Predicting Length of Stay in Cardiovascular Patients Using Count Regression and Machine Learning Approaches

This paper investigates the relationship between urban form and the spatial distribution of micro-retail activities. In the last decades, several works demonstrated how configurational properties of the street network and morphological descriptors of the urban built environment are significantly related to store distribution. However, two main challenges still need to be addressed. On the one side, the combined effect of different urban form properties should be considered providing a holistic study of the urban form and its relationship to retail patterns. On the other, analytical approaches should consider the discrete, skewed and zero-inflated nature of the micro-retail distribution. To overcome these limitations, this work compares two sophisticated modelling procedure: Penalised Count Regression and Machine Learning approaches. While the former is specifically conceived to account for retail count distribution, the latter can capture non-linear behaviours in the data. The two modelling procedures are implemented on the same large dataset of street-based measures describing the urban form of the French Riviera. The outcomes of the two modelling approaches are compared in terms of prediction performance and selection frequencies of the most recurrent variables among the implemented models.

BackgroundLarge cell neuroendocrine lung carcinoma (LCNEC) is a rare and aggressive subtype of lung cancer with high rates of lymph node metastasis (60–80%) and distant metastasis (40%) at diagnosis. This study aimed to develop and evaluate 5-year survival prognostic models for patients with LCNEC, comparing the traditional Cox proportional hazards regression model with machine learning approaches, including Gradient Boosting, XGboost, Random Survival Forests, Extra Survival Trees, and Neural Networks.MethodsThis retrospective cohort study utilized data from the Surveillance, Epidemiology, and End Results (SEER) database (2000–2021), including 6,062 patients with pathologically confirmed LCNEC. The primary outcome was the 5-year survival probability. The study employed regression and machine learning approaches, with data that was stratified into training and testing sets based on the year of diagnosis, and four stratification variables were analyzed. Internal-external cross-validation assessed the model performance, while decision curve analysis (DCA) evaluated clinical utility.ResultsThe Gradient Boosting model showed better discrimination than all others, achieving the best pooled metrics. Harrell’s C-index of 0.799, Brier score of 0.047, Calibration slope of 1.126 and Calibration-in-the-large of 0.155. Our SHAP value analysis identified chemotherapy as one of the most influential predictors of survival outcomes in LCNEC patients, highlighting its potential clinical importance in guiding treatment strategies for this population. DCA confirmed its superior clinical utility.ConclusionsGradient Boosting exhibited excellent predictive accuracy and clinical utility, demonstrating its potential for prognostic evaluation for LCNEC patients.

333 Background: Patients undergoing outpatient infusion chemotherapy for cancer are at risk for potentially preventable, unplanned acute care in the form of emergency department (ED) visits and hospital admissions. This can impact outcomes, patient decisions, and costs to the patient and healthcare system. To address this need, the Centers for Medicare & Medicaid Services developed the Chemotherapy Measure (OP-35). Recent randomized controlled data indicate that electronic health record (EHR)-based machine learning (ML) approaches accurately direct supportive care to reduce acute care during radiotherapy. As this may extend to systemic therapy, this study aims to develop and evaluate ML approaches to predict the risk of OP-35 qualifying, potentially preventable acute care within 30 days of infusional systemic therapy. Methods: This study included data from UCSF cancer patients receiving infusional chemotherapy from July 1, 2017, to February 11, 2021, (total 7,068 patients over 84,174 treatments). The data incorporated into the ML included 430 EHR-derived variables, including cancer diagnosis, therapeutic agents, laboratory values, vital signs, medications, and encounter history. Three ML approaches were trained to predict an OP-35 acute care risk following a systemic therapy infusion with least absolute shrinkage selection operator (LASSO), random forest, and gradient boosted trees (GBT; XGBoost) approaches. The models were trained on a subset (75% of patients; before October 12, 2019) of the dataset and validated on a mutually exclusive subset (25% patients; after October 12, 2019) based on the receiver operating characteristic (ROC) curves and calibration plots. Results: There were 1,651 total acute care visits (244 ED visits and 1,407 ED visits converted into hospitalization); 1,310 infusions included a qualifying acute care visit (200 with ED visits only, 0 direct hospital admissions, and 1,110 with both ED visit and hospitalization). Each ML approach demonstrated good performance in the internal validation cohort, with GBT (AUC 0.805) outpacing the random forest (0.750) and LASSO logistic regression (0.755) approaches. Visualization of calibration plots verified concordance between predicted and observed rates of acute care. All three models shared patient age and days elapsed since last treatment as important contributors. Conclusions: EHR-based ML approaches demonstrate high predictive ability for OP-35 qualifying acute care rates on a per-infusion basis, identifying 30-day potentially preventable acute care risk for patients undergoing chemotherapy. Prospective validation of these models is ongoing. Early prediction can facilitate interventional strategies which may reduce acute care, improve health outcomes, and reduce costs.

An improved machine learning approach for predicting granular flows

Optimized machine learning approaches for identifying vertical temperature gradient on ballastless track in natural environments

<p>The advancement of big data and increased computational power have contributed to an increased use of Machine Learning (ML) approaches in hydrological modelling. These approaches are powerful tools for modeling non-linear systems. However, the applicability of ML in non-stationary conditions needs to be studied further. As climate change will change hydrological patterns, testing ML approaches for non-stationary conditions is essential. Here, we used the Differential Split-Sample Test (DSST) to test the climate transposability of ML approaches (e.g., calibrating in a wet period and validating in a dry one, and vice-versa).  We applied five ML approaches using daily precipitation and temperature as input for the prediction of the daily discharge in six snow-dominated Swiss catchments. Lower and upper benchmarks were used to evaluate performances through a relative performance measure. The lower benchmark is the average of the bucket-type HBV model runs from 1000 random parameter sets. The upper benchmark is the automatically calibrated HBV model. In comparison with the stationary condition, the models performed slightly poorer in the non-stationary condition. The performance of simple ML approaches was poor for non-stationary conditions with an underestimation of peak flows, as well as a poor representation of the snow-melting period. On the other hand, a more complex ML approach (deep learning), the Long Short -Term Memory (LSTM), showed a good performance when compared with the lower and upper benchmarks. This might be explained by the fact that the so-called memory cell allowed to simulate the storage effects. </p>

Background: This paper attempts to identify suitable Machine Learning (ML) approach for image denoising of radiology based medical application. The Identification of ML approach is based on (i) Review of ML approach for denoising (ii) Review of suitable Medical Denoising approach.Discussion: The review focuses on six application of radiology: Medical Ultrasound (US) for fetus development, US Computer Aided Diagnosis (CAD) and detection for breast, skin lesions, brain tumor MRI diagnosis, X-Ray for chest analysis, Breast cancer using MRI imaging. This survey identifies the ML approach with better accuracy for medical diagnosis by radiologists. The image denoising approaches further includes basic filtering techniques, wavelet medical denoising, curvelet and optimization techniques. In most of the applications, the machine learning performance is better than the conventional image denoising techniques. For fast and computational results the radiologists are using the machine learning methods on MRI, US, X-Ray and Skin lesion images. The characteristics and contributions of different ML approaches are considered in this paper.Conclusion: The problem faced by the researchers during image denoising techniques and machine learning applications for clinical settings have also been discussed.

Recently, global climate change discussions have become more prominent, and forests are considered as the ecosystems most at risk by the consequences of climate change. Wildfires are among one of the main drivers leading to losses in forested areas. The increasing availability of free remotely sensed data has enabled the precise locations of wildfires to be reliably monitored. A wildfire data inventory was created by integrating global positioning system (GPS) polygons with data collected from the moderate resolution imaging spectroradiometer (MODIS) thermal anomalies product between 2012 and 2017 for Amol County, northern Iran. The GPS polygon dataset from the state wildlife organization was gathered through extensive field surveys. The integrated inventory dataset, along with sixteen conditioning factors (topographic, meteorological, vegetation, anthropological, and hydrological factors), was used to evaluate the potential of different machine learning (ML) approaches for the spatial prediction of wildfire susceptibility. The applied ML approaches included an artificial neural network (ANN), support vector machines (SVM), and random forest (RF). All ML approaches were trained using 75% of the wildfire inventory dataset and tested using the remaining 25% of the dataset in the four-fold cross-validation (CV) procedure. The CV method is used for dealing with the randomness effects of the training and testing dataset selection on the performance of applied ML approaches. To validate the resulting wildfire susceptibility maps based on three different ML approaches and four different folds of inventory datasets, the true positive and false positive rates were calculated. In the following, the accuracy of each of the twelve resulting maps was assessed through the receiver operating characteristics (ROC) curve. The resulting CV accuracies were 74%, 79% and 88% for the ANN, SVM and RF, respectively.

Performance optimization of wireless networks is typically complicated because of high computational complexity and dynamic channel conditions. Considering a specific case, the recent introduction of intelligent reflecting surface (IRS) can reshape the wireless channels by controlling the scattering elements' phase shifts, namely, passive beamforming. However, due to the large size of scattering elements, the IRS's beamforming optimization becomes intractable. In this article, we focus on machine learning (ML) approaches for complex optimization problems in wireless networks. ML approaches can provide flexibility and robustness against uncertain and dynamic systems. However, practical challenges still remain due to slow convergence in offline training or online learning. This motivated us to design a novel optimization-driven ML framework that exploits the efficiency of model-based optimization and the robustness of model-free ML approaches. Splitting the control variables into two parts allows one part to be updated by the outer loop ML approach while the other part is solved by the inner loop optimization. The case study in IRS-assisted wireless networks confirms that the optimization-driven ML framework can improve learning efficiency and the reward performance significantly compared to conventional model-free ML approaches.

Collaborative robots, or cobots, are designed to work alongside humans and to alleviate their physical burdens, such as lifting heavy objects or performing tedious tasks. Ensuring the safety of human-robot interaction (HRI) is paramount for effective collaboration. To achieve this, it is essential to have a reliable dynamic model of the cobot that enables the implementation of torque control strategies. These strategies aim to achieve accurate motion while minimizing the amount of torque exerted by the robot. However, modeling the complex non-linear dynamics of cobots with elastic actuators poses a challenge for traditional analytical modeling techniques. Instead, cobot dynamic modeling needs to be learned through data-driven approaches, rather than analytical equation-driven modeling. In this study, we propose and evaluate three machine learning (ML) approaches based on bidirectional recurrent neural networks (BRNNs) for learning the inverse dynamic model of a cobot equipped with elastic actuators. We also provide our ML approaches with a representative training dataset of the cobot's joint positions, velocities, and corresponding torque values. The first ML approach uses a non-parametric configuration, while the other two implement semi-parametric configurations. All three ML approaches outperform the rigid-bodied dynamic model provided by the cobot's manufacturer in terms of torque precision while maintaining their generalization capabilities and real-time operation due to the optimized sample dataset size and network dimensions. Despite the similarity in torque estimation of these three configurations, the non-parametric configuration was specifically designed for worst-case scenarios where the robot dynamics are completely unknown. Finally, we validate the applicability of our ML approaches by integrating the worst-case non-parametric configuration as a controller within a feedforward loop. We verify the accuracy of the learned inverse dynamic model by comparing it to the actual cobot performance. Our non-parametric architecture outperforms the robot's default factory position controller in terms of accuracy.

Do Machine Learning Approaches Perform Better Than Regression Models in Mapping Studies? A Systematic Review.

Brain age is an imaging-based biomarker with excellent feasibility for characterizing individual brain health and may serve as a single quantitative index for clinical and domain-specific usage. Brain age has been successfully estimated using extensive neuroimaging data from healthy participants with various feature extraction and conventional machine learning (ML) approaches. Recently, several end-to-end deep learning (DL) analytical frameworks have been proposed as alternative approaches to predict individual brain age with higher accuracy. However, the optimal approach to select and assemble appropriate input feature sets for DL analytical frameworks remains to be determined. In the Predictive Analytics Competition 2019, we proposed a hierarchical analytical framework which first used ML algorithms to investigate the potential contribution of different input features for predicting individual brain age. The obtained information then served as a priori knowledge for determining the input feature sets of the final ensemble DL prediction model. Systematic evaluation revealed that ML approaches with multiple concurrent input features, including tissue volume and density, achieved higher prediction accuracy when compared with approaches with a single input feature set [Ridge regression: mean absolute error (MAE) = 4.51 years, R2 = 0.88; support vector regression, MAE = 4.42 years, R2 = 0.88]. Based on this evaluation, a final ensemble DL brain age prediction model integrating multiple feature sets was constructed with reasonable computation capacity and achieved higher prediction accuracy when compared with ML approaches in the training dataset (MAE = 3.77 years; R2 = 0.90). Furthermore, the proposed ensemble DL brain age prediction model also demonstrated sufficient generalizability in the testing dataset (MAE = 3.33 years). In summary, this study provides initial evidence of how-to efficiency for integrating ML and advanced DL approaches into a unified analytical framework for predicting individual brain age with higher accuracy. With the increase in large open multiple-modality neuroimaging datasets, ensemble DL strategies with appropriate input feature sets serve as a candidate approach for predicting individual brain age in the future.

Machine learning (ML) approaches have emerged as promising tools for improving seizure-onset zone (SOZ) prediction in patients with drug-resistant epilepsy (DRE). This systematic review aimed to evaluate the application and performance of ML approaches for SOZ prediction in patients with DRE. A comprehensive search was conducted across PubMed/MEDLINE, the Cochrane Database of Systematic Reviews, and Epistemonikos databases for studies employing ML algorithms for SOZ prediction in patients with DRE. The Quality Assessment of Diagnostic Accuracy Studies version 2 (QUADAS-2) tool was adopted to assess the methodological quality and risk of bias of included studies. Data on patient demographics, data acquisition methods, ML algorithms, and performance metrics were extracted and systematically synthesized. Out of a total of 38 studies, 15 studies met the inclusion criteria, encompassing 352 patients (mean age: 28 years, 34% female population). The studies employed various ML techniques, including traditional methods such as support vector machines and advanced deep learning architectures. Performance metrics varied widely across studies, with some approaches achieving accuracy, sensitivity, and specificity values above 90%. Deep learning models generally outperformed traditional methods, particularly in handling complex, multimodal data. Notably, personalized models demonstrated superior performance in reducing localization error and spatial dispersion. However, heterogeneity in data acquisition methods, patient populations, and reporting standards complicated direct comparisons between studies. This review highlighted the potential of ML approaches, particularly deep learning and personalized models, to enhance SOZ prediction accuracy in patients with DRE. However, several challenges were identified, including the need for standardized data collection protocols, larger prospective studies, and improved model interpretability. The findings underscore the importance of considering network-level changes in epilepsy when developing ML models for SOZ prediction. Although ML approaches show promise for improving surgical planning and outcomes in DRE, their clinical utility, particularly in complex epilepsy cases, requires further investigation. Addressing these challenges will be crucial in realizing the full potential of ML in enhancing epilepsy care.

Efficient fertilizer application is vital for enhancing maize production and profitability in Sub-Saharan Africa, where soil fertility varies widely across regions. This study aimed to develop a machine learning approach for generating site-specific fertilizer recommendations for maize production in Ghana and to evaluate its performance against conventional and semi-mechanistic approaches. A random forest machine learning model was trained on 482 maize yield experiments, consisting of 3136 yield observations collected from 1991 to 2020, to predict maize yield response to different fertilizer rates. The model incorporated multiple explanatory variables, including soil properties, climate conditions, and management practices, to generate fertilizer response curves from which fertilizer recommendations were derived for 14 sites across three agro-ecological zones in Ghana where field validation experiments were conducted. On these sites, the recommendations were compared with recommendations derived from the Quantitative Evaluation of the Fertility of Tropical Soils (QUEFTS), Conventional Fertilizer Dose Response (CFDR), and Updated Conventional Fertilizer Dose Response (UCFDR) approaches and validated through field experiments. The machine learning approach generally recommended lower rates of phosphorus and potassium than the other approaches, while nitrogen recommendations were comparable. In the Guinea Savanna zone, the recommendations from the machine learning approach outperformed those from the other approaches, producing higher mean yields for three out of the four sites in the zone. In the Forest-Savanna Transition (FST) zone, the machine learning model recommendations led to higher mean yields at four sites, while the approaches based on QUEFTS and UCFDR performed best at two other sites. In the Semi-deciduous Forest zone, the recommendations of the QUEFTS approach resulted in the highest mean yields at three sites, and CFDR at one site. Despite high input prices during the period of experimentation, the machine learning approach-based recommendations demonstrated higher net profit margins in the FST zone, suggesting cost-effectiveness in this zone. These findings indicate that site-specific fertilizer recommendations are more efficient than blanket recommendations and that machine learning approaches offer a promising and innovative approach for generating cost-effective, site-specific fertilizer recommendations in tropical climates. • ML and QUEFTS approaches provided site-specific fertilizer recommendations. • ML and QUEFTS outperformed conventional fertilizer recommendation approaches. • CFDR and UCFDR were constrained by generalized, non-site-specific recommendations. • Machine learning supports sustainable fertilizer use.

As pharmaceutical development moves from early-stage in vitro experimentation to later in vivo and subsequent clinical trials, data and knowledge are acquired across multiple time and length scales, from the subcellular to whole patient cohort scale. Realizing the potential of this data for informing decision making in pharmaceutical development requires the individual and combined application of machine learning (ML) and mechanistic multiscale mathematical modeling approaches. Here we outline how these two approaches, both individually and in tandem, can be applied at different stages of the drug discovery and development pipeline to inform decision making compound development. The importance of discerning between knowledge and data are highlighted in informing the initial use of ML or mechanistic quantitative systems pharmacology (QSP) models. We discuss the application of sensitivity and structural identifiability analyses of QSP models in informing future experimental studies to which ML may be applied, as well as how ML approaches can be used to inform mechanistic model development. Relevant literature studies are highlighted and we close by discussing caveats regarding the application of each approach in an age of constant data acquisition. SIGNIFICANCE STATEMENT: We consider when best to apply machine learning (ML) and mechanistic quantitative systems pharmacology (QSP) approaches in the context of the drug discovery and development pipeline. We discuss the importance of prior knowledge and data available for the system of interest and how this informs the individual and combined application of ML and QSP approaches at each stage of the pipeline.