Reliability of a decision‐tree model in predicting occupational lead poisoning in a group of highly exposed workers

Stoia, Mihaela; Kurtanjek, Želimir; Oancea, Simona

doi:10.1002/ajim.22589

Cited by 10 publications

(8 citation statements)

References 28 publications

(26 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Occupational exposure to inorganic lead and its compounds in Romania Table 3. Blood-lead values for occupational exposed workers Interestingly, a previous Romanian study [5] showed that blood-lead level was less sensitive than cumulative blood lead index (CBLI) in predicting acute poisoning and highlighted the importance of CBLI ≥1,041 μg*years/dl and air lead concentration ≥0.3 mg/m 3 in the occurrence of occupational poisoning. More and more data from international studies indicate a poor correlation between lead air concentration, blood lead levels and chronic effects (including genotoxicity and reprotoxicity).…”

Section: Discussionmentioning

confidence: 98%

Occupational exposure to inorganic lead and its compounds in Romania

Negru

Calota

Călugăreanu

et al. 2020

Romanian Journal of Occupational Medicine

View full text Add to dashboard Cite

Lead and its compounds are hazardous chemical agents; some lead compounds, are classified as carcinogens in humans. In Romania, the occupational exposure to inorganic lead and its compounds occurs in many sectors: production of lead, manufacture of batteries, manufacture of thermal ceramic products (terracotta), production of electric and electronic components, manufacture of articles of metal wire, production of dyes and additives for plastics, recovery of lead from waste batteries, waste collection and treatment of electrical and electronic equipment, etc. The binding occupational limit value for inorganic lead compounds established under the national regulations is 0.15 mg/m3 in the air (measured in relation to a reference period of eight hours, time-weighted average, TWA). The binding biological limit value is 70 μg Pb/100 ml blood. We have summarized lead occupational exposure data collected from the regional public health authorities in Romania, for the period 2011-2019. The concentrations of lead recorded in the workplaces air varied between “not detected” and 0.22 mg/m3. The lead concentrations in the blood had high values (over the alert value of 40 μg/100 ml blood) in several activities (production of lead, recovery-recycling of lead from waste batteries, manufacture of batteries, and manufacture of articles of metal wire) leading to the need of continuous surveillance of health status for the exposed workers.

show abstract

Section: Discussionmentioning

confidence: 98%

Occupational exposure to inorganic lead and its compounds in Romania

Negru

Calota

Călugăreanu

et al. 2020

Romanian Journal of Occupational Medicine

View full text Add to dashboard Cite

show abstract

“…The best way to prevent and control disease is to predict ahead of time. In contrary to the field of medicine where prediction research is well-established [10–13], it is relatively new in the field of occupational health [14–16]. Accurate forecasting of occupational diseases can be achieved by analyzing sufficient historical data.…”

Section: Introductionmentioning

confidence: 99%

A Comparative Study on the Prediction of Occupational Diseases in China with Hybrid Algorithm Combing Models

Yan²,

Zhang

et al. 2019

Computational and Mathematical Methods in Medicine

View full text Add to dashboard Cite

Occupational disease is a huge problem in China, and many workers are under risk. Accurate forecasting of occupational disease incidence can provide critical information for prevention and control. Therefore, in this study, five hybrid algorithm combing models were assessed on their effectiveness and applicability to predict the incidence of occupational diseases in China. The five hybrid algorithm combing models are the combination of five grey models (EGM, ODGM, EDGM, DGM, and Verhulst) and five state-of-art machine learning models (KNN, SVM, RF, GBM, and ANN). The quality of the models were assessed based on the accuracy of model prediction as well as minimizing mean absolute percentage error (MAPE) and root-mean-squared error (RMSE). Our results showed that the GM-ANN model provided the most precise prediction among all the models with lowest mean absolute percentage error (MAPE) of 3.49% and root-mean-squared error (RMSE) of 1076.60. Therefore, the GM-ANN model can be used for precise prediction of occupational diseases in China, which may provide valuable information for the prevention and control of occupational diseases in the future.

show abstract

“…Commonly used methods include logistic regression, neural networks, decision trees, and SVM. Each of these methods has its own characteristics, has a strong representation in the classification algorithm, and has been widely and successfully applied in the medical field [14][15][16].…”

Section: Introductionmentioning

confidence: 99%

Differential Diagnosis Model of Hypocellular Myelodysplastic Syndrome and Aplastic Anemia Based on the Medical Big Data Platform

Zhang

Yin

et al. 2018

Complexity

View full text Add to dashboard Cite

The arrival of the era of big data has brought new ideas to solve problems for all walks of life. Medical clinical data is collected and stored in the medical field by utilizing the medical big data platform. Based on medical information big data, new ideas and methods for the differential diagnosis of hypo-MDS and AA are studied. The basic information, peripheral blood classification counts, peripheral blood cell morphology, bone marrow cell morphology, and other information were collected from patients diagnosed with hypo-MDS and AA diagnosed in the first diagnosis. First, statistical analysis was performed. Then, the logistic regression model, decision tree model, BP neural network model, and support vector machine (SVM) model of hypo-MDS and AA were established. The sensitivity, specificity, Youden index, positive likelihood ratio (+LR), negative likelihood ratio (−LR), area under curve (AUC), accuracy, Kappa value, positive predictive value (+PV), negative predictive value (−PV) of the four model training set and test set were compared, respectively. Finally, with the support of medical big data, using logistic regression, decision tree, BP neural network, and SVM four classification algorithms, the decision tree algorithm is optimal for the classification of hypo-MDS and AA and analyzes the characteristics of the optimal model misjudgment data.

show abstract

Reliability of a decision‐tree model in predicting occupational lead poisoning in a group of highly exposed workers

Abstract: Workers were at risk of poisoning as a result of their long term unacceptable exposure. Decision-tree modeling is potentially useful for risk management. Am. J. Ind. Med. 59:575-582, 2016. © 2016 Wiley Periodicals, Inc.

Cited by 10 publications

References 28 publications

Occupational exposure to inorganic lead and its compounds in Romania

Occupational exposure to inorganic lead and its compounds in Romania

A Comparative Study on the Prediction of Occupational Diseases in China with Hybrid Algorithm Combing Models

Differential Diagnosis Model of Hypocellular Myelodysplastic Syndrome and Aplastic Anemia Based on the Medical Big Data Platform

Contact Info

Product

Resources

About