scholarly journals Personalized survival probabilities for SARS-CoV-2 positive patients by explainable machine learning

2021 ◽  
Author(s):  
Adrian G. Zucco ◽  
Rudi Agius ◽  
Rebecka Svanberg ◽  
Kasper S. Moestrup ◽  
Ramtin Z. Marandi ◽  
...  
Keyword(s):  
Machine Learning ◽  
Risk Factors ◽  
Temporal Dynamics ◽  
Area Under The Curve ◽  
Routine Care ◽  
Individual Risk ◽  
Survival Probabilities ◽  
Machine Learning Model ◽  
Laboratory Test Results ◽  
Individual Risk Factors

Interpretable risk assessment of SARS-CoV-2 positive patients can aid clinicians to implement precision medicine. Here we trained a machine learning model to predict mortality within 12 weeks of a first positive SARS-CoV-2 test. By leveraging data on 33,928 confirmed SARS-CoV-2 cases in eastern Denmark, we considered 2,723 variables extracted from electronic health records (EHR) including demographics, diagnoses, medications, laboratory test results and vital parameters. A discrete-time framework for survival modelling enabled us to predict personalized survival curves and explain individual risk factors. Performances of weighted concordance index 0.95 and precision-recall area under the curve 0.71 were measured on the test set. Age, sex, number of medications, previous hospitalizations and lymphocyte counts were identified as top mortality risk factors. Our explainable survival model developed on EHR data also revealed temporal dynamics of the 22 selected risk factors. Upon further validation, this model may allow direct reporting of personalized survival probabilities in routine care.

A proof-of-concept study applying machine learning methods to putative risk factors for eating disorders: results from the multi-centre European project on healthy eating

2021 ◽  
pp. 1-10
Author(s):  
I. Krug ◽  
J. Linardon ◽  
C. Greenwood ◽  
G. Youssef ◽  
J. Treasure ◽  
...  
Keyword(s):  
Machine Learning ◽  
Risk Factors ◽  
Logistic Regression ◽  
Predictive Accuracy ◽  
Area Under The Curve ◽  
Prediction Rule ◽  
Predictive Performance ◽  
Individual Risk ◽  
European Project ◽  
Wide Range

Abstract Background Despite a wide range of proposed risk factors and theoretical models, prediction of eating disorder (ED) onset remains poor. This study undertook the first comparison of two machine learning (ML) approaches [penalised logistic regression (LASSO), and prediction rule ensembles (PREs)] to conventional logistic regression (LR) models to enhance prediction of ED onset and differential ED diagnoses from a range of putative risk factors. Method Data were part of a European Project and comprised 1402 participants, 642 ED patients [52% with anorexia nervosa (AN) and 40% with bulimia nervosa (BN)] and 760 controls. The Cross-Cultural Risk Factor Questionnaire, which assesses retrospectively a range of sociocultural and psychological ED risk factors occurring before the age of 12 years (46 predictors in total), was used. Results All three statistical approaches had satisfactory model accuracy, with an average area under the curve (AUC) of 86% for predicting ED onset and 70% for predicting AN v. BN. Predictive performance was greatest for the two regression methods (LR and LASSO), although the PRE technique relied on fewer predictors with comparable accuracy. The individual risk factors differed depending on the outcome classification (EDs v. non-EDs and AN v. BN). Conclusions Even though the conventional LR performed comparably to the ML approaches in terms of predictive accuracy, the ML methods produced more parsimonious predictive models. ML approaches offer a viable way to modify screening practices for ED risk that balance accuracy against participant burden.

scholarly journals Deep Neural Network for Predicting Diabetic Retinopathy from Risk Factors

Mathematics ◽  
2020 ◽  
Vol 8 (9) ◽  
pp. 1620 ◽  
Author(s):  
Ganjar Alfian ◽  
Muhammad Syafrudin ◽  
Norma Latif Fitriyani ◽  
Muhammad Anshari ◽  
Pavel Stasa ◽  
...  
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Risk Factors ◽  
Diabetic Retinopathy ◽  
Prediction Model ◽  
Deep Neural Network ◽  
Early Stage ◽  
Individual Risk ◽  
Proposed Model ◽  
Individual Risk Factors

Extracting information from individual risk factors provides an effective way to identify diabetes risk and associated complications, such as retinopathy, at an early stage. Deep learning and machine learning algorithms are being utilized to extract information from individual risk factors to improve early-stage diagnosis. This study proposes a deep neural network (DNN) combined with recursive feature elimination (RFE) to provide early prediction of diabetic retinopathy (DR) based on individual risk factors. The proposed model uses RFE to remove irrelevant features and DNN to classify the diseases. A publicly available dataset was utilized to predict DR during initial stages, for the proposed and several current best-practice models. The proposed model achieved 82.033% prediction accuracy, which was a significantly better performance than the current models. Thus, important risk factors for retinopathy can be successfully extracted using RFE. In addition, to evaluate the proposed prediction model robustness and generalization, we compared it with other machine learning models and datasets (nephropathy and hypertension–diabetes). The proposed prediction model will help improve early-stage retinopathy diagnosis based on individual risk factors.

scholarly journals COVID-19 severity prediction based on patient risk factors and number of vaccines received

2022 ◽  
Author(s):  
Ariel Israel ◽  
Alejandro A. Schäffer ◽  
Eugene Merzon ◽  
Ilan Green ◽  
Eli Magen ◽  
...  
Keyword(s):  
Risk Factors ◽  
Severe Disease ◽  
Area Under The Curve ◽  
Booster Vaccination ◽  
Rapid Identification ◽  
Individual Risk ◽  
Logistic Regression Models ◽  
Severity Prediction ◽  
Individual Risk Factors ◽  
To Receive

Background Vaccines are highly effective in preventing severe disease and death from COVID-19, and new medications that can reduce severity of disease have been approved. However, many countries are facing limited supply of vaccine doses and medications. A model estimating the probabilities for hospitalization and mortality according to individual risk factors and vaccine doses received could help prioritize vaccination and yet scarce medications to maximize lives saved and reduce the burden on hospitalization facilities. Methods Electronic health records from 101,034 individuals infected with SARS-CoV-2, since the beginning of the pandemic and until November 30, 2021 were extracted from a national healthcare organization in Israel. Logistic regression models were built to estimate the risk for subsequent hospitalization and death based on the number of BNT162b2 mRNA vaccine doses received and few major risk factors (age, sex, body mass index, hemoglobin A1C, kidney function, and presence of hypertension, pulmonary disease or malignancy). Results The models built predict the outcome of newly infected individuals with remarkable accuracy: area under the curve was 0.889 for predicting hospitalization, and 0.967 for predicting mortality. Even when a breakthrough infection occurs, having received three vaccination doses significantly reduces the risk of hospitalization by 66% (OR=0.336) and of death by 78% (OR=0.220). Conclusions The models enable rapid identification of individuals at high risk for hospitalization and death when infected. These patients can be prioritized to receive booster vaccination and the yet scarce medications. A calculator based on these models is made publicly available on http://covidest.web.app

A Model for Analyzing Suicide Prevention

Crisis ◽  
2000 ◽  
Vol 21 (2) ◽  
pp. 80-89 ◽  
Author(s):  
Maila Upanne
Keyword(s):  
Risk Factors ◽  
Theoretical Model ◽  
Protective Factors ◽  
Suicide Prevention ◽  
Suicide Risk ◽  
Practical Work ◽  
Individual Risk ◽  
Self Assessment ◽  
Prevention Project ◽  
Individual Risk Factors

This study monitored the evolution of psychologists' (n = 31) conceptions of suicide prevention over the 9-year course of the National Suicide Prevention Project in Finland and assessed the feasibility of the theoretical model for analyzing suicide prevention developed in earlier studies [ Upanne, 1999a , b ]. The study was formulated as a retrospective self-assessment where participants compared their earlier descriptions of suicide prevention with their current views. The changes in conceptions were analyzed and interpreted using both the model and the explanations given by the subjects themselves. The analysis proved the model to be a useful framework for revealing the essential features of prevention. The results showed that the freely-formulated ideas on prevention were more comprehensive than those evolved in practical work. Compared to the earlier findings, the conceptions among the group had shifted toward emphasizing a curative approach and the significance of individual risk factors. In particular, greater priority was focused on the acute suicide risk phase as a preventive target. Nonetheless, the overall structure of prevention ideology remained comprehensive and multifactorial, stressing multistage influencing. Promotive aims (protective factors) also remained part of the prevention paradigm. Practical working experiences enhanced the psychologists' sense of the difficulties of suicide prevention as well as their criticism and feeling of powerlessness.

scholarly journals Cardio-Metabolic Risk Factors in Scottish South Asian and Caucasian Youth

2021 ◽  
Vol 18 (9) ◽  
pp. 4667
Author(s):  
Meizi Wang ◽  
Jianhua Ying ◽  
Ukadike Chris Ugbolue ◽  
Duncan S. Buchan ◽  
Yaodong Gu ◽  
...  
Keyword(s):  
Risk Factors ◽  
Body Mass Index ◽  
Waist Circumference ◽  
Body Mass ◽  
South Asian ◽  
Metabolic Risk Factors ◽  
Individual Risk ◽  
Metabolic Risk ◽  
Asian Adolescents ◽  
Individual Risk Factors

(1) Background: Scotland has one of the highest rates of obesity in the Western World, it is well established that poor weight profiles, and particularly abdominal obesity, is strongly associated with Type II diabetes and cardiovascular diseases. Whether these associations are apparent in ethnic population groups in Scotland is unclear. The purpose of this study was to examine the associations between different measures of fatness with clustered cardio metabolic risk factors between Scottish South Asian adolescents and Scottish Caucasian adolescents; (2) Methods: A sample of 208 Caucasian adolescents and 52 South Asian adolescents participated in this study. Stature, waist circumference, body mass index, blood pressure, physical activity, and cardiovascular disease (CVD) risk were measured; (3) Results: Significant, partial correlations in the South Asian cohort between body mass index (BMI) and individual risk factors were generally moderate. However, correlations between Waist circumference (WC) and individual risk factors were significant and strong. In the Caucasian cohort, a significant yet weak correlation between WC and total cholesterol (TG) was noted although no other associations were evident for either WC or BMI. Multiple regression analysis revealed that both BMI and WC were positively associated with CCR (p < 0.01) in the South Asian group and with the additional adjustment of either WC or BMI, the independent associations with clustered cardio-metabolic risk (CCR) remained significant (p < 0.005); (4) Conclusions: No positive relationships were found between BMI, WC, and CCR in the Caucasian group. Strong and significant associations between measures of fatness and metabolic risk were evident in Scottish South Asian adolescents.

How Community and Individual Risk Factors Mutually Impact Youth’s Perceived Safety: A Syndemic Analysis Using Structural Equation Modeling

2021 ◽  
pp. 088626052110283
Author(s):  
Yingwei Yang ◽  
Karen D. Liller ◽  
Martha Coulter ◽  
Abraham Salinas-Miranda ◽  
Dinorah Martinez Tyson ◽  
...  
Keyword(s):  
Risk Factors ◽  
Structural Equation Modeling ◽  
Structural Equation ◽  
Community Safety ◽  
Equation Modeling ◽  
Individual Risk ◽  
Latent Factor ◽  
Community Factors ◽  
Individual Risk Factors ◽  
Syndemic Theory

The purpose of this study was to evaluate the mutual impact of community and individual factors on youth’s perceptions of community safety, using structural equation modeling (SEM) conceptualized by syndemic theory. This study used survey data collected from a county wide sample of middle and high school students (N=25,147) in West Central Florida in 2015. The outcome variable was youth’s perceptions of community safety. Predictors were latent individual and community factors constructed from 14 observed variables including gun accessibility, substance use, depressive symptoms, and multiple neighborhood disadvantage questions. Three structural equation models were conceptualized based on syndemic theory and analyzed in Mplus 8 using weighted least squares (WLS) estimation. Each model’s goodness of fit was assessed. Approximately seven percent of youth reported feeling unsafe in their community. After model modifications, the final model showed a good fit of the data and adhered to the theoretical assumption. In the final SEM model, an individual latent factor was implied by individual predictors measuring gun accessibility without adult’s permission (β=0.70), sadness and hopelessness (β=0.52), alcohol use (β=0.79), marijuana use (β=0.94), and illegal drug use (β=0.77). Meanwhile, a community latent factor was indicated by multiple community problems including public drinking (β=0.88), drug addiction (β=0.96), drug selling (β=0.97), lack of money (β=0.83), gang activities (β=0.90), litter and trash (β=0.79), graffiti (β=0.91), deserted houses (β=0.86), and shootings (β=0.93). A second-order syndemic factor that represented the individual and community factors showed a very strong negative association with youth’s safe perception (β=-0.98). This study indicates that individual risk factors and disadvantaged community conditions interacted with each other and mutually affected youth’s perceptions of community safety. To reduce these co-occurring effects and improve safe perceptions among youth, researchers and practitioners should develop and implement comprehensive strategies targeting both individual and community factors.

Clinical Score and Machine Learning-Based Model to Predict Diagnosis of Primary Aldosteronism in Arterial Hypertension

Hypertension ◽  
2021 ◽  
Vol 78 (5) ◽  
pp. 1595-1604
Author(s):  
Fabrizio Buffolo ◽  
Jacopo Burrello ◽  
Alessio Burrello ◽  
Daniel Heinrich ◽  
Christian Adolf ◽  
...  
Keyword(s):  
Machine Learning ◽  
Arterial Hypertension ◽  
Primary Aldosteronism ◽  
Learning Algorithm ◽  
Area Under The Curve ◽  
Clinical Score ◽  
Machine Learning Algorithms ◽  
Supervised Machine Learning ◽  
Individual Risk ◽  
The Individual

Primary aldosteronism (PA) is the cause of arterial hypertension in 4% to 6% of patients, and 30% of patients with PA are affected by unilateral and surgically curable forms. Current guidelines recommend screening for PA ≈50% of patients with hypertension on the basis of individual factors, while some experts suggest screening all patients with hypertension. To define the risk of PA and tailor the diagnostic workup to the individual risk of each patient, we developed a conventional scoring system and supervised machine learning algorithms using a retrospective cohort of 4059 patients with hypertension. On the basis of 6 widely available parameters, we developed a numerical score and 308 machine learning-based models, selecting the one with the highest diagnostic performance. After validation, we obtained high predictive performance with our score (optimized sensitivity of 90.7% for PA and 92.3% for unilateral PA [UPA]). The machine learning-based model provided the highest performance, with an area under the curve of 0.834 for PA and 0.905 for diagnosis of UPA, with optimized sensitivity of 96.6% for PA, and 100.0% for UPA, at validation. The application of the predicting tools allowed the identification of a subgroup of patients with very low risk of PA (0.6% for both models) and null probability of having UPA. In conclusion, this score and the machine learning algorithm can accurately predict the individual pretest probability of PA in patients with hypertension and circumvent screening in up to 32.7% of patients using a machine learning-based model, without omitting patients with surgically curable UPA.

‘Genetics load the gun, but the environment pulls the trigger’: novel, emerging and non-traditional risk factors in cardiovascular disease

2021 ◽  
pp. 1-3
Author(s):  
Andrew Richardson
Keyword(s):  
Risk Factors ◽  
Cardiovascular Disease ◽  
Environmental Factors ◽  
Individual Risk ◽  
Traditional Risk Factors ◽  
Individual Risk Factors ◽  
The Impact

In this article, Andy Richardson, BANCC Educational Advisor, examines several important environmental and individual risk factors for cardiovascular disease. Following on from the meeting of Global Leaders at COP26 in Glasgow, he considers the impact of, and exposure to, environmental factors, including pollution and noise.

Sign in / Sign up

Export Citation Format

Share Document