Utility Of Machine Learning Algorithms Research Articles

Machine Learning Approaches for Stroke Risk Prediction: Findings from the Suita Study.

Stroke constitutes a significant public health concern due to its impact on mortality and morbidity. This study investigates the utility of machine learning algorithms in predicting stroke and identifying key risk factors using data from the Suita study, comprising 7389 participants and 53 variables. Initially, unsupervised k-prototype clustering categorized participants into risk clusters, while five supervised models including Logistic Regression (LR), Random Forest (RF), Support Vector Machine (SVM), Extreme Gradient Boosting (XGBoost), and Light Gradient Boosted Machine (LightGBM) were employed to predict stroke outcomes. Stroke incidence disparities among identified risk clusters using the unsupervised k-prototype clustering method are substantial, according to the findings. Supervised learning, particularly RF, was a preferable option because of the higher levels of performance metrics. The Shapley Additive Explanations (SHAP) method identified age, systolic blood pressure, hypertension, estimated glomerular filtration rate, metabolic syndrome, and blood glucose level as key predictors of stroke, aligning with findings from the unsupervised clustering approach in high-risk groups. Additionally, previously unidentified risk factors such as elbow joint thickness, fructosamine, hemoglobin, and calcium level demonstrate potential for stroke prediction. In conclusion, machine learning facilitated accurate stroke risk predictions and highlighted potential biomarkers, offering a data-driven framework for risk assessment and biomarker discovery.

Evaluative Comparison of Machine Learning Algorithms for Precision Diagnosis in Breast Cancer

Breast cancer remains a prominent issue in worldwide public health, exhibiting a gender disparity that primarily impacts women. This study systematically evaluates the diagnostic capabilities of various machine learning algorithms in predicting breast cancer recurrences. Utilising a dataset of 569 data points, the algorithms scrutinised include Artificial Neural Networks (ANN), Support Vector Machines (SVM), Decision Trees (DT), Random Forests (RF), XGBoost (XGB), Logistic Regression (LR), and K-Nearest Neighbours (KNN). Principal Component Analysis (PCA) was applied and employed with the algorithmic evaluation for selecting features and reducing dimensionality. The study utilised multiple evaluative metrics, focusing on Receiver Operating Characteristic (ROC) curves and Area Under the Curve (AUC) values. The findings suggest that Logistic Regression and Support Vector Machines performed better than the other algorithms. Specifically, Logistic Regression achieved an AUC value of 99.77%, and Support Vector Machines achieved an AUC value of 99.74%. Additionally, these algorithms demonstrated an accuracy rate of 97.37%, precision of 97.62%, recall of 95.35%, F1 score of 96.47%, and Cohen's Kappa coefficient of 94.37%, consistent. The study suggests potential avenues for further investigation into the utility of machine learning algorithms and dimensionality reduction techniques in diagnosing breast cancer recurrence. These preliminary findings have the potential to make a valuable contribution to the current discourse around the use of machine learning technologies within healthcare environments

Predicting Personal Exposure to PM2.5 Using Different Determinants and Machine Learning Algorithms in Two Megacities, China

The primary aim of this study is to explore the utility of machine learning algorithms for predicting personal PM2.5 exposures of elderly participants and to evaluate the effect of individual variables on model performance. Personal PM2.5 was measured on five consecutive days across seasons in 66 retired adults in Beijing (BJ) and Nanjing (NJ), China. The potential predictors were extracted from routine monitoring data (ambient PM2.5 concentrations and meteorological factors), basic questionnaires (personal and household characteristics), and time-activity diary (TAD). Prediction models were developed based on either traditional multiple linear regression (MLR) or five advanced machine learning methods. Our results revealed that personal PM2.5 exposures were well predicted by both MLR and machine learning models with predictors extracted from routine monitoring data, which was indicated by the high nested cross-validation (CV) R2 ranging from 0.76 to 0.88. The addition of predictors from either the questionnaire or TAD did not improve predictive accuracy for all algorithms. The ambient PM2.5 concentrations were the most important predictor. Overall, the random forest, support vector machine, and extreme gradient boosting algorithms outperformed the reference MLR method. Compared with the traditional MLR approach, the CV R2 of the RF model increased up to 7% (from 0.82±0.13 to 0.88±0.10), while the RMSE reduced up to 18% (from 19.8±5.4 to 16.3±4.5) in BJ.

Design of oscillatory neural networks by machine learning.

We demonstrate the utility of machine learning algorithms for the design of oscillatory neural networks (ONNs). After constructing a circuit model of the oscillators in a machine-learning-enabled simulator and performing Backpropagation through time (BPTT) for determining the coupling resistances between the ring oscillators, we demonstrate the design of associative memories and multi-layered ONN classifiers. The machine-learning-designed ONNs show superior performance compared to other design methods (such as Hebbian learning), and they also enable significant simplifications in the circuit topology. We also demonstrate the design of multi-layered ONNs that show superior performance compared to single-layer ones. We argue that machine learning can be a valuable tool to unlock the true computing potential of ONNs hardware.

Fall risk classification with posturographic parameters in community-dwelling older adults: a machine learning and explainable artificial intelligence approach

BackgroundComputerized posturography obtained in standing conditions has been applied to classify fall risk for older adults or disease groups. Combining machine learning (ML) approaches is superior to traditional regression analysis for its ability to handle complex data regarding its characteristics of being high-dimensional, non-linear, and highly correlated. The study goal was to use ML algorithms to classify fall risks in community-dwelling older adults with the aid of an explainable artificial intelligence (XAI) approach to increase interpretability.MethodsA total of 215 participants were included for analysis. The input information included personal metrics and posturographic parameters obtained from a tracker-based posturography of four standing postures. Two classification criteria were used: with a previous history of falls and the timed-up-and-go (TUG) test. We used three meta-heuristic methods for feature selection to handle the large numbers of parameters and improve efficacy, and the SHapley Additive exPlanations (SHAP) method was used to display the weights of the selected features on the model.ResultsThe results showed that posturographic parameters could classify the participants with TUG scores higher or lower than 10 s but were less effective in classifying fall risk according to previous fall history. Feature selections improved the accuracy with the TUG as the classification label, and the Slime Mould Algorithm had the best performance (accuracy: 0.72 to 0.77, area under the curve: 0.80 to 0.90). In contrast, feature selection did not improve the model performance significantly with the previous fall history as a classification label. The SHAP values also helped to display the importance of different features in the model.ConclusionPosturographic parameters in standing can be used to classify fall risks with high accuracy based on the TUG scores in community-dwelling older adults. Using feature selection improves the model’s performance. The results highlight the potential utility of ML algorithms and XAI to provide guidance for developing more robust and accurate fall classification models.Trial registration Not applicable

Development of a Novel Methotrexate-Related Neurotoxicity Risk Score in Pediatric Acute Leukemia: A Report from the Reducing Ethnic Disparities in Acute Leukemia (REDIAL) Consortium

Introduction: Methotrexate (MTX) chemotherapy is a critical component of contemporary pediatric acute lymphoblastic leukemia (ALL) treatment regimens. However, intrathecal (IT) and intravenous (IV) MTX can result in dose-limiting acute neurotoxicity, which has been associated with an increased risk of ALL relapse. Emerging data suggest the likelihood of MTX neurotoxicity is elevated in Latino patients and those diagnosed at older age or treated with high-dose MTX (> 1g/m2); however, there are no established methods for identifying those at greatest risk. Therefore, we used machine learning algorithms to develop a neurotoxicity risk prediction model in a diverse, multi-ethnic cohort of pediatric patients with ALL. Methods: The Reducing Ethnic Disparities in Acute Leukemia (REDIAL) Consortium enrolls patients diagnosed with ALL from six participating treatment centers in the Southwestern U.S. This interim analysis included pediatric patients (age <20 years) diagnosed and treated for ALL at Texas Children's Hospital (2005-2019). Individuals diagnosed with infant leukemia (<1 year of age) and/or with preexisting neurologic disease were excluded. We retrospectively reviewed medical records to identify clinical, sociodemographic, and Common Terminology Criteria for Adverse Events (CTCAE) grading of toxicities such as transaminitis and hyperbilirubinemia. Address information at the time of diagnosis was geocoded and aligned to the American Community Survey at the census-tract level to define residential social determinants of health (SDOH). Cases of MTX neurotoxicity were identified by manual review of records for any patient who underwent brain MRI imaging during ALL therapy. Cases of acute MTX neurotoxicity were defined following Ponte di Legno Delphi Consensus definitions as neurologic episodes (e.g., seizure, stroke-like symptoms, altered mental status) occurring within 21 days of IV or IT MTX with no other identifiable underlying cause. Demographic and clinical factors were compared between cases of acute MTX-related neurotoxicity and controls using logistic regression models to estimate odds ratios (OR) and 95% confidence intervals (CI). The dataset was randomly split with 80% of observations used in the training stage and 20% reserved for testing. Random forest algorithms with boosting and down sampling were grown using 5-repeat, 10-fold cross validation to optimize tuning parameters. Model performance was evaluated using test and train error rate, area under the curve of the receiver operating characteristic (AUC-ROC), sensitivity, and specificity. Results: A total of 770 patients were eligible and met inclusion criteria. Patients were a mean age of 7.0 years at diagnosis, 54% male, 55% Latino and 45% treated with high-risk protocols. Acute MTX neurotoxicity developed in 134 (17.4%) of patients. In logistic regression models, neurotoxicity odds increased with older age at diagnosis (OR = 1.20, 95% CI: 1.15-1.26), Latino ethnicity (OR = 2.14, 95% CI: 1.38-3.38), treatment on high-risk protocols (OR=4.32, 95% CI: 2.75-6.99), obesity at diagnosis (vs normal weight, OR = 2.54, 95% CI: 1.51-4.22), and CTCAE grade 3 or higher transaminitis (OR = 2.02, 95% CI: 1.03-4.47) or hyperbilirubinemia (OR = 4.71, 95% CI: 1.21-18.41) during induction therapy. Overall, the random forest machine learning algorithm resulted in an AUC-ROC of 0.79 with an error rate of 0.26 in both the training and test sets. The overall sensitivity was 0.71, with a specificity of 0.67. Recognizing ethnic disparities in MTX neurotoxicity may exist, random forest models were generated stratifying on ethnicity (Figure 1), which yielded slightly better performance in non-Latino patients (AUC-ROC = 0.77) than Latino patients (AUC-ROC = 0.73). Conclusions: This interim analysis of data from the REDIAL Consortium demonstrates the potential utility of machine learning algorithms to develop a novel risk prediction model for acute MTX-related neurotoxicity. Efforts to expand this work within the larger REDIAL cohort (n>2,000) and incorporate inherited genetic data are ongoing. Ultimately, this work may inform efforts to preemptively risk-stratify patients and deliver targeted interventions to vulnerable individuals.

Identication and validation of cell senescence biomarkers in idiopathic pulmonary hypertension via integrated transcriptome analyses and machine learning

BackgroundIdiopathic pulmonary hypertension (IPAH) is a rare and severe disease that affects the pulmonary vasculature. As the diagnosis of IPAH requires invasive right heart catheterization surgery, early detection of this condition is notoriously challenging. Therefore, it is of utmost importance to investigate biomarkers present in peripheral blood that could aid physicians in the early identification and management of IPAH. MethodWe speculate that cellular senescence may be involved in the occurrence and development of IPAH through various pathways. In this study, we utilized integrated transcriptome analyses and machine learning-based approach to develop a diagnostic model for IPAH cell senescence. To select genetic features, we employed two machine learning algorithms: the Least Absolute Shrinkage and Selection Operator (LASSO) and Random Forest (RF). Additionally, we validated our findings through both external data sets and qRT-PCR experiments. ResultsThe resulting diagnostic nomogram was able to identify five important biomarkers that can aid in the diagnosis of IPAH, including TNFRSF1B, CCL16, GCLM, IL15, and SOD1. These genes are primarily associated with the immune system, as well as with cell senescence and apoptosis. ConclusionOur study demonstrates the utility of machine learning algorithms in making accurate diagnoses of IPAH, providing clinicians with a more directed approach to the diagnosis and treatment of this disease.

Utility of Machine Learning Algorithms for Opportunistic Bone Density Screening Using Conventional Radiographs

Utility of Machine Learning Algorithms for Opportunistic Bone Density Screening Using Conventional Radiographs

Utility of Machine Learning Algorithms in Predicting Preoperative Lymph Node Metastasis in Patients With Rectal Cancer Based on Three-Dimensional Endorectal Ultrasound and Clinical and Laboratory Data.

We aimed to investigate the value of a machine learning (ML) algorithm in the preoperative prediction of lymph node metastasis in patients with rectal cancer. Based on the histopathological results, 126 rectal cancer patients were divided into two groups: lymph node metastasis-positive and metastasis-negative groups. We collected clinical and laboratory data, three-dimensional endorectal ultrasound (3D-ERUS) findings, and parameters of the tumor for between-group comparisons. We constructed a clinical prediction model based on the ML algorithm, which demonstrated the best diagnostic performance. Finally, we analyzed the diagnostic results and processes of the ML model. Between the two groups, there were significant differences in serum carcinoembryonic antigen (CEA) levels, tumor length, tumor breadth, circumferential extent of the tumor, resistance index (RI), and ultrasound T-stage (P < 0.05). The extreme gradient boosting (XGBoost) model had the best comprehensive diagnostic performance for predicting lymph node metastasis in patients with rectal cancer. Compared with experienced radiologists, the XGBoost model showed significantly higher diagnostic value in predicting lymph node metastasis; the area under curve (AUC) value of the receiver operating characteristic (ROC) curveof the XGBoost model and experienced radiologists was 0.82 and 0.60, respectively. Preoperative predictive utility in lymph node metastasis was demonstrated by the XGBoost model based on the 3D-ERUS finding and related clinical information. This could be useful in guiding clinical decisions on the selection of different treatment strategies.

An evaluation of machine learning algorithms coupled to an electronic olfactory system: a study of the mint case

The aim of this investigatation is to compare the utility of machine learning algorithms in distinguishing between untreated and processed mint beside in predicting the spray day of the insecticide. Within seven days, mint treated samples with the malathion insecticide are collected, and their aromas are Studied using a laboratory-manufactured sensor array system based on commercial metallic semiconductor (MOS) gas sensors. To distinguish the mint type, some results of machine learning algorithms were compared to know the decision trees (DT), Naive Bayes, support vector machines (SVM), and ensemble classifier. Furthermore, to predict the treatment day support vector machines regression (SVMR) and partial least squares regression (PLSR) were compared. Regarding the best results, in the discrimination case, a success rate of 92.9% was achieved by the ensemble classifier while in the prediction case, a correlation coefficient of R=0.82 was reached by the SVMR. Good results are achieved if the right gas sensor array system is designed and realized coupled with a good choice of the appropriate machine learning algorithms.

The utility of machine learning algorithms for the prediction of patient-reported outcome measures following primary hip and knee total joint arthroplasty.

Patient-reported outcome measures (PROMs) are increasingly used as quality benchmark in total hip and knee arthroplasty (THA; TKA) due to bundled payment systems that aim to provide a patient-centered, value-based treatment approach. However, there is a paucity of predictive tools for postoperative PROMs. Therefore, this study aimed to develop and validate machine learning models for the prediction of numerous patient-reported outcome measures following primary hip and knee total joint arthroplasty. A total of 4526 consecutive patients (2137 THA; 2389 TKA) who underwent primary hip and knee total joint arthroplasty and completed both pre- and postoperative PROM scores was evaluated in this study. The following PROM scores were included for analysis: HOOS-PS, KOOS-PS, Physical Function SF10A, PROMIS SF Physical and PROMIS SF Mental. Patient charts were manually reviewed to identify patient demographics and surgical variables associated with postoperative PROM scores. Four machine learning algorithms were developed to predict postoperative PROMs following hip and knee total joint arthroplasty. Model assessment was performed through discrimination, calibration and decision curve analysis. The factors most significantly associated with the prediction of postoperative PROMs include preoperative PROM scores, Charlson Comorbidity Index, American Society of Anaesthesiology score, insurance status, age, length of hospital stay, body mass index and ethnicity. The four machine learning models all achieved excellent performance across discrimination (AUC > 0.83), calibration and decision curve analysis. This study developed machine learning models for the prediction of patient-reported outcome measures at 1-year following primary hip and knee total joint arthroplasty. The study findings show excellent performance on discrimination, calibration and decision curve analysis for all four machine learning models, highlighting the potential of these models in clinical practice to inform patients prior to surgery regarding their expectations of postoperative functional outcomes following primary hip and knee total joint arthroplasty. Level III, case control retrospective analysis.

Accuracy of Machine Learning Using the Montreal Cognitive Assessment for the Diagnosis of Cognitive Impairment in Parkinson’s Disease

Objective The Montreal Cognitive Assessment (MoCA) is recommended for assessing general cognition in Parkinson’s disease (PD). Several cutoffs of MoCA scores for diagnosing PD with cognitive impairment (PD-CI) have been proposed, with varying sensitivity and specificity. This study investigated the utility of machine learning algorithms using MoCA cognitive domain scores for improving diagnostic performance for PD-CI.Methods In total, 2,069 MoCA results were obtained from 397 patients with PD enrolled in the Parkinson’s Progression Markers Initiative database with a diagnosis of cognitive status based on comprehensive neuropsychological assessments. Using the same number of MoCA results randomly sampled from patients with PD with normal cognition or PD-CI, discriminant validity was compared between machine learning (logistic regression, support vector machine, or random forest) with domain scores and a cutoff method.Results Based on cognitive status classification using a dataset that permitted sampling of MoCA results from the same individual (n = 221 per group), no difference was observed in accuracy between the cutoff value method (0.74 ± 0.03) and machine learning (0.78 ± 0.03). Using a more stringent dataset that excluded MoCA results (n = 101 per group) from the same patients, the accuracy of the cutoff method (0.66 ± 0.05), but not that of machine learning (0.74 ± 0.07), was significantly reduced. Inclusion of cognitive complaints as an additional variable improved the accuracy of classification using the machine learning method (0.87–0.89).Conclusion Machine learning analysis using MoCA domain scores is a valid method for screening cognitive impairment in PD.

The Utility of Machine Learning Algorithms for the Prediction of Early Revision Surgery After Primary Total Hip Arthroplasty.

Revision total hip arthroplasty (THA) is associated with increased morbidity, mortality, and healthcare costs due to a technically more demanding surgical procedure when compared with primary THA. Therefore, a better understanding of risk factors for early revision THA is essential to develop strategies for mitigating the risk of patients undergoing early revision. This study aimed to develop and validate novel machine learning (ML) models for the prediction of early revision after primary THA. A total of 7,397 consecutive patients who underwent primary THA were evaluated, including 566 patients (6.6%) with confirmed early revision THA (<2 years from index THA). Electronic patient records were manually reviewed to identify patient demographics, implant characteristics, and surgical variables that may be associated with early revision THA. Six ML algorithms were developed to predict early revision THA, and these models were assessed by discrimination, calibration, and decision curve analysis. The strongest predictors for early revision after primary THA were Charlson Comorbidity Index, body mass index >35 kg/m2, and depression. The six ML models all achieved excellent performance across discrimination (area under the curve >0.80), calibration, and decision curve analysis. This study developed ML models for the prediction of early revision surgery for patients after primary THA. The study findings show excellent performance on discrimination, calibration, and decision curve analysis for all six candidate models, highlighting the potential of these models to assist in clinical practice patient-specific preoperative quantification of increased risk of early revision THA.

Predicting Cardiovascular Disease in the MASHAD Cohort Study: The Utility of Machine Learning Algorithms

Predicting Cardiovascular Disease in the MASHAD Cohort Study: The Utility of Machine Learning Algorithms

Utility of machine learning algorithms in degenerative cervical and lumbar spine disease: a systematic review

Machine learning is a rapidly evolving field that offers physicians an innovative and comprehensive mechanism to examine various aspects of patient data. Cervical and lumbar degenerative spine disorders are commonly age-related disease processes that can utilize machine learning to improve patient outcomes with careful patient selection and intervention. The aim of this study is to examine the current applications of machine learning in cervical and lumbar degenerative spine disease. A systematic review was conducted using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. A search of PubMed, Embase, Medline, and Cochrane was conducted through May 31st, 2020, using the following terms: "artificial intelligence" OR "machine learning" AND "neurosurgery" AND "spine." Studies were included if original research on machine learning was utilized in patient care for degenerative spine disease, including radiographic machine learning applications. Studies focusing on robotic applications in neurosurgery, navigation, or stereotactic radiosurgery were excluded. The literature search identified 296 papers, with 35 articles meeting inclusion criteria. There were nine studies involving cervical degenerative spine disease and 26 studies on lumbar degenerative spine disease. The majority of studies for both cervical and lumbar spines utilized machine learning for the prediction of postoperative outcomes, with 5 (55.6%) and 15 (61.5%) studies, respectively. Machine learning applications focusing on degenerative lumbar spine greatly outnumber the current volume of cervical spine studies. The current research in lumbar spine also demonstrates more advanced clinical applications of radiographic, diagnostic, and predictive machine learning models.

Comparison of 16S and whole genome dog microbiomes using machine learning

BackgroundRecent advances in sequencing technologies have driven studies identifying the microbiome as a key regulator of overall health and disease in the host. Both 16S amplicon and whole genome shotgun sequencing technologies are currently being used to investigate this relationship, however, the choice of sequencing technology often depends on the nature and experimental design of the study. In principle, the outputs rendered by analysis pipelines are heavily influenced by the data used as input; it is then important to consider that the genomic features produced by different sequencing technologies may emphasize different results.ResultsIn this work, we use public 16S amplicon and whole genome shotgun sequencing (WGS) data from the same dogs to investigate the relationship between sequencing technology and the captured gut metagenomic landscape in dogs. In our analyses, we compare the taxonomic resolution at the species and phyla levels and benchmark 12 classification algorithms in their ability to accurately identify host phenotype using only taxonomic relative abundance information from 16S and WGS datasets with identical study designs. Our best performing model, a random forest trained by the WGS dataset, identified a species (Bacteroides coprocola) that predominantly contributes to the abundance of leuB, a gene involved in branched chain amino acid biosynthesis; a risk factor for glucose intolerance, insulin resistance, and type 2 diabetes. This trend was not conserved when we trained the model using 16S sequencing profiles from the same dogs.ConclusionsOur results indicate that WGS sequencing of dog microbiomes detects a greater taxonomic diversity than 16S sequencing of the same dogs at the species level and with respect to four gut-enriched phyla levels. This difference in detection does not significantly impact the performance metrics of machine learning algorithms after down-sampling. Although the important features extracted from our best performing model are not conserved between the two technologies, the important features extracted from either instance indicate the utility of machine learning algorithms in identifying biologically meaningful relationships between the host and microbiome community members. In conclusion, this work provides the first systematic machine learning comparison of dog 16S and WGS microbiomes derived from identical study designs.

P19. Predicting readmission following fusion for scoliosis in pediatric patients: A machine-learning approach

<h3>BACKGROUND CONTEXT</h3> Spine fusion surgery is a common treatment for scoliosis in pediatric patients. Hospital readmission within 30-days of surgery is a costly event. While studies have been undertaken to predict readmission within 30-days for orthopedic procedures, such as total shoulder arthroplasty and adult spine fusion surgery, no research has been conducted on the utility of machine learning algorithms to predict postoperative complications for pediatric patients undergoing spinal procedures. <h3>PURPOSE</h3> The study presented here analyzes the predictive capacity of a set of machine learning algorithms to preoperatively predict 30-day readmission after posterior spine fusion surgery for pediatric patients with scoliosis. <h3>STUDY DESIGN/SETTING</h3> This study was an analysis of NSQIP pediatric data. <h3>PATIENT SAMPLE</h3> The NSQIP pediatric database was queried between 2012 and 2018 to select patients who had undergone posterior arthrodesis surgery for scoliosis treatment. <h3>OUTCOME MEASURES</h3> A 30-day readmission after pediatric posterior arthrodesis surgery. <h3>METHODS</h3> The NSQIP pediatric database was queried to select patients who had undergone posterior arthrodesis surgery for scoliosis treatment. Predictive variables of interest were quantitative variables such as height, weight, and age, as well as categorical variables such as race and the presence or absence of comorbidities such as asthma, lung disease, ASA Class, cardiac risk factors, cognitive function, seizure presence, cerebral palsy, ACQ abnormality, and neuromuscular disorder. Patients who had missing data for one or more variables of interest were excluded from the analysis. Python's Sci-Kit Learn package was utilized to run five machine learning algorithms: logistic regression (LR), decision tree (DT), random forest (RF), gradient boosting (GB) and neural network (NN). Patients were randomly split into two groups, where 70% of patients were used to train the neural network, while the remaining 30% were used to test the validity of the neural network. The area under the curve (AUC) and prediction accuracy were used to determine the capacity of the algorithm in predicting 30-day readmission. A multivariable logistic regression was performed in R to identify risk factors for readmission. The significance value was set at 0.05. <h3>RESULTS</h3> Initially, 24,271 patients met the inclusion criteria. However, after excluding patients who had missing variables, 17,873 patients were analyzed, 825 of which were readmitted within 30 days of surgery (4.62%). The machine-learning algorithms exhibited AUC values between 0.513 and 0.736, with the GB algorithm performing the best and the DT algorithm performing the worst, and prediction accuracies between 92.8% (DTC) and 96.5% (GB). The logistic regression identified obesity (Odds Ratio (OR): 2.51, 95% Confidence Interval (CI):2.04-3.10, p-value<0.0001), lung disease (OR: 1.32, 95% CI:1.03-1.68, p-value<0.0001), elevated ASA class (OR: 3.17, 95% CI:2.06-4.87, p-value<0.0001), cognitive impairment (OR: 1.79, 95% CI:1.46-2.19, p-value<0.0001), seizure history (OR: 1.32, 95% CI:1.06-1.66, p-value = 0.015), ACQ abnormality (OR: 1.33, 95% CI:1.12-1.59, p-value = 0.001), and neuromuscular disorder (OR: 1.40, 95% CI:1.17-1.68, p-value = 0.0003) as risk factors for 30-day readmission. <h3>CONCLUSIONS</h3> Machine learning algorithms are potentially valuable tools for predicting readmission after pediatric spine fusion surgery. These algorithms may assist clinicians and patients in determining the best treatment care plans to optimize outcomes and minimize re-admission risk. Examination of the external validity of these paradigms on other state, regional, and national databases to determine the applicability and accuracy of the algorithms may assist in someday bringing these predictive tools to clinical utilization. <h3>FDA DEVICE/DRUG STATUS</h3> This abstract does not discuss or include any applicable devices or drugs.

Implementation of a Machine-Learning Algorithm in the Electronic Health Record for Targeted Screening for Familial Hypercholesterolemia: A Quality Improvement Study.

Implementation of a Machine-Learning Algorithm in the Electronic Health Record for Targeted Screening for Familial Hypercholesterolemia: A Quality Improvement Study.

Comparative evaluation of intracranial oligodendroglioma and astrocytoma of similar grades using conventional and T1-weighted DCE-MRI.

This retrospective study was performed on a 3T MRI to determine the unique conventional MR imaging and T1-weighted DCE-MRI features of oligodendroglioma and astrocytoma and investigate the utility of machine learning algorithms in their differentiation. Histologically confirmed, 81 treatment-naïve patients were classified into two groups as per WHO 2016 classification: oligodendroglioma (n = 16; grade II, n = 25; grade III) and astrocytoma (n = 10; grade II, n = 30; grade III). The differences in tumor morphology characteristics were evaluated using Z-test. T1-weighted DCE-MRI data were analyzed using an in-house built MATLAB program. The mean 90th percentile of relative cerebral blood flow, relative cerebral blood volume corrected, volume transfer rate from plasma to extracellular extravascular space, and extravascular extracellular space volume values were evaluated using independent Student's t test. Support vector machine (SVM) classifier was constructed to differentiate two groups across grade II, grade III, and grade II+III based on statistically significant features. Z-test signified only calcification among conventional MR features to categorize oligodendroglioma and astrocytoma across grade III and grade II+III tumors. No statistical significance was found in the perfusion parameters between two groups and its subtypes. SVM trained on calcification also provided moderate accuracy to differentiate oligodendroglioma from astrocytoma. We conclude that conventional MR features except calcification and the quantitative T1-weighted DCE-MRI parameters fail to discriminate between oligodendroglioma and astrocytoma. The SVM could not further aid in their differentiation. The study also suggests that the presence of more than 50% T2-FLAIR mismatch may be considered as a more conclusive sign for differentiation of IDH mutant astrocytoma.

The Utility of Machine Learning Algorithms in Predicting In-hospital Mortality Following Traumatic Brain Injuries

Zreik, Jad BS; Goyal, Anshit MBBS; Bhandarkar, Archis R; Atkinson, John L.D MD; Burns, Terry C MD, PhD; Bydon, Mohamad MD Author Information