Oil yield prediction for sunflower hybrid selection using different machine learning algorithms

Due to the increased demand for sunflower production, its breeding assignment is the intensification of the development of highly productive oil seed hybrids to satisfy the edible oil industry. Sunflower Oil Yield Prediction (SOYP) can help breeders to identify desirable new hybrids with high oil yield and their characteristics using machine learning (ML) algorithms. In this study, we developed ML models to predict oil yield using two sets of features. Moreover, we evaluated the most relevant features for accurate SOYP. ML algorithms that were used and compared were Artificial Neural Network (ANN), Support Vector Regression, K-Nearest Neighbour, and Random Forest Regressor (RFR). The dataset consisted of samples for 1250 hybrids of which 70% were randomly selected and were used to train the model and 30% were used to test the model and assess its performance. Employing MAE, MSE, RMSE and R2 evaluation metrics, RFR consistently outperformed in all datasets, achieving a peak of 0.92 for R2 in 2019. In contrast, ANN recorded the lowest MAE, reaching 65 in 2018 The paper revealed that in addition to seed yield, the following characteristics of hybrids were important for SOYP: resistance to broomrape (Or) and downy mildew (Pl) and maturity. It was also disclosed that the locality feature could be used for the estimation of sunflower oil yield but it is highly dependable on weather conditions that affect the oil content and seed yield. Up to our knowledge, this is the first study in which ML was used for sunflower oil yield prediction. The obtained results indicate that ML has great potential for application in oil yield prediction, but also selection of parental lines for hybrid production, RFR algorithm was found to be the most effective and along with locality feature is going to be further evaluated as an alternative method for genotypic selection.

Methods for algorithmic diagnosis of metabolic syndrome

Metabolic Syndrome (MetS) is associated with the risk of developing chronic disease (atherosclerotic cardiovascular disease, type 2 diabetes, cancers and chronic kidney disease) and has an important role in early prevention. Previous research showed that an artificial neural network (ANN) is a suitable tool for algorithmic MetS diagnostics, that includes solely non-invasive, low-cost and easily-obtainabled (NI&LC&EO) diagnostic methods. This paper considers using four well-known machine learning methods (linear regression, artificial neural network, decision tree and random forest) for MetS predictions and provides their comparison, in order to induce and facilitate development of appropriate medical software by using these methods. Training, validation and testing are conducted on the large dataset that includes 3000 persons. Input vectors are very simple and contain the following parameters: gender, age, body mass index, waist-to-height ratio, systolic and diastolic blood pressures, while the output is MetS diagnosis in true/false form, made in accordance with International Diabetes Federation (IDF). Comparison leads to the conclusion that random forest achieves the highest specificity (SPC=0.9436), sensitivity (SNS=0.9154), positive (PPV=0.9379) and negative (NPV=0.9150) predictive values. Algorithmic diagnosis of MetS could be beneficial in everyday clinical practice since it can easily identify high risk patients.

Chronic Latent Magnesium Deficiency in Obesity Decreases Positive Effects of Vitamin D on Cardiometabolic Risk Indicators

BACKGROUND

Obesity and micronutrient deficiencies contribute to the risk of cardiometabolic diseases such are type 2 diabetes mellitus and Cardiovascular Disease (CVD).

OBJECTIVE

We examined the frequency of concomitant deficit of Magnesium (Mg) and vitamin D in obese patients and evaluated the connection of these combined deficiencies with indicators of cardiometabolic risk in non-diabetic subjects.

METHODS

Non-diabetic middle aged adults (n = 80; mean age 36 ± 4 years, 52% women) were recruited based on weight/adiposity parameters [i.e. Body Mass Index (BMI) and body fat percentage (FAT%)]. Cardiometabolic risk indicators [insulin resistance (Homeostatic Model Assessment for Insulin Resistance (HOMA-IR)) and CVD risk (Framingham risk score for predicting 10-year CVD)], Mg status (i.e. total serum Mg concentration (TMg), Chronic Latent Mg Deficiency (CLMD) - 0.75-0.85 mmol/L), vitamin D status (i.e. serum concentration of 25-hydroxyvitamin D (25(OH)D), vitamin D deficiency <50 nmol/l) were assessed.

RESULTS

Among obese subjects 36% presented a combination of vitamin D deficiency and CLMD. In all studied patients, 25(OH)D and TMg levels both, individually and combined, showed a negative linear correlation with HOMA-IR and CVD risk. In subjects with CLMD (TMg <0.85 mmol/L), a negative linear coefficient was found between 25(OH)D and, HOMA-IR and CVD risk, compared with subjects with normal TMg status (TMg ≥0.85 mmol/L).

CONCLUSION

CLMD and vitamin D deficiency may commonly be present in obese non-diabetic subjects. Individually and combined, both deficiencies predispose non-diabetic patients to increased risk of cardiometabolic diseases. Maintaining normal Mg status may improve the beneficial effects of vitamin D on cardiometabolic risk indicators.

What kind of Relationship is Between Body Mass Index and Body Fat Percentage?

Although body mass index (BMI) and body fat percentage (B F %) are well known as indicators of nutritional status, there are insuficient data whether the relationship between them is linear or not. There are appropriate linear and quadratic formulas that are available to predict B F % from age, gender and BMI. On the other hand, our previous research has shown that artificial neural network (ANN) is a more accurate method for that. The aim of this study is to analyze relationship between BMI and B F % by using ANN and big dataset (3058 persons). Our results show that this relationship is rather quadratic than linear for both gender and all age groups. Comparing genders, quadratic relathionship is more pronounced in women, while linear relationship is more pronounced in men. Additionaly, our results show that quadratic relationship is more pronounced in old than in young and middle-age men and it is slightly more pronounced in young and middle-age than in old women.

ANN Prediction of Metabolic Syndrome: a Complex Puzzle that will be Completed

The diagnosis of metabolic syndrome (MetS) has a leading role in the early prevention of chronic disease, such as cardiovascular disease, type 2 diabetes, cancers and chronic kidney disease. It would be very greatful that MetS diagnosis can be predicted in everyday clinical practice. This paper presents artificial neural network (ANN) prediction of the diagnosis of MetS that includes solely non-invasive, low-cost and easily-obtained diagnostic methods. This solution can extract the risky persons and suggests complete tests only on them by saving money and time. ANN input vectors are very simple and contain solely non-invasive, low-cost and easily-obtained parameters: gender, age, body mass index, waist-to-height ratio, systolic and diastolic blood pressures. ANN output is M e t S-coefficient in true/false form, obtained from MetS definition of International Diabetes Federation (IDF). ANN training, validation and testing are conducted on the large dataset that includes 2928 persons. Feed-forward ANNs with 1-100 hidden neurons were considered and an optimal architecture were determinated. Comparison with other authors leads to the conclusion that our solution achieves the highest positive predictive value P P V = 0.8579. Further, obtained negative predictive value N P V = 0.8319 is also high and close to PPV, which means that our ANN solution is suitable both for positive and negative MetS prediction.

Vitamin D and Dysfunctional Adipose Tissue in Obesity

Vitamin D deficiency and dysfunctional adipose tissue are involved in the development of cardiometabolic disturbances (eg, hypertension, insulin resistance, type 2 diabetes mellitus, obesity, and dyslipidemia). We evaluated the relation between vitamin D and adipocytokines derived from adipose tissue. We studied 50 obese individuals who were classified into different subgroups according to medians of observed anthropometric parameters (body mass index, body fat percentage, waist circumference, and trunk fat mass). There was a negative correlation between vitamin D level and leptin and resistin (r = -.61, P < .01), while a positive association with adiponectin concentrations was found (r = .7, P < .001). Trend estimation showed that increase in vitamin D level is accompanied by intensive increase in adiponectin concentrations (growth coefficient: 12.13). In conclusion, a positive trend was established between vitamin D and the protective adipocytokine adiponectin. The clinical relevance of this relationship needs to be investigated in larger studies.

Obesity and vitamin D deficiency: trends to promote a more proatherogenic cardiometabolic risk profile

Vitamin D deficiency is associated with cardiometabolic risk factors (eg, hypertension, insulin resistance, type 2 diabetes mellitus, obesity, and dyslipidemia). We studied 50 obese patients (body mass index [BMI]: 43.5 ± 9.2 kg/m(2)) and 36 normal weight participants (BMI: 22.6 ± 1.9 kg/m(2)). The prevalence of vitamin D deficiency (25-hydroxyvitamin D, 25(OH)D < 50 nmol/L) was 88% among obese patients and 31% among nonobese individuals; 25(OH)D levels were lower in the obese group (27.3 ± 13.7 vs 64.6 ± 21.3 nmol/L; P < .001). There was a negative correlation between vitamin D level and anthropometric indicators of obesity: BMI (r = -0.64; P < .001), waist circumference (r = -0.59; P < .001), and body fat percentage (r = -0.64; P < .001) as well as with fasting plasma insulin (r = -0.35; P < .001) and homeostasis model assessment of insulin resistance (r = -0.35; P < .001). In conclusion, we observed a higher prevalence of vitamin D deficiency among obese participants and this was associated with a proatherogenic cardiometabolic risk profile.

Predicting body fat percentage based on gender, age and BMI by using artificial neural networks

In the human body, the relation between fat and fat-free mass (muscles, bones etc.) is necessary for the diagnosis of obesity and prediction of its comorbidities. Numerous formulas, such as Deurenberg et al., Gallagher et al., Jackson and Pollock, Jackson et al. etc., are available to predict body fat percentage (BF%) from gender (GEN), age (AGE) and body mass index (BMI). These formulas are all fairly similar and widely applicable, since they provide an easy, low-cost and non-invasive prediction of BF%. This paper presents a program solution for predicting BF% based on artificial neural network (ANN). ANN training, validation and testing are done by randomly divided dataset that includes 2755 subjects: 1332 women (GEN = 0) and 1423 men (GEN = 1), with AGE from 18 to 88 y and BMI from 16.60 to 64.60 kg/m(2). BF% was estimated by using Tanita bioelectrical impedance measurements (Tanita Corporation, Tokyo, Japan). ANN inputs are: GEN, AGE and BMI, and output is BF%. The predictive accuracy of our solution is 80.43%. The main goal of this paper is to promote a new approach to predicting BF% that has same complexity and costs but higher predictive accuracy than above-mentioned formulas.

A primary estimation of the cardiometabolic risk by using artificial neural networks

Estimation of the cardiometabolic risk (CMR) has a leading role in the early prevention of atherosclerosis and cardiovascular diseases. The CMR estimation can be separated into two parts: primary estimation (PE-CMR) that includes easily-obtained, non-invasive and low-cost diagnostic methods and secondary estimation (SE-CMR) involving complex, invasive and/or expensive diagnostic methods. This paper presents a PE-CMR solution based on artificial neural networks (ANN) as it would be of great interest to develop a procedure for PE-CMR that would save time and money by extracting the persons with potentially higher CMR and conducting complete SE-CMR tests only on them. ANN inputs are values obtained by using PE-CMR methods, i.e. primary risk factors: gender, age, waist-to-height ratio, body mass index, systolic and diastolic blood pressures. ANN output is cmr-coefficient obtained from the number of disturbances in biochemical indicators, i.e. secondary risk factors: HDL-, LDL- and total cholesterol, triglycerides, glycemia, fibrinogen and uric acid. ANN training and testing are done by dataset that includes 1281 persons. The accuracy of our solution is 82.76%.