Search

Background: The coronavirus disease (COVID-19) pandemic is a global health emergency, and SARS-CoV-2 pneumonia poses significant challenges to health systems worldwide. Renal transplant recipients (RTRs) are a special group and are more vulnerable to viral pneumonia. However, few studies have elucidated the risk factors of SARS-CoV-2 pneumonia in RTRs infected with COVID-19. This study aimed to build a risk prediction model for SARS-CoV-2 pneumonia among RTRs based on demographic and clinical information. Methods: We conducted a prospective cohort study among 383 RTRs (age ≥ 18 years) diagnosed with COVID-19 from December 21, 2022, to March 26, 2023. Patients' demographic and clinical information was collected through a questionnaire survey combined with electronic medical records. A stepwise logistic regression model was established to test the predictors of SARS-CoV-2 pneumonia. We assessed the diagnostic performance of the model by calculating the area under the curve (AUC) of the receiver operating characteristic (ROC) and calibration using the Hosmer–Lemeshow (HL) goodness-of-fit test. Results: Our study showed that the incidence of SARS-CoV-2 pneumonia among RTRs was 31.1%. Older age (OR = 2.08–3.37,95%CI:1.05–7.23), shorter post-transplantation duration (OR = 0.92,95% CI: 0.87,0.99), higher post-transplant Charlson Comorbidity Index (CCI) (OR = 1.84, 95%CI: 1.14,2.98), pulmonary infection history (OR = 3.44, 95%CI: 1.459, 8.099, P = 0.005), fatigue (OR = 2.11, 95%CI: 1.14, 3.90), cough (OR = 2.03, 95%CI: 1.08, 3.81), and lower estimated glomerular filtration rate (eGFR) at COVID-19 diagnosis (OR = 0.98, 95%CI:0.97,0.99) predicted a higher risk for SARS-CoV-2 pneumonia. The model showed good diagnostic performance with Chi-Square = 10.832 (P > 0.05) and AUC = 0.839 (P < 0.001). Conclusions: Our study showed a high incidence of SARS-CoV-2 pneumonia among RTRs, and we built a risk prediction model for SARS-CoV-2 pneumonia based on patients' demographic and clinical characteristics. The model can help identify RTRs infected with COVID-19 at high risk of SARS-CoV-2 pneumonia to inform timely, targeted, and effective prevention and intervention efforts. [ABSTRACT FROM AUTHOR]

Background: The amount of prediction models for disability in older adults is increasing but the prediction performance of different models varies greatly, and the quality of prediction models is still unclear. Objectives: To systematically review and critically appraise the studies on risk prediction models for disability in older adults. Methods: A systematic literature search was conducted on PubMed, Embase, Web of Science, Cochrane Library, Cumulative Index to Nursing and Allied Health Literature (CINAHL), China National Knowledge Infrastructure (CNKI), China Science and Technology Journal Database (VIP), and Wanfang Database, published up until June 30, 2023. Data were extracted according to the Checklist for critical Appraisal and data extraction for systematic Reviews of prediction Modelling Studies (CHARMS). The Prediction Model Risk of Bias Assessment Tool (PROBAST) was used to assess the risk of bias and applicability of the included studies. In addition, all included studies were evaluated for clinical value. Results: A total of 5722 articles were initially retrieved from databases, 16 studies and 17 prediction models were finally included after screening. The sample sizes of studies ranged from 420 to 90,889. Model development methods mainly included logistic regression analysis, Cox proportional hazards regression, and machine learning methods. The C statistic or area under the curve (AUC) of models ranged from 0.650 to 0.853, and nine models had C statistic/AUC higher than 0.75. Age, chronic disease, gender, self-rated health, body mass index (BMI), drinking, smoking and education level were the most common predictors. According to the PROBAST, all included studies were at high risk of bias, and 10 studies were at high concerns for applicability. Only two studies reported following the Transparent Reporting of a Multivariate Prediction Model for Individual Prognosis or Diagnosis (TRIPOD) statement. After evaluation, only two models reached the standard of clinical value. Conclusion: Although most of the included prediction models had acceptable discrimination, the overall quality and clinical value of the current studies were poor. In the future, researchers should follow the TRIPOD statement and PROBAST checklist to develop prediction models with larger sample sizes, more reasonable study designs, and more scientific analysis methods, to improve the predictive performance and application value. Trial registration: The review protocol was registered in PROSPERO (registration ID: CRD42023446657). [ABSTRACT FROM AUTHOR]

Objective: This study aimed to develop and validate a nomogram for assessing the risk of nosocomial infections among obstetric inpatients, providing a valuable reference for predicting and mitigating the risk of postpartum infections. Methods: A retrospective observational study was performed on a cohort of 28,608 obstetric patients admitted for childbirth between 2017 and 2022. Data from the year 2022, comprising 4,153 inpatients, were utilized for model validation. Univariable and multivariable stepwise logistic regression analyses were employed to identify the factors influencing nosocomial infections among obstetric inpatients. A nomogram was subsequently developed based on the final predictive model. The receiver operating characteristic (ROC) curve was utilized to calculate the area under the curve (AUC) to evaluate the predictive accuracy of the nomogram in both the training and validation datasets. Results: The gestational weeks > = 37, prenatal anemia, prenatal hypoproteinemia, premature rupture of membranes (PROM), cesarean sction, operative delivery, adverse birth outcomes, length of hospitalization (days) > 5, CVC use and catheterization of ureter were included in the ultimate prediction model. The AUC of the nomogram was 0.828 (0.823, 0.833) in the training dataset and 0.855 (0.844, 0.865) in the validation dataset. Conclusion: Through a large-scale retrospective study conducted in China, we developed and independently validated a nomogram to enable personalized postpartum infections risk estimates for obstetric inpatients. Its clinical application can facilitate early identification of high-risk groups, enabling timely infection prevention and control measures. [ABSTRACT FROM AUTHOR]

Objective: To analyze the influencing factors of postoperative thrombocytopenia in critically ill patients with heart disease and construct a nomogram prediction model. Methods: From October 2022 to October 2023, 319 critically ill patients with heart disease who visited our hospital were collected and separated into postoperative thrombocytopenia group (n = 142) and no postoperative thrombocytopenia group (n = 177) based on their postoperative thrombocytopenia, Logistic regression analysis was applied to screen risk factors for postoperative thrombocytopenia in critically ill patients with heart disease; R software was applied to construct a nomogram for predicting postoperative thrombocytopenia in critically ill patients with heart disease, and ROC curves, calibration curves, and Hosmer-Lemeshow goodness of fit tests were applied to evaluate nomogram. Results: A total of 142 out of 319 critically ill patients had postoperative thrombocytopenia, accounting for 44.51%. Logistic regression analysis showed that gender (95% CI 1.607–4.402, P = 0.000), age ≥ 60 years (95% CI 1.380–3.697, P = 0.001), preoperative antiplatelet therapy (95% CI 1.254–3.420, P = 0.004), and extracorporeal circulation time > 120 min (95% CI 1.681–4.652, P = 0.000) were independent risk factors for postoperative thrombocytopenia in critically ill patients with heart disease. The area under the ROC curve was 0.719 (95% CI: 0.663–0.774). The slope of the calibration curve was close to 1, and the Hosmer-Lemeshow goodness of fit test was χ2 = 6.422, P = 0.491. Conclusion: Postoperative thrombocytopenia in critically ill patients with heart disease is influenced by gender, age ≥ 60 years, preoperative antiplatelet therapy, and extracorporeal circulation time > 120 min. A nomogram established based on above multiple independent risk factors provides a method for clinical prediction of the risk of postoperative thrombocytopenia in critically ill patients with heart disease. [ABSTRACT FROM AUTHOR]

Background: In this study, we investigated the relationship between the risk of postoperative progressive disease (PD) in breast cancer and depression and sleep disorders in order to develop and validate a suitable risk prevention model. Methods: A total of 750 postoperative patients with breast cancer were selected from the First People's Hospital of LianYunGang, and the indices of two groups (an event group and a non-event group) were compared to develop and validate a risk prediction model. The relationship between depression, sleep disorders, and PD events was investigated using the follow-up data of the 750 patients. Results: SAS, SDS, and AIS scores differed in the group of patients who experienced postoperative disease progression versus those who did not; the differences were statistically significant and the ability to differentiate prognosis was high. The area under the receiver operating characteristic (ROC) curves (AUC) were: 0.8049 (0.7685–0.8613), 0.768 (0.727–0.809), and 0.7661 (0.724-–0.808), with cut-off values of 43.5, 48.5, and 4.5, respectively. Significant variables were screened by single-factor analysis and multi-factor analysis to create model 1, by lasso regression and cross-lasso regression analysis to create model 2, by random forest calculation method to create model 3, by stepwise regression method (backward method) to create model 4, and by including all variables for Cox regression to include significant variables to create model 5. The AUC of model 2 was 0.883 (0.848–0.918) and 0.937 (0.893–0.981) in the training set and validation set, respectively. The clinical efficacy of the model was evaluated using decision curve analysis and clinical impact curve, and then the model 2 variables were transformed into scores, which were validated in two datasets, the training and validation sets, with AUCs of 0.884 (0.848–0.919) and 0.885 (0.818–0.951), respectively. Conclusion: We established and verified a model including SAS, SDS and AIS to predict the prognosis of breast cancer patients, and simplified it by scoring, making it convenient for clinical use, providing a theoretical basis for precise intervention in these patients. However, further research is needed to verify the generalization ability of our model. [ABSTRACT FROM AUTHOR]

Background: In familial pulmonary fibrosis (FPF) at least two biological relatives are affected. Patients with FPF have diverse clinical features. Research question: We aimed to characterize demographic and clinical features, re-evaluate high-resolution computed tomography (HRCT) scans and histopathology of surgical lung biopsies, assess survival and investigate the suitability of risk prediction models for FPF patients. Study design: A retrospective cohort study. Methods: FPF data (n = 68) were collected from the medical records of Oulu University Hospital (OUH) and Oulaskangas District Hospital between 1 Jan 2000 and 11 Jan 2023. The inclusion criterion was pulmonary fibrosis (PF) (ICD 10-code J84.X) and at least one self-reported relative with PF. Clinical information was gathered from hospital medical records. HRCT scans and histology were re-evaluated. Results: Thirty-seven (54.4%) of the patients were men, and 31 (45.6%) were women. The mean ages of the women and men were 68.6 and 61.7 years, respectively (p = 0.003). Thirty-seven (54.4%) patients were nonsmokers. The most common radiological patterns were usual interstitial pneumonia (UIP) (51/75.0%), unclassifiable (8/11.8%) and nonspecific interstitial pneumonia (NSIP) (3/4.4%). Pleuroparenchymal fibroelastosis (PPFE) was observed as a single or combined pattern in 13.2% of the patients. According to the 2022 guidelines for idiopathic pulmonary fibrosis (IPF), the patients were categorized as UIP (31/45.6%), probable UIP (20/29.4%), indeterminate for UIP (7/10.3%) or alternative diagnosis (10/14.7%). The histopathological patterns were UIP (7/41.2%), probable UIP (1/5.9%), indeterminate for UIP (8/47.2%) and alternative diagnosis (1/5.9%). Rare genetic variants were found in 9 patients; these included telomerase reverse transcriptase (TERT, n = 6), telomerase RNA component (TERC, n = 2) and regulator of telomere elongation helicase 1 (RTEL1, n = 1). Half of the patients died (n = 29) or underwent lung transplantation (n = 5), with a median survival of 39.9 months. The risk prediction models composite physiology index (CPI), hazard ratio (HR) 1.07 (95.0% CI 1.04–1.10), and gender-age-physiology index (GAP) stage I predicted survival statistically significantly (p<0.001) compared to combined stages II and III. Conclusions: This study confirmed the results of earlier studies showing that FPF patients' radiological and histopathological patterns are diverse. Moreover, radiological and histological features revealed unusual patterns and their combinations. [ABSTRACT FROM AUTHOR]

Background: Severity of illness scoring systems are used in intensive care units to enable the calculation of adjusted outcomes for audit and benchmarking purposes. Similar tools are lacking for pre-hospital emergency medicine. Therefore, using a national helicopter emergency medical services database, we developed and internally validated a mortality prediction algorithm. Methods: We conducted a multicentre retrospective observational register-based cohort study based on the patients treated by five physician-staffed Finnish helicopter emergency medical service units between 2012 and 2019. Only patients aged 16 and over treated by physician-staffed units were included. We analysed the relationship between 30-day mortality and physiological, patient-related and circumstantial variables. The data were imputed using multiple imputations employing chained equations. We used multivariate logistic regression to estimate the variable effects and performed derivation of multiple multivariable models with different combinations of variables. The models were combined into an algorithm to allow a risk estimation tool that accounts for missing variables. Internal validation was assessed by calculating the optimism of each performance estimate using the von Hippel method with four imputed sets. Results: After exclusions, 30 186 patients were included in the analysis. 8611 (29%) patients died within the first 30 days after the incident. Eleven predictor variables (systolic blood pressure, heart rate, oxygen saturation, Glasgow Coma Scale, sex, age, emergency medical services vehicle type [helicopter vs ground unit], whether the mission was located in a medical facility or nursing home, cardiac rhythm [asystole, pulseless electrical activity, ventricular fibrillation, ventricular tachycardia vs others], time from emergency call to physician arrival and patient category) were included. Adjusted for optimism after internal validation, the algorithm had an area under the receiver operating characteristic curve of 0.921 (95% CI 0.918 to 0.924), Brier score of 0.097, calibration intercept of 0.000 (95% CI -0.040 to 0.040) and slope of 1.000 (95% CI 0.977 to 1.023). Conclusions: Based on 11 demographic, mission-specific, and physiologic variables, we developed and internally validated a novel severity of illness algorithm for use with patients encountered by physician-staffed helicopter emergency medical services, which may help in future quality improvement. [ABSTRACT FROM AUTHOR]

Background: Asthma patients experience higher rates of hospitalizations due to exacerbations leaving a considerable clinical and economic burden on the healthcare system. The use of a simple, risk prediction tool offers a low-cost mechanism to identify these high-risk asthma patients for specialized care. The study aimed to develop and validate a risk prediction model to identify high-risk asthma patients for hospitalization due to exacerbations. Methods: Hospital-based, case-control study was carried out among 466 asthma patients aged ≥ 20 years recruited from four tertiary care hospitals in a district of Sri Lanka to identify risk factors for asthma-related hospitalizations. Patients (n = 116) hospitalized due to an exacerbation with respiratory rate > 30/min, pulse rate > 120 bpm, O2 saturation (on air) < 90% on admission, selected consecutively from medical wards; controls (n = 350;1:3 ratio) randomly selected from asthma/medical clinics. Data was collected via a pre-tested Interviewer-Administered Questionnaire (IAQ). Logistic Regression (LR) analyses were performed to develop the model with consensus from an expert panel. A second case-control study was carried out to assess the criterion validity of the new model recruiting 158 cases and 101 controls from the same hospitals. Data was collected using an IAQ based on the newly developed risk prediction model. Results: The developed model consisted of ten predictors with an Area Under the Curve (AUC) of 0.83 (95% CI: 0.78 to 0.88, P < 0.001), sensitivity 69.0%, specificity 86.1%, positive predictive value (PPV) 88.6%, negative predictive value (NPV) 63.9%. Positive and negative likelihood ratios were 4.9 and 0.3, respectively. Conclusions: The newly developed model was proven valid to identify adult asthma patients who are at risk of hospitalization due to exacerbations. It is recommended as a simple, low-cost tool for identifying and prioritizing high-risk asthma patients for specialized care. [ABSTRACT FROM AUTHOR]

Introduction: Venous thromboembolism(VTE) is a leading cause of death in patients with lung cancer. Furthermore, hospitalization of patients with advanced lung cancer for VTE treatment represents a major economic burden on the national public health resources. Therefore, we performed this prospective study to identify clinical biomarkers for the early identification of VTE in lung cancer patients. Methods: This prospective study enrolled 158 patients with confirmed lung cancer, including 27 who were diagnosed with VTE within six months of the follow-up after lung cancer diagnosis. Multivariate logistic regression analysis was used to evaluate the diagnostic performancese of all the relevant clinical features and laboratory indicators in identifying lung cancer patients with a higher risk of VTE. A novel risk prediction model was constructed consisting of five clinical variables with the best diagnostic performances and was validated using the receiver operation characteristic(ROC) curves. The diagnostic performances of the new risk prediction model was also compared with the Khorana risk score (KRS) and the Padua risk score (PRS). Results: The VTE group of lung cancer patients (n = 27) showed significantly higher serum levels of fibrin degradation products (FDP), D-dimer, thrombomodulin (TM), thrombin-antithrombin-complex (TAT), α2-plasmin inhibitor-plasmin Complex (PIC), and tissue plasminogen activator-plasminogen activator inhibitor complex (t-PAIC) compared to those in the non-VTE group (n = 131). ROC curve analyses showed that the diagnostic efficacy of the new VTE risk prediction model with TM ≥ 9.75 TU/ml, TAT ≥ 2.25ng/ml, t-PAIC ≥ 7.35ng/ml, history of VTE, and ECOG PS score ≥ 2 was superior than the KRS and the PRS in the early identification of lung cancer patients with a higher risk of VTE. Conclusions: The new risk prediction model showed significantly high diagnostic efficacy in the early identification of lung cancer patients with a high risk of VTE. The diagnostic efficacy of the new risk prediction model was higher than the KRS and the PRS in this cohort of lung cancer patients. [ABSTRACT FROM AUTHOR]

Objectives: This study constructed a nomogram based on grayscale ultrasound features and real-time shear wave elastography (SWE) parameters to predict thyroid cancer. Methods: Clinical data of 217 thyroid nodules of 201 patients who underwent grayscale ultrasound, real-time SWE, and thyroid function laboratory examination in Ma'anshan People's Hospital from January 2019 to December 2020 were retrospectively analyzed. The subjects were divided into a benign nodule group (106 nodules) and a malignant nodule group (111 nodules). The differences in grayscale ultrasound features, quantitative parameters of real-time SWE, and laboratory results of thyroid function between benign and malignant thyroid nodules were analyzed. We used a chi-square test for categorical variables and a t-test for continuous variables. Then, the independent risk factors for thyroid cancer were analyzed using multivariate logistic regression. Based on the independent risk factors, a nomogram for predicting thyroid cancer risk was constructed using the RMS package of the R software. Results: Multivariate logistic regression showed that the grayscale ultrasound features of thyroid nodules were the shape, margin, echogenicity, and echogenic foci of the nodules,the maximum Young's modulus (SWE-max) of thyroid nodules, and the ratio of thyroid nodule and peripheral gland (SWE-ratio) measured by real-time SWE were independent risk factors for thyroid cancer (all p < 0.05), and the other variables had no statistical difference (p > 0.05). Based on the shape (OR = 5.160, 95% CI: 2.252–11.825), the margin (OR = 9.647, 95% CI: 2.048–45.443), the echogenicity (OR = 6.512, 95% CI: 1.729–24.524), the echogenic foci (OR = 2.049, 95% CI: 1.118–3.756), and the maximum Young's modulus (SWE-max) (OR = 1.296, 95% CI: 1.140–1.473), the SWE-ratio (OR = 2.001, 95% CI: 1.403–2.854) of the thyroid nodule to peripheral gland was used to establish the related nomogram prediction model. The bootstrap self-sampling method was used to verify the model. The consistency index (C-index) was 0.979, ROC curve was used to analyze the nomogram scores of all patients, and the AUC of nomogram prediction of thyroid cancer was 0.976, indicating that the nomogram model had high accuracy in the risk prediction of thyroid cancer. Conclusions: The nomogram model of grayscale ultrasound features combined with SWE parameters can accurately predict thyroid cancer. [ABSTRACT FROM AUTHOR]

Objective: Diabetes mellitus is a global epidemic disease. Long-time exposure of patients to hyperglycemia can lead to various type of chronic tissue damage. Early diagnosis of and screening for diabetes are crucial to population health. Methods: We collected the national physical examination data in Xinjiang, China, in 2020 (a total of more than 4 million people). Three types of physical examination indices were analyzed: questionnaire, routine physical examination and laboratory values. Integrated learning, deep learning and logistic regression methods were used to establish a risk model for type-2 diabetes mellitus. In addition, to improve the convenience and flexibility of the model, a diabetes risk score card was established based on logistic regression to assess the risk of the population. Results: An XGBoost-based risk prediction model outperformed the other five risk assessment algorithms. The AUC of the model was 0.9122. Based on the feature importance ranking map, we found that hypertension, fasting blood glucose, age, coronary heart disease, ethnicity, parental diabetes mellitus, triglycerides, waist circumference, total cholesterol, and body mass index were the most important features of the risk prediction model for type-2 diabetes. Conclusions: This study established a diabetes risk assessment model based on multiple ethnicities, a large sample and many indices, and classified the diabetes risk of the population, thus providing a new forecast tool for the screening of patients and providing information on diabetes prevention for healthy populations. [ABSTRACT FROM AUTHOR]

Background: People with intermediate hyperglycemia (IH), including impaired fasting glucose and/or impaired glucose tolerance, are at higher risk of developing type 2 diabetes (T2D) than those with normoglycemia. We aimed to evaluate the performance of published T2D risk prediction models in Chinese people with IH to inform them about the choice of primary diabetes prevention measures. Methods: A systematic literature search was conducted to identify Asian-derived T2D risk prediction models, which were eligible if they were built on a prospective cohort of Asian adults without diabetes at baseline and utilized routinely-available variables to predict future risk of T2D. These Asian-derived and five prespecified non-Asian derived T2D risk prediction models were divided into BASIC (clinical variables only) and EXTENDED (plus laboratory variables) versions, with validation performed on them in three prospective Chinese IH cohorts: ACE (n = 3241), Luzhou (n = 1333), and TCLSIH (n = 1702). Model performance was assessed in terms of discrimination (C-statistic) and calibration (Hosmer–Lemeshow test). Results: Forty-four Asian and five non-Asian studies comprising 21 BASIC and 46 EXTENDED T2D risk prediction models for validation were identified. The majority were at high (n = 43, 87.8%) or unclear (n = 3, 6.1%) risk of bias, while only three studies (6.1%) were scored at low risk of bias. BASIC models showed poor-to-moderate discrimination with C-statistics 0.52–0.60, 0.50–0.59, and 0.50–0.64 in the ACE, Luzhou, and TCLSIH cohorts respectively. EXTENDED models showed poor-to-acceptable discrimination with C-statistics 0.54–0.73, 0.52–0.67, and 0.59–0.78 respectively. Fifteen BASIC and 40 EXTENDED models showed poor calibration (P < 0.05), overpredicting or underestimating the observed diabetes risk. Most recalibrated models showed improved calibration but modestly-to-severely overestimated diabetes risk in the three cohorts. The NAVIGATOR model showed the best discrimination in the three cohorts but had poor calibration (P < 0.05). Conclusions: In Chinese people with IH, previously published BASIC models to predict T2D did not exhibit good discrimination or calibration. Several EXTENDED models performed better, but a robust Chinese T2D risk prediction tool in people with IH remains a major unmet need. [ABSTRACT FROM AUTHOR]

Objective: The internal workings ofmachine learning algorithms are complex and considered as low-interpretation "black box" models, making it difficult for domain experts to understand and trust these complex models. The study uses metabolic syndrome (MetS) as the entry point to analyze and evaluate the application value of model interpretability methods in dealing with difficult interpretation of predictive models. Methods: The study collects data from a chain of health examination institution in Urumqi from 2017 ~ 2019, and performs 39,134 remaining data after preprocessing such as deletion and filling. RFE is used for feature selection to reduce redundancy; MetS risk prediction models (logistic, random forest, XGBoost) are built based on a feature subset, and accuracy, sensitivity, specificity, Youden index, and AUROC value are used to evaluate the model classification performance; post-hoc model-agnostic interpretation methods (variable importance, LIME) are used to interpret the results of the predictive model. Results: Eighteen physical examination indicators are screened out by RFE, which can effectively solve the problem of physical examination data redundancy. Random forest and XGBoost models have higher accuracy, sensitivity, specificity, Youden index, and AUROC values compared with logistic regression. XGBoost models have higher sensitivity, Youden index, and AUROC values compared with random forest. The study uses variable importance, LIME and PDP for global and local interpretation of the optimal MetS risk prediction model (XGBoost), and different interpretation methods have different insights into the interpretation of model results, which are more flexible in model selection and can visualize the process and reasons for the model to make decisions. The interpretable risk prediction model in this study can help to identify risk factors associated with MetS, and the results showed that in addition to the traditional risk factors such as overweight and obesity, hyperglycemia, hypertension, and dyslipidemia, MetS was also associated with other factors, including age, creatinine, uric acid, and alkaline phosphatase. Conclusion: The model interpretability methods are applied to the black box model, which can not only realize the flexibility of model application, but also make up for the uninterpretable defects of the model. Model interpretability methods can be used as a novel means of identifying variables that are more likely to be good predictors. [ABSTRACT FROM AUTHOR]

Background: Despite increasing prevalence, age-specific risk predictive models for erosive tooth wear in preschool-age children have not been developed. Identification of at-risk groups and the timely introduction of behavioural change or treatment will stop the progression of erosive wear in the permanent dentition. This study aimed to identify age-specific risk factors for erosive wear. Distinct risk prediction models for 3-year-old and 5-year-old children were developed. Methods: A prospective cohort study included school-based clinical examinations and parent administered questionnaires for consented 3 and 5-year-old healthy children. Calibrated examiners measured the following health parameters under standardised conditions: erosion, using the Basic Erosive Wear Examination Index (BEWE), caries using the International Caries Detection and Assessment System (ICDAS), plaque and calculus according to the British Association for the Study of Community Dentistry (BASCD) scores, dental traumatic injuries and soft tissue lesions, salivary testing and BMI. Other health conditions were collected via a parent-administered questionnaire that explored oral- and general-health. Non parametric tests were utilised to explore the temporal relation of erosion with, demographic factors, oral hygiene habits, general health and dietary habits. Variables showing significance with a difference in BEWE cumulative score over time were utilised to develop two risk prediction models. The models were evaluated by Receiver Operating Characteristics analysis. Results: Risk factors for the 3-year-old cohort (N = 336) included erosive wear (χ2(1, 92) = 12.829, p < 0.001), district (χ2(5, 92) = 17.032, p = 0.004) and family size (χ2(1, 92) = 4.547, p = 0.033). Risk factors for the 5-year-old cohort (N = 441) also included erosive wear (χ2(1, 144) = 4.768, p = 0.029), gender (χ2(1, 144) = 19.399, p < 0.001), consumption of iced tea (χ2(1, 144) = 8.872, p = 0.003) and dry mouth (χ2(1, 144) = 9.598, p = 0.002). Conclusions: Predictive risk factors for 3-year-old children are based on demographic factors and are distinct from those for 5-year-old children based on biological and behavioural factors. Erosive wear is a risk factor for further wear in both age cohorts. [ABSTRACT FROM AUTHOR]

Background: The etiology of hamstring strain injury (HSI) in American football is multi-factorial and understanding these risk factors is paramount to developing predictive models and guiding prevention and rehabilitation strategies. Many player-games are lost due to the lack of a clear understanding of risk factors and the absence of effective methods to minimize re-injury. This paper describes the protocol that will be followed to develop the HAMstring InjuRy (HAMIR) index risk prediction models for HSI and re-injury based on morphological, architectural, biomechanical and clinical factors in National Collegiate Athletic Association Division I collegiate football players. Methods: A 3-year, prospective study will be conducted involving collegiate football student-athletes at four institutions. Enrolled participants will complete preseason assessments of eccentric hamstring strength, on-field sprinting biomechanics and muscle–tendon volumes using magnetic-resonance imaging (MRI). Athletic trainers will monitor injuries and exposure for the duration of the study. Participants who sustain an HSI will undergo a clinical assessment at the time of injury along with MRI examinations. Following completion of structured rehabilitation and return to unrestricted sport participation, clinical assessments, MRI examinations and sprinting biomechanics will be repeated. Injury recurrence will be monitored through a 6-month follow-up period. HAMIR index prediction models for index HSI injury and re-injury will be constructed. Discussion: The most appropriate strategies for reducing risk of HSI are likely multi-factorial and depend on risk factors unique to each athlete. This study will be the largest-of-its-kind (1200 player-years) to gather detailed information on index and recurrent HSI, and will be the first study to simultaneously investigate the effect of morphological, biomechanical and clinical variables on risk of HSI in collegiate football athletes. The quantitative HAMIR index will be formulated to identify an athlete's propensity for HSI, and more importantly, identify targets for injury mitigation, thereby reducing the global burden of HSI in high-level American football players. Trial Registration The trial is prospectively registered on ClinicalTrials.gov (NCT05343052; April 22, 2022). [ABSTRACT FROM AUTHOR]

Aim: To develop and validate a prediction model to evaluate the perioperative hypoglycemia risk in hospitalized type 2 diabetes mellitus (T2DM) patients undergoing elective surgery.Methods: We retrospectively analyzed the electronic medical records of 1410 T2DM patients who had been hospitalized and undergone elective surgery. Regression analysis was used to develop a predictive model for perioperative hypoglycemia risk. The receiver operating characteristic (ROC) curve and the Hosmer-Lemeshow test were used to verify the model.Results: Our study showed an incidence of 10.7% for level 1 hypoglycemia and 1.8% for level 2 severe hypoglycemia during the perioperative period. A perioperative hypoglycemic risk prediction model was developed that was mainly composed of four predictors: duration of diabetes ≥ 10 year, body mass index (BMI) < 18.5 kg/m2, standard deviation of blood glucose (SDBG) ≥ 3.0 mmol/L, and preoperative hypoglycemic regimen of insulin subcutaneous. Based on this model, patients were categorized into three groups: low, medium, and high risk. Internal validation of the prediction model showed high discrimination (ROC statistic = 0.715) and good calibration (no significant differences between predicted and observed risk: Pearson χ2 goodness-of-fit P = 0.765).Conclusions: The perioperative hypoglycemic risk prediction model categorizes the risk of hypoglycemia using only four predictors and shows good reliability and validity. The model serves as a favorable tool for clinicians to predict hypoglycemic risk and guide future interventions to reduce hypoglycemia risk. [ABSTRACT FROM AUTHOR]

Background: This study aimed to investigate the prevalence of preoperative deep venous thrombosis (DVT) following intertrochanteric fractures in the elderly and identify the associated factors, based on which a risk prediction model was developed.Method: This was a retrospective single-center study of elderly patients presenting with intertrochanteric fractures between our institution between January 2017 and December 2020. Patients' duplex ultrasound (DUS) or venography results were retrieved to evaluate whether they had a preoperative deep venous thrombosis (DVT) of bilateral extremities, whereby patients were dichotomized. Various variables of interest on demographics, comorbidities, injury and biomarkers were extracted and their relationship between DVT were investigated. Statistically significant variables tested in multivariate logistics regression analyses were used to develop a risk prediction model.Results: There were 855 patients eligible to be included in this study, and 105 were found to have preoperative DVT, with a prevalence rate of 12.3%. Ten factors were tested as significantly different and 2 marginally significant between DVT and non-DVT groups in the univariate analyses, but only 6 demonstrated the independent effect on DVT occurrence, including history of a VTE event (OR, 4.43; 95%CI, 2.04 to 9.62), time from injury to DVT screening (OR, 1.19; 95%CI, 1.13 to 1.25), BMI (OR, 1.11; 95%CI, 1.04-1.18), peripheral vascular disease (OR, 2.66; 95%CI, 1.10 to 6.40), reduced albumin (2.35; 95%CI, 1.48 to 3.71) and D-Dimer > 1.0 mg/L(OR, 1.90; 95%CI, 1.13 to 3.20). The DVT risk model showed an AUC of 0.780 (95%CI, 0.731 to 0.829), with a sensitivity of 0.667 and a specificity of 0.777.Conclusion: Despite without a so high prevalence rate of DVT in a general population with intertrochanteric fracture, particular attention should be paid to those involved in the associated risk factors above. The risk prediction model exhibited the improved specificity, but its validity required further studies to verify. [ABSTRACT FROM AUTHOR]

Background: To develop a reliable model to predict rapid kidney function decline (RKFD) among population at risk of cardiovascular disease.Methods: In this retrospective study, key monitoring residents including the elderly, and patients with hypertension or diabetes of China National Basic Public Health Service who underwent community annual physical examinations from January 2015 to December 2020 were included. Healthy records were extracted from regional chronic disease management platform. RKFD was defined as the reduction of estimated glomerular filtration rate (eGFR) ≥ 40% during follow-up period. The entire cohort were randomly assigned to a development cohort and a validation cohort in a 2:1 ratio. Cox regression analysis was used to identify the independent predictors. A nomogram was established based on the development cohort. The concordance index (C-index) and calibration plots were calculated. Decision curve analysis was applied to evaluate the clinical utility.Results: A total of 8455 subjects were included. During the median follow-up period of 3.72 years, the incidence of RKFD was 11.96% (n = 1011), 11.98% (n = 676) and 11.92% (n = 335) in the entire cohort, development cohort and validation cohort, respectively. Age, eGFR, hemoglobin, systolic blood pressure, and diabetes were identified as predictors for RKFD. Good discriminating performance was observed in both the development (C-index, 0.73) and the validation (C-index, 0.71) cohorts, and the AUCs for predicting 5-years RKFD was 0.763 and 0.740 in the development and the validation cohort, respectively. Decision curve analysis further confirmed the clinical utility of the nomogram.Conclusions: Our nomogram based on five readily accessible variables (age, eGFR, hemoglobin, systolic blood pressure, and diabetes) is a useful tool to identify high risk patients for RKFD among population at risk of cardiovascular disease in primary care. Whereas, further external validations are needed before clinical generalization. [ABSTRACT FROM AUTHOR]

Background: High-risk surgical procedures represent a fundamental part of general surgery practice due to its significant rates of morbidity and mortality. Different predictive tools have been created in order to quantify perioperative morbidity and mortality risk. POSSUM (Physiological and Operative Severity Score for the enumeration of Mortality and morbidity) is one of the most widely validated predictive scores considering physiological and operative variables to precisely define morbimortality risk. Nevertheless, seeking greater accuracy in predictions P-POSSUM was proposed. We aimed to compare POSSUM and P-POSSUM for patients undergoing abdominal surgery.Methods: A retrospective observational study with a prospective database was conducted. Patients over 18 years old who complied with inclusion criteria between 2015 and 2016 were included. Variables included in the POSSUM and P-POSSUM Scores were analyzed. Descriptive statistics of all study parameters were provided. The analysis included socio-demographic data, laboratory values ​​, and imaging. Bivariate analysis was performed.Results: 350 Patients were included in the analysis, 55.1% were female. The mean age was 55.9 ± 20.4 years old. POSSUM revealed a moderated index score in 61.7% of the patients, mean score of 12.85 points ± 5.61. 89.1% of patients had no neoplastic diagnosis associated. Overall morbidity and mortality rate was 14.2% and 7.1%. P-POSSUM could predict more precisely mortality (p < 0.00).Conclusions: The POSSUM score is likely to overestimate the risk of morbidity and mortality in patients with high/moderate risk, while the P-POSSUM score seems to be a more accurate predictor of mortality risk. Further studies are needed to confirm our results. [ABSTRACT FROM AUTHOR]

Background: Accurate, pragmatic risk stratification for postoperative delirium (POD) is necessary to target preventative resources toward high-risk patients. Machine learning (ML) offers a novel approach to leveraging electronic health record (EHR) data for POD prediction. We sought to develop and internally validate a ML-derived POD risk prediction model using preoperative risk features, and to compare its performance to models developed with traditional logistic regression. Methods: This was a retrospective analysis of preoperative EHR data from 24,885 adults undergoing a procedure requiring anesthesia care, recovering in the main post-anesthesia care unit, and staying in the hospital at least overnight between December 2016 and December 2019 at either of two hospitals in a tertiary care health system. One hundred fifteen preoperative risk features including demographics, comorbidities, nursing assessments, surgery type, and other preoperative EHR data were used to predict postoperative delirium (POD), defined as any instance of Nursing Delirium Screening Scale ≥2 or positive Confusion Assessment Method for the Intensive Care Unit within the first 7 postoperative days. Two ML models (Neural Network and XGBoost), two traditional logistic regression models ("clinician-guided" and "ML hybrid"), and a previously described delirium risk stratification tool (AWOL-S) were evaluated using the area under the receiver operating characteristic curve (AUC-ROC), sensitivity, specificity, positive likelihood ratio, and positive predictive value. Model calibration was assessed with a calibration curve. Patients with no POD assessments charted or at least 20% of input variables missing were excluded. Results: POD incidence was 5.3%. The AUC-ROC for Neural Net was 0.841 [95% CI 0. 816–0.863] and for XGBoost was 0.851 [95% CI 0.827–0.874], which was significantly better than the clinician-guided (AUC-ROC 0.763 [0.734–0.793], p < 0.001) and ML hybrid (AUC-ROC 0.824 [0.800–0.849], p < 0.001) regression models and AWOL-S (AUC-ROC 0.762 [95% CI 0.713–0.812], p < 0.001). Neural Net, XGBoost, and ML hybrid models demonstrated excellent calibration, while calibration of the clinician-guided and AWOL-S models was moderate; they tended to overestimate delirium risk in those already at highest risk. Conclusion: Using pragmatically collected EHR data, two ML models predicted POD in a broad perioperative population with high discrimination. Optimal application of the models would provide automated, real-time delirium risk stratification to improve perioperative management of surgical patients at risk for POD. [ABSTRACT FROM AUTHOR]

Background: Early unplanned hospital readmissions are associated with increased harm to patients, increased medical costs, and negative hospital reputation. With the identification of at-risk patients, a crucial step toward improving care, appropriate interventions can be adopted to prevent readmission. This study aimed to build machine learning models to predict 14-day unplanned readmissions.Methods: We conducted a retrospective cohort study on 37,091 consecutive hospitalized adult patients with 55,933 discharges between September 1, 2018, and August 31, 2019, in an 1193-bed university hospital. Patients who were aged < 20 years, were admitted for cancer-related treatment, participated in clinical trial, were discharged against medical advice, died during admission, or lived abroad were excluded. Predictors for analysis included 7 categories of variables extracted from hospital's medical record dataset. In total, four machine learning algorithms, namely logistic regression, random forest, extreme gradient boosting, and categorical boosting, were used to build classifiers for prediction. The performance of prediction models for 14-day unplanned readmission risk was evaluated using precision, recall, F1-score, area under the receiver operating characteristic curve (AUROC), and area under the precision-recall curve (AUPRC).Results: In total, 24,722 patients were included for the analysis. The mean age of the cohort was 57.34 ± 18.13 years. The 14-day unplanned readmission rate was 1.22%. Among the 4 machine learning algorithms selected, Catboost had the best average performance in fivefold cross-validation (precision: 0.9377, recall: 0.5333, F1-score: 0.6780, AUROC: 0.9903, and AUPRC: 0.7515). After incorporating 21 most influential features in the Catboost model, its performance improved (precision: 0.9470, recall: 0.5600, F1-score: 0.7010, AUROC: 0.9909, and AUPRC: 0.7711).Conclusions: Our models reliably predicted 14-day unplanned readmissions and were explainable. They can be used to identify patients with a high risk of unplanned readmission based on influential features, particularly features related to diagnoses. The operation of the models with physiological indicators also corresponded to clinical experience and literature. Identifying patients at high risk with these models can enable early discharge planning and transitional care to prevent readmissions. Further studies should include additional features that may enable further sensitivity in identifying patients at a risk of early unplanned readmissions. [ABSTRACT FROM AUTHOR]

Objective: To establish a risk prediction model for pancreatic fistula according to the pancreatic fistula standards of the 2016 edition. Methods: Clinical data from 223 patients with PD admitted to Tianjin Third Central Hospital from January 2016 to December 2020 were retrospectively analyzed. Patients were divided into modeling (January 2016 to December 2018) and validation (January 2019 to December 2020) sets according to the time of admission. The risk factors for postoperative pancreatic fistula (POPF) were screened by univariate and multivariate logistic regression analyses, and a risk prediction model for POPF was established in the modeling set. This score was tested in the validation set. Results: Logistic regression analysis showed that the main pancreatic duct index and CT value were independent risk factors according to the 2016 pancreatic fistula grading standard, based on which a risk prediction model for POPF was established. Receiver operating characteristic curve analysis showed that the area under the curve was 0.775 in the modeling set and 0.848 in the validation set. Conclusion: The main pancreatic duct index and CT value of the pancreas are closely related to the occurrence of pancreatic fistula after PD, and the established risk prediction model for pancreatic fistula has good prediction accuracy. [ABSTRACT FROM AUTHOR]

Since the start of the coronavirus disease 2019 (COVID-19) pandemic, it has remained unknown whether conventional risk prediction tools used in intensive care units are applicable to patients with COVID-19. Therefore, we assessed the performance of established risk prediction models using the Japanese Intensive Care database. Discrimination and calibration of the models were poor. Revised risk prediction models are needed to assess the clinical severity of COVID-19 patients and monitor healthcare quality in ICUs overwhelmed by patients with COVID-19. [ABSTRACT FROM AUTHOR]

Objectives: The occurrence of pulmonary infection after congenital heart disease (CHD) surgery can lead to significant increases in intensive care in cardiac intensive care unit (CICU) retention time, medical expenses, and risk of death risk. We hypothesized that patients with a high risk of pulmonary infection could be screened out as early after surgery. Hence, we developed and validated the first risk prediction model to verify our hypothesis.Methods: Patients who underwent CHD surgery from October 2012 to December 2017 in the Children's Hospital of Chongqing Medical University were included in the development group, while patients who underwent CHD surgery from December 2017 to October 2018 were included in the validation group. The independent risk factors associated with pulmonary infection following CHD surgery were screened using univariable and multivariable logistic regression analyses. The corresponding nomogram prediction model was constructed according to the regression coefficients. Model discrimination was evaluated by the area under the receiver operating characteristic curve (ROC) (AUC), and model calibration was conducted with the Hosmer-Lemeshow test.Results: The univariate and multivariate logistic regression analyses identified the following six independent risk factors of pulmonary infection after cardiac surgery: age, weight, preoperative hospital stay, risk-adjusted classification for congenital heart surgery (RACHS)-1 score, cardiopulmonary bypass time and intraoperative blood transfusion. We established an individualized prediction model of pulmonary infection following cardiopulmonary bypass surgery for CHD in children. The model displayed accuracy and reliability and was evaluated by discrimination and calibration analyses. The AUCs for the development and validation groups were 0.900 and 0.908, respectively, and the P-values of the calibration tests were 0.999 and 0.452 respectively. Therefore, the predicted probability of the model was consistent with the actual probability.Conclusions: Identified the independent risk factors of pulmonary infection after cardiopulmonary bypass surgery. An individualized prediction model was developed to evaluate the pulmonary infection of patients after surgery. For high-risk patients, after surgery, targeted interventions can reduce the risk of pulmonary infection. [ABSTRACT FROM AUTHOR]

Background: The Acute Physiology and Chronic Health Evaluation (APACHE) III-j model is widely used to predict mortality in Japanese intensive care units (ICUs). Although the model's discrimination is excellent, its calibration is poor. APACHE III-j overestimates the risk of death, making its evaluation of healthcare quality inaccurate. This study aimed to improve the calibration of the model and develop a Japan Risk of Death (JROD) model for benchmarking purposes. Methods: A retrospective analysis was conducted using a national clinical registry of ICU patients in Japan. Adult patients admitted to an ICU between April 1, 2018, and March 31, 2019, were included. The APACHE III-j model was recalibrated with the following models: Model 1, predicting mortality with an offset variable for the linear predictor of the APACHE III-j model using a generalized linear model; model 2, predicting mortality with the linear predictor of the APACHE III-j model using a generalized linear model; and model 3, predicting mortality with the linear predictor of the APACHE III-j model using a hierarchical generalized additive model. Model performance was assessed with the area under the receiver operating characteristic curve (AUROC), the Brier score, and the modified Hosmer–Lemeshow test. To confirm model applicability to evaluating quality of care, funnel plots of the standardized mortality ratio and exponentially weighted moving average (EWMA) charts for mortality were drawn. Results: In total, 33,557 patients from 44 ICUs were included in the study population. ICU mortality was 3.8%, and hospital mortality was 8.1%. The AUROC, Brier score, and modified Hosmer–Lemeshow p value of the original model and models 1, 2, and 3 were 0.915, 0.062, and <.001; 0.915, 0.047, and <.001; 0.915, 0.047, and.002; and 0.917, 0.047, and.84, respectively. Except for model 3, the funnel plots showed overdispersion. The validity of the EWMA charts for the recalibrated models was determined by visual inspection. Conclusions: Model 3 showed good performance and can be adopted as the JROD model for monitoring quality of care in an ICU, although further investigation of the clinical validity of outlier detection is required. This update method may also be useful in other settings. [ABSTRACT FROM AUTHOR]

Background: Cerebral-cardiac syndrome, newly developed cardiac damage manifestations subsequent to cerebral injuries, is a common complication of stroke and leads to increased morbidity and mortality. The current study is aimed to develop a risk prediction scale to stratify high-risk population of CCS among ischemic stroke patients.Methods: The study included 410 cases from four tertiary medical centers from June 2018 to April 2019. The risk prediction model was established via logistic regression from the derivation cohort including 250 cases admitted between June 2018 and December 2018. Another 160 cases admitted from January 2019 to April 2019 were included as the validation cohort for external validation. The performance of the model was determined by the area under curve of the receiver operating characteristic curve. A rating scale was developed based on the magnitude of the logistic regression coefficient.Results: The prevalence of CCS was 55.2% in our study. The predictive model derived from the derivation cohort showed good calibration by Hosmer-Lemeshow test (P = 0.492), and showed sensitivity of 0.935, specificity of 0.720, and Youden index of 0.655. The C-statistic for derivation and validation cohort were 0.888 and 0.813, respectively. Our PANSCAN score (0 to 10 points) was then established, which consists of the following independent risk factors: PT(12 s-14 s = 0; otherwise = 1), APTT(30s-45s = 0, otherwise = 1), Neutrophils(50-70% = 0; otherwise = 1), Sex(female = 1), Carotid artery stenosis(normal or mild = 0; moderate to severe = 2), Age(≥65 years = 1), NIHSS score(1 to 4 = 2; ≥5 = 3). Patients scored 3 or more points were stratified as high risk.Conclusion: The risk prediction model showed satisfactory prediction effects. The PANSCAN scale provides convenient reference for preventative treatment and early management for high-risk patients.Trial Registration: The study was retrospectively registered in Chinese Trial Registry. The date of registration is April 17, 2019.Trial Registration Number: ChiCTR1900022587 . [ABSTRACT FROM AUTHOR]

Background: The decision of transarterial chemoembolization (TACE) initiation and/or repetition remains challenging in patients with unresectable hepatocellular carcinoma (HCC). The aim was to develop a prognostic scoring system to guide TACE initiation/repetition.Methods: A total of 597 consecutive patients who underwent TACE as their initial treatment for unresectable HCC were included. We derived a prediction model using independent risk factors for overall survival (OS), which was externally validated in an independent cohort (n = 739).Results: Independent risk factors of OS included Albumin-bilirubin (ALBI) grade, maximal tumor size, alpha-fetoprotein, and tumor response to initial TACE, which were used to develop a scoring system ("ASAR"). C-index values for OS were 0.733 (95% confidence interval [CI] = 0.570-0.871) in the derivation, 0.700 (95% CI = 0.445-0.905) in the internal validation, and 0.680 (95% CI = 0.652-0.707) in the external validation, respectively. Patients with ASAR< 4 showed significantly longer OS than patients with ASAR≥4 in all three datasets (all P < 0.001). Among Child-Pugh class B patients, a modified model without TACE response, i.e., "ASA(R)", discriminated OS with a c-index of 0.788 (95% CI, 0.703-0.876) in the derivation, and 0.745 (95% CI, 0.646-0.862) in the internal validation, and 0.670 (95% CI, 0.605-0.725) in the external validation, respectively. Child-Pugh B patients with ASA(R) < 4 showed significantly longer OS than patients with ASA(R) ≥ 4 in all three datasets (all P < 0.001).Conclusions: ASAR provides refined prognostication for repetition of TACE in patients with unresectable HCC. For Child-Pugh class B patients, a modified model with baseline factors might guide TACE initiation. [ABSTRACT FROM AUTHOR]

Background: Guidelines recommend identifying in early pregnancy women at elevated risk of pre-eclampsia. The aim of this study was to develop and validate a pre-eclampsia risk prediction model for nulliparous women attending routine antenatal care "the Western Sydney (WS) model"; and to compare its performance with the National Institute of Health and Care Excellence (NICE) risk factor-list approach for classifying women as high-risk.Methods: This retrospective cohort study included all nulliparous women who gave birth in three public hospitals in the Western-Sydney-Local-Health-District, Australia 2011-2014. Using births from 2011 to 2012, multivariable logistic regression incorporated established maternal risk factors to develop and internally validate the WS model. The WS model was then externally validated using births from 2013 to 2014, assessing its discrimination and calibration. We fitted the final WS model for all births from 2011 to 2014, and compared its accuracy in predicting pre-eclampsia with the NICE approach.Results: Among 12,395 births to nulliparous women in 2011-2014, there were 293 (2.4%) pre-eclampsia events. The WS model included: maternal age, body mass index, ethnicity, multiple pregnancy, family history of pre-eclampsia, autoimmune disease, chronic hypertension and chronic renal disease. In the validation sample (6201 births), the model c-statistic was 0.70 (95% confidence interval 0.65-0.75). The observed:expected ratio for pre-eclampsia was 0.91, with a Hosmer-Lemeshow goodness-of-fit test p-value of 0.20. In the entire study sample of 12,395 births, 374 (3.0%) women had a WS model-estimated pre-eclampsia risk ≥8%, the pre-specified risk-threshold for considering aspirin prophylaxis. Of these, 54 (14.4%) developed pre-eclampsia (sensitivity 18% (14-23), specificity 97% (97-98)). Using the NICE approach, 1173 (9.5%) women were classified as high-risk, of which 107 (9.1%) developed pre-eclampsia (sensitivity 37% (31-42), specificity 91% (91-92)). The final model showed similar accuracy to the NICE approach when using lower risk-threshold of ≥4% to classify women as high-risk for pre-eclampsia.Conclusion: The WS risk model that combines readily-available maternal characteristics achieved modest performance for prediction of pre-eclampsia in nulliparous women. The model did not outperform the NICE approach, but has the advantage of providing individualised absolute risk estimates, to assist with counselling, inform decisions for further testing, and consideration of aspirin prophylaxis. [ABSTRACT FROM AUTHOR]

Background: Breast cancer survivors are at risk for contralateral breast cancer (CBC), with the consequent burden of further treatment and potentially less favorable prognosis. We aimed to develop and validate a CBC risk prediction model and evaluate its applicability for clinical decision-making.Methods: We included data of 132,756 invasive non-metastatic breast cancer patients from 20 studies with 4682 CBC events and a median follow-up of 8.8 years. We developed a multivariable Fine and Gray prediction model (PredictCBC-1A) including patient, primary tumor, and treatment characteristics and BRCA1/2 germline mutation status, accounting for the competing risks of death and distant metastasis. We also developed a model without BRCA1/2 mutation status (PredictCBC-1B) since this information was available for only 6% of patients and is routinely unavailable in the general breast cancer population. Prediction performance was evaluated using calibration and discrimination, calculated by a time-dependent area under the curve (AUC) at 5 and 10 years after diagnosis of primary breast cancer, and an internal-external cross-validation procedure. Decision curve analysis was performed to evaluate the net benefit of the model to quantify clinical utility.Results: In the multivariable model, BRCA1/2 germline mutation status, family history, and systemic adjuvant treatment showed the strongest associations with CBC risk. The AUC of PredictCBC-1A was 0.63 (95% prediction interval (PI) at 5 years, 0.52-0.74; at 10 years, 0.53-0.72). Calibration-in-the-large was -0.13 (95% PI: -1.62-1.37), and the calibration slope was 0.90 (95% PI: 0.73-1.08). The AUC of Predict-1B at 10 years was 0.59 (95% PI: 0.52-0.66); calibration was slightly lower. Decision curve analysis for preventive contralateral mastectomy showed potential clinical utility of PredictCBC-1A between thresholds of 4-10% 10-year CBC risk for BRCA1/2 mutation carriers and non-carriers.Conclusions: We developed a reasonably calibrated model to predict the risk of CBC in women of European-descent; however, prediction accuracy was moderate. Our model shows potential for improved risk counseling, but decision-making regarding contralateral preventive mastectomy, especially in the general breast cancer population where limited information of the mutation status in BRCA1/2 is available, remains challenging. [ABSTRACT FROM AUTHOR]

Background: Compelled by the intuitive appeal of predicting each individual patient's risk of an outcome, there is a growing interest in risk prediction models. While the statistical methods used to build prediction models are increasingly well understood, the literature offers little insight to researchers seeking to gauge a priori whether a prediction model is likely to perform well for their particular research question. The objective of this study was to inform the development of new risk prediction models by evaluating model performance under a wide range of predictor characteristics. Methods: Data from all births to overweight or obese women in British Columbia, Canada from 2004 to 2012 (n = 75,225) were used to build a risk prediction model for preeclampsia. The data were then augmented with simulated predictors of the outcome with pre-set prevalence values and univariable odds ratios. We built 120 risk prediction models that included known demographic and clinical predictors, and one, three, or five of the simulated variables. Finally, we evaluated standard model performance criteria (discrimination, risk stratification capacity, calibration, and Nagelkerke's r2) for each model. Results: Findings from our models built with simulated predictors demonstrated the predictor characteristics required for a risk prediction model to adequately discriminate cases from non-cases and to adequately classify patients into clinically distinct risk groups. Several predictor characteristics can yield well performing risk prediction models; however, these characteristics are not typical of predictor-outcome relationships in many population-based or clinical data sets. Novel predictors must be both strongly associated with the outcome and prevalent in the population to be useful for clinical prediction modeling (e.g., one predictor with prevalence ≥20 % and odds ratio ≥8, or 3 predictors with prevalence ≥10 % and odds ratios ≥4). Area under the receiver operating characteristic curve values of >0.8 were necessary to achieve reasonable risk stratification capacity. Conclusions: Our findings provide a guide for researchers to estimate the expected performance of a prediction model before a model has been built based on the characteristics of available predictors. [ABSTRACT FROM AUTHOR]

Background: A high-quality risk prediction model is urgently needed for the clinical management of ovarian cancer. However most existing models are solely based on clinical parameters, and molecular classifications in recent reports are still being debated. This study aimed to establish a risk prediction model by using both clinicopathological and molecular factors (the synthetic model) for epithelial ovarian cancer. Methods: A retrospective cohort study was conducted in epithelial ovarian cancer patients (n = 161) treated with primary debulking surgery and adjuvant chemotherapy. The expression level of 15 selected molecular markers were measured using immunohistochemistry. A risk model was developed using COX regression analysis with overall survival as the primary outcome. A simplified scoring system for each prognostic factor was based on its coefficient. Independent validation (n = 40) was conducted to evaluate the performance of the model. Results: A total of 10 out of 15 molecular markers were significantly associated with clinical characteristics and overall survival. The synthetic model performed better than the clinicopathological risk model or the molecular risk model alone, as assessed by analysis of the receiver-operating characteristics curve area and the Youden index. The synthetic model included parity (>3), peritoneal metastasis, stage, tumor type, residual disease, and expression of human epidermal growth factor receptor 2 (HER2), epidermal growth factor receptor (EGFR), breast cancer 1 (BRCA1), murine sarcoma viral oncogene homolog B (BRAF) and Kirsten rat sarcoma viral oncogene homolog (KRAS). Conclusions: Our synthetic risk model may more accurately predict survival of epithelial ovarian cancer patients than current models. [ABSTRACT FROM AUTHOR]