DEVS execution acceleration with machine learning

The aging and multimorbid population and health personnel shortages pose a substantial burden on primary health care. While predictive machine learning (ML) algorithms have the potential to address these challenges, concerns include transparency and insufficient reporting of model validation and effectiveness of the implementation in the clinical workflow. To systematically identify predictive ML algorithms implemented in primary care from peer-reviewed literature and US Food and Drug Administration (FDA) and Conformité Européene (CE) registration databases and to ascertain the public availability of evidence, including peer-reviewed literature, gray literature, and technical reports across the artificial intelligence (AI) life cycle. PubMed, Embase, Web of Science, Cochrane Library, Emcare, Academic Search Premier, IEEE Xplore, ACM Digital Library, MathSciNet, AAAI.org (Association for the Advancement of Artificial Intelligence), arXiv, Epistemonikos, PsycINFO, and Google Scholar were searched for studies published between January 2000 and July 2023, with search terms that were related to AI, primary care, and implementation. The search extended to CE-marked or FDA-approved predictive ML algorithms obtained from relevant registration databases. Three reviewers gathered subsequent evidence involving strategies such as product searches, exploration of references, manufacturer website visits, and direct inquiries to authors and product owners. The extent to which the evidence for each predictive ML algorithm aligned with the Dutch AI predictive algorithm (AIPA) guideline requirements was assessed per AI life cycle phase, producing evidence availability scores. The systematic search identified 43 predictive ML algorithms, of which 25 were commercially available and CE-marked or FDA-approved. The predictive ML algorithms spanned multiple clinical domains, but most (27 [63%]) focused on cardiovascular diseases and diabetes. Most (35 [81%]) were published within the past 5 years. The availability of evidence varied across different phases of the predictive ML algorithm life cycle, with evidence being reported the least for phase 1 (preparation) and phase 5 (impact assessment) (19% and 30%, respectively). Twelve (28%) predictive ML algorithms achieved approximately half of their maximum individual evidence availability score. Overall, predictive ML algorithms from peer-reviewed literature showed higher evidence availability compared with those from FDA-approved or CE-marked databases (45% vs 29%). The findings indicate an urgent need to improve the availability of evidence regarding the predictive ML algorithms' quality criteria. Adopting the Dutch AIPA guideline could facilitate transparent and consistent reporting of the quality criteria that could foster trust among end users and facilitating large-scale implementation.

Category:Ankle Arthritis; AnkleIntroduction/Purpose:Ankle arthrodesis and total ankle replacement are the most commonly performed procedures for surgical management of ankle arthritis. Arthrodesis provides effective pain relief but the rate of complications after arthrodesis is higher as it is more commonly performed in patients with comorbidities that preclude ankle replacement. Accurately risk- stratifying patients who undergo ankle arthrodesis would be of great utility, given the significant cost and morbidity associated with developing major perioperative complications. There is a paucity of accurate prediction models that can be used to pre- operatively risk-stratify patients for ankle arthrodesis. We aim to develop a machine learning (ML) algorithm for prediction of major perioperative complication after ankle arthrodesis as well as compare its performance against traditional predictive models based on logistic regression.Methods:This is a retrospective cohort study of adult patients who underwent ankle arthrodesis at any non-federal California hospital between 2015 and 2017. The primary outcome was readmission within 30 days or major perioperative complication - venous thromboembolism within 30 days, myocardial infarction within 7 days, pneumonia within 7 days, systemic infection within 7 days, surgical site bleeding within 90 days, and wound complications within 90 days. We build ML and logistic regression models that span different classes of modeling approaches: XGBoost, AdaBoost, Gradient Boosting, and Random Forest. Discrimination and calibration were assessed using area under the receiver operating characteristic curve (AUROC) and Brier score, respectively. We utilize a partial dependence function to measure the importance of an individual feature by assessing the average effect in predicted risks when its value is altered. We rank the contribution of the included variables to the prediction of adverse outcomes.Results:A total of 1,084 patients met inclusion criteria for this study. There were 131 major complications or readmission (12.1%). The optimized XGBoost algorithm demonstrates higher discrimination (AUROC: 0.707 + 0.052) compared to LR (0.691 + 0.055). The receiver operating characteristic curves for the XGBoost and logistic regression models are visualized in Figure 1. XGBoost also outperforms the three other ML models. This model was well calibrated (Brier score: 0.103 + 0.001). The variables most important for the XGBoost model include diabetes, chronic kidney disease, implant complication, and major fracture. Five of the ten most important features for XGBoost were markedly less important for the traditional logistic regression model: male sex, prior hip fracture, cardiorespiratory failure, acute renal failure, and dialysis status.Conclusion:We report a ML algorithm for prediction of major perioperative complications after ankle arthrodesis. The optimized XGBoost model is well-calibrated and demonstrates superior risk prediction to logistic regression. This tool may identify and address potentially modifiable risk factors, helping to accurately risk-stratify patients and decrease likelihood of major complications. Notably, the predictors most important for XGBoost are different from those for logistic regression. This suggests that the superior discriminative capability of ML methods stems from their ability to capture complex non-linear relationships between variables that logistic regression is unable to detect.

Background and purpose — External validation of machine learning (ML) prediction models is an essential step before clinical application. We assessed the proportion, performance, and transparent reporting of externally validated ML prediction models in orthopedic surgery, using the Transparent Reporting for Individual Prognosis or Diagnosis (TRIPOD) guidelines. Material and methods — We performed a systematic search using synonyms for every orthopedic specialty, ML, and external validation. The proportion was determined by using 59 ML prediction models with only internal validation in orthopedic surgical outcome published up until June 18, 2020, previously identified by our group. Model performance was evaluated using discrimination, calibration, and decision-curve analysis. The TRIPOD guidelines assessed transparent reporting. Results — We included 18 studies externally validating 10 different ML prediction models of the 59 available ML models after screening 4,682 studies. All external validations identified in this review retained good discrimination. Other key performance measures were provided in only 3 studies, rendering overall performance evaluation difficult. The overall median TRIPOD completeness was 61% (IQR 43–89), with 6 items being reported in less than 4/18 of the studies. Interpretation — Most current predictive ML models are not externally validated. The 18 available external validation studies were characterized by incomplete reporting of performance measures, limiting a transparent examination of model performance. Further prospective studies are needed to validate or refute the myriad of predictive ML models in orthopedics while adhering to existing guidelines. This ensures clinicians can take full advantage of validated and clinically implementable ML decision tools.

This dissertation contributes with novel predictive modelling approaches to data-driven computational psychiatry and offers alternative analyses frameworks to the standard statistical analyses in psychiatric research. In particular, this document advances research in medical data mining, especially psychiatry, via two phases. In the first phase, this document promotes research by proposing synergistic machine learning and statistical approaches for detecting patterns and developing predictive models in clinical psychiatry data to classify diseases, predict treatment outcomes or improve treatment selections. In particular, these data-driven approaches are built upon several machine learning techniques whose predictive models have been pre-processed, trained, optimised, post-processed and tested in novel computationally intensive frameworks. In the second phase, this document advances research in medical data mining by proposing several novel extensions in the area of data classification by offering a novel decision tree algorithm, which we call PIDT, based on parameterised impurities and statistical pruning approaches toward building more accurate decision trees classifiers and developing new ensemblebased classification methods. In particular, the experimental results show that by building predictive models with the novel PIDT algorithm, these models primarily led to better performance regarding accuracy and tree size than those built with traditional decision trees. The contributions of the proposed dissertation can be summarised as follow. Firstly, several statistical and machine learning algorithms, plus techniques to improve these algorithms, are explored. Secondly, prediction modelling and pattern detection approaches for the first-episode psychosis associated with cannabis use are developed. Thirdly, a new computationally intensive machine learning framework for understanding the link between cannabis use and first-episode psychosis was introduced. Then, complementary and equally sophisticated prediction models for the first-episode psychosis associated with cannabis use were developed using artificial neural networks and deep learning within the proposed novel computationally intensive framework. Lastly, an efficient novel decision tree algorithm (PIDT) based on novel parameterised impurities and statistical pruning approaches is proposed and tested with several medical datasets. These contributions can be used to guide future theory, experiment, and treatment development in medical data mining, especially psychiatry.

Due to the growing concern on the issues of global warming, climate change, and energy shortage, more rigorous requirements are imposed on the energy conversion process of combustion. Due to the relative safety and convenience in transportation and storage, liquid fuels are commonly used in many practical combustion systems such as diesel engines, gas turbines and industrial furnaces. In these combustion devices, turbulent spray flows are involved. The character of spray dispersion, evaporation, mixing and combustion of fuel droplets strongly determines the performance of these systems with respect to the combustion efficiency, stability, and emissions. Therefore, an improved understanding of turbulent spray combustion and the development of predictive models are needed for a better design of more efficient combustion systems. The present work focuses on the development of a computational methodology based on the transported joint probability density function (PDF) method for the modeling and simulation of two-phase turbulent spray flows without and with chemical reactions. In the non-reacting situation, the dependent variables of the joint PDF include the gas velocity and the mixture fraction. For the simulation of reacting spray flows, a three-variate joint PDF transport equation is derived and modeled in order to account for the pre-vaporization effects and partially premixed regime in turbulent spray flames. The dependent variables include the gas phase mixture fraction, the reaction progress variable and gas enthalpy. Detailed combustion chemistry is considered through an extended spray flamelet model by including a reaction progress variable in addition to the classical formulation. The dilute spray is simulated using a Lagrangian discrete parcel method for the description of droplet motion, heating and evaporation. The infinite conductivity model with consideration of non-equilibrium effects based on the Langmuir-Knudsen law is considered. The spray evolution and flame structures in the frame of the polydisperse reacting spray flows are investigated. Numerical results are compared with experimental data provided by Prof. Masri at the University of Sydney, Australia, and the test cases include three different turbulent non-reacting acetone spray flows in air and turbulent spray flames with the liquid fuel ethanol. For the acetone spray flows, computational results generally show good agreement with experimental data in terms of the droplet size and mean velocity distribution, as well as the liquid volume flux. The results show that the inflow liquid mass loading hardly affects the droplet diameter distribution, whereas the inlet turbulence level has a pronounced effect. The tendency of droplet accumulation near the jet centerline is found with a somewhat overprediction of liquid volume flux at downstream locations. A more sophisticated turbulence model is expected to eliminate this discrepancy. Moreover, the local joint PDF of the gas velocity and the mixture fraction is analyzed. A linear correlation of the gas velocity and the mixture fraction exists close to the nozzle exit outside the main spray jet, and no regions are found where statistical independence prevails. For the simulation of spray flames, computations with the newly developed spray flamelet/progress variable approach and with the previous standard spray flamelet formulation are carried out and compared with the experiments by Prof. Masri at the University of Sydney. A good agreement between the computations with the new formulation and the experiments for gas temperature and droplet size and velocity is achieved. The major spray and combustion properties are correctly captured using this new formulation, which is compared with an unphysically attached flame near the nozzle exit predicted by the previous model. A partially premixed combustion prevails in this piloted turbulent spray flame. Due to the prevaporization of the ethanol droplets near the nozzle exit, a lean premixed gas mixture is found at the inner side of spray jet. Moving downstream, the lean-sided diffusion flame is promoted towards the inner fuel-rich side by heating up the inner premixed core that is controlled by the droplet evaporation. Additionally, it is observed that in the far-field region, the diffusion flame becomes the dominant combustion mode. In summary, an efficient computational model based on the transported joint PDF method is developed to two-phase turbulent spray flows. The combined transported joint PDF and a newly proposed spray flamelet/progress variable approach shows an improved performance in the prediction of complex turbulent spray flames, and new insights on the local flame structure influenced by evaporating sprays are obtained.

Artificial intelligence (AI) algorithms are transforming several areas of the digital world and are increasingly being applied in healthcare. Mobile apps based on predictive machine learning models have the potential to improve health outcomes, but there is still no consensus on how to inform doctors about their results. The aim of this study was to investigate how healthcare professionals prefer to receive predictions generated by machine learning algorithms. A systematic search in MEDLINE, via PubMed, EMBASE and Web of Science was first performed. We developed a mobile app, RandomIA, to predict the occurrence of clinical outcomes, initially for COVID-19 and later expected to be expanded to other diseases. A questionnaire called System Usability Scale (SUS) was selected to assess the usability of the mobile app. A total of 69 doctors from the five regions of Brazil tested RandomIA and evaluated three different ways to visualize the predictions. For prognostic outcomes (mechanical ventilation, admission to an intensive care unit, and death), most doctors (62.9%) preferred a more complex visualization, represented by a bar graph with three categories (low, medium, and high probability) and a probability density graph for each outcome. For the diagnostic prediction of COVID-19, there was also a majority preference (65.4%) for the same option. Our results indicate that doctors could be more inclined to prefer receiving detailed results from predictive machine learning algorithms.

BackgroundCervical cancer is a common malignant tumor of the female reproductive system and is considered a leading cause of mortality in women worldwide. The analysis of time to event, which is crucial for any clinical research, can be well done with the method of survival prediction. This study aims to systematically investigate the use of machine learning to predict survival in patients with cervical cancer.MethodAn electronic search of the PubMed, Scopus, and Web of Science databases was performed on October 1, 2022. All articles extracted from the databases were collected in an Excel file and duplicate articles were removed. The articles were screened twice based on the title and the abstract and checked again with the inclusion and exclusion criteria. The main inclusion criterion was machine learning algorithms for predicting cervical cancer survival. The information extracted from the articles included authors, publication year, dataset details, survival type, evaluation criteria, machine learning models, and the algorithm execution method.ResultsA total of 13 articles were included in this study, most of which were published from 2018 onwards. The most common machine learning models were random forest (6 articles, 46%), logistic regression (4 articles, 30%), support vector machines (3 articles, 23%), ensemble and hybrid learning (3 articles, 23%), and Deep Learning (3 articles, 23%). The number of sample datasets in the study varied between 85 and 14946 patients, and the models were internally validated except for two articles. The area under the curve (AUC) range for overall survival (0.40 to 0.99), disease-free survival (0.56 to 0.88), and progression-free survival (0.67 to 0.81), respectively from (lowest to highest) received. Finally, 15 variables with an effective role in predicting cervical cancer survival were identified.ConclusionCombining heterogeneous multidimensional data with machine learning techniques can play a very influential role in predicting cervical cancer survival. Despite the benefits of machine learning, the problem of interpretability, explainability, and imbalanced datasets is still one of the biggest challenges. Providing machine learning algorithms for survival prediction as a standard requires further studies.

Surface water pollution become a nuisance for humankind as river water fulfill requirement of a major population and traditional method of water quality assessment and evaluation is inadequate in this era. So using advance method of machine learning in prediction of surface water proves to be helpful to prevent future water accident. As we seen many recent studies of water quality prediction and river water assessment using machine learning approach for better accuracy and less labor and to optimize its overall results. It’s become essential to review the recent studies which used Machine Learning algorithms for prediction, analysis, evaluation and assessment of river water quality and different models used in these studies for different environmental conditions. Machine learning models are superior to handle such complex and non linear data such as water quality parameters with greater accuracy, reliability, cost-effectiveness and efficiency as considered as great tool for surface Water Quality monitoring, prediction, future projects and help lawmakers in policy. In this report we reviewed around 17 research papers which uses machine learning approach from different journal and concise it to covers the structure of study, datasets used, methodology analysis, models performance, environment susceptibility, comparative analysis and assessments of Machine Learning models progress in river water quality research. For better management and control of surface water quality and its treatment, this study will help in understanding and analyzing the studies reviewed in this paper and its future application. We can conclude that research on Water Quality prediction using Machine Learning model are inadequate in the context future vulnerability, observing increasing pollution in recent years we require more research in this field. Finally, this study provides breakthrough in Surface Water Engineering and Management to give a new direction to fore coming studies and fortified it scope also gives a comparative approach for its implementation in new studies.

This dissertation addresses two significant issues in the effective application of machine learning algorithms and models for the physical and engineering sciences. The first is the broad challenge of automated modeling of data across different processes in a physical system. The second is the dilemma of obtaining insightful interpretations on the relationships between the inputs and outcome of a system as inferred from complex, black box machine learning models.Automated Geometric Shape Deviation Modeling for Additive Manufacturing SystemsAdditive manufacturing systems possess an intrinsic capability for one-of-a-kind manufacturing of a vast variety of shapes across a wide spectrum of processes. One major issue in AM systems is geometric accuracy control for the inevitable shape deviations that arise in AM processes. Current effective approaches for shape deviation control in AM involve the specification of statistical or machine learning deviation models for additively manufactured products. However, this task is challenging due to the constraints on the number of test shapes that can be manufactured in practice, and limitations on user efforts that can be devoted for learning deviation models across different shape classes and processes in an AM system. We develop an automated, Bayesian neural network methodology for comprehensive shape deviation modeling in an AM system. A fundamental innovation in this machine learning method is our new and connectable neural network structures that facilitate the transfer of prior knowledge and models on deviations across different shape classes and AM processes. Several case studies on in-plane and out-of-plane deviations, regular and free-form shapes, and different settings of lurking variables serve to validate the power and broad scope of our methodology, and its potential to advance high-quality manufacturing in an AM system.Interpretable Machine LearningMachine learning algorithms and models constitute the dominant set of predictive methods for a wide range of complex, real-world processes. However, interpreting what such methods effectively infer from data is difficult in general. This is because their typical black box natures possess a limited ability to directly yield insights on the underlying relationships between inputs and the outcome for a process. We develop methodologies based on new predictive comparison estimands that effectively enable one to ``mine’’ machine learning models, in the sense of (a) interpreting their inferred associations between inputs and/or functional forms of inputs with the outcome, (b) identifying the inputs that they effectively consider relevant, and (c) interpreting the inferred conditional and two-way associations of the inputs with the outcome. We establish Fisher consistent estimators, and their corresponding standard errors, for our new estimands under a condition on the inputs' distributions. The significance of our predictive comparison methodology is demonstrated with a wide range of simulation and case studies that involve Bayesian additive regression trees, neural networks, and support vector machines. Our extended study of interpretable machine learning for AM systems demonstrates how our method can contribute to smarter advanced manufacturing systems, especially as current machine learning methods for AM are lacking in their ability to yield meaningful engineering knowledge on AM processes.

Although interaction effects can be exploited to improve predictions and allow for valuable insights into covariate interplay, they are given little attention in analysis. We introduce interaction forests, which are a variant of random forests for categorical, continuous, and survival outcomes, explicitly considering quantitative and qualitative interaction effects in bivariable splits performed by the trees constituting the forests. The new effect importance measure (EIM) associated with interaction forests allows ranking of the covariate pairs with respect to their interaction effects' importance for prediction. Using EIM, separate importance value lists for univariable effects, quantitative interaction effects, and qualitative interaction effects are obtained. In the spirit of interpretable machine learning, the bivariable split types of interaction forests target well interpretable interaction effects that are easy to communicate. To learn about the nature of the interplay between identified interacting covariate pairs it is convenient to visualise their estimated bivariable influence. We provide functions that perform this task in the R package diversityForest that implements interaction forests. In a large-scale empirical study using 220 data sets, interaction forests tended to deliver better predictions than conventional random forests and competing random forest variants that use multivariable splitting. In a simulation study, EIM delivered considerably better rankings for the relevant quantitative and qualitative interaction effects than competing approaches. These results indicate that interaction forests are suitable tools for the challenging task of identifying and making use of well interpretable interaction effects in predictive modelling.

A key component of research in the aerospace industry constitutes hypersonic flights (M>5) which includes the design of commercial high-speed aircrafts and development of rockets. Computational analysis becomes more important due to the difficulty in performing experiments and reliability of its results at these harsh operating conditions. There is an increasing demand from the industry for the accurate prediction of wall-shear and heat transfer with a low computational cost. Direct Numerical Simulations (DNS) create the standard for accuracy, but its practical usage is difficult and limited because of its high cost of computation. The usage of Reynold's Averaged Navier Stokes (RANS) simulations provide an affordable gateway for industry to capitalize its lower computational time for practical applications. However, the presence of existing RANS turbulence closure models and associated wall functions result in poor prediction of wall fluxes and inaccurate solutions in comparison with high fidelity DNS data. In recent years, machine learning emerged as a new approach for physical modeling. This thesis explores the potential of employing Machine Learning (ML) to improve the predictions of wall fluxes for hypersonic turbulent boundary layers. Fine-grid RANS simulations are used as training data to construct a suitable machine learning model to improve the solutions and predictions of wall quantities for coarser meshes. This strategy eliminates the usage of wall models and extends the range of applicability of grid sizes without a significant drop in accuracy of solutions. Random forest methodology coupled with a bagged aggregation algorithm helps in modeling a correction factor for the velocity gradient at the first grid points. The training data set for the ML model extracted from fine-grid RANS, includes neighbor cell information to address the memory effect of turbulence, and an optimal set of parameters to model the gradient correction factor. The successful demonstration of accurate predictions of wall-shear for coarse grids using this methodology, provides the confidence to build machine learning models to use DNS or high-fidelity modeling results as training data for reduced-order turbulence model development. This paves the way to integrate machine learning with RANS to produce accurate solutions with significantly lesser computational costs for hypersonic boundary layer problems.

This works deals with the power-aware job dispatching problem in supercomputers; broadly speaking the dispatching consists of assigning finite capacity resources to a set of activities, with a special concern toward power and energy efficient solutions. We introduce novel optimization approaches to address its multiple aspects.
\nThe proposed techniques have a broad application range but are aimed at applications in the field of High Performance Computing (HPC) systems.
\n
\nDevising a power-aware HPC job dispatcher is a complex, where contrasting goals must be satisfied. Furthermore, the online nature of the problem request that solutions must be computed in real time respecting stringent limits. This aspect historically discouraged the usage of exact methods and favouring instead the adoption of heuristic techniques. The application of optimization approaches to the dispatching task is still an unexplored area of research and can drastically improve the performance of HPC systems.
\n
\nIn this work we tackle the job dispatching problem on a real HPC machine, the Eurora supercomputer hosted at the Cineca research center, Bologna. We propose a Constraint Programming (CP) model that outperforms the dispatching software currently in use. An essential element to take power-aware decisions during the job dispatching phase is the possibility to estimate jobs power consumptions before their execution. To this end, we applied Machine Learning techniques to create a prediction model that was trained and tested on the Euora supercomputer, showing a great prediction accuracy. Then we finally develop a power-aware solution, considering the same target machine, and we devise different approaches to solve the dispatching problem while curtailing the power consumption of the whole system under a given threshold. We proposed a heuristic technique and a CP/heuristic hybrid method, both able to solve practical size instances and outperform the current state-of-the-art techniques.

In general design and analysis of a tunnel boring machine (TBM), many analytical models are proposed to predict the TBM's performance. Various models may result in different performance predictions for the same TBM excavating under the same geological conditions. Therefore, it is essential to perform the quantitative analysis of the impacts from different prediction models and the corresponding key input factors on the TBM's performance. Recently, there is almost no relevant study on such issues for TBM and it is urgent to fill this gap. In this paper, by comparing and analyzing the TBM's performance using different prediction models, three types of total thrust prediction models (the rapid-growth type, the intermediate type, and the slow-growth type) and two types of total torque prediction models (the rapid-growth type and the slow-growth type) are classified and defined for the first time in the TBM-related fields. Then, a global sensitivity analysis (SA) of TBM's performance using the Sobol' method is developed regarding key input factors, including control, structural, and geological parameters. It is found that the relative impacts of the input factors to TBM's performance vary appreciably with the selection of prediction models. Specifically, a global SA on the minimized construction period of a tunneling project with respect to structure parameters is performed. The results show that the structure parameters have similar impacts on the minimized construction period irrespective of the selection of prediction models. The impacts of different prediction models on the minimized construction period of a tunneling project using Genetic Algorithm (GA) are investigated by finding the optimal control and structure parameters. The results interestingly show that the selection of the TBM's performance prediction models has a marginal impact on the minimized construction period but yields partly different key parameters.

Background: Cholangiocarcinoma is a molecularly heterogenous cancer arising from the biliary epithelium. Individual omic techniques have identified clinically relevant, targetable subtypes but most tumors have no targetable alterations based on exome or transcriptomic evaluation. Integrated multiomics approaches incorporating transcriptomic, proteomic, and phosphoproteomic characterization provide deeper understanding and identify non-mutated, activated pathways that can be targeted. To optimize the potential clinical utility of these approaches, minimal classifier features must be defined. Methods: Approximately 60,000 RNA, protein, and phosphoprotein features were extracted from 35 cholangiocarcinomas treated at the primary US study site. 206 patients treated and profiled at an institution in China were also included. Using the Multiomics Factor Analysis clustering method, patients were sorted into 3 distinct molecular profiles. Important molecular features were selected using competing feature selection (FS) methods: Boruta, RreliefF, variable selection using random forests (RF), recursive factor elimination (RFE), median decrease accuracy in RF, and Concrete Autoencoders. Machine learning classification prediction models including Extreme Gradient Boosting, gradient-boosted trees, multinomial logit, and support vector machine (SVM) were tested on each FS. Each combination of FS and predictive model was tested with 10 replicates of 10-fold cross-validation of a randomly-selected balanced test set and an oversampled, balanced training subset. Accuracy, F1 score, AUC, precision, and recall were assessed for each FS and predictive model combination. A custom function of physical assay cost and classification accuracy was optimized to find the best assay. KEGG pathway overrepresentation analysis was used to analyze feature subsets. Results: A consistent set of 50 important RNA and protein features was identified, including previously reported prognostic factors, like SpryD4 protein expression, as well as previously unreported pathway surrogates, such as Slc2A2 or Pipox protein. Pathway overrepresentation analysis found insulin signaling and resistance and amino acid biosynthesis/metabolism pathways were overrepresented in the discriminative feature set. The gradient-boosted trees algorithm combined with the RFE FS method had the best performance, with a multiclass macro average (±sd) cross-validation accuracy 89% (±6%), F1 score 89% (±8%), AUC 0.98 (±0.02), precision 90% (±10%), recall 89% (±6%). Conclusions: Feature selection methods and predictive machine learning models work synchronously to develop accurate molecular subtype assays based on just 50 protein and RNA levels. This strategy has the potential to make molecular subtyping for cholangiocarcinoma and other molecularly complex cancers fast and widely available. Citation Format: Ellen Larson, Erik Jessen, Dong-Gi Mun, Jennifer Tomlinson, Amro Abdelrahman, Danielle Carlson, Hojjat Salehinejad, Rory Smoot. Feature selection and machine learning strategies optimize an affordable molecular assay for cholangiocarcinoma subtype [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2025; Part 1 (Regular Abstracts); 2025 Apr 25-30; Chicago, IL. Philadelphia (PA): AACR; Cancer Res 2025;85(8_Suppl_1):Abstract nr 1107.

Machine Learning and Neurosurgical Outcome Prediction: A Systematic Review.