariate logistic regression analysis was used to identify independent risk factors, which were then used to establish a nomogram model. The predictive performance of the model was evaluated using the area under the receiver operating characteristic curve (ROC, AUC), and the calibration curve was used to evaluate the calibration of the nomogram. ResultsThere was a statistically significant difference in the distribution of eight variables between the groups, including post-discharge use of biguanide hypoglycemic drugs, insulin, systolic blood pressure, exercise status, alcohol consumption, smoking status, age, and gender (P < 0.05). Multivariate logistic regression analysis suggested that gender, smoking after discharge, alcohol consumption, lack of exercise, and oral administration of biguanide hypoglycemic drugs are independent risk factors for poor prognosis in patients with CI (P < 0.05). The personalized poor prognosis nomogram constructed based on these five predictive factors showed good discriminative ability and predictive stability, with AUCs of 0.768 (95 % CI: 0.712–0.825) and 0.775 (95 % CI: 0.725–0.836) before and after internal validation, respectively. The calibration curve confirmed the accuracy and consistency of the nomogram (P = 0.956). ConclusionFemale gender, smoking, alcohol consumption, lack of exercise, and post-discharge use of biguanide hypoglycemic drugs are independent risk factors for poor prognosis in patients with CI. The constructed nomogram shows good predictive efficiency for post-discharge prognosis and can help in clinical decision-making.

Estimating surgical probability: Development and validation of a prognostic model for patients with lumbar disc herniation treated with acupuncture.

Lumbar disc herniation (LDH) is a common cause of pain in the lumbar spine and legs. While acupuncture has become the primary conservative treatment for LDH, some patients experience treatment failure and require surgery, causing substantial concern for clinicians. We developed an effective personalized clinical prediction model to identify the independent risk factors associated with acupuncture failure in patients with LDH. Our model aimed to predict the probability of surgery within 6 months of acupuncture failure in patients with LDH. A total of 738 patients with LDH who underwent acupuncture at 4 Chinese hospitals between January 2019 and October 2021 were selected. The patients were divided into training (n = 496) and validation (n = 242) cohorts. Seven predictive variables, including smoking, Oswestry Disability Index (ODI) score, lower-limb herniation, disc herniation type, lumbar spinal stenosis, lumbar lateral recess stenosis, and acupuncture frequency, were selected as risk factors using least absolute shrinkage and selection operato (LASSO) regression. A prediction model was developed using multivariate logistic regression analysis and a nomogram was constructed. The model exhibited good discrimination, with an area under the ROC curve (AUC) of 0.903 for the development cohort and 0.899 for the validation cohort. The Hosmer-Lemeshow goodness-of-fit test was a good fit for both cohorts (P = .956 for the development cohort; P = .513 for the validation cohort). Decision curve analysis (DCA) demonstrated that the threshold probabilities for the 2 cohorts ranged from > 4% and 5-95%, respectively. Therefore, the prediction model had a good net benefit. The nomogram established in this study, incorporating 7 risk factors, demonstrated a good predictive ability. It could predict acupuncture failure in LDH patients and the risk of surgery within 6 months, enabling physicians to conduct individualized treatment measures.

Abstract 347: Artificial Intelligence for Targeted and Personalized Prediction of Sudden Cardiac Death in the General Population: A Machine Learning Study Based on Electronic Health Records

Background: Identification of subjects from the general population with an increased risk of Sudden Cardiac Death (SCD) remains highly challenging, particularly at an individual level. Methods: Every case of SCD + 18 y.o. that occurred since 2011 in Paris and its inner suburbs was prospectively included in the Paris Sudden Death Expertise Center (SDEC) registry (6.7M inhabitants). SCD cases were matched by age, sex, and residence area with a control group (70000) sampled from the general population. All data from the French National Health Insurance database (SNDS) were collected: prescribed drugs, examinations and diagnoses that occurred up to 10 y. before the event, including cardiovascular and non-cardiovascular variables (10000). We provide a detailed explanation of the prediction at the individual level. For each subject, we computed the Shapley scores from the supervised learning model (CatBoost) to evaluate the contribution of variables to its predicted risk. The model used was derived from 12338 SCD cases and matched controls cohort (2011-15) and validated on 11620 cases cohort (2016-20). Results: A total of 23958 equations have been built with personalized variables and coefficients, achieving an AUC of 0.80 in the derivation cohort (with a PPV=77%, sensitivity=68%). One example is shown below, with an individual predicted risk of SCD at 3 months (89.3%), and the most important factors that increase (red) or decrease (blue) the risk of SCD. Conclusions: For the first time, we provide a personalized prediction model of SCD, which explains the predicted risk at the individual level. These findings offer a new step toward personalized prevention and global public health interventions