scholarly journals A machine learning classifier approach for identifying the determinants of under-five child undernutrition in Ethiopian administrative zones

2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Haile Mekonnen Fenta ◽  
Temesgen Zewotir ◽  
Essey Kebede Muluneh
Keyword(s):  
Machine Learning ◽  
Logistic Regression ◽  
Child Death ◽  
Area Under The Curve ◽  
Cross Sectional Survey ◽  
Cross Sectional ◽  
Machine Learning Classification ◽  
Under Five ◽  
Child Undernutrition ◽  
Sensitivity Specificity

Abstract Background Undernutrition is the main cause of child death in developing countries. This paper aimed to explore the efficacy of machine learning (ML) approaches in predicting under-five undernutrition in Ethiopian administrative zones and to identify the most important predictors. Method The study employed ML techniques using retrospective cross-sectional survey data from Ethiopia, a national-representative data collected in the year (2000, 2005, 2011, and 2016). We explored six commonly used ML algorithms; Logistic regression, Least Absolute Shrinkage and Selection Operator (L-1 regularization logistic regression), L-2 regularization (Ridge), Elastic net, neural network, and random forest (RF). Sensitivity, specificity, accuracy, and area under the curve were used to evaluate the performance of those models. Results Based on different performance evaluations, the RF algorithm was selected as the best ML model. In the order of importance; urban–rural settlement, literacy rate of parents, and place of residence were the major determinants of disparities of nutritional status for under-five children among Ethiopian administrative zones. Conclusion Our results showed that the considered machine learning classification algorithms can effectively predict the under-five undernutrition status in Ethiopian administrative zones. Persistent under-five undernutrition status was found in the northern part of Ethiopia. The identification of such high-risk zones could provide useful information to decision-makers trying to reduce child undernutrition.

scholarly journals Identification of Metabolic Syndrome Based on Anthropometric, Blood and Spirometric Risk Factors Using Machine Learning

2020 ◽  
Vol 10 (21) ◽  
pp. 7741
Author(s):  
Sang Yeob Kim ◽  
Gyeong Hee Nam ◽  
Byeong Mun Heo
Keyword(s):  
Machine Learning ◽  
Metabolic Syndrome ◽  
Logistic Regression ◽  
Prediction Model ◽  
Prediction Models ◽  
Strong Association ◽  
Forced Expiratory Volume ◽  
Binary Logistic Regression Analysis ◽  
Cross Sectional Survey ◽  
Cross Sectional

Metabolic syndrome (MS) is an aggregation of coexisting conditions that can indicate an individual’s high risk of major diseases, including cardiovascular disease, stroke, cancer, and type 2 diabetes. We conducted a cross-sectional survey to evaluate potential risk factor indicators by identifying relationships between MS and anthropometric and spirometric factors along with blood parameters among Korean adults. A total of 13,978 subjects were enrolled from the Korea National Health and Nutrition Examination Survey. Statistical analysis was performed using a complex sampling design to represent the entire Korean population. We conducted binary logistic regression analysis to evaluate and compare potential associations of all included factors. We constructed prediction models based on Naïve Bayes and logistic regression algorithms. The performance evaluation of the prediction model improved the accuracy with area under the curve (AUC) and calibration curve. Among all factors, triglyceride exhibited a strong association with MS in both men (odds ratio (OR) = 2.711, 95% confidence interval (CI) [2.328–3.158]) and women (OR = 3.515 [3.042–4.062]). Regarding anthropometric factors, the waist-to-height ratio demonstrated a strong association in men (OR = 1.511 [1.311–1.742]), whereas waist circumference was the strongest indicator in women (OR = 2.847 [2.447–3.313]). Forced expiratory volume in 6s and forced expiratory flow 25–75% strongly associated with MS in both men (OR = 0.822 [0.749–0.903]) and women (OR = 1.150 [1.060–1.246]). Wrapper-based logistic regression prediction model showed the highest predictive power in both men and women (AUC = 0.868 and 0.932, respectively). Our findings revealed that several factors were associated with MS and suggested the potential of employing machine learning models to support the diagnosis of MS.

scholarly journals Untargeted metabolomics yields insight into ALS disease mechanisms

2020 ◽  
Vol 91 (12) ◽  
pp. 1329-1338 ◽  
Author(s):  
Stephen A Goutman ◽  
Jonathan Boss ◽  
Kai Guo ◽  
Fadhl M Alakwaa ◽  
Adam Patterson ◽  
...  
Keyword(s):  
Machine Learning ◽  
Logistic Regression ◽  
Area Under The Curve ◽  
Enrichment Analysis ◽  
Group Lasso ◽  
Untargeted Metabolomics ◽  
Pathway Enrichment Analysis ◽  
Machine Learning Classification ◽  
Clinical Literature ◽  
Adjusted Logistic Regression

ObjectiveTo identify dysregulated metabolic pathways in amyotrophic lateral sclerosis (ALS) versus control participants through untargeted metabolomics.MethodsUntargeted metabolomics was performed on plasma from ALS participants (n=125) around 6.8 months after diagnosis and healthy controls (n=71). Individual differential metabolites in ALS cases versus controls were assessed by Wilcoxon rank-sum tests, adjusted logistic regression and partial least squares-discriminant analysis (PLS-DA), while group lasso explored sub-pathway-level differences. Adjustment parameters included sex, age and body mass index (BMI). Metabolomics pathway enrichment analysis was performed on metabolites selected by the above methods. Finally, machine learning classification algorithms applied to group lasso-selected metabolites were evaluated for classifying case status.ResultsThere were no group differences in sex, age and BMI. Significant metabolites selected were 303 by Wilcoxon, 300 by logistic regression, 295 by PLS-DA and 259 by group lasso, corresponding to 11, 13, 12 and 22 enriched sub-pathways, respectively. ‘Benzoate metabolism’, ‘ceramides’, ‘creatine metabolism’, ‘fatty acid metabolism (acyl carnitine, polyunsaturated)’ and ‘hexosylceramides’ sub-pathways were enriched by all methods, and ‘sphingomyelins’ by all but Wilcoxon, indicating these pathways significantly associate with ALS. Finally, machine learning prediction of ALS cases using group lasso-selected metabolites achieved the best performance by regularised logistic regression with elastic net regularisation, with an area under the curve of 0.98 and specificity of 83%.ConclusionIn our analysis, ALS led to significant metabolic pathway alterations, which had correlations to known ALS pathomechanisms in the basic and clinical literature, and may represent important targets for future ALS therapeutics.

scholarly journals The Economic Cost of Diet and Its Association with Adherence to the Mediterranean Diet in a Cohort of Spanish Primary Schoolchildren

2021 ◽  
Vol 18 (3) ◽  
pp. 1282
Author(s):  
Rosario Pastor ◽  
Noemi Pinilla ◽  
Josep A. Tur
Keyword(s):  
Mediterranean Diet ◽  
Fast Food ◽  
Area Under The Curve ◽  
Economic Cost ◽  
Food Prices ◽  
Cross Sectional Survey ◽  
Cross Sectional ◽  
Old Spanish ◽  
Total Economic Cost ◽  
Data Frequency

Background: Adoption of a certain dietary pattern is determined by different factors such as taste, cost, convenience, and nutritional value of food. Objective: To assess the association between the daily cost of a diet and its overall quality in a cohort of 6–12-year-old Spanish schoolchildren. Methods: A cross-sectional survey was conducted on a cohort (n = 130; 47% female) of 6–12-year-old children schooled in primary education in the central region of Spain. Three-day 24 h records were administered, and the nutritional quality of the diet was also determined by means of Mediterranean Adequacy Index (MAI). A questionnaire on sociodemographic data, frequency of eating in fast-food restaurants, and supplement intake were also recorded. The person responsible for the child’s diet and the schooler himself completed the questionnaires, and homemade measures were used to estimate the size of the portions. Food prices were obtained from the Household Consumption Database of the Spanish Ministry of Agriculture, Fisheries and Food. The economic cost of the diet was calculated by multiplying the amount in grams of the food consumed by each child by the corresponding price in grams and adding up the total amount for each participant. The total economic cost of the diet was calculated in €/day and in €/1000 kcal/day. Results: The area under the curve (AUC) for €/day and €/1000 kcal/day represent 62.6% and 65.6%, respectively. According to AUC values, adherence to Mediterranean diet (MD) is a moderate predictor of the monetary cost of the diet. A direct relationship between the cost of the diet and the adherence to MD was observed [OR (€/1000 kcal/day) = 3.012; CI (95%): 1.291; 7.026; p = 0.011]. Conclusions: In a cohort of Spanish schoolchildren with low adherence to the MD, a higher cost of the diet standardized to 1000 kcal was associated with above-average MAI values.

Determinants of Anthropometric Failure Among Tribal Children Younger than 5 Years of Age in Palghar, Maharashtra, India

2021 ◽  
Vol 42 (1) ◽  
pp. 55-64
Author(s):  
Angeline Jeyakumar ◽  
Swapnil Godbharle ◽  
Bibek Raj Giri
Keyword(s):  
Odds Ratio ◽  
Composite Index ◽  
Z Score ◽  
Short Term ◽  
Cross Sectional Survey ◽  
Crude Odds Ratio ◽  
Cross Sectional ◽  
Independent Variables ◽  
Child Undernutrition

Background: Measuring undernutrition using composite index of anthropometric failure (CIAF) and identifying its determinants in tribal regions is essential to recognize the true burden of undernutrition in these settings. Objective: To determine anthropometric failure and its determinants among tribal children younger than 5 years in Palghar, Maharashtra, India. Methods: A cross-sectional survey employing CIAF was performed in children <5 years to estimate undernutrition in the tribal district of Palghar in Maharashtra, India. Anthropometric measurements, maternal and child characteristics were recorded from 577 mother–child pairs in 9 villages. Results: As per Z score, prevalence of stunting, wasting, and underweight were 48%, 13%, and 43%, respectively. According to CIAF, 66% of children had at least one manifestation of undernutrition and 40% had more than one manifestation of undernutrition. Odds of anthropometric failure were 1.5 times higher among children of mothers who were illiterate (adjusted odds ratio [AOR] =1.57, 95% CI: 1.0-2.3), children who had birth weight >2.5 kg had lesser odds (AOR: 0.63, 95% CI: 0.4-0.9) of anthropometric failure, and children who had initiated early breastfeeding had 1.5 times higher odds of anthropometric failure (crude odds ratio: 1.5, 95% CI: 1.0-2.1). However, when adjusted for other independent variables, the results were not significant. Conclusion: The alarming proportion of anthropometric failure among tribal children calls for urgent short-term interventions to correct undernutrition and long-term interventions to improve maternal literacy and awareness to prevent and manage child undernutrition.

scholarly journals Development of Machine Learning Models to Predict Probabilities and Types of Stroke at Prehospital Stage: the Japan Urgent Stroke Triage Score Using Machine Learning (JUST-ML)

2021 ◽  
Author(s):  
Kazutaka Uchida ◽  
Junichi Kouno ◽  
Shinichi Yoshimura ◽  
Norito Kinjo ◽  
Fumihiro Sakakibara ◽  
...  
Keyword(s):  
Machine Learning ◽  
Logistic Regression ◽  
Random Forests ◽  
Prediction Models ◽  
Characteristic Curve ◽  
Predictive Performance ◽  
Vessel Occlusion ◽  
Predictive Values ◽  
Training Cohort ◽  
Sensitivity Specificity

AbstractIn conjunction with recent advancements in machine learning (ML), such technologies have been applied in various fields owing to their high predictive performance. We tried to develop prehospital stroke scale with ML. We conducted multi-center retrospective and prospective cohort study. The training cohort had eight centers in Japan from June 2015 to March 2018, and the test cohort had 13 centers from April 2019 to March 2020. We use the three different ML algorithms (logistic regression, random forests, XGBoost) to develop models. Main outcomes were large vessel occlusion (LVO), intracranial hemorrhage (ICH), subarachnoid hemorrhage (SAH), and cerebral infarction (CI) other than LVO. The predictive abilities were validated in the test cohort with accuracy, positive predictive value, sensitivity, specificity, area under the receiver operating characteristic curve (AUC), and F score. The training cohort included 3178 patients with 337 LVO, 487 ICH, 131 SAH, and 676 CI cases, and the test cohort included 3127 patients with 183 LVO, 372 ICH, 90 SAH, and 577 CI cases. The overall accuracies were 0.65, and the positive predictive values, sensitivities, specificities, AUCs, and F scores were stable in the test cohort. The classification abilities were also fair for all ML models. The AUCs for LVO of logistic regression, random forests, and XGBoost were 0.89, 0.89, and 0.88, respectively, in the test cohort, and these values were higher than the previously reported prediction models for LVO. The ML models developed to predict the probability and types of stroke at the prehospital stage had superior predictive abilities.

scholarly journals PvMSP8 as a Novel Plasmodium vivax Malaria Sero-Marker for the Peruvian Amazon

Pathogens ◽  
2021 ◽  
Vol 10 (3) ◽  
pp. 282
Author(s):  
Elizabeth Villasis ◽  
Katherine Garro ◽  
Angel Rosas-Aguirre ◽  
Pamela Rodriguez ◽  
Jason Rosado ◽  
...  
Keyword(s):  
Plasmodium Vivax ◽  
Area Under The Curve ◽  
Surface Protein ◽  
Merozoite Surface Protein ◽  
Population Based ◽  
Peruvian Amazon ◽  
Cross Sectional Survey ◽  
Cross Sectional ◽  
Malaria Exposure ◽  
Plasmodium Vivax Malaria

The measurement of recent malaria exposure can support malaria control efforts. This study evaluated serological responses to an in-house Plasmodium vivax Merozoite Surface Protein 8 (PvMSP8) expressed in a Baculovirus system as sero-marker of recent exposure to P. vivax (Pv) in the Peruvian Amazon. In a first evaluation, IgGs against PvMSP8 and PvMSP10 proteins were measured by Luminex in a cohort of 422 Amazonian individuals with known history of Pv exposure (monthly data of infection status by qPCR and/or microscopy over five months). Both serological responses were able to discriminate between exposed and non-exposed individuals in a good manner, with slightly higher performance of anti-PvMSP10 IgGs (area under the curve AUC = 0.78 [95% CI = 0.72–0.83]) than anti-PvMSP8 IgGs (AUC = 0.72 [95% CI = 0.67–0.78]) (p = 0.01). In a second evaluation, the analysis by ELISA of 1251 plasma samples, collected during a population-based cross-sectional survey, confirmed the good performance of anti-PvMSP8 IgGs for discriminating between individuals with Pv infection at the time of survey and/or with antecedent of Pv in the past month (AUC = 0.79 [95% CI = 0.74–0.83]). Anti-PvMSP8 IgG antibodies can be considered as a good biomarker of recent Pv exposure in low-moderate transmission settings of the Peruvian Amazon.

scholarly journals Attitudes towards the New Zealand Government’s Smokefree 2025 goal associated with smoking and vaping in university students aged 18 to 24 years: results of a 2018 national cross-sectional survey

BMJ Open ◽  
2020 ◽  
Vol 10 (11) ◽  
pp. e037362
Author(s):  
Ben Wamamili ◽  
Mark Wallace-Bell ◽  
Ann Richardson ◽  
Randolph C Grace ◽  
Pat Coope
Keyword(s):  
Logistic Regression ◽  
Regression Analysis ◽  
New Zealand ◽  
University Students ◽  
Confidence Intervals ◽  
Logistic Regression Analysis ◽  
Smoking Prevalence ◽  
Cross Sectional Survey ◽  
Cross Sectional ◽  
Lower Odds

ObjectiveIn March 2011, New Zealand (NZ) launched an aspirational goal to reduce smoking prevalence to 5% or less by 2025 (Smokefree 2025 goal). Little is known about university students’ awareness of, support for and perceptions about this goal. We sought to narrow the knowledge gap.SettingUniversity students in NZ.MethodsWe analysed data from a 2018 cross-sectional survey of university students across NZ. Logistic regression analysis examined the associations between responses about the Smokefree goal with smoking and vaping, while controlling for age, sex and ethnicity. Confidence intervals (95% CI) were reported where appropriate.ParticipantsThe sample comprised 1476 students: 919 (62.3%) aged 18 to 20 and 557 (37.7%) aged 21 to 24 years; 569 (38.6%) male and 907 (61.4%) female; 117 (7.9%) Māori and 1359 (92.1%) non-Māori. Of these, 10.5% currently smoked (ie, smoked at least monthly) and 6.1% currently vaped (ie, used an e-cigarette or vaped at least once a month).ResultsOverall awareness of the Smokefree goal was 47.5% (95% CI: 44.9 to 50.1); support 96.9% (95% CI: 95.8 to 97.8); belief that it can be achieved 88.8% (95% CI: 86.8 to 90.7) and belief that e-cigarettes/vaping can help achieve it 88.1% (95% CI: 86.0 to 89.9).Dual users of tobacco cigarettes and e-cigarettes had greater odds of being aware of the Smokefree goal (OR=3.07, 95% CI: 1.19 to 7.92), current smokers had lower odds of supporting it (OR=0.13, 95% CI: 0.06 to 0.27) and of believing that it can be achieved (OR=0.15, 95% CI: 0.09 to 0.24) and current vapers had greater odds of believing that e-cigarettes/vaping can help to achieve it (OR=8.57, 95% CI: 1.18 to 62.52) compared with non-users.ConclusionsThe results suggest strong overall support for the Smokefree goal and belief that it can be achieved and that e-cigarettes/vaping can help achieve it. Smoking and vaping were associated with high awareness of the Smokefree goal, but lower support and optimism that it can be achieved.

Physician Perceptions on Quality of Life and Resuscitation Preferences for Extremely Early Newborns

2021 ◽  
Author(s):  
Danielle LoRe ◽  
Christopher Mattson ◽  
Dalia M. Feltman ◽  
Jessica T. Fry ◽  
Kathleen G. Brennan ◽  
...  
Keyword(s):  
Quality Of Life ◽  
Logistic Regression ◽  
Regression Models ◽  
Mixed Effects ◽  
Cross Sectional Survey ◽  
Cross Sectional ◽  
Comfort Care ◽  
Logistic Regression Models ◽  
Extremely Preterm

Objective The study aimed to explore physician views on whether extremely early newborns will have an acceptable quality of life (QOL), and if these views are associated with physician resuscitation preferences. Study Design We performed a cross-sectional survey of neonatologists and maternal fetal medicine (MFM) attendings, fellows, and residents at four U.S. medical centers exploring physician views on future QOL of extremely early newborns and physician resuscitation preferences. Mixed-effects logistic regression models examined association of perceived QOL and resuscitation preferences when adjusting for specialty, level of training, gender, and experience with ex-premature infants. Results A total of 254 of 544 (47%) physicians were responded. A minority of physicians had interacted with surviving extremely early newborns when they were ≥3 years old (23% of physicians in pediatrics/neonatology and 6% in obstetrics/MFM). The majority of physicians did not believe an extremely early newborn would have an acceptable QOL at the earliest gestational ages (11% at 22 and 23% at 23 weeks). The majority of physicians (73%) believed that having an extremely preterm infant would have negative effects on the family's QOL. Mixed-effects logistic regression models (odds ratio [OR], 95% confidence interval [CI]) revealed that physicians who believed infants would have an acceptable QOL were less likely to offer comfort care only at 22 (OR: 0.19, 95% CI: 0.05–0.65, p < 0.01) and 23 weeks (OR: 0.24, 95% CI: 0.07–0.78, p < 0.02). They were also more likely to offer active treatment only at 24 weeks (OR: 9.66, 95% CI: 2.56–38.87, p < 0.01) and 25 weeks (OR: 19.51, 95% CI: 3.33–126.72, p < 0.01). Conclusion Physician views of extremely early newborns' future QOL correlated with self-reported resuscitation preferences. Residents and obstetric physicians reported more pessimistic views on QOL. Key Points

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 Using a Guided Machine Learning Ensemble Model to Predict Discharge Disposition following Meningioma Resection

2017 ◽  
Vol 79 (02) ◽  
pp. 123-130 ◽  
Author(s):  
Whitney Muhlestein ◽  
Dallin Akagi ◽  
Justiss Kallos ◽  
Peter Morone ◽  
Kyle Weaver ◽  
...  
Keyword(s):  
Machine Learning ◽  
Logistic Regression ◽  
Patient Outcomes ◽  
Predictive Power ◽  
Univariate Analysis ◽  
Area Under The Curve ◽  
Motor Deficit ◽  
Ensemble Model ◽  
Algorithm Selection ◽  
Discharge Disposition

Objective Machine learning (ML) algorithms are powerful tools for predicting patient outcomes. This study pilots a novel approach to algorithm selection and model creation using prediction of discharge disposition following meningioma resection as a proof of concept. Materials and Methods A diversity of ML algorithms were trained on a single-institution database of meningioma patients to predict discharge disposition. Algorithms were ranked by predictive power and top performers were combined to create an ensemble model. The final ensemble was internally validated on never-before-seen data to demonstrate generalizability. The predictive power of the ensemble was compared with a logistic regression. Further analyses were performed to identify how important variables impact the ensemble. Results Our ensemble model predicted disposition significantly better than a logistic regression (area under the curve of 0.78 and 0.71, respectively, p = 0.01). Tumor size, presentation at the emergency department, body mass index, convexity location, and preoperative motor deficit most strongly influence the model, though the independent impact of individual variables is nuanced. Conclusion Using a novel ML technique, we built a guided ML ensemble model that predicts discharge destination following meningioma resection with greater predictive power than a logistic regression, and that provides greater clinical insight than a univariate analysis. These techniques can be extended to predict many other patient outcomes of interest.

Sign in / Sign up

Export Citation Format

Share Document