Using measures of race to make clinical predictions: Decision making, patient health, and fairness.

The use of race measures in clinical prediction models is contentious. We seek to inform the discourse by evaluating the inclusion of race in probabilistic predictions of illness that support clinical decision making. Adopting a static utilitarian framework to formalize social welfare, we show that patients of all races benefit when clinical decisions are jointly guided by patient race and other observable covariates. Similar conclusions emerge when the model is extended to a two-period setting where prevention activities target systemic drivers of disease. We also discuss non-utilitarian concepts that have been proposed to guide allocation of health care resources.

Identifying digenic disease genes via machine learning in the Undiagnosed Diseases Network.

Rare diseases affect millions of people worldwide, and discovering their genetic causes is challenging. More than half of the individuals analyzed by the Undiagnosed Diseases Network (UDN) remain undiagnosed. The central hypothesis of this work is that many of these rare genetic disorders are caused by multiple variants in more than one gene. However, given the large number of variants in each individual genome, experimentally evaluating combinations of variants for potential to cause disease is currently infeasible. To address this challenge, we developed the digenic predictor (DiGePred), a random forest classifier for identifying candidate digenic disease gene pairs by features derived from biological networks, genomics, evolutionary history, and functional annotations. We trained the DiGePred classifier by using DIDA, the largest available database of known digenic-disease-causing gene pairs, and several sets of non-digenic gene pairs, including variant pairs derived from unaffected relatives of UDN individuals. DiGePred achieved high precision and recall in cross-validation and on a held-out test set (PR area under the curve > 77%), and we further demonstrate its utility by using digenic pairs from the recent literature. In contrast to other approaches, DiGePred also appropriately controls the number of false positives when applied in realistic clinical settings. Finally, to enable the rapid screening of variant gene pairs for digenic disease potential, we freely provide the predictions of DiGePred on all human gene pairs. Our work enables the discovery of genetic causes for rare non-monogenic diseases by providing a means to rapidly evaluate variant gene pairs for the potential to cause digenic disease.

Variability in the prevalence of depression among adults with chronic pain: UK Biobank analysis through clinical prediction models.

BACKGROUND: The prevalence of depression among people with chronic pain remains unclear due to the heterogeneity of study samples and definitions of depression. We aimed to identify sources of variation in the prevalence of depression among people with chronic pain and generate clinical prediction models to estimate the probability of depression among individuals with chronic pain. METHODS: Participants were from the UK Biobank. The primary outcome was a "lifetime" history of depression. The model's performance was evaluated using discrimination (optimism-corrected C statistic) and calibration (calibration plot). RESULTS: Analyses included 24,405 patients with chronic pain (mean age 64.1 years). Among participants with chronic widespread pain, the prevalence of having a "lifetime" history of depression was 45.7% and varied (25.0-66.7%) depending on patient characteristics. The final clinical prediction model (optimism-corrected C statistic: 0.66; good calibration on the calibration plot) included age, BMI, smoking status, physical activity, socioeconomic status, gender, history of asthma, history of heart failure, and history of peripheral artery disease. Among participants with chronic regional pain, the prevalence of having a "lifetime" history of depression was 30.2% and varied (21.4-70.6%) depending on patient characteristics. The final clinical prediction model (optimism-corrected C statistic: 0.65; good calibration on the calibration plot) included age, gender, nature of pain, smoking status, regular opioid use, history of asthma, pain location that bothers you most, and BMI. CONCLUSIONS: There was substantial variability in the prevalence of depression among patients with chronic pain. Clinically relevant factors were selected to develop prediction models. Clinicians can use these models to assess patients' treatment needs. These predictors are convenient to collect during daily practice, making it easy for busy clinicians to use them.

Establishment and evaluation of a clinical prediction model for cognitive impairment in patients with cerebral small vessel disease.

BACKGROUND: There are currently no effective prediction methods for evaluating the occurrence of cognitive impairment in patients with cerebral small vessel disease (CSVD). AIMS: To investigate the risk factors for cognitive dysfunction in patients with CSVD and to construct a risk prediction model. METHODS: A retrospective study was conducted on 227 patients with CSVD. All patients were assessed by brain magnetic resonance imaging (MRI), and the Montreal Cognitive Assessment (MoCA) was used to assess cognitive status. In addition, the patient's medical records were also recorded. The clinical data were divided into a normal cognitive function group and a cognitive impairment group. A MoCA score < 26 (an additional 1 point for education < 12 years) is defined as cognitive dysfunction. RESULTS: A total of 227 patients (mean age 66.7 ± 6.99 years) with CSVD were included in this study, of whom 68.7% were male and 100 patients (44.1%) developed cognitive impairment. Age (OR = 1.070; 95% CI = 1.015 ~ 1.128, p < 0.05), hypertension (OR = 2.863; 95% CI = 1.438 ~ 5.699, p < 0.05), homocysteine(HCY) (OR = 1.065; 95% CI = 1.005 ~ 1.127, p < 0.05), lacunar infarct score(Lac_score) (OR = 2.732; 95% CI = 1.094 ~ 6.825, P < 0.05), and CSVD total burden (CSVD_score) (OR = 3.823; 95% CI = 1.496 ~ 9.768, P < 0.05) were found to be independent risk factors for cognitive decline in the present study. The above 5 variables were used to construct a nomogram, and the model was internally validated by using bootstrapping with a C-index of 0.839. The external model validation C-index was 0.867. CONCLUSIONS: The nomogram model based on brain MR images and clinical data helps in individualizing the probability of cognitive impairment progression in patients with CSVD.

Designing an Implementable Clinical Prediction Model for Near-Term Mortality and Long-Term Survival in Patients on Maintenance Hemodialysis.

RATIONALE & OBJECTIVE: The life expectancy of patients treated with maintenance hemodialysis (MHD) is heterogeneous. Knowledge of life-expectancy may focus care decisions on near-term versus long-term goals. The current tools are limited and focus on near-term mortality. Here, we develop and assess potential utility for predicting near-term mortality and long-term survival on MHD. STUDY DESIGN: Predictive modeling study. SETTING & PARTICIPANTS: 42,351 patients contributing 997,381 patient months over 11 years, abstracted from the electronic health record (EHR) system of midsize, nonprofit dialysis providers. NEW PREDICTORS & ESTABLISHED PREDICTORS: Demographics, laboratory results, vital signs, and service utilization data available within dialysis EHR. OUTCOME: For each patient month, we ascertained death within the next 6 months (ie, near-term mortality) and survival over more than 5 years during receipt of MHD or after kidney transplantation (ie, long-term survival). ANALYTICAL APPROACH: We used least absolute shrinkage and selection operator logistic regression and gradient-boosting machines to predict each outcome. We compared these to time-to-event models spanning both time horizons. We explored the performance of decision rules at different cut points. RESULTS: All models achieved an area under the receiver operator characteristic curve of≥0.80 and optimal calibration metrics in the test set. The long-term survival models had significantly better performance than the near-term mortality models. The time-to-event models performed similarly to binary models. Applying different cut points spanning from the 1st to 90th percentile of the predictions, a positive predictive value (PPV) of 54% could be achieved for near-term mortality, but with poor sensitivity of 6%. A PPV of 71% could be achieved for long-term survival with a sensitivity of 67%. LIMITATIONS: The retrospective models would need to be prospectively validated before they could be appropriately used as clinical decision aids. CONCLUSIONS: A model built with readily available clinical variables to support easy implementation can predict clinically important life expectancy thresholds and shows promise as a clinical decision support tool for patients on MHD. Predicting long-term survival has better decision rule performance than predicting near-term mortality. PLAIN-LANGUAGE SUMMARY: Clinical prediction models (CPMs) are not widely used for patients undergoing maintenance hemodialysis (MHD). Although a variety of CPMs have been reported in the literature, many of these were not well-designed to be easily implementable. We consider the performance of an implementable CPM for both near-term mortality and long-term survival for patients undergoing MHD. Both near-term and long-term models have similar predictive performance, but the long-term models have greater clinical utility. We further consider how the differential performance of predicting over different time horizons may be used to impact clinical decision making. Although predictive modeling is not regularly used for MHD patients, such tools may help promote individualized care planning and foster shared decision making.

Development of an IVF prediction model for donor oocytes: a retrospective analysis of 10 877 embryo transfers.

STUDY QUESTION: Can we develop a prediction model for the chance of a live birth following the transfer of an embryo created using donated oocytes? SUMMARY ANSWER: Three primary models that included patient, past treatment, and cycle characteristics were developed using Australian data to predict the chance of a live birth following the transfer of an embryo created using donated oocytes; these models were well-calibrated to the population studied, achieved reasonable predictive power and generalizability when tested on New Zealand data. WHAT IS KNOWN ALREADY: Nearly 9% of ART embryo transfer cycles performed globally use embryos created using donated oocytes. This percentage rises to one-quarter and one-half in same-sex couples and women aged over 45 years, respectively. STUDY DESIGN, SIZE, DURATION: This study uses population-based Australian clinical registry data comprising 9384 embryo transfer cycles that occurred between 2015 and 2021 for model development, with an external validation cohort of 1493 New Zealand embryo transfer cycles. PARTICIPANTS/MATERIALS, SETTING, METHODS: Three prediction models were compared that incorporated patient characteristics, but differed in whether they considered use of prior autologous treatment factors and current treatment parameters. We internally validated the models on Australian data using grouped cross-validation and reported several measures of model discrimination and calibration. Variable importance was measured through calculating the change in predictive performance that resulted from variable permutation. The best-performing model was externally validated on data from New Zealand. MAIN RESULTS AND THE ROLE OF CHANCE: The best-performing model had an internal validation AUC-ROC of 0.60 and Brier score of 0.20, and external validation AUC-ROC of 0.61 and Brier score of 0.23. While these results indicate ∼15% less discriminatory ability compared to models assessed on an autologous cohort from the same population the performance of the models was clearly statistically significantly better than random, demonstrated generalizability, and was well-calibrated to the population studied. The most important variables for predicting the chance of a live birth were the oocyte donor age, the number of prior oocyte recipient embryo transfer cycles, whether the transferred embryo was cleavage or blastocyst stage and oocyte recipient age. Of lesser importance were the oocyte-recipient parity, whether donor or partner sperm was used, the number of prior autologous embryo transfer cycles and the number of embryos transferred. LIMITATIONS, REASONS FOR CAUTION: The models had relatively weak discrimination suggesting further features need to be added to improve their predictive power. Variation in donor oocyte cohorts across countries due to differences such as whether anonymous and compensated donation are allowed may necessitate the models be recalibrated prior to application in non-Australian cohorts. WIDER IMPLICATIONS OF THE FINDINGS: These results confirm the well-established importance of oocyte age and ART treatment history as the key prognostic factors in predicting treatment outcomes. One of the developed models has been incorporated into a consumer-facing website (YourIVFSuccess.com.au/Estimator) to allow patients to obtain personalized estimates of their chance of success using donor oocytes. STUDY FUNDING/COMPETING INTEREST(S): This research was funded by the Australian government as part of the Medical Research Future Fund (MRFF) Emerging Priorities and Consumer Driven Research initiative: EPCD000007. L.R. declares personal consulting fees from Abbott and Merck, lecture fees from Abbott, receipt of an educational grant from Merck, past presidency of the Fertility Society of Australia & New Zealand and World Endometriosis Society and being a minor shareholder in Monash IVF Group (ASX:MVF). G.M.C. declares receipt of Australian government grant funding for the research study and the development and maintenance of the YourIVFSuccess website. O.F., J.N., and A.P. report no conflicts of interest. TRIAL REGISTRATION NUMBER: N/A.

A nomogram clinical prediction model for predicting urinary infection stones: development and validation in a retrospective study.

PURPOSE: This study aimed to develop a nomogram prediction model to predict the exact probability of urinary infection stones before surgery in order to better deal with the clinical problems caused by infection stones and take effective treatment measures. METHODS: We retrospectively collected the clinical data of 390 patients who were diagnosed with urinary calculi by imaging examination and underwent postoperative stone analysis between August 2018 and August 2023. The patients were randomly divided into training group (n = 312) and validation group (n = 78) using the "caret" R package. The clinical data of the patients were evaluated. Univariate and multivariate logistic regression analysis were used to screen out the independent influencing factors and construct a nomogram prediction model. The receiver operating characteristic curve (ROC), calibration curves, and decision curve analysis (DCA) and clinical impact curves were used to evaluate the discrimination, accuracy, and clinical application efficacy of the prediction model. RESULTS: Gender, recurrence stones, blood uric acid value, urine pH, and urine bacterial culture (P < 0.05) were independent predictors of infection stones, and a nomogram prediction model ( https://zhaoyshenjh.shinyapps.io/DynNomInfectionStone/ ) was constructed using these five parameters. The area under the ROC curve of the training group was 0.901, 95% confidence interval (CI) (0.865-0.936), and the area under the ROC curve of the validation group was 0.960, 95% CI (0.921-0.998). The results of the calibration curve for the training group showed a mean absolute error of 0.015 and the Hosmer-Lemeshow test P > 0.05. DCA and clinical impact curves showed that when the threshold probability value of the model was between 0.01 and 0.85, it had the maximum net clinical benefit. CONCLUSIONS: The nomogram developed in this study has good clinical predictive value and clinical application efficiency can help with risk assessment and decision-making for infection stones in diagnosing and treating urolithiasis.

Calibration plots for multistate risk predictions models.

INTRODUCTION: There is currently no guidance on how to assess the calibration of multistate models used for risk prediction. We introduce several techniques that can be used to produce calibration plots for the transition probabilities of a multistate model, before assessing their performance in the presence of random and independent censoring through a simulation. METHODS: We studied pseudo-values based on the Aalen-Johansen estimator, binary logistic regression with inverse probability of censoring weights (BLR-IPCW), and multinomial logistic regression with inverse probability of censoring weights (MLR-IPCW). The MLR-IPCW approach results in a calibration scatter plot, providing extra insight about the calibration. We simulated data with varying levels of censoring and evaluated the ability of each method to estimate the calibration curve for a set of predicted transition probabilities. We also developed evaluated the calibration of a model predicting the incidence of cardiovascular disease, type 2 diabetes and chronic kidney disease among a cohort of patients derived from linked primary and secondary healthcare records. RESULTS: The pseudo-value, BLR-IPCW, and MLR-IPCW approaches give unbiased estimates of the calibration curves under random censoring. These methods remained predominately unbiased in the presence of independent censoring, even if the censoring mechanism was strongly associated with the outcome, with bias concentrated in low-density regions of predicted transition probability. CONCLUSIONS: We recommend implementing either the pseudo-value or BLR-IPCW approaches to produce a calibration curve, combined with the MLR-IPCW approach to produce a calibration scatter plot. The methods have been incorporated into the "calibmsm" R package available on CRAN.

Addressing the implementation challenge of risk prediction model due to missing risk factors: The submodel approximation approach.

Clinical prediction models have been widely acknowledged as informative tools providing evidence-based support for clinical decision making. However, prediction models are often underused in clinical practice due to many reasons including missing information upon real-time risk calculation in electronic health records (EHR) system. Existing literature to address this challenge focuses on statistical comparison of various approaches while overlooking the feasibility of their implementation in EHR. In this article, we propose a novel and feasible submodel approach to address this challenge for prediction models developed using the model approximation (also termed "preconditioning") method. The proposed submodel coefficients are equivalent to the corresponding original prediction model coefficients plus a correction factor. Comprehensive simulations were conducted to assess the performance of the proposed method and compared with the existing "one-step-sweep" approach as well as the imputation approach. In general, the simulation results show the preconditioning-based submodel approach is robust to various heterogeneity scenarios and is comparable to the imputation-based approach, while the "one-step-sweep" approach is less robust under certain heterogeneity scenarios. The proposed method was applied to facilitate real-time implementation of a prediction model to identify emergency department patients with acute heart failure who can be safely discharged home.

Scoring System to Evaluate Risk of Nonoperative Management Failure in Children With Intussusception.

INTRODUCTION: Typical first-line management of children with intussusception is enema reduction; however, failure necessitates surgical intervention. The number of attempts varies by clinician, and predictors of failed nonoperative management are not routinely considered in practice. The purpose of this study is to create a scoring system that predicts risk of nonoperative failure and need for surgical intervention. METHODS: Children diagnosed with intussusception upon presentation to the emergency department of a tertiary children's hospital between 2019 and 2022 were retrospectively identified. Univariable logistic regression identified predictors of nonoperative failure used as starting covariates for multivariable logistic regression with final model determined by backwards elimination. Regression coefficients for final predictors were used to create the scoring system and optimal cut-points were delineated. RESULTS: We identified 143 instances of ultrasound-documented intussusception of which 28 (19.6%) required operative intervention. Predictors of failed nonoperative management included age ≥4 y (odds ratio [OR] 32.83, 95% confidence interval [CI]: 1.91-564.23), ≥1 failed enema reduction attempts (OR 189.53, 95% CI: 19.07-1884.11), presenting heart rate ≥128 (OR 3.38, 95% CI: 0.74-15.36), presenting systolic blood pressure ≥115 mmHg (OR 6.59, 95% CI: 0.93-46.66), and trapped fluid between intussuscepted loops on ultrasound (OR 17.54, 95% CI: 0.77-397.51). Employing these factors, a novel risk scoring system was developed (area under the curve 0.96, 95% CI: 0.93-0.99). Scores range from 0 to 8; ≤2 have low (1.1%), 3-4 moderate (50.0%), and ≥5 high (100%) failure risk. CONCLUSIONS: Using known risk factors for enema failure, we produced a risk scoring system with outstanding discriminate ability for children with intussusception necessitating surgical intervention. Prospective validation is warranted prior to clinical integration.

Construction of a Prognostic Nomogram for Major Amputation Within 30 Days Postrevascularization in Patients With Acute Lower Limb Ischemia Based on 2D Perfusion Parameters.

PURPOSE: The purpose of the study is to develop a prediction model for major amputation (MA) within 30 days after arterial revascularization in patients with acute lower limb ischemia (ALLI) using 2-dimensional (2D) perfusion imaging parameters. MATERIALS AND METHODS: A retrospective study was performed in ALLI patients undergoing arterial revascularization between October 2015 and May 2022. Patients were randomly assigned into training and validation cohorts in a ratio of 7:3. Variables were selected using univariate and multivariate logistic regression. A nomogram for the MA risk within 30 days after arterial revascularization in ALLI patients was created. Its discrimination, calibration, and clinical effectiveness were reported. RESULTS: A total of 310 ALLI patients (326 limbs) were included. The MA rate within 30 days after arterial revascularization was 11.6%. Skin speckle, myoglobin, and time-to-peak were independent risk factors, while atrial fibrillation was a protective factor (all p<0.05). The nomogram predicted 30-day MA with satisfactory discriminative ability. The integrated discrimination improvement was 0.279 and 0.379 for the training and validation cohorts, respectively (both p<0.001). Calibration curves were close to the standard curve. The decision curve analysis demonstrated net benefits. CONCLUSION: This 2D perfusion imaging parameter-based nomogram could accurately predict the risk of MA within 30 days postrevascularization in ALLI patients. CLINICAL IMPACT: This study introduces a novel nomogram based on 2-dimensional (2D) perfusion imaging that can significantly advance the prognosis prediction in ALLI patients. By calculating the risk of major amputation within 30 days postrevascularization, this nomogram offers an accurate predictive tool and can lead to more informed decision-making on patient management. The innovative aspect of this research lies in its utilization of 2D perfusion parameters, a novel approach that enhances risk assessment accuracy in ALLI patients. This nomogram represents a significant step toward risk stratification and can guide future research for appropriate management on ALLI patients with different risk profiles.

Framework for personalized prediction of treatment response in relapsing-remitting multiple sclerosis: a replication study in independent data.

BACKGROUND: Individualizing and optimizing treatment of relapsing-remitting multiple sclerosis patients is a challenging problem, which would benefit from a clinically valid decision support. Stühler et al. presented black box models for this aim which were developed and internally evaluated in a German registry but lacked external validation. METHODS: In patients from the French OFSEP registry, we independently built and validated models predicting being free of relapse and free of confirmed disability progression (CDP), following the methodological roadmap and predictors reported by Stühler. Hierarchical Bayesian models were fit to predict the outcomes under 6 disease-modifying treatments given the individual disease course up to the moment of treatment change. Data was temporally split on 2017, and models were developed in patients treated earlier (n = 5517). Calibration curves, discrimination, mean squared error (MSE) and relative percentage of root MSE (RMSE%) were assessed by external validation of models in more-recent patients (n = 3768). Non-Bayesian fixed-effects GLMs were also applied and their outcomes were compared to these of the Bayesian ones. For both, we modelled the number of on-therapy relapses with a negative binomial distribution, and CDP occurrence with a binomial distribution. RESULTS: The performance of our temporally-validated relapse model (MSE: 0.326, C-Index: 0.639) is potentially superior to that of Stühler's (MSE: 0.784, C-index: 0.608). Calibration plots revealed miscalibration. Our CDP model (MSE: 0.072, C-Index: 0.777) was also better than its counterpart (MSE: 0.131, C-index: 0.554). Results from non-Bayesian fixed-effects GLM models were similar to the Bayesian ones. CONCLUSIONS: The relapse and CDP models rebuilt and externally validated in independent data could compare and strengthen the credibility of the Stühler models. Their model-building strategy was replicable.

Predictive etiological classification of acute ischemic stroke through interpretable machine learning algorithms: a multicenter, prospective cohort study.

BACKGROUND: The prognosis, recurrence rates, and secondary prevention strategies varied significantly among different subtypes of acute ischemic stroke (AIS). Machine learning (ML) techniques can uncover intricate, non-linear relationships within medical data, enabling the identification of factors associated with etiological classification. However, there is currently a lack of research utilizing ML algorithms for predicting AIS etiology. OBJECTIVE: We aimed to use interpretable ML algorithms to develop AIS etiology prediction models, identify critical factors in etiology classification, and enhance existing clinical categorization. METHODS: This study involved patients with the Third China National Stroke Registry (CNSR-III). Nine models, which included Natural Gradient Boosting (NGBoost), Categorical Boosting (CatBoost), Extreme Gradient Boosting (XGBoost), Random Forest (RF), Light Gradient Boosting Machine (LGBM), Gradient Boosting Decision Tree (GBDT), Adaptive Boosting (AdaBoost), Support Vector Machine (SVM), and logistic regression (LR), were employed to predict large artery atherosclerosis (LAA), small vessel occlusion (SVO), and cardioembolism (CE) using an 80:20 randomly split training and test set. We designed an SFS-XGB with 10-fold cross-validation for feature selection. The primary evaluation metrics for the models included the area under the receiver operating characteristic curve (AUC) for discrimination and the Brier score (or calibration plots) for calibration. RESULTS: A total of 5,213 patients were included, comprising 2,471 (47.4%) with LAA, 2,153 (41.3%) with SVO, and 589 (11.3%) with CE. In both LAA and SVO models, the AUC values of the ML models were significantly higher than that of the LR model (P < 0.001). The optimal model for predicting SVO (AUC [RF model] = 0.932) outperformed the optimal LAA model (AUC [NGB model] = 0.917) and the optimal CE model (AUC [LGBM model] = 0.846). Each model displayed relatively satisfactory calibration. Further analysis showed that the optimal CE model could identify potential CE patients in the undetermined etiology (SUE) group, accounting for 1,900 out of 4,156 (45.7%). CONCLUSIONS: The ML algorithm effectively classified patients with LAA, SVO, and CE, demonstrating superior classification performance compared to the LR model. The optimal ML model can identify potential CE patients among SUE patients. These newly identified predictive factors may complement the existing etiological classification system, enabling clinicians to promptly categorize stroke patients' etiology and initiate optimal strategies for secondary prevention.

Prediction of postoperative complications following transanal total mesorectal excision in middle and low rectal cancer: development and internal validation of a clinical prediction model.

PURPOSE: The objective of this study is to develop a nomogram for the personalized prediction of postoperative complication risks in patients with middle and low rectal cancer who are undergoing transanal total mesorectal excision (taTME). This tool aims to assist clinicians in early identification of high-risk patients and in addressing preoperative risk factors to enhance surgical safety. METHODS: In this case-control study, 207 patients diagnosed with middle and low rectal cancer and undergoing taTME between February 2018 and November 2023 at The First Affiliated Hospital of Xiamen University were included. Independent risk factors for postoperative complications were analyzed using the Least Absolute Shrinkage and Selection Operator (LASSO) regression and multifactorial logistic regression models. A predictive nomogram was constructed using R Studio. RESULTS: Among the 207 patients, 57 (27.5%) experienced postoperative complications. The LASSO and multifactorial logistic regression analyses identified operation time (OR = 1.010, P = 0.007), smoking history (OR = 9.693, P < 0.001), anastomotic technique (OR = 0.260, P = 0.004), and ASA score (OR = 9.077, P = 0.051) as significant predictors. These factors were integrated into the nomogram. The model's accuracy was validated through receiver operating characteristic curves, calibration curves, consistency indices, and decision curve analysis. CONCLUSION: The developed nomogram, incorporating operation time, smoking history, anastomotic technique, and ASA score, effectively forecasts postoperative complication risks in taTME procedures. It is a valuable tool for clinicians to identify patients at heightened risk and initiate timely interventions, ultimately improving patient outcomes.

Preoperative risk prediction models for acute kidney injury after noncardiac surgery: an independent external validation cohort study.

BACKGROUND: Numerous models have been developed to predict acute kidney injury (AKI) after noncardiac surgery, yet there is a lack of independent validation and comparison among them. METHODS: We conducted a systematic literature search to review published risk prediction models for AKI after noncardiac surgery. An independent external validation was performed using a retrospective surgical cohort at a large Chinese hospital from January 2019 to October 2022. The cohort included patients undergoing a wide range of noncardiac surgeries with perioperative creatinine measurements. Postoperative AKI was defined according to the Kidney Disease Improving Global Outcomes creatinine criteria. Model performance was assessed in terms of discrimination (area under the receiver operating characteristic curve, AUROC), calibration (calibration plot), and clinical utility (net benefit), before and after model recalibration through intercept and slope updates. A sensitivity analysis was conducted by including patients without postoperative creatinine measurements in the validation cohort and categorising them as non-AKI cases. RESULTS: Nine prediction models were evaluated, each with varying clinical and methodological characteristics, including the types of surgical cohorts used for model development, AKI definitions, and predictors. In the validation cohort involving 13,186 patients, 650 (4.9%) developed AKI. Three models demonstrated fair discrimination (AUROC between 0.71 and 0.75); other models had poor or failed discrimination. All models exhibited some miscalibration; five of the nine models were well-calibrated after intercept and slope updates. Decision curve analysis indicated that the three models with fair discrimination consistently provided a positive net benefit after recalibration. The results were confirmed in the sensitivity analysis. CONCLUSIONS: We identified three models with fair discrimination and potential clinical utility after recalibration for assessing the risk of acute kidney injury after noncardiac surgery.

Multivariable machine learning models for clinical prediction of subsequent hip fractures in older people using the Chinese population database.

PURPOSE: This study aimed to develop and validate clinical prediction models using machine learning (ML) algorithms for reliable prediction of subsequent hip fractures in older individuals, who had previously sustained a first hip fracture, and facilitate early prevention and diagnosis, therefore effectively managing rapidly rising healthcare costs in China. METHODS: Data were obtained from Grade A Tertiary hospitals for older patients (age ≥ 60 years) diagnosed with hip fractures in southwest China between 1 January 2009 and 1 April 2020. The database was built by collecting clinical and administrative data from outpatients and inpatients nationwide. Data were randomly split into training (80%) and testing datasets (20%), followed by six ML-based prediction models using 19 variables for hip fracture patients within 2 years of the first fracture. RESULTS: A total of 40,237 patients with a median age of 66.0 years, who were admitted to acute-care hospitals for hip fractures, were randomly split into a training dataset (32,189 patients) and a testing dataset (8,048 patients). Our results indicated that three of our ML-based models delivered an excellent prediction of subsequent hip fracture outcomes (the area under the receiver operating characteristics curve: 0.92 (0.91-0.92), 0.92 (0·92-0·93), 0.92 (0·92-0·93)), outperforming previous prediction models based on claims and cohort data. CONCLUSIONS: Our prediction models identify Chinese older people at high risk of subsequent hip fractures with specific baseline clinical and demographic variables such as length of hospital stay. These models might guide future targeted preventative treatments.

A predictive model for depression in Chinese middle-aged and elderly people with physical disabilities.

BACKGROUND: Middle-aged and older adults with physical disabilities exhibit more common and severe depressive symptoms than those without physical disabilities. Such symptoms can greatly affect the physical and mental health and life expectancy of middle-aged and older persons with disabilities. METHOD: This study selected 2015 and 2018 data from the China Longitudinal Study of Health and Retirement. After analyzing the effect of age on depression, we used whether middle-aged and older adults with physical disabilities were depressed as the dependent variable and included a total of 24 predictor variables, including demographic factors, health behaviors, physical functioning and socialization, as independent variables. The data were randomly divided into training and validation sets on a 7:3 basis. LASSO regression analysis combined with binary logistic regression analysis was performed in the training set to screen the predictor variables of the model. Construct models in the training set and perform model evaluation, model visualization and internal validation. Perform external validation of the model in the validation set. RESULT: A total of 1052 middle-aged and elderly persons with physical disabilities were included in this study, and the prevalence of depression in the elderly group > middle-aged group. Restricted triple spline indicated that age had different effects on depression in the middle-aged and elderly groups. LASSO regression analysis combined with binary logistic regression screened out Gender, Location of Residential Address, Shortsightedness, Hearing, Any possible helper in the future, Alcoholic in the Past Year, Difficulty with Using the Toilet, Difficulty with Preparing Hot Meals, and Unable to work due to disability constructed the Chinese Depression Prediction Model for Middle-aged and Older People with Physical Disabilities. The nomogram shows that living in a rural area, lack of assistance, difficulties with activities of daily living, alcohol abuse, visual and hearing impairments, unemployment and being female are risk factors for depression in middle-aged and older persons with physical disabilities. The area under the ROC curve for the model, internal validation and external validation were all greater than 0.70, the mean absolute error was less than 0.02, and the recall and precision were both greater than 0.65, indicating that the model performs well in terms of discriminability, accuracy and generalisation. The DCA curve and net gain curve of the model indicate that the model has high gain in predicting depression. CONCLUSION: In this study, we showed that being female, living in rural areas, having poor vision and/or hearing, lack of assistance from others, drinking alcohol, having difficulty using the restroom and preparing food, and being unable to work due to a disability were risk factors for depression among middle-aged and older adults with physical disabilities. We developed a depression prediction model to assess the likelihood of depression in Chinese middle-aged and older adults with physical disabilities based on the above risk factors, so that early identification, intervention, and treatment can be provided to middle-aged and older adults with physical disabilities who are at high risk of developing depression.

Prediction of mortality in acute pulmonary embolism in cancer-associated thrombosis (MAUPE-C): derivation and validation of a multivariable model.

Optimal risk stratification of patients with cancer and pulmonary embolism (PE) remains unclear. We constructed a clinical prediction rule (CPR) named 'MAUPE-C' to identify patients with low 30 days mortality. The study retrospectively developed and internally validated a CPR for 30 days mortality in a cohort of patients with cancer and PE (both suspected and unsuspected). Candidate variables were chosen based on the EPIPHANY study, which categorized patients into 3 groups based on symptoms, signs, suspicion and patient setting at PE diagnosis. The performance of 'MAUPE-C' was compared to RIETE and sPESI scores. Univariate analysis confirmed that the presence of symptoms, signs, suspicion and inpatient diagnosis were associated with 30 days mortality. Multivariable logistic regression analysis led to the exclusion of symptoms as predictive variable. 'MAUPE-C' was developed by assigning weights to risk factors related to the ß coefficient, yielding a score range of 0 to 4.5. After receiver operating characteristic (ROC) curve analysis, a cutoff point was established at ≤ 1. Prognostic accuracy was good with an area under the curve (AUC) of 0.77 (95% CI 0.71-0.82), outperforming RIETE and sPESI scores in this cohort (AUC of 0.64 [95% CI 0.57-0.71] and 0.57 [95% CI 0.49-0.65], respectively). Forty-five per cent of patients were classified as low risk and experienced a 2.79% 30 days mortality. MAUPE-C has good prognostic accuracy in identifying patients at low risk of 30 days mortality. This CPR could help physicians select patients for early discharge.

Telephone triage of chest pain in out-of-hours primary care: external validation of a symptom-based prediction rule to rule out acute coronary syndromes.

INTRODUCTION: Telephone triage is pivotal for evaluating the urgency of patient care, and in the Netherlands, the Netherlands Triage Standard (NTS) demonstrates moderate discrimination for chest pain. To address this, the Safety First Prediction Rule (SFPR) was developed to improve the safety of ruling out acute coronary syndrome (ACS) during telephone triage. METHODS: We conducted an external validation of the SFPR using data from the TRACE study, a retrospective cohort study in out-of-hours primary care. We evaluated the diagnostic accuracy assessment for ACS, major adverse cardiovascular events (MACE), and major events within 6 weeks. Moreover, we compared its performance with that of the NTS algorithm. RESULTS: Among 1404 included patients (57.3% female, 6.8% ACS, 8.6% MACE), the SFPR demonstrated good discrimination for ACS (C-statistic: 0.79; 95%-CI: 0.75-0.83) and MACE (C-statistic: 0.79; 95%-CI: 0.0.76-0.82). Calibration was satisfactory, with overestimation observed in high-risk patients for ACS. The SFPR (risk threshold 2.5%) trended toward higher sensitivity (95.8% vs. 86.3%) and negative predictive value (99.3% vs. 97.6%) with a lower negative likelihood ratio (0.10 vs. 0.34) than the NTS algorithm. CONCLUSION: The SFPR proved robust for risk stratification in patients with acute chest pain seeking out-of-hours primary care in the Netherlands. Further prospective validation and implementation are warranted to refine and establish the rule's clinical utility.

Prospective external validation of the FluScore risk score for influenza in outpatients.

BACKGROUND: Testing for influenza in patients with acute lower respiratory tract infection (LRTI) is common and in some cases is performed for all patients with LRTI. A more selective approach to testing could be more efficient. METHODS: We used data from two prospective studies in the US primary and urgent care settings that enrolled patients with acute LRTI or influenza-like illness. Data were collected in the 2016, 2019, 2021, and 2022 flu seasons. All patients underwent polymerase chain reaction (PCR) testing for influenza and the FluScore was calculated based on patient-reported symptoms at their initial visit. The probability of influenza in each risk group was reported, as well as stratum-specific likelihood ratios (SSLRs) for each risk level. RESULTS: The prevalence of influenza within risk groups varied based on overall differences in flu seasons and populations. However, the FluScore exhibited consistent performance across various seasons and populations based on the SSLRs. The FluScore had a consistent SSLR range of 0.20 to 0.23 for the low-risk group, 0.63 to 0.99 for the moderate-risk group, and 1.46 to 1.67 for the high-risk group. The diagnostic odds ratio based on the midpoints of these ranges was 7.25. CONCLUSIONS: The FluScore could streamline patient categorization, identifying patients who could be exempted from testing, while identifying candidates for rapid influenza tests. This has the potential to be more efficient than a "one size fits all" test strategy, as it strategically targets the use of tests on patients most likely to benefit. It is potentially usable in a telehealth setting.