scholarly journals High Accurancy and Low Risk Prediction and Diagnosis Heart Disease using Gradient Boosting Algorithm

2021 ◽  
Vol 174 (28) ◽  
pp. 25-28
Author(s):  
Sachin Sahu ◽  
Zuber Farooqui
Keyword(s):  
Heart Disease ◽  
Risk Prediction ◽  
Low Risk ◽  
Gradient Boosting ◽  
Boosting Algorithm

scholarly journals Machine learning augmented predictive and generative model for rupture life in ferritic and austenitic steels

2021 ◽  
Vol 5 (1) ◽  
Author(s):  
Osman Mamun ◽  
Madison Wenzlick ◽  
Arun Sathanur ◽  
Jeffrey Hawk ◽  
Ram Devanathan
Keyword(s):  
Pearson Correlation ◽  
Rupture Life ◽  
Model Performance ◽  
Austenitic Stainless Steels ◽  
Generative Model ◽  
Austenitic Steels ◽  
Gradient Boosting ◽  
Variational Autoencoder ◽  
Feature Importance ◽  
Boosting Algorithm

AbstractThe Larson–Miller parameter (LMP) offers an efficient and fast scheme to estimate the creep rupture life of alloy materials for high-temperature applications; however, poor generalizability and dependence on the constant C often result in sub-optimal performance. In this work, we show that the direct rupture life parameterization without intermediate LMP parameterization, using a gradient boosting algorithm, can be used to train ML models for very accurate prediction of rupture life in a variety of alloys (Pearson correlation coefficient >0.9 for 9–12% Cr and >0.8 for austenitic stainless steels). In addition, the Shapley value was used to quantify feature importance, making the model interpretable by identifying the effect of various features on the model performance. Finally, a variational autoencoder-based generative model was built by conditioning on the experimental dataset to sample hypothetical synthetic candidate alloys from the learnt joint distribution not existing in both 9–12% Cr ferritic–martensitic alloys and austenitic stainless steel datasets.

An intelligent evolutionary extreme gradient boosting algorithm development for modeling scour depths under submerged weir

2021 ◽  
Author(s):  
Hai Tao ◽  
Maria Habib ◽  
Ibrahim Aljarah ◽  
Hossam Faris ◽  
Haitham Abdulmohsin Afan ◽  
...  
Keyword(s):  
Gradient Boosting ◽  
Algorithm Development ◽  
Extreme Gradient Boosting ◽  
Boosting Algorithm

scholarly journals Gradient boosting for linear mixed models

2021 ◽  
Vol 0 (0) ◽  
Author(s):  
Colin Griesbach ◽  
Benjamin Säfken ◽  
Elisabeth Waldmann
Keyword(s):  
Random Effects ◽  
Mixed Models ◽  
Selection Procedure ◽  
Classification Theory ◽  
Gradient Boosting ◽  
Random Structure ◽  
Boosting Algorithm ◽  
The One ◽  
Biased Estimates ◽  
Selection Of

Abstract Gradient boosting from the field of statistical learning is widely known as a powerful framework for estimation and selection of predictor effects in various regression models by adapting concepts from classification theory. Current boosting approaches also offer methods accounting for random effects and thus enable prediction of mixed models for longitudinal and clustered data. However, these approaches include several flaws resulting in unbalanced effect selection with falsely induced shrinkage and a low convergence rate on the one hand and biased estimates of the random effects on the other hand. We therefore propose a new boosting algorithm which explicitly accounts for the random structure by excluding it from the selection procedure, properly correcting the random effects estimates and in addition providing likelihood-based estimation of the random effects variance structure. The new algorithm offers an organic and unbiased fitting approach, which is shown via simulations and data examples.

scholarly journals Accuracy of risk prediction scores in pregnant women with congenital heart disease

2019 ◽  
Vol 14 (3) ◽  
pp. 470-478 ◽  
Author(s):  
Yuli Y. Kim ◽  
Leah A. Goldberg ◽  
Katherine Awh ◽  
Tanmay Bhamare ◽  
David Drajpuch ◽  
...  
Keyword(s):  
Congenital Heart Disease ◽  
Heart Disease ◽  
Pregnant Women ◽  
Risk Prediction ◽  
Congenital Heart

Accuracy of the CARG chemotherapy toxicity risk prediction tool in older Indian patients with cancer.

2021 ◽  
Vol 39 (15_suppl) ◽  
pp. e24023-e24023
Author(s):  
Shreya Gattani ◽  
Vanita Noronha ◽  
Anant Ramaswamy ◽  
Renita Castelino ◽  
Vandhita Nair ◽  
...  
Keyword(s):  
High Risk ◽  
Cancer Patients ◽  
Risk Prediction ◽  
Risk Group ◽  
High Risk Group ◽  
Low Risk ◽  
Chemotherapy Toxicity ◽  
Patients With Cancer ◽  
Indian Patients ◽  
Grade 3

e24023 Background: Clinical judgement alone is inadequate in accurately predicting chemotherapy toxicity in older adult cancer patients. Hurria and colleagues developed and validated, the CARG score (range, 0–17) as a convenient and reliable tool for predicting chemotherapy toxicity in older cancer patients in America, however, its applicability in Indian patients is unknown. Methods: An observational retrospective and prospective study between 2018 and 2020 was conducted in the Department of Medical Oncology at Tata Memorial Hospital, Mumbai, India. The study was approved by the institutional ethics committee (IEC-III; Project No. 900596) and registered in the Clinical Trials Registry of India (CTRI/2020/04/024675). Written informed consent was obtained in the prospective part of the study. Patients aged ≥ 60 years and planned for systemic therapy were evaluated in the geriatric oncology clinic and their CARG score was calculated. Patients were stratified into low (0-4), intermediate (5-9) and high risk (10-17) based on the CARG scores. The CARG score was provided to the treating physicians, along with the results of the geriatric assessment. Chemotherapy-related toxicities were captured from the electronic medical record and graded as per the NCI CTCAE, version 4.0. Results: We assessed 130 patients, with a median age 69 years (IQR, 60 to 84); 72% patients were males. The common malignancies included gastrointestinal (52%) and lung (30%). Approximately 78% patients received polychemotherapy and 53% received full dose chemotherapy. Based on the CARG score, 28 (22%) patients belonged to low risk, 80 (61%) to intermediate risk and 22 (17%) to the high risk category. The AU-ROC of the CARG score in predicting grade 3-5 toxicities was 0.61 (95% CI, 0.51-0.71). The sensitivity and specificity of the CARG score in predicting grade 3-5 toxicities were 60.8% and 78.6%. Grade 3-5 toxicities occurred in 6/28 patients (21%) in the low risk group, compared to 62/102 patients (61%) in the intermediate /high risk group, p = 0.0002. There was also a significant difference in the time to development of grade 3-5 toxicities, which occurred at a median of 2.5 cycles (IQR, 1-3.8) in the intermediate /high risk group and at a median of 6 cycles (IQR, 3.5-8) in the low risk group, p = 0.0011. Conclusions: In older Indian patients with cancer, the CARG score reliably stratifies patients into low risk and intermediate/high risk categories, predicting both the occurrence and the time to occurrence of grade 3-5 toxicities from chemotherapy. The CARG score may aid the oncologist in estimating the risk-benefit ratio of chemotherapy. An important limitation was that we provided the CARG score to the treating oncologists prior to the start of chemotherapy, which may have resulted in alterations in the chemotherapy regimen and dose and may have impacted the CARG risk prediction model. Clinical trial information: CTRI/2020/04/024675.

scholarly journals Risk Prediction of Cardiovascular Complications in Pregnant Women With Heart Disease

2016 ◽  
Author(s):  
Luciana Carvalho Martins ◽  
Claudia Maria Vilas Freire ◽  
Carolina Andrade Bragança Capuruçu ◽  
Maria do Carmo Pereira Nunes ◽  
Cezar Alencar de Lima Rezende
Keyword(s):  
Heart Disease ◽  
Pregnant Women ◽  
Risk Prediction ◽  
Cardiovascular Complications

scholarly journals Risk prediction models for atherosclerotic cardiovascular disease: A systematic assessment with particular reference to Qatar

2021 ◽  
Vol 2021 (2) ◽  
Author(s):  
Aziz Sheikh ◽  
Ulugbek Nurmatov ◽  
Huda Amer Al-Katheeri ◽  
Rasmeh Ali Al Huneiti
Keyword(s):  
Risk Prediction ◽  
Prediction Models ◽  
Ethnically Diverse ◽  
Risk Of Bias ◽  
Low Risk ◽  
Atherosclerotic Cardiovascular Disease ◽  
Eligibility Criteria ◽  
Risk Prediction Models ◽  
Ascvd Risk

Background: Atherosclerotic cardiovascular disease (ASCVD) is a common disease in the State of Qatar and results in considerable morbidity, impairment of quality of life and mortality. The American College of Cardiology/American Heart Association Pooled Cohort Equations (PCE) is currently used in Qatar to identify those at high risk of ASCVD. However, it is unclear if this is the optimal ASCVD risk prediction model for use in Qatar's ethnically diverse population. Aims: This systematic review aimed to identify, assess the methodological quality of and compare the properties of established ASCVD risk prediction models for the Qatari population. Methods: Two reviewers performed head-to-head comparisons of established ASCVD risk calculators systematically. Studies were independently screened according to predefined eligibility criteria and critically appraised using Prediction Model Risk Of Bias Assessment Tool. Data were descriptively summarized and narratively synthesized with reporting of key statistical properties of the models. Results: We identified 20,487 studies, of which 41 studies met our eligibility criteria. We identified 16 unique risk prediction models. Overall, 50% (n = 8) of the risk prediction models were judged to be at low risk of bias. Only 13% of the studies (n = 2) were judged at low risk of bias for applicability, namely, PREDICT and QRISK3.Only the PREDICT risk calculator scored low risk in both domains. Conclusions: There is no existing ASCVD risk calculator particularly well suited for use in Qatar's ethnically diverse population. Of the available models, PREDICT and QRISK3 appear most appropriate because of their inclusion of ethnicity. In the absence of a locally derived ASCVD for Qatar, there is merit in a formal head-to-head comparison between PCE, which is currently in use, and PREDICT and QRISK3.

scholarly journals Establishment of non–small-cell lung cancer risk prediction model based on prognosis-associated ADME genes

2021 ◽  
Author(s):  
Ke Han ◽  
Jukun Wang ◽  
Kun Qian ◽  
Teng Zhao ◽  
Yi Zhang
Keyword(s):  
Lung Cancer ◽  
Prediction Model ◽  
Risk Prediction ◽  
Risk Score ◽  
Small Cell ◽  
Risk Prediction Model ◽  
Low Risk ◽  
Regression Analyses ◽  
Small Cell Lung ◽  
Immune Infiltration

Purpose: ADME genes are those involved in the absorption, distribution, metabolism, and excretion (ADME) of drugs. In this study, a non–small-cell lung cancer (NSCLC) risk prediction model was established using prognosis-associated ADME genes, and the predictive performance of this model was evaluated and verified. In addition, multifaceted difference analysis was performed on groups with high and low risk scores. Methods: An NSCLC sample transcriptome and clinical data were obtained from public databases. The prognosis-associated ADME genes were obtained by univariate Cox and lasso regression analyses to build a risk model. Tumor samples were divided into high-risk and low-risk score groups according to the risk score. Gene Ontology and Kyoto Encyclopedia of Genes and Genomes enrichment analyses of the differentially expressed genes and the differences in the immune infiltration, mutation, and medication reactions in the two groups were studied in detail. Results: A risk prediction model was established with seven prognosis-associated ADME genes. Its good predictive ability was confirmed by studies of the model’s effectiveness. Univariate and multivariate Cox regression analyses showed that the model’s risk score was an independent prognostic factor for patients with NSCLC. The study also showed that the risk score closely correlated with immune infiltration, mutations, and medication reactions. Conclusion: The risk prediction model established with seven ADME genes in this study can predict the prognosis of patients with NSCLC. In addition, significant differences in immune infiltration, mutations, and therapeutic efficacy exist between the high- and low-risk score groups.

Sign in / Sign up

Export Citation Format

Share Document