Advancing precision prognostication in neuro-oncology: Machine learning models for data-driven personalized survival predictions in IDH-wildtype glioblastoma.

Background: Glioblastoma (GBM) remains associated with a dismal prognoses despite standard therapies. While population-level survival statistics are established, generating individualized prognosis remains challenging. We aim to develop machine learning (ML) models that generate personalized survival predictions for GBM patients to enhance prognostication. Methods: Adult patients with histologically confirmed IDH-wildtype GBM from the National Cancer Database (NCDB) were analyzed. ML models were developed with TabPFN, TabNet, XGBoost, LightGBM, and Random Forest algorithms to predict mortality at 6, 12, 18, and 24 months postdiagnosis. SHapley Additive exPlanations (SHAP) were employed to enhance the interpretability of the models. Models were primarily evaluated using the area under the receiver operating characteristic (AUROC) values, and the top-performing models indicated by the highest AUROCs for each outcome were deployed in a web application that was created for individualized predictions. Results: A total of 7537 patients were retrieved from the NCDB. Performance evaluation revealed the top-performing models for each outcome were built using the TabPFN algorithm. The TabPFN models yielded mean AUROCs of 0.836, 0.78, 0.732, and 0.724 in predicting 6, 12, 18, and 24 month mortality, respectively. Conclusions: This study establishes ML models tailored to individual patients to enhance GBM prognostication. Future work should focus on external validation and dynamic updating as new data emerge.

Development and validation of machine learning models to predict MDRO colonization or infection on ICU admission by using electronic health record data.

BACKGROUND: Multidrug-resistant organisms (MDRO) pose a significant threat to public health. Intensive Care Units (ICU), characterized by the extensive use of antimicrobial agents and a high prevalence of bacterial resistance, are hotspots for MDRO proliferation. Timely identification of patients at high risk for MDRO can aid in curbing transmission, enhancing patient outcomes, and maintaining the cleanliness of the ICU environment. This study focused on developing a machine learning (ML) model to identify patients at risk of MDRO during the initial phase of their ICU stay. METHODS: Utilizing patient data from the First Medical Center of the People's Liberation Army General Hospital (PLAGH-ICU) and the Medical Information Mart for Intensive Care (MIMIC-IV), the study analyzed variables within 24 h of ICU admission. Machine learning algorithms were applied to these datasets, emphasizing the early detection of MDRO colonization or infection. Model efficacy was evaluated by the area under the receiver operating characteristics curve (AUROC), alongside internal and external validation sets. RESULTS: The study evaluated 3,536 patients in PLAGH-ICU and 34,923 in MIMIC-IV, revealing MDRO prevalence of 11.96% and 8.81%, respectively. Significant differences in ICU and hospital stays, along with mortality rates, were observed between MDRO positive and negative patients. In the temporal validation, the PLAGH-ICU model achieved an AUROC of 0.786 [0.748, 0.825], while the MIMIC-IV model reached 0.744 [0.723, 0.766]. External validation demonstrated reduced model performance across different datasets. Key predictors included biochemical markers and the duration of pre-ICU hospital stay. CONCLUSIONS: The ML models developed in this study demonstrated their capability in early identification of MDRO risks in ICU patients. Continuous refinement and validation in varied clinical contexts remain essential for future applications.

"Using network analysis modularity to group health code systems and decrease dimensionality in machine learning models".

Background: Machine learning (ML) prediction models in healthcare and pharmacy-related research face challenges with encoding high-dimensional Healthcare Coding Systems (HCSs) such as ICD, ATC, and DRG codes, given the trade-off between reducing model dimensionality and minimizing information loss. Objectives: To investigate using Network Analysis modularity as a method to group HCSs to improve encoding in ML models. Methods: The MIMIC-III dataset was utilized to create a multimorbidity network in which ICD-9 codes are the nodes and the edges are the number of patients sharing the same ICD-9 code pairs. A modularity detection algorithm was applied using different resolution thresholds to generate 6 sets of modules. The impact of four grouping strategies on the performance of predicting 90-day Intensive Care Unit readmissions was assessed. The grouping strategies compared: 1) binary encoding of codes, 2) encoding codes grouped by network modules, 3) grouping codes to the highest level of ICD-9 hierarchy, and 4) grouping using the single-level Clinical Classification Software (CCS). The same methodology was also applied to encode DRG codes but limiting the comparison to a single modularity threshold to binary encoding.The performance was assessed using Logistic Regression, Support Vector Machine with a non-linear kernel, and Gradient Boosting Machines algorithms. Accuracy, Precision, Recall, AUC, and F1-score with 95% confidence intervals were reported. Results: Models utilized modularity encoding outperformed ungrouped codes binary encoding models. The accuracy improved across all algorithms ranging from 0.736 to 0.78 for the modularity encoding, to 0.727 to 0.779 for binary encoding. AUC, recall, and precision also improved across almost all algorithms. In comparison with other grouping approaches, modularity encoding generally showed slightly higher performance in AUC, ranging from 0.813 to 0.837, and precision, ranging from 0.752 to 0.782. Conclusions: Modularity encoding enhances the performance of ML models in pharmacy research by effectively reducing dimensionality and retaining necessary information. Across the three algorithms used, models utilizing modularity encoding showed superior or comparable performance to other encoding approaches. Modularity encoding introduces other advantages such as it can be used for both hierarchical and non-hierarchical HCSs, the approach is clinically relevant, and can enhance ML models' clinical interpretation. A Python package has been developed to facilitate the use of the approach for future research.

Predictive modeling for ubiquitin proteins through advanced machine learning technique.

Ubiquitination is an essential post-translational modification mechanism involving the ubiquitin protein's bonding to a substrate protein. It is crucial in a variety of physiological activities including cell survival and differentiation, and innate and adaptive immunity. Any alteration in the ubiquitin system leads to the development of various human diseases. Numerous researches show the highly reversibility and dynamic of ubiquitin system, making the experimental identification quite difficult. To solve this issue, this article develops a model using a machine learning approach, tending to improve the ubiquitin protein prediction precisely. We deeply investigate the ubiquitination data that is proceed through different features extraction methods, followed by the classification. The evaluation and assessment are conducted considering Jackknife tests and 10-fold cross-validation. The proposed method demonstrated the remarkable performance in terms of 100 %, 99.88 %, and 99.84 % accuracy on Dataset-I, Dataset-II, and Dataset-III, respectively. Using Jackknife test, the method achieves 100 %, 99.91 %, and 99.99 % for Dataset-I, Dataset-II and Dataset-III, respectively. This analysis concludes that the proposed method outperformed the state-of-the-arts to identify the ubiquitination sites and helpful in the development of current clinical therapies. The source code and datasets will be made available at Github.

A privacy-preserving platform oriented medical healthcare and its application in identifying patients with candidemia.

Federated learning (FL) has emerged as a significant method for developing machine learning models across multiple devices without centralized data collection. Candidemia, a critical but rare disease in ICUs, poses challenges in early detection and treatment. The goal of this study is to develop a privacy-preserving federated learning framework for predicting candidemia in ICU patients. This approach aims to enhance the accuracy of antifungal drug prescriptions and patient outcomes. This study involved the creation of four predictive FL models for candidemia using data from ICU patients across three hospitals in China. The models were designed to prioritize patient privacy while aggregating learnings across different sites. A unique ensemble feature selection strategy was implemented, combining the strengths of XGBoost's feature importance and statistical test p values. This strategy aimed to optimize the selection of relevant features for accurate predictions. The federated learning models demonstrated significant improvements over locally trained models, with a 9% increase in the area under the curve (AUC) and a 24% rise in true positive ratio (TPR). Notably, the FL models excelled in the combined TPR + TNR metric, which is critical for feature selection in candidemia prediction. The ensemble feature selection method proved more efficient than previous approaches, achieving comparable performance. The study successfully developed a set of federated learning models that significantly enhance the prediction of candidemia in ICU patients. By leveraging a novel feature selection method and maintaining patient privacy, the models provide a robust framework for improved clinical decision-making in the treatment of candidemia.

Modeling the growth of Salmonella in raw ground pork under dynamic conditions of temperature abuse.

Salmonella contamination of pork products is a significant public health concern. Temperature abuse scenarios, such as inadequate refrigeration or prolonged exposure to room temperature, can enhance Salmonella proliferation. This study aimed to develop and validate models for Salmonella growth considering competition with background microbiota in raw ground pork, under isothermal and dynamic conditions of temperature abuse between 10 and 40 °C. The maximum specific growth rate (µmax) and maximum population density (MPD) were estimated to quantitatively describe the growth behavior of Salmonella. To reflect more realistic microbial interactions in Salmonella-contaminated product, our model considered competition with the background microbiota, measured as mesophilic aerobic plate counts (APC). Notably, the µmax of Salmonella in low-fat samples (∼5 %) was significantly higher (p < 0.05) than that in high-fat samples (∼25 %) at 10, 20, and 30 °C. The average doubling time of Salmonella was 26, 4, 2, 1.5, 0.8, and 1.1 h at 10, 15, 20, 25, 30, and 40 °C, respectively. The initial concentration of Salmonella minimally impacted its growth in ground pork at any temperature. The MPD of APC consistently exceeded that of Salmonella, indicating the growth of APC without competition from Salmonella. The competition model exhibited excellent fit with the experimental data, as 95 % (627/660) of residual errors fell within the desired acceptable prediction zone (pAPZ >0.70). The theoretical minimum and optimum growth temperatures for Salmonella ranged from 5 to 6 °C and 35 to 36 °C, respectively. The dynamic model displayed strong predictive performance, with 90 % (57/63) of residual errors falling within the APZ. Dynamic models could be valuable tools for validating and refining simpler static or isothermal models, ultimately improving their predictive capabilities to enhance food safety.

Predictive modeling for identification of older adults with high utilization of health and social services.

AIM: Machine learning techniques have demonstrated success in predictive modeling across various clinical cases. However, few studies have considered predicting the use of multisectoral health and social services among older adults. This research aims to utilize machine learning models to detect high-risk groups of excessive health and social services utilization at early stage, facilitating the implementation of preventive interventions. METHODS: We used pseudonymized data covering a four-year period and including information on a total of 33,374 senior citizens from Southern Finland. The endpoint was defined based on the occurrence of unplanned healthcare visits and the total number of different services used. Input features included individual's basic demographics, health status and past usage of healthcare resources. Logistic regression and eXtreme Gradient Boosting (XGBoost) methods were used for binary classification, with the dataset split into 70% training and 30% testing sets. RESULTS: Subgroup-based results mirrored trends observed in the full cohort, with age and certain health issues, e.g. mental health, emerging as positive predictors for high service utilization. Conversely, hospital stay and urban residence were associated with decreased risk. The models achieved a classification performance (AUC) of 0.61 for the full cohort and varying in the range of 0.55-0.62 for the subgroups. CONCLUSIONS: Predictive models offer potential for predicting future high service utilization in the older adult population. Achieving high classification performance remains challenging due to diverse contributing factors. We anticipate that classification performance could be increased by including features based on additional data categories such as socio-economic data.

Development and validation of machine-learning algorithms predicting retention, overdoses, and all-cause mortality among US military veterans treated with buprenorphine for opioid use disorder.

BACKGROUND: Buprenorphine for opioid use disorder (B-MOUD) is essential to improving patient outcomes; however, retention is essential. OBJECTIVE: To develop and validate machine-learning algorithms predicting retention, overdoses, and all-cause mortality among US military veterans initiating B-MOUD. METHODS: Veterans initiating B-MOUD from fiscal years 2006-2020 were identified. Veterans' B-MOUD episodes were randomly divided into training (80%;n = 45,238) and testing samples (20%;n = 11,309). Candidate algorithms [multiple logistic regression, least absolute shrinkage and selection operator regression, random forest (RF), gradient boosting machine (GBM), and deep neural network (DNN)] were used to build and validate classification models to predict six binary outcomes: 1) B-MOUD retention, 2) any overdose, 3) opioid-related overdose, 4) overdose death, 5) opioid overdose death, and 6) all-cause mortality. Model performance was assessed using standard classification statistics [e.g., area under the receiver operating characteristic curve (AUC-ROC)]. RESULTS: Episodes in the training sample were 93.0% male, 78.0% White, 72.3% unemployed, and 48.3% had a concurrent drug use disorder. The GBM model slightly outperformed others in predicting B-MOUD retention (AUC-ROC = 0.72). RF models outperformed others in predicting any overdose (AUC-ROC = 0.77) and opioid overdose (AUC-ROC = 0.77). RF and GBM outperformed other models for overdose death (AUC-ROC = 0.74 for both), and RF and DNN outperformed other models for opioid overdose death (RF AUC-ROC = 0.79; DNN AUC-ROC = 0.78). RF and GBM also outperformed other models for all-cause mortality (AUC-ROC = 0.76 for both). No single predictor accounted for >3% of the model's variance. CONCLUSIONS: Machine-learning algorithms can accurately predict OUD-related outcomes with moderate predictive performance; however, prediction of these outcomes is driven by many characteristics.

Fully Automatic Deep Learning Model for Spine Refracture in Patients with OVCF: A Multi-Center Study.

BACKGROUND: The reaserch of artificial intelligence (AI) model for predicting spinal refracture is limited to bone mineral density, X-ray and some conventional laboratory indicators, which has its own limitations. Besides, it lacks specific indicators related to osteoporosis and imaging factors that can better reflect bone quality, such as computed tomography (CT). OBJECTIVE: To construct a novel predicting model based on bone turn-over markers and CT to identify patients who were more inclined to suffer spine refracture. METHODS: CT images and clinical information of 383 patients (training set = 240 cases of osteoporotic vertebral compression fractures (OVCF), validation set = 63, test set = 80) were retrospectively collected from January 2015 to October 2022 at three medical centers. The U-net model was adopted to automatically segment ROI. Three-dimensional (3D) cropping of all spine regions was used to achieve the final ROI regions including 3D_Full and 3D_RoiOnly. We used the Densenet 121-3D model to model the cropped region and simultaneously build a T-NIPT prediction model. Diagnostics of deep learning models were assessed by constructing ROC curves. We generated calibration curves to assess the calibration performance. Additionally, decision curve analysis (DCA) was used to assess the clinical utility of the predictive models. RESULTS: The performance of the test model is comparable to its performance on the training set (dice coefficients of 0.798, an mIOU of 0.755, an SA of 0.767, and an OS of 0.017). Univariable and multivariable analysis indicate that T_P1NT was an independent risk factor for refracture. The performance of predicting refractures in different ROI regions showed that 3D_Full model exhibits the highest calibration performance, with a Hosmer-Lemeshow goodness-of-fit (HL) test statistic exceeding 0.05. The analysis of the training and test sets showed that the 3D_Full model, which integrates clinical and deep learning results, demonstrated superior performance with significant improvement (p-value < 0.05) compared to using clinical features independently or using only 3D_RoiOnly. CONCLUSION: T_P1NT was an independent risk factor of refracture. Our 3D-FULL model showed better performance in predicting high-risk population of spine refracture than other models and junior doctors do. This model can be applicable to real-world translation due to its automatic segmentation and detection.

Predicting dyslipidemia incidence: unleashing machine learning algorithms on Lifestyle Promotion Project data.

BACKGROUND: Dyslipidemia, characterized by variations in plasma lipid profiles, poses a global health threat linked to millions of deaths annually. OBJECTIVES: This study focuses on predicting dyslipidemia incidence using machine learning methods, addressing the crucial need for early identification and intervention. METHODS: The dataset, derived from the Lifestyle Promotion Project (LPP) in East Azerbaijan Province, Iran, undergoes a comprehensive preprocessing, merging, and null handling process. Target selection involves five distinct dyslipidemia-related variables. Normalization techniques and three feature selection algorithms are applied to enhance predictive modeling. RESULT: The study results underscore the potential of different machine learning algorithms, specifically multi-layer perceptron neural network (MLP), in reaching higher performance metrics such as accuracy, F1 score, sensitivity and specificity, among other machine learning methods. Among other algorithms, Random Forest also showed remarkable accuracies and outperformed K-Nearest Neighbors (KNN) in metrics like precision, recall, and F1 score. The study's emphasis on feature selection detected meaningful patterns among five target variables related to dyslipidemia, indicating fundamental shared unities among dyslipidemia-related factors. Features such as waist circumference, serum vitamin D, blood pressure, sex, age, diabetes, and physical activity related to dyslipidemia. CONCLUSION: These results cooperatively highlight the complex nature of dyslipidemia and its connections with numerous factors, strengthening the importance of applying machine learning methods to understand and predict its incidence precisely.

Predictive modeling of perioperative patient deterioration: combining unanticipated ICU admissions and mortality for improved risk prediction.

OBJECTIVE: This paper presents a comprehensive analysis of perioperative patient deterioration by developing predictive models that evaluate unanticipated ICU admissions and in-hospital mortality both as distinct and combined outcomes. MATERIALS AND METHODS: With less than 1% of cases resulting in at least one of these outcomes, we investigated 98 features to identify their role in predicting patient deterioration, using univariate analyses. Additionally, multivariate analyses were performed by employing logistic regression (LR) with LASSO regularization. We also assessed classification models, including non-linear classifiers like Support Vector Machines, Random Forest, and XGBoost. RESULTS: During evaluation, careful attention was paid to the data imbalance therefore multiple evaluation metrics were used, which are less sensitive to imbalance. These metrics included the area under the receiver operating characteristics, precision-recall and kappa curves, and the precision, sensitivity, kappa, and F1-score. Combining unanticipated ICU admissions and mortality into a single outcome improved predictive performance overall. However, this led to reduced accuracy in predicting individual forms of deterioration, with LR showing the best performance for the combined prediction. DISCUSSION: The study underscores the significance of specific perioperative features in predicting patient deterioration, especially revealed by univariate analysis. Importantly, interpretable models like logistic regression outperformed complex classifiers, suggesting their practicality. Especially, when combined in an ensemble model for predicting multiple forms of deterioration. These findings were mostly limited by the large imbalance in data as post-operative deterioration is a rare occurrence. Future research should therefore focus on capturing more deterioration events and possibly extending validation to multi-center studies. CONCLUSIONS: This work demonstrates the potential for accurate prediction of perioperative patient deterioration, highlighting the importance of several perioperative features and the practicality of interpretable models like logistic regression, and ensemble models for the prediction of several outcome types. In future clinical practice these data-driven prediction models might form the basis for post-operative risk stratification by providing an evidence-based assessment of risk.

Artificial intelligence and machine learning in peritoneal dialysis: a systematic review of clinical outcomes and predictive modeling.

BACKGROUND: The integration of artificial intelligence (AI) and machine learning (ML) in peritoneal dialysis (PD) presents transformative opportunities for optimizing treatment outcomes and informing clinical decision-making. This study aims to provide a comprehensive overview of the applications of AI/ML techniques in PD, focusing on their potential to predict clinical outcomes and enhance patient care. MATERIALS AND METHODS: This systematic review was conducted according to PRISMA guidelines (2020), searching key databases for articles on AI and ML applications in PD. The inclusion criteria were stringent, ensuring the selection of high-quality studies. The search strategy comprised MeSH terms and keywords related to PD, AI, and ML. 793 articles were identified, with nine ultimately meeting the inclusion criteria. The review utilized a narrative synthesis approach to summarize findings due to anticipated study heterogeneity. RESULTS: Nine studies met the inclusion criteria. The studies varied in sample size and employed diverse AI and ML techniques, reflecting the breadth of data considered. Mortality prediction emerged as a recurrent theme, demonstrating the significance of AI and ML in prognostic accuracy. Predictive modeling extended to technique failure, hospital stay prediction, and pathogen-specific immune responses, showcasing the versatility of AI and ML applications in PD. CONCLUSIONS: This systematic review highlights the diverse applications of AI/ML in peritoneal dialysis, demonstrating their potential to enhance predictive accuracy, risk stratification, and decision support. However, limitations such as small sample sizes, single-center studies, and potential biases warrant further research and external validation. Future perspectives include integrating these AI/ML models into routine clinical practice and exploring additional use cases to improve patient outcomes and healthcare decision-making in PD.

Predicting response to chemotherapy in brain tumor patients based on MRI features.

Chemotherapy in brain tumors is tailored based on tumor type, grade, and molecular markers, which are crucial for predicting responses and survival outcomes. This review summarizes the role of chemotherapy in gliomas, glioneuronal and neuronal tumors, ependymomas, choroid plexus tumors, medulloblastomas, and meningiomas, discussing standard treatment protocols and recent developments in targeted therapies.Furthermore, the studies reporting the integration of MRI-based radiomics and deep learning models for predicting treatment outcomes are reviewed. Advances in MRI-based radiomics and deep learning models have significantly enhanced the prediction of chemotherapeutic benefits, survival prediction following chemotherapy, and differentiating tumor progression with psuedoprogression. These non-invasive techniques offer valuable insights into tumor characteristics and treatment responses, facilitating personalized therapeutic strategies. Further research is warranted to refine these models and expand their applicability across different brain tumor types.

Development and validation of a nomogram predictive model for cognitive impairment in cerebral small vessel disease: a comprehensive retrospective analysis.

Background: Cerebral small vessel disease (CSVD) is a common neurodegenerative condition in the elderly, closely associated with cognitive impairment. Early identification of individuals with CSVD who are at a higher risk of developing cognitive impairment is crucial for timely intervention and improving patient outcomes. Objective: The aim of this study is to construct a predictive model utilizing LASSO regression and binary logistic regression, with the objective of precisely forecasting the risk of cognitive impairment in patients with CSVD. Methods: The study utilized LASSO regression for feature selection and logistic regression for model construction in a cohort of CSVD patients. The model's validity was assessed through calibration curves and decision curve analysis (DCA). Results: A nomogram was developed to predict cognitive impairment, incorporating hypertension, CSVD burden, apolipoprotein A1 (ApoA1) levels, and age. The model exhibited high accuracy with AUC values of 0.866 and 0.852 for the training and validation sets, respectively. Calibration curves confirmed the model's reliability, and DCA highlighted its clinical utility. The model's sensitivity and specificity were 75.3 and 79.7% for the training set, and 76.9 and 74.0% for the validation set. Conclusion: This study successfully demonstrates the application of machine learning in developing a reliable predictive model for cognitive impairment in CSVD. The model's high accuracy and robust predictive capability provide a crucial tool for the early detection and intervention of cognitive impairment in patients with CSVD, potentially improving outcomes for this specific condition.

[Prediction of risk of in-hospital death in patients with chronic heart failure complicated by lung infections using interpretable machine learning].

OBJECTIVE: To predict the risk of in-hospital death in patients with chronic heart failure (CHF) complicated by lung infections using interpretable machine learning. METHODS: The clinical data of 1415 patients diagnosed with CHF complicated by lung infections were obtained from the MIMIC-IV database. According to the pathogen type, the patients were categorized into bacterial pneumonia and non-bacterial pneumonia groups, and their risks of in-hospital death were compared using Kaplan-Meier survival curves. Univariate analysis and LASSO regression were used to select the features for constructing LR, AdaBoost, XGBoost, and LightGBM models, and their performance was compared in terms of accuracy, precision, F1 value, and AUC. External validation of the models was performed using the data from eICU-CRD database. SHAP algorithm was applied for interpretive analysis of XGBoost model. RESULTS: Among the 4 constructed models, the XGBoost model showed the highest accuracy and F1 value for predicting the risk of in-hospital death in CHF patients with lung infections in the training set. In the external test set, the XGBoost model had an AUC of 0.691 (95% CI: 0.654-0.720) in bacterial pneumonia group and an AUC of 0.725 (95% CI: 0.577-0.782) in non-bacterial pneumonia group, and showed better predictive ability and stability than the other models. CONCLUSION: The overall performance of the XGBoost model is superior to the other 3 models for predicting the risk of in-hospital death in CHF patients with lung infections. The SHAP algorithm provides a clear interpretation of the model to facilitate decision-making in clinical settings.

Interpretable machine learning predicts postpartum hemorrhage with severe maternal morbidity in a lower-risk laboring obstetric population.

BACKGROUND: Early identification of patients at increased risk for postpartum hemorrhage (PPH) associated with severe maternal morbidity (SMM) is critical for preparation and preventative intervention. However, prediction is challenging in patients without obvious risk factors for postpartum hemorrhage with severe maternal morbidity. Current tools for hemorrhage risk assessment use lists of risk factors rather than predictive models. OBJECTIVE: To develop, validate (internally and externally), and compare a machine learning model for predicting PPH associated with SMM against a standard hemorrhage risk assessment tool in a lower risk laboring obstetric population. STUDY DESIGN: This retrospective cross-sectional study included clinical data from singleton, term births (>=37 weeks' gestation) at 19 US hospitals (2016-2021) using data from 58,023 births at 11 hospitals to train a generalized additive model (GAM) and 27,743 births at 8 held-out hospitals to externally validate the model. The outcome of interest was PPH with severe maternal morbidity (blood transfusion, hysterectomy, vascular embolization, intrauterine balloon tamponade, uterine artery ligation suture, uterine compression suture, or admission to intensive care). Cesarean birth without a trial of vaginal birth and patients with a history of cesarean were excluded. We compared the model performance to that of the California Maternal Quality Care Collaborative (CMQCC) Obstetric Hemorrhage Risk Factor Assessment Screen. RESULTS: The GAM predicted PPH with an area under the receiver-operating characteristic curve (AUROC) of 0.67 (95% CI 0.64-0.68) on external validation, significantly outperforming the CMQCC risk screen AUROC of 0.52 (95% CI 0.50-0.53). Additionally, the GAM had better sensitivity of 36.9% (95% CI 33.01-41.02) than the CMQCC screen sensitivity of 20.30% (95% CI 17.40-22.52) at the CMQCC screen positive rate of 16.8%. The GAM identified in-vitro fertilization as a risk factor (adjusted OR 1.5; 95% CI 1.2-1.8) and nulliparous births as the highest PPH risk factor (adjusted OR 1.5; 95% CI 1.4-1.6). CONCLUSION: Our model identified almost twice as many cases of PPH as the CMQCC rules-based approach for the same screen positive rate and identified in-vitro fertilization and first-time births as risk factors for PPH. Adopting predictive models over traditional screens can enhance PPH prediction.

An inaugural forum on epidemiological modeling for public health stakeholders in Arizona.

Epidemiological models-which help us understand and forecast the spread of infectious disease-can be valuable tools for public health. However, barriers exist that can make it difficult to employ epidemiological models routinely within the repertoire of public health planning. These barriers include technical challenges associated with constructing the models, challenges in obtaining appropriate data for model parameterization, and problems with clear communication of modeling outputs and uncertainty. To learn about the unique barriers and opportunities within the state of Arizona, we gathered a diverse set of 48 public health stakeholders for a day-and-a-half forum. Our research group was motivated specifically by our work building software for public health-relevant modeling and by our earnest desire to collaborate closely with stakeholders to ensure that our software tools are practical and useful in the face of evolving public health needs. Here we outline the planning and structure of the forum, and we highlight as a case study some of the lessons learned from breakout discussions. While unique barriers exist for implementing modeling for public health, there is also keen interest in doing so across diverse sectors of State and Local government, although issues of equal and fair access to modeling knowledge and technologies remain key issues for future development. We found this forum to be useful for building relationships and informing our software development, and we plan to continue such meetings annually to create a continual feedback loop between academic molders and public health practitioners.

Development of Predictive Modeling for Removal of Multispecies Biofilms of Salmonella Enteritidis, Escherichia coli, and Campylobacter jejuni from Poultry Slaughterhouse Surfaces.

Salmonella Enteritidis, Escherichia coli, and Campylobacter jejuni are among the most common foodborne pathogens worldwide, and poultry products are strongly associated with foodborne pathogen outbreaks. These pathogens are capable of producing biofilms on several surfaces used in the food processing industry, including polyethylene and stainless steel. However, studies on multi-species biofilms are rare. Therefore, this study aimed to develop predictive mathematical models to simulate the adhesion and removal of multispecies biofilms. All combinations of microorganisms resulted in biofilm formation with differences in bacterial counts. E. coli showed the greatest ability to adhere to both surfaces, followed by S. Enteritidis and C. jejuni. The incubation time and temperature did not influence adhesion. Biofilm removal was effective with citric acid and benzalkonium chloride but not with rhamnolipid. Among the generated models, 46 presented a significant coefficient of determination (R2), with the highest R2 being 0.88. These results provide support for the poultry industry in creating biofilm control and eradication programs to avoid the risk of contamination of poultry meat.

Consensus modeling: Safer transfer learning for small health systems.

Predictive modeling is becoming an essential tool for clinical decision support, but health systems with smaller sample sizes may construct suboptimal or overly specific models. Models become over-specific when beside true physiological effects, they also incorporate potentially volatile site-specific artifacts. These artifacts can change suddenly and can render the model unsafe. To obtain safer models, health systems with inadequate sample sizes may adopt one of the following options. First, they can use a generic model, such as one purchased from a vendor, but often such a model is not sufficiently specific to the patient population and is thus suboptimal. Second, they can participate in a research network. Paradoxically though, sites with smaller datasets contribute correspondingly less to the joint model, again rendering the final model suboptimal. Lastly, they can use transfer learning, starting from a model trained on a large data set and updating this model to the local population. This strategy can also result in a model that is over-specific. In this paper we present the consensus modeling paradigm, which uses the help of a large site (source) to reach a consensus model at the small site (target). We evaluate the approach on predicting postoperative complications at two health systems with 9,044 and 38,045 patients (rare outcomes at about 1% positive rate), and conduct a simulation study to understand the performance of consensus modeling relative to the other three approaches as a function of the available training sample size at the target site. We found that consensus modeling exhibited the least over-specificity at either the source or target site and achieved the highest combined predictive performance.

A nomogram to predict the risk of proliferative lupus nephritis in patients with systemic lupus erythematosus involving the kidneys.

Proliferative lupus nephritis (PLN) is a serious organ-threatening manifestation of systemic lupus erythematosus (SLE) that is associated with high mortality and renal failure. Here, we analyzed data from 1287 SLE patients with renal manifestations, including 780 of which were confirmed as proliferative or non-proliferative LN patients by renal biopsy, divided into a training cohort (547 patients) and a validation cohort (233 patients). By applying a least absolute shrinkage and selection operator (LASSO) regression approach combined with multivariate logistic regression analysis to build a nomogram for prediction of PLN that was then assessed by receiver operating characteristic (ROC) curves, calibration curves, and clinical decision curves (DCA) in both the training and validation cohorts. The area under the ROC curve (AUC) of the model in the training cohort was 0.921 (95% confidence interval (CI): 0.895-0.946), the AUC of internal validation in the training cohort was 0.909 and the AUC of external validation was 0.848 (95% CI: 0.796-0.900). The nomogram showed good performance as evaluated using calibration and DCA curves. Taken together, our results indicate that our nomogram that comprises 12 significantly relevant variables could be clinically valuable to prognosticate on the risk of PLN in SLE, so as to improve patient prognoses.