Machine Learning Algorithms Logistic Regression Research Articles

The Comparison of Accuracy on Classification Climate Change Data with Logistic Regression

Machine learning methods can be used to generate climate change models. The goal of this study is to use logistic regression machine learning algorithms to classify data on greenhouse gas emissions. The data used is climate change data of several countries obtained from The World Bank, with total greenhouse gas emissions as the response variable and 61 other attributes as explanatory variables. This data is preprocessed using min-max normalization to handle unbalanced ranges, and then the data is split into 70% training data and 30% testing data. Based on the logistic regression modeling, it was discovered that the data from the min-max transformation resulted in better modeling than the data modeling without the transformation process. The accuracy, precision, sensitivity, and specificity of the transformation are 87.60%, 87.76%, 87.04%, and 88.14%, respectively

Predicting In-Hospital Mortality After Acute Myeloid Leukemia Therapy: Through Supervised Machine Learning Algorithms

Despite careful patient selection, induction chemotherapy for acute myeloid leukemia (AML) is associated with a considerable risk for treatment-related mortality (5%-20%). We evaluated machine learning (ML) algorithms trained using factors available at the time of admission for AML therapy to predict death during the hospitalization. We included AML discharges with age > 17 years who received inpatient chemotherapy from State Inpatient Database from Arizona, Florida, New York, Maryland, Washington, and New Jersey for years 2008-2014. The primary objective was to predict inpatient mortality in patients undergoing chemotherapy using covariates present before initiation of chemotherapy. ML algorithms logistic regression (LR), decision tree, and random forest were compared. 29,613 hospitalizations for patients with AML were included in the analysis each with 4,177 features. The median age was 58.9 (18-101) years, 13,689 (53.7%) were male, and 20,203 (69%) were White. The mean time from admission to chemotherapy was 3 days (95% CI, 2.9 to 3.1), and 2,682 (9.1%) died during the hospitalization. Both LR and random forest models achieved an area under the curve (AUC) score of 0.78, whereas decision tree achieved an AUC of 0.70. The baseline LR model with age yielded an AUC of 0.62. To clinically balance and minimize false positives, we selected a decision threshold of 0.7 and at this threshold, 51 of our test set of 5,923 could have potentially averted treatment-related mortality. Using readily accessible variables, inpatient mortality of patients on track for chemotherapy to treat AML can be predicted through ML algorithms. The model also predicted inpatient mortality when tested on different data representations and paves the way for future research.

Down-Regulation of lncRNA MBNL1-AS1 Promotes Tumor Stem Cell-like Characteristics and Prostate Cancer Progression through miR-221-3p/CDKN1B/C-myc Axis

The recurrence, progression, and drug resistance of prostate cancer (PC) is closely related to the cancer stem cells (CSCs). Therefore, it is necessary to find the key regulators of prostate cancer stem cells (PCSCs). Here, we analyzed the results of a single-class logistic regression machine learning algorithm (OCLR) to identify the PCSC-associated lncRNA MBNL1-AS1. The effects of MBNL1-AS1 on the stemness of CSCs was assessed using qPCR, western blot and sphere-forming assays. The role of MBNL1-AS1 in mediating the proliferation and invasion of the PC cell lines was examined using Transwell, wounding-healing, CCK-8, EdU and animal assays. Dual-luciferase and ChIRP assays were used to examine the molecular mechanism of MBNL1-AS1 in PCSCs. MBNL1-AS1 was shown to be negatively correlated with stemness index (mRNAsi), and even prognosis, tumor progression, recurrence, and drug resistance in PC patients. The knockdown of MBNL1-AS1 significantly affected the stemness of the PC cells, and subsequently their invasive and proliferative abilities. Molecular mechanism studies suggested that MBNL1-AS1 regulates CDKN1B through competitive binding to miR-221-3p, which led to the inhibition of the Wnt signaling pathway to affect PCSCs. In conclusion, our study identified MBNL1-AS1 as a key regulator of PCSCs and examined its mechanism of action in the malignant progression of PC.

Machine learning outperforms traditional logistic regression and offers new possibilities for cardiovascular risk prediction: A study involving 143,043 Chinese patients with hypertension.

Identifying people at risk of cardiovascular diseases (CVD) is a cornerstone of preventive cardiology. We developed machine learning (ML) algorithms and investigated their performance in predicting patients' current CVD risk (coronary heart disease and stroke in this study). We compared traditional logistic regression (LR) with five ML algorithms LR with Elastic-Net, Random Forest (RF), XGBoost (XGB), Support Vector Machine, Deep Learning, and an Ensemble model averaging predictions from RF, XGB, and Deep Learning for CVD risk prediction using pre-existing patient-level data from a multi-center, cross-sectional study (the Microalbuminuria Screening in Hypertensive Patients Project initiated by the China International Exchange and Promotive Association for Medical and Healthcare) that enrolled 143,043 patients with hypertension from 600 tertiary, secondary, or community hospitals. Each of the five ML algorithms incorporated 18 variables, such as demographics, examinations, comorbidities, and treatment regimens, and were trained and evaluated using 5-fold cross-validation. Predictive accuracy was assessed by the area under the receiver operating curve (AUROC). Patients' mean age was 62 ± 12 years and 57% were men. Advanced ML algorithms outperformed the traditional LR model. Particularly, the Ensemble model had superior discrimination with an AUROC of 0.760 than LR (AUC = 0.737) and other tested models. We establishes an Ensemble model that shows better performance in predicting patients' current CVD risk using routine information compared to the traditional LR model. ML can help physicians design follow-up plans with more accurate results, offering new possibilities for short-term risk prediction and early detection. Further, ML models can be trained with longitudinal data and used to predict long-term CVD risks, thereby informing CVD prevention.

A Rough Set Approach to Dimensionality Reduction for Performance Enhancement in Machine Learning

Machine learning uses complex mathematical algorithms to turn data set into a model for a problem domain. Analysing high dimensional data in their raw form usually causes computational overhead because the higher the size of the data, the higher the time it takes to process it. Therefore, there is a need for a more robust dimensionality reduction approach, among other existing methods, for feature projection (extraction) and selection from data set, which can be passed to a machine learning algorithm for optimal performance. This paper presents a generic mathematical approach for transforming data from a high dimensional space to low dimensional space in such a manner that the intrinsic dimension of the original data is preserved using the concept of indiscernibility, reducts, and the core of the rough set theory. The flue detection dataset available on the Kaggle website was used in this research for demonstration purposes. The original and reduced datasets were tested using a logistic regression machine learning algorithm yielding the same accuracy of 97% with a training time of 25 min and 11 min respectively.

Predicting responders to prone positioning in mechanically ventilated patients with COVID-19 using machine learning

BackgroundFor mechanically ventilated critically ill COVID-19 patients, prone positioning has quickly become an important treatment strategy, however, prone positioning is labor intensive and comes with potential adverse effects. Therefore, identifying which critically ill intubated COVID-19 patients will benefit may help allocate labor resources.MethodsFrom the multi-center Dutch Data Warehouse of COVID-19 ICU patients from 25 hospitals, we selected all 3619 episodes of prone positioning in 1142 invasively mechanically ventilated patients. We excluded episodes longer than 24 h. Berlin ARDS criteria were not formally documented. We used supervised machine learning algorithms Logistic Regression, Random Forest, Naive Bayes, K-Nearest Neighbors, Support Vector Machine and Extreme Gradient Boosting on readily available and clinically relevant features to predict success of prone positioning after 4 h (window of 1 to 7 h) based on various possible outcomes. These outcomes were defined as improvements of at least 10% in PaO2/FiO2 ratio, ventilatory ratio, respiratory system compliance, or mechanical power. Separate models were created for each of these outcomes. Re-supination within 4 h after pronation was labeled as failure. We also developed models using a 20 mmHg improvement cut-off for PaO2/FiO2 ratio and using a combined outcome parameter. For all models, we evaluated feature importance expressed as contribution to predictive performance based on their relative ranking.ResultsThe median duration of prone episodes was 17 h (11–20, median and IQR, N = 2632). Despite extensive modeling using a plethora of machine learning techniques and a large number of potentially clinically relevant features, discrimination between responders and non-responders remained poor with an area under the receiver operator characteristic curve of 0.62 for PaO2/FiO2 ratio using Logistic Regression, Random Forest and XGBoost. Feature importance was inconsistent between models for different outcomes. Notably, not even being a previous responder to prone positioning, or PEEP-levels before prone positioning, provided any meaningful contribution to predicting a successful next proning episode.ConclusionsIn mechanically ventilated COVID-19 patients, predicting the success of prone positioning using clinically relevant and readily available parameters from electronic health records is currently not feasible. Given the current evidence base, a liberal approach to proning in all patients with severe COVID-19 ARDS is therefore justified and in particular regardless of previous results of proning.

Differences in brain connectivity of meditators during assessing neurocognition via gamified experimental logic task: A machine learning approach.

Meditation practices increase attention, memory, and self-awareness. The neuroscientific study of meditation has helped gain useful insights into the functional changes in the brain. In this study, we have assessed the performance of meditators with different years of practice while performing an engaging task rather than studying the meditation practice itself. This task helps assess many neural processes simultaneously and represents task performance in presence of multiple audio-visual distractors as in a real-life scenario. The long-term practice of meditation could bring neuroplastic changes in the way cognitive processing is carried out. It could be conscious and effortful in short-term practitioners and relatively unconscious and effortless in long-term practitioners. Our goal is to understand if it is possible to differentiate between long-term and short-term meditators solely based on their cognitive processing. A group of proficient Rajayoga meditators from the Brahma Kumaris were recruited based on their meditation experience-Long-Term Practitioners (n = 12, mean 13,596h) and Short-Term Practitioners (n = 10, mean 1095h). A task-based functional Magnetic Resonance Imaging was acquired while the subjects performed the task. Functional Connectivity Analysis was performed to derive the correlation measures to be used as features for classification. Five supervised Machine Learning algorithms Logistic Regression, Support Vector Machine, Decision Tree, Random Forest, and Gradient Boosted Tree were used for classification. Among all the classifiers Gradient Boosted Tree performed the best with an accuracy of 77% when all the four Functional Connectivity Metrics were used. Connectivity in visual areas, cerebellum, left rostral prefrontal cortex, and middle frontal gyrus was found to be higher in long-term meditators. Such a classification demonstrates that long-term meditation practice brings about neuroplastic changes that influence cognitive processing.

Feasibility of Machine Learning in the Prediction of Short-Term Outcomes Following Anterior Cervical Discectomy and Fusion

Increased emphasis is being placed on efficiency and resource utilization when performing anterior cervical discectomy and fusion (ACDF), and accurate prediction of complications is increasingly important to optimize care. This study aimed to compare predictive models for postoperative complications following ACDF using machine learning (ML) models based on traditional comorbidity indices. In this retrospective case series, the American College of Surgeons National Surgical Quality Improvement Program database was queried between 2011 and 2017 for all elective, primary ACDF cases. Levels of surgery, use of interbody implants, and graft selection were calculated by procedural codes. Six ML algorithms were constructed using available preoperative and intraoperative features. The overall dataset was randomly split into training (80%) and validation (20%) subsets wherein the training subset optimized the model, and the validation subset was evaluated for accuracy. ML models were compared with models constructed from American Society of Anesthesiologists classification and frailty index alone. There were 42,194 ACDF cases eligible for inclusion. Mean age was 47.7 ± 11.6 years, body mass index was 30.4 ± 6.7, and levels of operation were 1.6 ± 0.7. ML algorithms uniformly outperformed comorbidity indices in predicting complications. Logistic regression ML algorithm was the best performing for predicting any adverse event (area under the curve [AUC] 0.73), transfusion (AUC 0.90), surgical site infection (AUC 0.63), and pneumonia (AUC 0.80). Gradient boosting trees ML algorithm was the best performing for predicting extended length of stay (AUC 0.73). ML algorithms modeled the development of postoperative adverse events with superior accuracy to that of comorbidity indices and may guide preoperative clinical decision making before ACDF.

Stemness inhibition by (+)-JQ1 in canine and human mammary cancer cells revealed by machine learning

Stemness is a phenotype associated with cancer initiation and progression, malignancy, and therapeutic resistance, exhibiting particular molecular signatures. Targeting stemness has been proposed as a promising strategy against breast cancer stem cells that can play a key role in breast cancer progression, metastasis, and multiple drug resistance. Here, using a previously published one-class logistic regression machine learning algorithm (OCLR) built on pluripotent stem cells to predict stemness in human cancer samples, we provide the stemness index (mRNAsi) of different canine non-tumor and mammary cancer cells. Then, we confirmed that inhibition of BET proteins by (+)-JQ1 reduces stemness in a high mRNAsi canine cancer cell. Furthermore, using public data, we observed that (+)-JQ1 can also decrease stemness in human triple-negative breast cancer cells. Our work suggests that mRNAsi can be used to estimate stemness in different species and confirm epigenetic modulation by BET inhibition as a promising strategy for modulating the stemness phenotype in canine and human mammary cancer cells.

CENPA regulates tumor stemness in lung adenocarcinoma.

Lung adenocarcinoma is a malignant and fatal respiratory disease. However, due to its complex pathogenesis and poorly effective therapeutic options, accurate early diagnosis and prognosis remain elusive. Now, there is increasing evidence that tumor stem cells are involved in tumorigenesis, metastasis, relapse, resistance to chemotherapy and radiotherapy and are one of the reasons why tumors cannot be cured. The mRNA expression based-stemness index (mRNAsi) is a parameter obtained by Malta and his colleagues applying innovative one-class logistic regression machine learning algorithm (OCLR) on mRNA expression in normal stem cells and their progeny. It is a valid evaluation parameter and is currently employed to evaluate the degree of differentiation of a certain tumor. In this study, we first used WGCNA and the software Cytoscape to obtain key modules and hub genes. We then applied LASSO regression analysis to calculate the genes in the key module to obtain a six-gene risk model. Moreover, the accuracy of this model was validated. Finally, we took the intersection of hub genes and risk genes and validated CENPA as both a tumor stemness regulator and a tumor prognostic factor in lung cancer.

Using Preoperative and Intraoperative Factors to Predict the Risk of Surgical Site Infections After Lumbar Spinal Surgery: A Machine Learning–Based Study

To develop a model based on machine learning to predict surgical site infection (SSI) risk in patients after lumbar spinal surgery (LSS). Patients who developed postoperative SSI after LSS in the First Affiliated Hospital of Nanchang University between December 2010 and December 2019 were retrospectively reviewed. Preoperative and intraoperative variables, including age, diabetes mellitus, hypertension, body mass index, previous spinal surgery history, surgical duration, number of fused segments, blood loss, and surgical procedure were analyzed. Six machine learning algorithms-logistic regression, multilayer perceptron, decision tree, random forest, gradient boosting machine, and extreme gradient boosting-were used to build prediction models. The performance of the models was evaluated using the area under the curve, accuracy, precision, sensitivity, and F1 score. A web predictor was developed based on the best-performing model. The study included 288 patients who underwent LSS, of whom 144 developed SSI and 144 did not develop SSI. The extreme gradient boosting model offers the best predictive performance among these 6 models (area under the curve= 0.923, accuracy= 0.860, precision= 0.900, sensitivity= 0.834, F1 score= 0.864). An extreme gradient boosting model-based web predictor was developed to predict SSI in patients after LSS. This study developed a machine learning model and a web predictor for predicting SSI in patients after LSS, which may help clinicians screen high-risk patients, provide personalized treatment, and reduce the incidence of SSI after LSS.

Machine Learning-Enhanced Play Fairway Analysis for Uncertainty Characterization and Decision Support in Geothermal Exploration

Geothermal exploration has traditionally relied on geological, geochemical, or geophysical surveys for evidence of adequate enthalpy, fluids, and permeability in the subsurface prior to drilling. The recent adoption of play fairway analysis (PFA), a method used in oil and gas exploration, has progressed to include machine learning (ML) for predicting geothermal drill site favorability. This study introduces a novel approach that extends ML PFA predictions with uncertainty characterization. Four ML algorithms—logistic regression, a decision tree, a gradient-boosted forest, and a neural network—are used to evaluate the subsurface enthalpy resource potential for conventional or EGS prospecting. Normalized Shannon entropy is calculated to assess three spatially variable sources of uncertainty in the analysis: model representation, model parameterization, and feature interpolation. When applied to southwest New Mexico, this approach reveals consistent enthalpy trends embedded in a high-dimensional feature set and detected by multiple algorithms. The uncertainty analysis highlights spatial regions where ML models disagree, highly parameterized models are poorly constrained, and predictions show sensitivity to errors in important features. Rapid insights from this analysis enable exploration teams to optimize allocation decisions of limited financial and human resources during the early stages of a geothermal exploration campaign.

Performance Analysis of Machine Learning and Deep Learning Architectures on Early Stroke Detection Using Carotid Artery Ultrasound Images.

Atherosclerotic plaque deposit in the carotid artery is used as an early estimate to identify the presence of cardiovascular diseases. Ultrasound images of the carotid artery are used to provide the extent of stenosis by examining the intima-media thickness and plaque diameter. A total of 361 images were classified using machine learning and deep learning approaches to recognize whether the person is symptomatic or asymptomatic. CART decision tree, random forest, and logistic regression machine learning algorithms, convolutional neural network (CNN), Mobilenet, and Capsulenet deep learning algorithms were applied in 202 normal images and 159 images with carotid plaque. Random forest provided a competitive accuracy of 91.41% and Capsulenet transfer learning approach gave 96.7% accuracy in classifying the carotid artery ultrasound image database.

Implications of Stemness Features in 1059 Hepatocellular Carcinoma Patients from Five Cohorts: Prognosis, Treatment Response, and Identification of Potential Compounds.

Simple SummaryCancer stemness has been reported to drive hepatocellular carcinoma (HCC) tumorigenesis and treatment resistance. However, comprehensive interpretations of transcriptomic stemness features in HCC patients have not been conducted in multiple cohorts. Our aim was to interpret clinical and therapeutic implications of transcriptional stemness features and explore potential compounds for HCC treatment. We found that transcriptional stemness indexes (mRNAsi) were independently associated with worse HCC prognosis. The HCC stemness risk model (HSRM) developed in this study significantly predicted prognosis and treatment response in various HCC cohorts. Analysis of two stemness subtypes suggested several liver-specific metabolic pathways, and mutations of TP53 and RB1 were associated with HCC transcriptional stemness. Moreover, we also identified potential compounds that target HCC transcriptional stemness. Our findings comprehensively characterized transcriptional stemness as a risk factor in HCC progression and treatment.Cancer stemness has been reported to drive hepatocellular carcinoma (HCC) tumorigenesis and treatment resistance. In this study, five HCC cohorts with 1059 patients were collected to calculate transcriptional stemness indexes (mRNAsi) by the one-class logistic regression machine learning algorithm. In the TCGA-LIHC cohort, we found mRNAsi was an independent prognostic factor, and 626 mRNAsi-related genes were identified by Spearman correlation analysis. The HCC stemness risk model (HSRM) was trained in the TCGA-LIHC cohort and significantly discriminated overall survival in four independent cohorts. HSRM was also significantly associated with transarterial chemoembolization treatment response and rapid tumor growth in HCC patients. Consensus clustering was conducted based on mRNAsi-related genes to divide 1059 patients into two stemness subtypes. On gene set variation analysis, samples of subtype I were found enriched with pathways such as DNA replication and cell cycle, while several liver-specific metabolic pathways were inhibited in these samples. Somatic mutation analysis revealed more frequent mutations of TP53 and RB1 in the subtype I samples. In silico analysis suggested topoisomerase, cyclin-dependent kinase, and histone deacetylase as potential targets to inhibit HCC stemness. In vitro assay showed two predicted compounds, Aminopurvalanol-a and NCH-51, effectively suppressed oncosphere formation and impaired viability of HCC cell lines, which may shed new light on HCC treatment.

Heart Disease Prediction Using Machine Learning Algorithms Logistic Regression, Support Vector Machine and Random Forest Classification Techniques

Heart Disease Prediction Using Machine Learning Algorithms Logistic Regression, Support Vector Machine and Random Forest Classification Techniques

Identifying Children at Readmission Risk: At-Admission versus Traditional At-Discharge Readmission Prediction Model.

The timing of 30-day pediatric readmissions is skewed with approximately 40% of the incidents occurring within the first week of hospital discharges. The skewed readmission time distribution coupled with delay in health information exchange among healthcare providers might offer a limited time to devise a comprehensive intervention plan. However, pediatric readmission studies are thus far limited to the development of the prediction model after hospital discharges. In this study, we proposed a novel pediatric readmission prediction model at the time of hospital admission which can improve the high-risk patient selection process. We also compared proposed models with the standard at-discharge readmission prediction model. Using the Hospital Cost and Utilization Project database, this prognostic study included pediatric hospital discharges in Florida from January 2016 through September 2017. Four machine learning algorithms—logistic regression with backward stepwise selection, decision tree, Support Vector machines (SVM) with the polynomial kernel, and Gradient Boosting—were developed for at-admission and at-discharge models using a recursive feature elimination technique with a repeated cross-validation process. The performance of the at-admission and at-discharge model was measured by the area under the curve. The performance of the at-admission model was comparable with the at-discharge model for all four algorithms. SVM with Polynomial Kernel algorithms outperformed all other algorithms for at-admission and at-discharge models. Important features associated with increased readmission risk varied widely across the type of prediction model and were mostly related to patients’ demographics, social determinates, clinical factors, and hospital characteristics. Proposed at-admission readmission risk decision support model could help hospitals and providers with additional time for intervention planning, particularly for those targeting social determinants of children’s overall health.

Dysregulation of MAD2L1/CAMK2A/PTTG1 Gene Cluster Maintains the Stemness Characteristics of Uterine Corpus Endometrial Carcinoma

Objective To study the stemness characteristics of uterine corpus endometrial carcinoma(UCEC)and its potential regulatory mechanism.Methods Transcriptome sequencing data of UCEC was obtained from The Cancer Genome Atlas.Gene expression profile was normalized by edgeR package in R3.5.1.A one-class logistic regression machine learning algorithm was employed to calculated the mRNA stemness index(mRNAsi)of each UCEC sample.Then,the prognostic significance of mRNAsi and candidate genes was evaluated by survminer and survival packages.The high-frequency sub-pathways mining approach(HiFreSP)was used to identify the prognosis-related sub-pathways enriched with differentially expressed genes(DEGs).Subsequently,a gene co-expression network was constructed using WGCNA package,and the key gene modules were analyzed.The clusterProfiler package was adopted to the function annotation of the modules highly correlated with mRNAsi.Finally,the Human Protein Atlas(HPA)was retrieved for immunohistochemical validation.Results The mRNAsi of UCEC samples was significantly higher than that of normal tissues(t=25.095,P<0.001),and the lower degree of differentiation corresponded to higher mRNAsi in tumor tissues.The mRNAsi of UCEC increased gradually with tumor staging.The prognostic analysis showed that high mRNAsi was correlated with short overall survival in patients with UCEC(χ2=6.864,P=0.0088).There were 570 DEGs between the high-and low-mRNAsi groups.By using the HiFreSP algorithm,we identified that the oocyte meiosis sub-pathway(Oocyte meiosis_1)and cell cycle sub-pathway(Cell cycle_3)had significant prognostic significance.These pathways contained 11 DEGs(MAD2L1,CAMK2A,PTTG1,PLK1,CCNE1,CCNE2,ESPL1,CDC20,CCNB1,CCNB2,and SMC1B),which were significantly associated with the prognosis of UCEC patients.Gene co-expression network showed that mRNAsi,as well as MAD2L1,CAMK2A,and PTTG1,was associated with three gene modules.The immunohistochemical analysis demonstrated that MAD2L1 and PTTG1 showed up-regulated expression while CAMK2A showed down-regulated expression in UCEC,which was consistent with the results of transcriptome sequencing.Conclusions On the basis of machine learning,this study characterizes the stemness characteristics of UCEC.We identify the key sub-pathways related to prognosis and demonstrate that MAD2L1,CAMK2A,PTTG1 are closely related to the stemness of UCEC,which provides insight into the regulatory mechanism of cancer stemness and reveals the potential therapeutic targets of UCEC.

Prediction of Labor Activity Recognition in Construction with Machine Learning Algorithms

It is essential that the control and management of the work of labors in construction project management is effective. In this study, it is aimed to building artificial intelligence models to recognition on activities in a construction work to effectively utilization project management and control. In accordance with this purpose, 3-axis accelerometer, gyroscope, and magnetometer data were obtained from the labors through the sensor to predict the activities determined for a construction work. These raw data were made compliance for the model by going through a series of preprocessing applications. These data are trained and modeled with basic machine learning algorithms logistic regression, SVC, DT and KNN algorithms. According to the results of the analysis, the best prediction was obtained with the SVC algorithm with an accuracy of 90%. In other algorithms, respectively, 87% accuracy was contrived in the KNN algorithm, and approximately 80% accuracy in the logistic regression and DT algorithms. According to these values, it has been observed that the activities performed in a construction work can be estimated at a high rate. In this way, at the construction sites, it can be automatically determined which work the laborer do at a certain accuracy rate.

On Scene Injury Severity Prediction (OSISP) machine learning algorithms for motor vehicle crash occupants in US

A significant proportion of motor vehicle crash fatalities are potentially preventable with improved acute care. By increasing the accuracy of triage more victims could be transported directly to the best suited care facility and be provided optimal care. We hypothesize that On Scene Injury Severity Prediction (OSISP) algorithms, developed utilizing machine learning methods, have potential to improve triage by complementing the field triage protocol. In this study, the accuracy of OSISP algorithms based on the “National Automotive Sampling System - Crashworthiness Data System” (NASS-CDS) of crashes involving adult occupants for calendar years 2010–2015 was evaluated. Severe injury was the dependent variable, defined as Injury Severity Score (ISS) > 15. The dataset contained 37873 subjects, whereof 21589 included injury data and were further analyzed. Selection of model predictors was based on potential for injury severity prediction and perceived feasibility of assessment by first responders. We excluded vehicle telemetry data due to the limited availability of these systems in the contemporary vehicle fleet, and because this data is not yet being utilized in prehospital care. The machine learning algorithms Logistic Regression, Ridge Regression, Bernoulli Naïve Bayes, Stochastic Gradient Descent and Artificial Neural Networks were evaluated. Best performance with small margin was achieved with Logistic Regression, achieving area under the receiver operator characteristic curve (AUC) of 0.86 (95% confidence interval 0.82–0.90), as estimated by 10-fold stratified cross-validation. Ejection, Entrapment, Belt use, Airbag deployment and Crash type were good predictors. Using only a subset of the 5–7 best predictors approached the prediction accuracy achieved when using the full set (14 predictors). A simplified benefit analysis indicated that nationwide implementation of OSISP in the US could bring improved care for 3100 severely injured patients, and reduce unnecessary use of trauma center resources for 94000 non-severely injured patients, every year.

Abstract 3113: Pan-cancer stemness defined by CPTAC proteogenomics guides personalized therapies

Abstract Cancer progression involves the gradual loss of a differentiated phenotype and acquisition of progenitor and stem cell-like features. Here, we provide new stemness indices for assessing the degree of oncogenic dedifferentiation. We used machine learning approaches to extract epigenetic, transcriptomic, and proteomic features from human stem cells and applied the computed result to index the Clinical Proteomic Tumor Analysis Consortium (CPTAC) tumor samples by their proteogenomic hallmarks of stemness. Leveraging the resource generated by Human Induced Pluripotent Stem Cells Consortium (HipSci), we extracted stemness signatures from the coherent epigenetic, transcriptomic, and proteomic datasets, using one-class logistic regression machine learning algorithm. The newly obtained stemness scores based on the DNA methylation and gene expression are significantly more robust compared to our previous published work based on the dataset obtained from a smaller number of samples with only genomics data. The stemness score computed by machine learning algorithms using proteomic datasets is novel and original. The obtained proteomic score is able to classify stem cells and non-stem cell classes. Indexing of CPTAC tumors with proteomic stemness score brought us with previously unappreciated findings. We have used the stemness scores computed using gene expression, DNA methylation, and proteins and their modifications to interrogate the coherent proteogenomic CPTAC datasets. The initial analysis of over 2000 tumor samples obtained from twelve types of primary carcinomas of breast, ovary, lung, kidney, uterus, brain (pediatric and adult), head and neck, liver, stomach, colon, and pancreas has confirmed our previously published results. Importantly, our original proteomic-based score brought the analyses to a novel dimension, far beyond previously described results. The initial findings of our work identified proteins and phospho-proteins as active nodes of signaling pathways and transcriptional networks that drive aggressiveness of the primary tumors that cause resistance to existing therapies. Our results indicate that cancer stemness is associated with the engagement of developmental pathways shaping tumor plasticity. Progressive oncogenic de-differentiation of cancer cells impacts tumor microenvironment and is associated with “cold” tumors thus impairing anti-tumor immune response and limiting the efficacy of immunotherapies. Hallmarks of cancer stemness correlate with increased tumor pathology grade and clinical stage and results in worse survival of the cancer patients across analyzed tumor types. Targeting identified proteins and cellular mechanisms that drive lethal phenotype of de-differentiated tumors with existing or novel drugs may pave the way for clinical development of effective cures for cancer patients. Citation Format: Maciej Wiznerowicz, Antono Colaprico, Erik Storrs, Francesca Petralia, Iga Kołodziejczak, Felipe da Veiga Leprevost, Weiping Ma, Daniel Cui Zhou, Bo Wen, Alexander Lazar, Pietro Pugliese, Michele Ceccarelli, Bożena Kamińska, Jan Lubiński, Alexey Nesvizhskii, Bing Zhang, Henry Rodriguez, Ana L. Robles, Mehdi Mesri. Pan-cancer stemness defined by CPTAC proteogenomics guides personalized therapies [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2021; 2021 Apr 10-15 and May 17-21. Philadelphia (PA): AACR; Cancer Res 2021;81(13_Suppl):Abstract nr 3113.