Risk Prediction Model Research Articles

Novel risk score for predicting acute cardiovascular and cerebrovascular events after chest radiotherapy in patients with breast or lung cancer.

Radiation therapy (RT) is an integral component of cancer therapy but associated with adverse events. Our goal was to establish risk prediction models for major adverse cardiovascular and cerebrovascular events (MACCE) after chest RT. A retrospective study of lung/breast cancer patients who had chest RT with planning CT at Mayo Clinic between 01/2010 and 01/2014. Predictive models were developed based on weighted independent predictors using a derivation (406 lung and 711 breast cancer) and validation cohort (179 lung and 234 breast cancer). Patient characteristics, pre-RT CT for coronary artery calcification (CAC), and post-RT MACCE data were reviewed. Post-RT MACCE occurred in 6.1 and 5.6% in the derivation and validation cohort over a mean follow-up of 42 ± 13 months. Post-therapy model (C2AD2) included CAC (two points), MACCE history (two points), age ≥74 (three points), DM (two points), and mean heart radiation dose ≥ 850 mGy (two points), and pre-therapy model (C2AD) included post-therapy model parameters minus mean heart radiation dose. Both models stratified patients into three risk groups: low (0-2), intermediate (3-5), and high (≥6). Post-RT MACCE across these groups were 2.7, 8.9, and 19.8% in the derivation, and 3.9, 6.6, and 16.4% in the validation cohort for post-therapy model (C2AD2) and 2.8, 9.2, and 20.4% in the derivation and 3.7, 9.2, and 13.2% in the validation cohort for pre-therapy model. Both models showed statistically significant graded survival outcome. Post-therapy (C2AD2) and pre-therapy (C2AD) models are simple, easy to use and effective tools to stratify breast and lung cancer patients undergoing chest radiation for post-RT MACCE.

Predicting Biochemical Recurrence of Prostate Cancer Post-Prostatectomy Using Artificial Intelligence: A Systematic Review

Background/Objectives: Biochemical recurrence (BCR) after radical prostatectomy (RP) is a significant predictor of distal metastases and mortality in prostate cancer (PCa) patients. This systematic review aims to evaluate the accuracy of artificial intelligence (AI) in predicting BCR post-RP. Methods: Adhering to PRISMA guidelines, a comprehensive literature search was conducted across Medline, Embase, Web of Science, and IEEE Xplore. Studies were included if they utilised AI to predict BCR in patients post-RP. Studies involving patients who underwent radiotherapy or salvage RP were excluded. This systematic review was registered on PROSPERO (International prospective register of systematic reviews) under the ID CRD42023482392. Results: After screening 9764 articles, 24 met the inclusion criteria. The included studies involved 27,216 patients, of whom 7267 developed BCR. AI algorithms developed using radiological parameters demonstrated higher predictive accuracy (median AUROC of 0.90) compared to algorithms based solely on pathological variables (median AUROC of 0.74) or clinicopathological variables (median AUROC of 0.81). According to the Prediction Model Risk of Bias Assessment Tool (PROBAST), the overall risk of bias was unclear in three studies due to ambiguous inclusion criteria and the exclusion of many patients because of missing follow-up data. In seven studies, the developed AI outperformed or was at least equivocal to traditional methods of BCR prediction. Conclusions: AI shows promise in predicting BCR post-RP, particularly when radiological data were used in its development. However, the significant variability in AI performance and study methodologies highlights the need for larger, standardised prospective studies with external validation prior to clinical application.

Investigation of factors influencing abnormal pulmonary ventilation function in occupational exposed populations and the establishment of a risk prediction model

The purpose of this study is to investigate the influencing factors of abnormal pulmonary ventilation function in occupational exposed populations and to establish a risk prediction model. The findings will provide a basis for formulating corresponding strategies for the prevention and treatment of occupational diseases. The study focused on workers who underwent occupational health examinations in the year 2020. Statistical analysis was conducted using methods such as t-tests, chi-square tests, and multiple logistic regression analysis. Additionally, machine learning methods were employed to establish multiple models to address classification problems. Among the 7472 workers who participated in the occupational health examination, 1681 cases of abnormal pulmonary ventilation function were detected, resulting in a detection rate of 22.6%. Based on the analysis of occupational hazard data, a risk prediction model was established. Age, work tenure, type of the employing enterprise, and type of dust exposure are all identified as driving factors for abnormal pulmonary function. These factors were used as predictive variables for establishing the risk prediction model. Among the various models evaluated, the logistic regression model was found to be the optimal model for predicting abnormal pulmonary ventilation function.

Simulation-based adaptive optimization for passenger flow control measures at metro stations

Effective passenger flow control measures are essential for the safe operation of metro stations. Existing in-station control measures include adjusting the operation mode of escalators and setting up temporary fences. However, in practice, metro operators often adopt fixed operation modes during fixed periods, indicating that the current passenger flow control measures at metro stations are overly rigidified. Therefore, developing an adaptive control strategy to constantly balance the wildly fluctuating passenger flow and optimize the operation performance is a key issue in current research. In this study, transportation efficiency and congestion risk are selected as evaluation objectives for passenger transportation risk, and passenger flow feature, station structure, and passenger flow control measures are considered key influential factors. Subsequently, an adaptive optimization method integrating simulation and data interpolation is proposed. The software Legion is used to conduct 150 orthogonal simulations, and prediction models for passenger transportation risk are obtained by performing data interpolation on the simulation results. Finally, taking a certain metro station as a case study, the optimal passenger flow control strategy under any passenger flow composition is obtained by scenario acquisition, risk identification, and adaptive decision-making. The results show that setting up temporary fences can reduce the passenger density near the fare gates, while adjusting the running direction of escalators can reduce overcrowding on the platform. Under varying passenger flow composition, the optimal strategy for the current scenario can be obtained, controlling passenger transportation risk within an acceptable range and providing assistance for metro operators in decision-making.

Development and validation of a risk prediction model for feeding intolerance in neurocritical patients with enteral nutrition

BackgroundThis study collects and analyzes clinical data on enteral nutrition therapy in neurocritical patients, develops and validates a feeding intolerance (FI) risk prediction model, and provides a theoretical basis for screening patients with high risk of feeding intolerance (FI) and delivering personalized care.MethodsA convenience sampling method was employed to select 300 patients who were admitted to a tertiary hospital in China for early enteral nutrition therapy in the neurointensive care unit between April 2022 and December 2022. Independent risk factors for FI were identified using univariate and logistic regression analyses. A prediction model was established, and the goodness of fit and discriminant validity of the model were evaluated.ResultsThe incidence of FI in neurocritical patients receiving enteral nutrition was 71%. Logistic regression analysis identified age, Glasgow Coma Scale (GCS) scores, Acute Physiology and Chronic Health Evaluation II (APACHE II) scores, mechanical ventilation, feeding via the nasogastric tube route, hyperglycemia, and low serum albumin as independent risk factors for the development of FI (p < 0.05). The predictive formula for FI risk was established as follows: Logit p = −14.737 + 1.184 × mechanical ventilation +2.309 × feeding route +1.650 × age + 1.336 × GCS tertile (6–8 points) + 1.696 × GCS tertile (3–5 points) + 1.753 × APACHE II score + 1.683 × blood glucose value +1.954 × serum albumin concentration. The Hosmer–Lemeshow test showed χ2 = 9.622, p = 0.293, and the area under the ROC curve was 0.941 (95% confidence interval: 0.912–0.970, p < 0.001). The optimal critical value was 0.767, with a sensitivity of 85.9%, a specificity of 90.8%, and a Youden index of 0.715.ConclusionThe early enteral nutrition FI risk prediction model developed in this study demonstrated good predictive ability. This model can serve as a valuable reference for effectively assessing the risk of FI in neurocritical patients, thereby enhancing clinical outcomes.

Development and assessment of a machine learning tool for predicting emergency admission in Scotland

Emergency admissions (EA), where a patient requires urgent in-hospital care, are a major challenge for healthcare systems. The development of risk prediction models can partly alleviate this problem by supporting primary care interventions and public health planning. Here, we introduce SPARRAv4, a predictive score for EA risk that will be deployed nationwide in Scotland. SPARRAv4 was derived using supervised and unsupervised machine-learning methods applied to routinely collected electronic health records from approximately 4.8M Scottish residents (2013-18). We demonstrate improvements in discrimination and calibration with respect to previous scores deployed in Scotland, as well as stability over a 3-year timeframe. Our analysis also provides insights about the epidemiology of EA risk in Scotland, by studying predictive performance across different population sub-groups and reasons for admission, as well as by quantifying the effect of individual input features. Finally, we discuss broader challenges including reproducibility and how to safely update risk prediction models that are already deployed at population level.

Identification of risk factors and establishment of prediction models for mortality risk in patients with acute kidney injury: A retrospective cohort study.

This study investigated factors influencing death in patients with Acute Kidney Injury (AKI) and developed models to predict their mortality risk. We analyzed data from 1079 AKI patients admitted to Changsha First Hospital using a retrospective design. Patient information including demographics, medical history, lab results, and treatments were collected. Logistic regression models were built to identify risk factors and predict 90-day and 1-year mortality. The 90-day mortality rate among 1079 AKI patients was 13.8% (149/1079) and the one-year mortality rate was 14.8% (160/1079). For both 90-day and 1-year mortality in patients with AKI, age over 60, anemia, hypotension, organ failure, and an admission Scr level above 682.3 μmol/L were identified as independent risk factors through multivariate logistic regression analysis. Additionally, mechanical ventilation was associated with an increased risk of death at one year. To ensure the generalizability of the models, we employed a robust 5-fold cross-validation technique. Both the 90-day and 1-year mortality models achieved good performance, with area under the curve (AUC) values exceeding 0.8 in the training set. Importantly, the AUC values in the validation set (0.828 for 90-day and 0.796 for 1-year) confirmed that the models' accuracy holds true for unseen data. Additionally, calibration plots and decision curves supported the models' usefulness in predicting patient outcomes. The logistic regression models built using these factors effectively predicted 90-day and 1-year mortality risk. These findings can provide valuable insights for clinical risk management in AKI patients.

Clustering-aided prediction of outcomes in patients with idiopathic pulmonary fibrosis

BackgroundBlood biomarkers predictive of the progression of idiopathic pulmonary fibrosis (IPF) would be of value for research and clinical practice. We used data from the IPF-PRO Registry to investigate whether the addition of “omics” data to risk prediction models based on demographic and clinical characteristics improved prediction of the progression of IPF.MethodsThe IPF-PRO Registry enrolled patients with IPF at 46 sites across the US. Patients were followed prospectively. Median follow-up was 27.2 months. Prediction models for disease progression included omics data (proteins and microRNAs [miRNAs]), demographic factors and clinical factors, all assessed at enrollment. Data on proteins and miRNAs were included in the models either as raw values or based on clusters in various combinations. Least absolute shrinkage and selection operator (Lasso) Cox regression was applied for time-to-event composite outcomes and logistic regression with L1 penalty was applied for binary outcomes assessed at 1 year. Model performance was assessed using Harrell’s C-index (for time-to-event outcomes) or area under the curve (for binary outcomes).ResultsData were analyzed from 231 patients. The models based on demographic and clinical factors, with or without omics data, were the top-performing models for prediction of all the time-to-event outcomes. Relative changes in average C-index after incorporating omics data into models based on demographic and clinical factors ranged from 1.7 to 3.2%. Of the blood biomarkers, surfactant protein-D, serine protease inhibitor A7 and matrix metalloproteinase-9 (MMP-9) were among the top predictors of the outcomes. For the binary outcomes, models based on demographics alone and models based on demographics plus omics data had similar performances. Of the blood biomarkers, CC motif chemokine 11, vascular cell adhesion protein-1, adiponectin, carcinoembryonic antigen and MMP-9 were the most important predictors of the binary outcomes.ConclusionsWe identified circulating protein and miRNA biomarkers associated with the progression of IPF. However, the integration of omics data into prediction models that included demographic and clinical factors did not materially improve the performance of the models.Trial registrationClinicalTrials.gov; No: NCT01915511; registered August 5, 2013; URL: www.clinicaltrials.gov.

Development and validation of a cardiovascular risk prediction model for Sri Lankans using machine learning.

Sri Lankans do not have a specific cardiovascular (CV) risk prediction model and therefore, World Health Organization(WHO) risk charts developed for the Southeast Asia Region are being used. We aimed to develop a CV risk prediction model specific for Sri Lankans using machine learning (ML) of data of a population-based, randomly selected cohort of Sri Lankans followed up for 10 years and to validate it in an external cohort. The cohort consisted of 2596 individuals between 40-65 years of age in 2007, who were followed up for 10 years. Of them, 179 developed hard CV diseases (CVD) by 2017. We developed three CV risk prediction models named model 1, 2 and 3 using ML. We compared predictive performances between models and the WHO risk charts using receiver operating characteristic curves (ROC). The most predictive and practical model for use in primary care, model 3 was named "SLCVD score" which used age, sex, smoking status, systolic blood pressure, history of diabetes, and total cholesterol level in the calculation. We developed an online platform to calculate the SLCVD score. Predictions of SLCVD score were validated in an external hospital-based cohort. Model 1, 2, SLCVD score and the WHO risk charts predicted 173, 162, 169 and 10 of 179 observed events and the area under the ROC (AUC) were 0.98, 0.98, 0.98 and 0.52 respectively. During external validation, the SLCVD score and WHO risk charts predicted 56 and 18 respectively of 119 total events and AUCs were 0.64 and 0.54 respectively. SLCVD score is the first and only CV risk prediction model specific for Sri Lankans. It predicts the 10-year risk of developing a hard CVD in Sri Lankans. SLCVD score was more effective in predicting Sri Lankans at high CV risk than WHO risk charts.

C6 and KLRG2 are pyroptosis subtype-related prognostic biomarkers and correlated with tumor-infiltrating lymphocytes in lung adenocarcinoma

Pyroptosis plays an important role in lung adenocarcinoma (LUAD). In this study, we aimed to explore the pyroptosis-related gene (PRG) expression pattern and to identify promising pyroptosis-related biomarkers to improve the prognosis of LUAD. The gene expression profiles and clinical information of LUAD patients were downloaded from the Cancer Genome Atlas (TCGA), and validation cohort information was extracted from the Gene Expression Omnibus database. Gene expression data were analyzed using the limma package and visualized using the ggplot2 package as well as the pheatmap package in R software. Functional enrichment analysis was also performed for the 44 differentially expressed PRGs (DEPRGs). Then, consensus clustering revealed pyroptosis-related tumor subtypes, and differentially expressed genes (DEGs) were screened according to the subtypes. Next, univariate Cox and multivariate Cox regression analyses were used to identify independent prognostic PRGs. After overlapping DEGs and the Lasso regression analysis-based prognostic genes, the predictive risk model was established and validated. Correlation analysis between PRGs and clinicopathological variables was also explored. Finally, the TIMER and TISIDB databases were used to further explore the correlation analysis between immune cell infiltration levels, the risk score, and clinicopathological variables in the predictive risk model. A total of 52 genes from the PubMed were identified as PRGs, and 44 of the 52 genes were pooled as DEPRGs. The most significant GO term was “collagen trimer” (P = 2.46E-13), and KEGG analysis results indicated that 44 DEPRGs were significantly enriched in Salmonella infection (P < 0.001). Then, consensus clustering analysis divided LUAD patients into two clusters, and a total of 79 DEGs were identified according to these cluster subtypes. Subsequently, univariate and multivariate Cox regression analyses were used to identify 12 genes that could serve as independent prognostic indicators and we also performed Lasso regression analysis and screened 23 DEGs. After overlapping 23 DEGs and 12 genes, only 4 (KLRG2, MAPK4, C6 and SFRP5) of 12 genes were selected for the further exploration of the prognostic pattern. Survival analysis results indicated that this risk model effectively predicted the prognosis (P < 0.001). Combined with the correlation analysis results between the 4 genes and clinicopathological variables, C6 and KLRG2 were screened as prognostic genes. In this study, we constructed a predictive risk model and identified two pyroptosis subtype-related gene expression patterns to improve the prognosis of LUAD. Understanding the subtypes of LUAD is helpful for accurately characterizing the LUAD and developing personalized treatment.

Combustion efficiency analysis and thermal radiation risk quantification for spill fire in sealed ship cabin

In this study, the authors conducted a series of one-dimensional spill fire experiments in a sealed model-scale ship cabin with different leakage rates to reveal the combustion characteristics. The results showed that a stable combustion stage with a consistent combustion area and flame height appears around the cut-off of the fuel, where the consumption of oxygen increases when the leakage rate increases. And the CO2 concentration increases more rapidly and the upward trend is found to appear earlier. Compared with the film thickness in the open space, that of the spill fire in the sealed ship cabin is slightly thinner because of the ventilation control effect. Using the “oxygen-consumption” method, the η of this stage was calculated and verified with the “mass loss rate” method. With these two methods, the HRR of spill fie when burning steadily is calculated. This work also improved the predicting model for the flame height of rectangular pool fire and developed a predicting model for the flame height of a steadily burning spill fire. The error is 14.35 %. Additionally, a predictive model of thermal radiation risk in ship spill fire is developed, and the death risk and unacceptable risk areas are delimited.

A predictive model for secondary central nervous system infection after craniotomy based on machine learning

To analyze the risk factors of secondary Central nervous system infections (CNSIs) after craniotomy, and to establish an individualized predictive model for CNSIs risk. The independent risk factors were screened by univariate and multivariate logistic regression analysis. Logistic regression, naive bayes, random forest, light GBM and adaboost algorithms were used to establish predictive models for secondary CNSIs after craniotomy. The predictive model based on the Adaboost algorithm demonstrated superior prediction performance compared to the other four models. Under 5-fold cross validation, the accuracy was 0.80, the precision was 0.69, the recall was 0.85, the F1-score was 0.76, the area under the ROC curve was 0.897,and the average precision was 0.880. The top 5 variables of importance in Adaboost model were operation time, indwelling time of lumbar drainage tube, indwelling lumbar drainage tube during operation, indwelling epidural drainage tube during operation, and GCS score. In addition, Adaboost model with the best prediction performance was used for clinical verification, and the prediction results were compared with the actual occurrence of CNSIs after surgery. The results showed that the accuracy of Adaboost model in predicting CNSIs was 60%, the accuracy of Adaboost model in predicting non-CNSIS was 92%, and the overall prediction accuracy was 76%.

Development and validation of a nomogram to predict the risk of adjacent segment disease after transforaminal lumbar interbody fusion in patients with lumbar degenerative diseases

BackgroundAdjacent segment disease (ASD) is a common and serious complication that can develop in the mid- to long-term after lumbar fusion surgery. However, the underlying mechanisms of ASD are not yet fully understood. This study aimed to develop and validate a risk prediction model for ASD in patients who underwent transforaminal lumbar interbody fusion (TLIF) for lumbar degenerative diseases.MethodsPatients with lumbar degenerative disease who underwent TLIF between January 2015 and December 2016 were included in the retrospective study. The participants were divided into two groups: ASD and non-ASD. Univariate and multivariate logistic regression analyses were performed to identify factors influencing ASD after TLIF surgery. The receiver operating characteristic (ROC) curve, calibration curve, and decision curve analysis (DCA) were used to evaluate the model’s discrimination, calibration and clinical value, respectively.ResultsA total of 11.5% (59/513) of patients developed ASD. Higher BMI, lower BMD, higher disc grade, and reduced disc height were identified as independent risk factors for ASD after TLIF. The model demonstrated good discrimination in both the training and validation sets, with calibration and Hosmer-Lemeshow tests confirming accuracy, and DCA demonstrating clinical applicability.ConclusionsThe nomogram model demonstrated promise in predicting ASD in patients who underwent TLIF, aiding clinicians in selecting the most suitable surgical approach and optimizing surgical decisions.

Meta-analysis of prediction models for predicting lymph node metastasis in thyroid cancer

BackgroundThe purpose of this systematic review and meta-analysis is to assess the efficacy of various machine learning (ML) techniques in predicting preoperative lymph node metastasis (LNM) in patients diagnosed with papillary thyroid carcinoma (PTC). Although prior studies have investigated the potential of ML in this context, the current evidence is not sufficiently strong. Hence, we undertook a thorough analysis to ascertain the predictive accuracy of different ML models and their practical relevance in predicting preoperative LNM in PTC patients.Materials and methodsIn our search, we thoroughly examined PubMed, Cochrane Library, Embase, and Web of Science, encompassing their complete database history until December 3rd, 2022. To evaluate the potential bias in the machine learning models documented in the included studies, we employed the Prediction Model Risk of Bias Assessment Tool (PROBAST).ResultsA total of 107 studies, involving 136,245 patients, were included. Among them, 21,231 patients showed central LNM (CLNM) and 4,637 had lateral LNM (LLNM). The meta-analysis results revealed that the c-index for predicting LNM, CLNM, and LLNM were 0.762 (95% CI: 0.747–0.777), 0.762 (95% CI: 0.747–0.777), and 0.803 (95% CI: 0.773–0.834) in the training set, and 0.773 (95% CI: 0.754–0.791), 0.762 (95% CI: 0.747–0.777), and 0.829 (95% CI: 0.779–0.879) in the validation set, respectively. A total of 134 machine learning-based prediction models were included, covering 10 different types. Logistic Regression (LR) was the most commonly used model, accounting for 81.34% (109/134) of the included models.ConclusionsMachine learning methods have shown a certain level of accuracy in predicting preoperative LNM in PTC patients, indicating their potential as a predictive tool. Their use in the clinical management of PTC holds great promise. Among the various ML models investigated, the performance of logistic regression-based nomograms was deemed satisfactory.

Development and construction of a cataract risk prediction model based on biochemical indices: the National Health and Nutrition Examination Survey, 2005–2008

PurposeThe aim of this study is to develop and validate a novel multivariable prediction model capable of accurately estimating the probability of cataract development, utilizing parameters such as blood biochemical markers and age.DesignThis population-based cross-sectional study comprised 9,566 participants drawn from the National Health and Nutrition Examination Survey (NHANES) across the 2005–2008 cycles.MethodsDemographic information and laboratory test results from the patients were collected and analyzed using LASSO regression and multivariate logistic regression to accurately capture the influence of biochemical indicators on the outcomes. The SHAP (Shapley Additive Explanations) scale was employed to assess the importance of each clinical feature, excluding age. A multivariate logistic regression model was then developed and visualized as a nomogram. To assess the model’s performance, its discrimination, calibration, and clinical utility were evaluated using receiver operating characteristic (ROC) curves, 10-fold cross-validation, Hosmer-Lemeshow calibration curves, and decision curve analysis (DCA), respectively.ResultsLogistic regression analysis identified age, erythrocyte folate (nmol/L), blood glucose (mmol/L), and blood urea nitrogen (mmol/L) as independent risk factors for cataract, and these variables were incorporated into a multivariate logistic regression-based nomogram for cataract risk prediction. The area under the receiver operating characteristic (ROC) curve (AUC) for cataract risk prediction was 0.917 (95% CI: 0.9067–0.9273) in the training cohort, and 0.9148 (95% CI: 0.8979–0.9316) in the validation cohort. The Hosmer-Lemeshow calibration curve demonstrated a good fit, indicating strong model calibration. Ten-fold cross-validation confirmed the logistic regression model’s robust predictive performance and stability during internal validation. Decision curve analysis (DCA) demonstrated that the nomogram prediction model provided greater clinical benefit for predicting cataract risk when the patient’s threshold probability ranged from 0.10 to 0.90.ConclusionThis study identified blood urea nitrogen (mmol/L), serum glucose (mmol/L), and erythrocyte folate (mmol/L) as significant risk factors for cataract. A risk prediction model was developed, demonstrating strong predictive accuracy and clinical utility, offering clinicians a reliable tool for early and effective diagnosis. Cataract development may be delayed by reducing levels of blood urea nitrogen, serum glucose, and erythrocyte folate through lifestyle improvements and dietary modifications.

Risk Factors and Risk Prediction Model of Poor Prognosis in Patients with Chronic Dacryocystitis Treated by Endoscopic Nasal Dacryocystostomy.

Chronic dacryocystitis often leads to a poor prognosis due to factors like chronic inflammation resulting in lacrimal duct obstruction and recurrent infections. Therefore, this study aims to investigate the risk factors of poor prognosis in patients with chronic dacryocystitis treated by endoscopic nasal dacryocystostomy and to establish a risk prediction model. We retrospectively analyzed the clinical data of chronic dacryocystitis patients (n = 101) treated between January 2022 and February 2024. They were divided into a training set (n = 71) and a validation set (n = 30). Patients were followed up for three months post-operation, and recurrence rates were assessed. Logistic regression analysis was used to identify risk factors for poor prognosis, and a nomogram model was developed utilizing these risk factors. Model validation involved the bootstrap method, calibration curves, receiver operator characteristic (ROC) curves, and the Hosmer-Lemeshow test. Out of the 101 patients, 27 (26.73%) experienced recurrence. The older age, longer operation time, and greater intraoperative bleeding were all associated with poor prognosis (all p < 0.05). Multivariate regression indicated that age (odds ratio (OR) = 2.18, 95% CI: 1.30-3.68), operation time (OR = 1.89, 95% confidence interval (CI): 1.13-3.17), and intraoperative bleeding (OR = 1.69, 95% CI: 1.06-2.69) were significant risk factors. The nomogram model incorporating these factors showed an area under the curve (AUC) of 0.666 for the training set and 0.585 for the validation set. Furthermore, for the training set, sensitivity and specificity were 0.654 and 0.621, and for the validation set, they were 0.598 and 0.548, respectively, with calibration curves indicating good agreement. Age, operation time, and intraoperative bleeding are significant factors affecting the prognosis of patients with chronic dacryocystitis.

Related Factors and Risk Prediction of Chronic Pain after Knee Replacement.

This study aimed to explore potential risk factors associated with chronic pain after total knee arthroplasty (TKA) and to establish the risk prediction model of chronic postoperative pain (CPSP). This study retrospectively analyzed the clinical data of 160 patients who underwent TKA in our hospital between January 2021 and January 2024. Relevant data such as the baseline characteristics, past medical history, CPSP condition, and pain numerical rating scale (NRS) were retrieved from the medical information system. Logistic regression analysis was performed on the risk factors affecting the postoperative CPSP of the patients. The identified risk factors were incorporated to develop a risk-prediction model. Among the 160 patients, 67 (41.88%) had CPSP at or around the operation incision. The NRS pain score was significantly higher in the CPSP group than in the non-CPSP group during exercise preoperative and 3 months post-operation. Furthermore, the CPSP group had a higher NRS score than the non-CPSP group at rest 3 months after the procedure (p < 0.05). We observed that the preoperative NRS score, preoperative hospital for special surgery (HSS) score, postoperative functional training, and postoperative adverse events were the independent factors influencing the occurrence of CPSP after TKA (p < 0.05). Additionally, there was a significant positive correlation between preoperative NRS score, postoperative adverse events, and CPSP pain severity, and a significant negative correlation between preoperative HSS score, postoperative functional training, and CPSP pain severity (p < 0.05). The receiver operating characteristic (ROC) curve had excellent calibration and prediction capabilities for the predictive model of CPSP after TKA, with the area under the curve (AUC) of 0.868 (95% CI: 0.811-0.925). In this study, the predictive model of CPSP risk for patients after TKA surgery was initially constructed, which can help medical staff predict the risk of CPSP in patients after surgery individually, thereby preventing the occurrence of CPSP.

Data-driven Machine Learning Models for Risk Stratification and Prediction of Emergence Delirium in Pediatric Patients Underwent Tonsillectomy/Adenotonsillectomy.

In the pediatric surgical population, Emergence Delirium (ED) poses a significant challenge. This study aims to develop and validate machine learning (ML) models to identify key features associated with ED and predict its occurrence in children undergoing tonsillectomy or adenotonsillectomy. The analysis involved data cleaning, exploratory data analysis (EDA), supervised predictive modeling, and unsupervised learning on a medical dataset (n = 423). After preliminary data cleaning, EDA encompassed plotting histograms, boxplots, pairplots, and correlation heatmaps to understand variable distributions and relationships. Four predictive models were trained including logistic regression (LR), random forest (RF), Support Vector Machine (SVM), and Gradient Boosting (XGBoost). The models were evaluated and compared using Receiver Operating Characteristic (ROC) Area Under the Curve (AUC), precision, recall, and feature importance. The RF model showed better performance and was used for the test (AUC-ROC 0.96, precision 1.00, and recall 0.92 on the validation set). K-means clustering was applied to find groups within the data. Elbow method and silhouette scores were used to determine the optimal number of clusters. The formed clusters were analyzed by aggregating features to understand the characteristics of each cluster. EDA revealed significant positive correlations between age, weight, American Society of Anesthesiologists (ASA) health score, and surgery duration with the risk of developing ED. Among the ML models, RF achieved the highest performance. Key predictive variables, based on the model's feature importance, included delirium screening scales, extubation time, and time to regain consciousness. Unsupervised K-means clustering identified 2-3 optimal clusters, which represented distinct patient subgroups: younger, healthier, low-risk individuals (cluster 0), and older patients with increasing chronic disease burden, higher delirium screening scores, and consequently higher post-operative delirium risk (clusters 1 and 2). ML techniques are valuable tools for extracting insights and making accurate predictions from healthcare data. High-performing algorithm-based models can be implemented for clinical decision support systems, facilitating early identification and intervention for ED in pediatric patients. By investigating various variables, it is possible to assess risk and implement preventive measures effectively. Furthermore, unsupervised clustering reveals distinct patient subgroups, enabling personalized perioperative management strategies and enhancing overall patient care.

Construction and verification of the prediction model for risk of sleep disturbance in elderly patients with hypertension: a cross-sectional survey based on NHANES database from 2005 to 2018

ObjectiveTo construct and verify a risk prediction model for sleep disturbance in elderly patients with hypertension, aiming to offer guidance for sleep management in this demographic.MethodsA cohort of 6,708 elderly hypertensive patients from the NHANES database, spanning 2005 to 2018, met the inclusion criteria and were selected for this study. Participants were randomly assigned to a development group (n = 4,696) and a verification group (n = 2,012) in a 7:3 ratio. The occurrence of sleep disturbance was assessed across the subjects. Independent risk factors for sleep disturbance were analyzed using weighted multivariate logistic regression within the development group. A predictive model for sleep disturbance risk in elderly hypertensive patients was developed and verified using Stata 17.0. The model's predictive accuracy and stability were evaluated using the verification group's data.ResultsOf the 6,708 subjects, 2,014 (30.02%) were identified with sleep disturbance, and the weighted prevalence of sleep disturbance among elderly hypertensive patients was 33.283%. Weighted multivariate logistic regression analysis in the development group revealed that six factors were independently associated with sleep disturbance: higher total depression scores, higher education level, asthma, overweight, arthritis, and work restriction (OR > 1 and P < 0.05). The area under the receiver operating characteristic (ROC) curve (AUC) for the nomogram prediction model was 0.709 in the development group and 0.707 in the verification group, indicating good discrimination ability. Brier scores for the nomogram model were 0.185 in the development group and 0.189 in the verification group, both below 0.25, suggesting good calibration. Decision Curve Analysis (DCA) determined that the nomogram's clinical net benefit was maximized when the threshold probability for sleep disturbance in elderly hypertensive patients was 0.13–0.67 in the development group and 0.14–0.61 in the verification group, highlighting the model's clinical utility.LimitationsThis study is not without its limitations, including issues with data collection, the absence of external validation, and the non-extrapolation of results.ConclusionThe prevalence of sleep disturbance among elderly hypertensive patients stands at 33.283%. The nomogram model, based on identified risk factors for sleep disturbance in this population, has demonstrated good predictive efficiency and clinical relevance. It serves as a valuable tool to assist healthcare providers in identifying elderly hypertensive patients at high risk for sleep disturbance.

Nationwide study on development and validation of a risk prediction model for CIN3+ and cervical cancer in Estonia

Transitioning to an individualized risk-based approach can significantly enhance cervical cancer screening programs. We aimed to derive and internally validate a prediction model for assessing the risk of cervical intraepithelial neoplasia grade 3 or higher (CIN3+) and cancer in women eligible for screening. This retrospective study utilized data from the Estonian electronic health records, including 517,884 women from the health insurance database and linked health registries. We employed Cox proportional hazard regression, incorporating reproductive and medical history variables (14 covariates), and utilized the least absolute shrinkage and selection operator (LASSO) for variable selection. A 10-fold cross-validation for internal validation of the model was used. The main outcomes were the performance of discrimination and calibration. Over the 8-year follow-up, we identified 1326 women with cervical cancer and 5929 with CIN3+, with absolute risks of 0.3% and 1.1%, respectively. The prediction model for CIN3 + and cervical cancer had good discriminative power and was well calibrated Harrell’s C of 0.74 (0.73–0.74) (calibration slope 1.00 (0.97–1.02) and 0.67 (0.66–0.69) (calibration slope 0.92 (0.84–1.00) respectively. A developed model based on nationwide electronic health data showed potential utility for risk stratification to supplement screening efforts. This work was supported through grants number PRG2218 from the Estonian Research Council, and EMP416 from the EEA (European Economic Area) and Norway Grants.